Zero Hunger Lab special (English)

Page 1




Tilburg School of Economics and Management Tilburg School of Economics and Management (TiSEM) is the leading European School for research and education in the fields of Business and Economics. TiSEM’s mission is to contribute to the development and transfer of top level knowledge in all the main fields in business and economics, by way of preexperience and post-experience education, research and PhD program and societal outreach.

Research facts • #5 in Europe in the UT Dallas Business School Ranking 2021 • #6 in Europe in Economics & Business US News Best Global University 2021

Education facts • 8050 students of which 18% international • 7 Bachelor’s programs

• #27 in the world in Economics & Business US News Best Global University 2022

• 400 scientists, 50% of whom are international • 35 PhD dissertations in 2021

• #37 in the world in Business & Economics Times Higher Education 2022 • 2 Research Masters • #1 in the Netherlands 3 Bsc and 5 Msc programs of which 4 with TOP Program distinction

• 89% of our MSc graduates are satisfied about the program (National Alumni Survey 2020)

• 15 Master’s programs

School of Economics and Management


This special was created by the editors of New Scientist on behalf of the Tilburg School of Economics and ­Management, Tilburg University. ZERO HUNGER LAB Hein Fleuren, Marleen Balvert, Frans ­Cruijssen, Miriam Crousen, Perry Heijne, Koen Peters, Meike Reusken, Melissa Koenen, Valentijn Stienen, Hezha MohammedKhan, Joris Wagenaar, Eelke Bakker, Julius Kaut Final editors TiSEM/Zero Hunger Lab Miriam Crousen, Annemeike Tan Publisher Veen Media B.V. Editor-in-chief Jim Jansen Final editor Jean-Paul Keulen Contributors to this issue Bram Belloni, Laura Bergshoef, Bob Bronshoff, Mirna van Dijk, Dick den Hertog, Marleen Hoebe, Peter de Jong, Eline Kraaijenvanger, Maaike Putman, Wouter Schreuder, Pascal Tieman, Norbert Vermeer, Sebastiaan van de Water Basic design Sanna Terpstra (Twin Media bv) Design Donna van Kessel (Twin Media bv) CONTACT NEW SCIENTIST Email (for press releases), for questions to editors only), Tel +31-(0)85-6202600 Address (postal and street address) Oostenburgervoorstraat 166, NL-1018 MR Amsterdam Brand manager Thijs van der Post ( Marketing and sales Alex Sieval ( CONTACT ZERO HUNGER LAB Communications Manager Miriam Crousen Email Tel +31-(0)13-4663347 Postal address PO Box 90153, NL-5000 LE Tilburg Street address Warandelaan 2, NL-5037 AB Tilburg Website zerohungerlab Printing Habo DaCosta bv ISSN 2214-7403 The publisher is not liable for damages as a result of printing and typesetting errors. COPYRIGHT Nothing in this publication may be copied or stored in a database or retrieval system in any way without the written permission of the publisher. The publisher has endeavored to fulfil all legal requirements relating to the copyright of the illustrations. Anyone who is of the opinion that other copyright regulations apply, may apply to the publisher.

Intelligent bytes In July 1963, world chess champion and professor Max Euwe and his team introduced Tilburg University’s first scientific computer. Expectations regarding this IBM 1620 were high. In the then emerging fields of operations research and linear programming, it was hoped that it could be used to make important breakthroughs. Since then, the continued emergence and development of digital technologies have greatly influenced society. This is equally true of science itself: the way in which researchers develop and test theories is fundamentally changing. In ­dialectical terms, quantitative steps result in qualitative leaps. The fundamental scientific approach to complex problems is consistent with our university’s ambition to contribute to solving the equally ­fundamental problems of our global community. One such challenge is known as Sustainable

04 Improve helping Perry Heijne and Hein Fleuren spearheaded the Zero Hunger Lab.

06 Real impact

Meet the Zero Hunger Lab’s management team.

10 Structure, love, and language

Margriet Sitskoorn is in favor of a stable and stress-free childhood.

11 Nanostores

Jan Fransoo takes a close look at small stores.



12 Sustainable nourishment

Saskia de Pee and Melissa Koenen strive for a healthy diet on a healthy planet.

14 Candid report

A week with Eelke Bakker and Julius Kaut.

Prof. dr. Wim van de Donk Rector Magnificus and President of the Executive Board

22 Digital revolu­ tion With OPTIMUS, Koen Peters made an impression at the World Food Programme.

24 Greaseman ­

Myrtille Danse on the role of the Netherlands Food Partnership.

16 Strengthening systems ­

25 Local resilience

18 Mapped out The

26 Playing for keeps Three

Gerrit-Jan van Uffelen and Frans Cruijssen look for long-term solutions. Zero Hunger Lab works on site with a variety of organizations.

20 Complex logistics What is the best way to transport food to food banks?


Development Goal number two, or in short: zero hunger. It is impressive to see how fantastic (data) science is enabling NGOs and the United Nations to feed more people. The OPTIMUS ­model developed by the Zero Hunger Lab team (see page 22) shows that intelligent bytes ­significantly increase the number of bites. Tilburg University is immensely proud to have this inspiring and committed team within our academic community.

Marriët Schuurman on what the Netherlands will do against global famine.

30 Photo check

This app remotely searches for malnourished children.

32 Idealists

Three alumni of the Zero Hunger Lab talk about their research.

35 Broader use

Other sustainable development goals can also benefit from analytics, says Professor Dick den Hertog.

students developed games in which players optimize the food supply.

28 Hidden path­ ways Valentijn

Stienen and Joris Wagenaar lead farmers and food to the right place.

A publication of


Special Zero Hunger Lab | New Scientist | 3



Together, Perry Heijne (left) and Hein Fleuren (right) were the founders of the Zero Hunger Lab (ZHL). Fleuren: “We’ve been at it for about three years now, but in the ten years before that it had been in the back of my mind. Together with Dick den Hertog, I came up with the concept for the Zero Hunger Lab. With Perry, I then developed and built the lab into a research institute with social impact.” Heijne: “When Hein and I sit down together, the ideas immediately start flowing and suddenly there’s a plan, which, by the way, can also be an overly ambitious or wild plan. We ask each other critical questions, there is some chaffing and polishing, and often this results in a concrete project or research. In this way, science and practice greatly enhance each other.” Fleuren: “Ultimately, the Zero Hunger Lab stands for two things: emergency relief and sustainable development. We are using mathematics to provide more effective food aid in disaster situations and to make our global food system smarter for the sake of the health of the planet and all its inhabitants. In other words, we are helping to improve helping.” Heijne: “Academia and the NGO world don’t always speak the same language. My role is to translate the math into humanitarian practice and to make sure scientific ideas are embraced and have real impact.” Fleuren: “Perry and I always find common ground in our desire to make this world a better place for everyone: less poverty, more equality, more well-being. In short, the seventeen Sustainable Development Goals. We can become very enthusiastic and driven when thinking about solutions to, for example, refugees, child poverty, famine, water pollution or child welfare.” Heijne: “With the Zero Hunger Lab, we recently won the Franz Edelman Award as a scientific partner of the World Food ­Programme. That was a real recognition of what we do. Many people involved in development cooperation and humanitarian aid see that, for example, smart algorithms can help them, but they find it difficult to translate this into practical solutions and concrete results. With us, it’s really about the application. A ­striking example is what we have demonstrated using data ­analytics with the World Food Programme in South Sudan.” Fleuren: “I am sometimes asked if we will ever be rid of the problem. You can look at it in two ways: optimistically or realistically. If you want to eliminate hunger structurally for 800 million people, it has been calculated that you need about 250 billion euros. That’s a huge amount of money. Still: financially and ­technically, we are able to solve this problem. But then you encounter global politics and things move slowly.” Heijne: “I don’t know whether the world food problem will be solved by 2030. But the knowledge, skills, and money are there. I believe that together with governments, businesses, and social and knowledge institutions, we can radically improve our food systems. And everyone who puts a healthy and ­sustainable meal on the table today is helping to do that.” Text: Jim Jansen


Helping to improve helping

“With a small team, we are ­making a meaningful contribution”


Together, Marleen Balvert, Hein Fleuren, and Frans Cruijssen form the management team of the Zero Hunger Lab. All three are involved in the lab in their own way. What binds them together is that each wants to use smart mathematical processes to ­eliminate structural hunger.

Text: Jim Jansen Photos: Bob Bronshoff


am someone who likes to make this world a better place,” says Hein Fleuren, director of the Zero Hunger Lab (ZHL), when asked how he thought up the lab ten years ago. ZHL operates independently within Tilburg University on solutions to the world hunger problem. “Privately, I am much concerned with how we can live more sustainably,” he continues. “I am looking at how I can shape the energy transition in my own environment and how I can make sure I produce less waste.” How did it start out? Fleuren: “I had already been to the World

Food Programme, the WFP, in Rome on a student trip for econometrics students from the Tilburg School of Economics and Management. I was deeply impressed by their operations and the scale on which they worked, but especially by the photographs on the wall. They showed what they had done and the people they had helped. We have built mathematical models of the highly complex logistics of courier delivery services company TNT Express. In doing so, we came up with much better ways of working, which led to savings of hundreds of ­millions and a reduction of a quarter of a ­billion kilos in carbon dioxide emissions. Then Peter Bakker, former top executive of TNT and PostNL, asked whether this might also be something for the WFP. I immediate-


Hein Fleuren (1960) is ­professor of applications of business analytics and director of the Zero Hunger Lab, which works to reduce world hunger using data science.

ly jumped at the opportunity. The advantage of having someone like Peter is that you come in ‘at the top’. That’s when the ball started rolling.” Frans Cruijssen, member of the ZHL management team: “After my employment at TNT Express, I stayed in touch with my then colleague Perry Heijne. Occasional phone calls or a run. He told me about the ZHL he was preparing with Hein (see page 4 – ed.). I immediately thought it was a great initiative. I later started thinking about it more deeply, when I was considering quitting the consulting company that I was co-owner of at the time. I felt like doing more of my own calculations and writing, something I didn’t get to do much of in my managerial role. The ZHL gave me a chance to get started right away. What’s more, I was able to work with my supervisor Hein Fleuren again.” Marleen Balvert, management team member: “I was already familiar with OPTIMUS, the research done by Hein and external PhD student Koen Peters with the WFP, from my time as a PhD student in Tilburg. It is a fantastic example of how to apply optimization; a story like that does the rounds through the department. In January 2019 – I was no longer working in Tilburg – I ran into Hein at a conference, where he told me about the Special Zero Hunger Lab | New Scientist | 7


Zero Hunger Lab. In the meantime, he had the funding in place to really get started and the plan sounded great. Never before had I heard of a group that wanted to work so intensively and on such a scale on research for such a wonderful cause.” What motivates you to work day and night on a serious topic like hunger? Fleuren: “Hunger is one of the biggest basic

challenges in this world and I can actually contribute to the solution from my field. When it comes to fighting hunger, you have


Frans Cruijssen (1979) ­studied econometrics in Tilburg and received his PhD from the same university in 2006. After a fourteen-year stint in business, he returned to Tilburg in 2020 to join the Zero Hunger Lab.

8 | New Scientist | Special Zero Hunger Lab

to deal with things like transport, ­setting up sustainable chains, reducing l­ osses, and producing locally. And you can model all these very well mathematically. I put my field of expertise into action in a ­relevant way to really improve the world.” Cruijssen: “Our purely quantitative way of working is quite unique in the humanitarian world. This allows us to make a meaningful contribution to the quality of decisions within NGOs with a small team of researchers. We have a unique position within the university. With our team, we are gradually establishing the theme of hunger elimination as a central theme within the university. We do great research and make sure it is applied directly in practice.” Balvert: “The direct collaboration with NGOs is unique. We can make a real impact because we use a wide range of techniques and integrate different disciplines into one project, all of which fit under that one umbrella: bytes for bites.” You deal with hunger all day long in an academic way. Have you ever felt hunger yourself? Cruijssen: “Not really. Wealth, in this case rep-

resented by the availability of healthy and sufficient food, is so unfairly distributed around the world. I grew up in a hospitality business where I could always grab a Mars bar or something else from the storage room. Total abundance. I’ve had to exercise vigorously to compensate for that.” Fleuren: “Yes, I actually know the feeling a little

bit. For my own health, I do intermittent fasting. I eat during an eight-hour window; the other sixteen hours, I have nothing except water or tea. Of course, it’s a watered-down version of what people with real hunger feel, because that feeling goes on day in, day out.” How does this work affect your private lives? Have you adjusted your lifestyle and consumption patterns? Fleuren: “Certainly. Privately, we try to make

sure that we never throw away food. My wife is an expert at turning leftover food into a whole meal. I also grow all kinds of vegetables and fruits myself, as sustainably as ­possible. I don’t grow anything in a heated greenhouse or use pesticides. Not only do I enjoy it, but it gives me a feel for how much work it takes to grow to a really good tomato or bell pepper, for example.” Cruijssen: “I have become much more aware of both the privileged position we have in Western Europe and the waste we cause here. Our situation is difficult to compare with a family in, say, southern Somalia, but my projects with the Food Banks provide a clearer mirror. Poverty and hunger don’t only occur in developing countries. Even around the corner, people can have a hard time getting a complete meal. This gives us a responsibility to assign food the proper ­value. At home, we only throw something away sporadically.” Balvert: “I have become aware of the need for sustainable aid. Emergency aid is very good and sending goods and money is ­necessary

“Above all, I hope we make the shift to really ­tackling hunger”


Marleen Balvert (1989) is assistant professor of ­operations research & machine ­learning. She develops mathematical and statistical methods to address social issues, for example in genetics and at the Zero Hunger Lab.

to help people through a crisis ­situation. But sending money and goods to people in need alone won’t get us there. In fact, if you don’t do it in the right way, it can cause people to become dependent on aid. We need to put energy into providing aid to build sustainable solutions and let people take control of their own lives. This insight has, for example, helped me better understand the importance of microcredit (small loans to entrepreneurs, often women, in developing countries – ed.). In addition, the ZHL has impact in my own kitchen. We were already conscious of our food choices at home, and my work has only reinforced that awareness.” Where will we be in 2030? Cruijssen:“That’squiteaquestion.Our­second

Sustainable Development Goal is to eliminate hunger by 2030. I don’t think we’re going to achieve that. The world is too unstable, and we are facing too many challenges. If you look back at the Millennium Development Goals from 2000: not all of them were met by 2015 either. But they did lead to real action.” Balvert: “By 2030, hunger will not be eradicated. Eight years is a very short time to solve such a big problem. Covid has also shown us that there is a lot that we can’t anticipate. I do hope, however, that in eight years’ time

we will have much better insights into how we can improve our food chain, both in the West and in countries with food shortages, to enable people to live healthier lives, to ­significantly reduce hunger, and to have a fairer distribution of wealth across the world. I am also confident that some great strides will have been made by then. We are already seeing a lot of progress and many wonderful initiatives that are making a difference.” Fleuren: “Above all, I hope we make the shift to really tackling hunger. And I hope that through science, humanity will become more awake to problems of health, water, hunger, and poverty. That’s what happened with the climate crisis. It is threatening us very directly and still you see that humanity isn’t sounding the alarm yet. But the other problems will also affect us; they will ­eventually trigger large flows of people. And be honest: what would you do in a situation like that?” Finally, will we ever completely eliminate hunger? Balvert: “There will always be natural or

human factors that continue to cause

­ unger. For example, flooding, landslides or h conflict and violence. I do hope, however, that through sustainable development we can provide a stable basis for the elimination of structural hunger. And that we can deal with the unexpected shocks faster and more successfully with emergency aid and ­reconstruction.” Cruijssen: “There will always be emergencies that can make people suddenly vulnerable. What we need to work on is the resilience of people, logistics chains, and food systems to deal with these changes without them turning into a disaster.” Fleuren: “I think that with a lot of effort, it will be possible to tackle hunger structurally and make it a thing of the past. I would also love it if we could ensure that the number of people suffering from structural hunger is reduced by hundreds of millions in the ­coming years and by hundreds of millions more in the years after that. One day, an organization like the WFP will be able to offer more incidental help and we can rightly say: ‘We’ve had to help out a little bit, but this year no one has gone hungry.’ I’m 61 now; I hope to live to see that year.”

Prestigious award In 2021, the WFP won the international Franz Edelman Award, in part due to solutions from the Zero Hunger Lab. This is the world’s most prestigious award in the field of the application of analytics, which looks not only at innovation, but also at impact. In previous years, this award was won by Tilburg University ­several times. Hein Fleuren, director of the Zero Hunger Lab: “Hunger is, of ­course, an appealing topic where successful application of mathematics can have a great deal of impact. A lot of people respond to the name of our lab alone. We stick tightly to the rule that our research has to be scientific and must have impact. If you make sure that the impact is high and the research is scientifically sound, you can often come up with very innovative approaches and insights. In addition, hunger and a stable food supply are such big issues that you can help a lot of people – indirectly – very quickly.”

Special Zero Hunger Lab | New Scientist | 9


“You can’t think without food” Professor of clinical neuropsychology Margriet Sitskoorn hopes to work with the Zero Hunger Lab to create a stable and stress-free environment for children.

How does stress affect child ­development?

“Prolonged stress – caused by hunger and poverty, for example – can prevent young brains from developing properly. Scientists see this effect mainly in brain regions related to stress and in the prefrontal cortex, an area at the front of the brain. When the prefrontal cortex develops incorrectly, it cannot, for example, properly regulate the stress system. In addition, people ­become more sensitive to short-term stimuli, which makes them more likely to choose behaviors that provide short-term benefits. Indeed, the prefrontal cortex is also important for planning and achieving long-term goals.” How can childhood brains be prevented from developing incorrectly?

“First and foremost, it’s important that people around the world no longer go hungry. That is the goal of the Zero Hunger Lab. You can’t think without food, because when you’re hungry there is less energy for 10 | New Scientist | Special Zero Hunger Lab

thinking. There are also a lot of other things that can help. A stable environment with structure and love is incredibly important for brain development. And language also helps children to move forward.” In what ways can language help?

“Language is important for all kinds of cognitive skills and for expressing feelings. When children frequently interact with language – for example, through their parents talking, singing, and ­playing games with them – it helps their ­development. This allows them to ­understand things better, for example. Through the Language Treasures ­project, which involves pediatricians, speech therapists, childcare, and ­education, we try to encourage parents to engage in a lot of interaction with their children. For example, we advise parents to always talk about what they are doing and to identify what their children are seeing. In this way, we want to ensure that children enter school within five years with adequate language skills and develop correctly. That’s ­important not only for now, but also for the future.”


Text: Marleen Hoebe

More than half of the world’s population gets their food from small family stores. Jan Fransoo, professor of operations and logistics management, researches such nanostores. Text: Marleen Hoebe


Why are small family stores in developing countries so important?

“My research group estimates that there are 50 million such stores worldwide, ­providing food for 4 billion people. They are family stores of about 10 square meters where you can buy food in, for example, Asia and South America. They have different names in each country; we call them nanostores. Nanostores are important for employment and for neighborhood consumers. Shopkeepers have close contacts. Governments can take advantage of this, for example by distributing vitamins through these stores to raise awareness of health.” How do you research nanostores?

“Ten years ago, I began this research by riding along on trucks supplying stores in Latin America. This allowed me to figure out the processes behind nanostores. We approached companies and now we are getting data from suppliers who service

the stores, such as trucks’ GPS tracks. We also work with local universities. In ­Mexico, for example, we had one square kilometer of a city at our disposal to study whether monitored loading and unloading areas could help make better use of space and reduce truck parking time. This turned out to work well.” Isn’t it very inefficient that there are so many little stores?

“Many of the nanostores’ processes are not yet efficient. My colleagues and I analyze how they can be improved. In Mexico, for example, 70 percent of the population has no bank account; people there often pay in lots of change. Shopkeepers also pay their suppliers in cash, and handling that kind of payment takes time. However, the vast majority of the population does have a cell phone. We are, therefore, looking at whether payment via a digital wallet could work ­efficiently. Shopkeepers can top up the wallet with cash and then pay their suppliers using QR codes. With concepts like this, we are trying to accelerate ­distribution.”

“The processes behind ­nanostores are not yet efficient” Special Zero Hunger Lab | New Scientist | 11

“ Putting all the data together is a hell of a job” With the ENHANCE project, Saskia de Pee and Melissa Koenen aim to create a healthy diet for healthy people on a healthy planet. But what such a diet entails may vary by region. CV

Saskia de Pee (1967) is team lead systems analysis and science for nutrition at the World Food Programme. She received her PhD in 1996 from the then Agricultural University of Wageningen.

12 | New Scientist | Special Zero Hunger Lab

Text: Eline Kraaijenvanger Photos: Bram Belloni


round the world, some 811 million people are going hungry. Fortunately, you notice little of this on the Tilburg University campus. AH-to-go and Starbucks shine right next to the building that houses the Zero Hunger Lab. There, on the sixth floor, people are working hard to find solutions to eliminate the hunger problem. With this idealistic goal in mind, PhD student Melissa Koenen delves into numbers

and algorithms on a daily basis. She is working on the ENHANCE project, a unique collaboration between the Zero Hunger Lab, Capgemini, Johns Hopkins University in the United States of America, and the World Food Programme. Saskia de Pee is team lead systems analysis and science for food and nutrition, and heads the ENHANCE project. ENHANCE focuses on ‘healthy diets for healthy people on a healthy planet’. Quite a few conditions in one sentence. Saskia de Pee: “These days we talk about

sustainable healthy diets, or foods that are


“If you know that vitamin D is never a problem in a country, it doesn’t necessarily have to be part of the diet” healthy for people and the planet. This is indeed a huge challenge: food has to be healthy, produced safely, affordable, and in a form that people want to eat. In addition, the planet can’t suffer.” The food situation is not the same in every country. Doesn’t that make this pursuit incredibly difficult? De Pee: “There are even regional differenc-

es within countries! With ENHANCE, we aim to provide information that can be used to make informed decisions around food security at the national and sub-­ national levels. For each region, we first ask the question: what is most important here? Then we look at where we are now and how we can best achieve our goals. Ultimately, we want every country to arrive at the same end point.”

food produced, and what is the impact on the planet? So far, we have done analyses for Indonesia, Ethiopia, and Bangladesh; they provided a patchwork of information. Putting all the data together and comparing it is a hell of a job.” Melissa Koenen: “You really need an optimization model that takes all the input and makes assessments. As a human being, you are able to come up with a food choice that meets certain nutritional requirements, but that’s where it ends. You won’t find the best diet achievable. The model takes into account an enormous number of aspects, which often conflict: nutritional values, cultural preferences, costs, greenhouse gas emissions... You enter all that data, and our computer program turns it into a mathematical model.”


Melissa Koenen (1996) has been pursuing a PhD at Tilburg University’s Zero Hunger Lab since 2019. ­Before that, she studied econometrics and ­manage­ment science at Erasmus ­University Rotterdam.

What are the goals for the future? De Pee: “By mid-2022, we want to have a

version that will allow us, at the very least, to do the makeshift analysis we’ve done for Indonesia, Ethiopia, and Bangladesh more easily for other countries. We are also working on optimizations of the model. In that respect, we have a long wish list.”

Can you give an example?

And then a ready-made diet comes rolling out?

And what’s on your list?

De Pee: “In the Netherlands, obesity is a

Koenen: “This is indeed how you find the

De Pee laughs: “Well, we want to better

problem. So, there should be healthier food, while unhealthy food should slowly disappear. In other countries, people are starving, not to mention that food has little nutritional value. There, food diversity must be increased, and poor people must have greater access to food. At the same time, in thirty years, you don’t want to have the same problems there that we have now. So, you have to consider the way the food is produced.”

cheapest combination of foods that meets all the conditions entered. But the goal is not necessarily a diet that you recommend to people. It’s more of an insight that tells people: this is really the bare minimum. Ideally, the model offers multiple options.” De Pee: “The final decision is up to the government. We mainly want to provide insight so that people know what the latitude is and what the impact is of one thing or another. You can also see how other countries are doing. For example, greenhouse emissions are lower for the same food item. Why is that? How is that foodstuff produced there? And can we perhaps use those production methods here as well? That way, you can better understand where you can make a difference with what you have.”

­ efine certain nutritional values. Now, in d addition to proteins and fats, we have nine vitamins and four minerals in the model. But proteins are made up of amino acids and fats are made up of fatty acids. There are also maximum and minimum values for how many vitamins and minerals you should be getting.” Koenen: “It would be nice to put all these specifications into the optimization model, which you can then turn on and off by area. For example, if you know that vitamin D is never a problem in a country, it doesn’t necessarily have to be part of the diet. Not to mention climate effects, ­impact on land use, biodiversity, and the like. But it’s an incredibly fun project. When you talk about it, it automatically makes you happy.”

And that’s where you come in. De Pee: “We want to establish a data plat-

form that informs and advises governments about food supplies and ‘desired’ diets, in particular. This platform contains data from four main areas: what is the cost, what is the nutritional value, how is the

Special Zero Hunger Lab | New Scientist | 13

A week with Eelke and Julius Zero Hunger Lab researchers Eelke Bakker (26) and Julius Kaut (27) like giving their lives big twists. So, she will soon be cycling to Tajikistan, while he fantasizes about moving to Brabant, ­having ­previously lived in Myanmar, Norway, and Israel, among other ­places. Meanwhile, their minds travel to the Horn of Africa every morning. Why? The duo ­explains in this candid report of their week. Editing: Sebastiaan van de Water


food security in the Horn of Africa. This week, we hope to complete the first draft.

Eelke 9:32 AM

Our Plan B goes into effect today. It feels good after months of preparation, but ­honestly? Plan A would have been even more exciting. In that case, I would have been on a stage in Uganda today, to give d ­ ata-science training to East African agriculturists. Covid wasn’t the only thing that thwarted our plan. Arranging visas for all the participants from South ­Sudan and Somalia was at risk of b ­ ecoming a bureaucratic nightmare. But scrap the courses? No way! They are the first pillar of the project that I’m working on with Julius. On ­behalf of the Zero Hunger Lab, we want to increase local clout in the Horn of ­Africa to prevent famines. So, we quickly had brochures distributed about our alternative: a customized video course. The first recordings will start soon. Here in Tilburg, that is. In a sweater and jeans, in a deserted lecture hall.

Julius 2:20 PM

I hear the floor above me creak as my parents walk back and forth. I had hoped to live in ­Tilburg by now, but I underestimated the housing crisis in the Netherlands. So, for weeks I have been living and working in the basement of my parents’ new house in the 14 | New Scientist | Special Zero Hunger Lab

TUESDAY Eelke 5:44 PM

Julius’ workplace, in the basement of his parents’ house

German town of Durmersheim. I am now ­sitting at an old-fashioned school desk with two monitors on it. A window lets in some daylight. Outside flows the Rhine, and beyond that lies France. But in my head, I’m somewhere else. For months, Eelke and I have been working on the second pillar of our project: a paper in which we try to quantify

It feels strange to have to talk enthusiastically to four hundred empty chairs. Normally, I like to look at the faces in the audience when I teach. All that frowning and whispering helps me assess whether my explanation of missing values is catching on, or whether I’m rambling on too much about clever use of color in data visualization. But you can get used to anything, as has been proved today. I’m not saying I’m going to launch my own YouTube channel, because I have yet to watch the footage and I’ll probably get ­annoyed with my wild gestures. But when my colleague Miriam was recently speculating about a podcast about data science... Well, that seems like fun. Now I have to finish my bowl of soup here at the university and then go back to my little room in Tilburg.

Julius 6:50 PM

Surely being a farmer in Somalia is different from running a farm here near the Black ­Forest. Today, I delved into the disaster

Julius Kaut

Eelke in an empty lecture hall

Julius 5:29 PM

s­ cenarios that they are struggling with there. Every year, floods and droughts can ruin the work of several seasons. And crops that do ripen successfully are often eaten by swarms of desert locusts. Still, I think famine is avoidable. We just need to learn to predict food scarcity better. But how do you know if a ­locust infestation is coming? That’s what ­Eelke and I are figuring out together.


Found it! A database of locust sightings in the Horn of Africa. It even says whether a specific locust is a male or female. And what species it is. These kinds of sources can really help predict food shortages. Unfortunately, our search work doesn’t always run smoothly. ­Today, I also wanted to know: how many healthcare institutions are there in each province of ­Somalia? Impossible to find! Eelke Bakker

Tonight, a childhood friend from Karlsruhe is coming over to play pool with me here in the town center. I am going to ask him a question that I found the answer to today: how many armed conflicts have taken place in Somalia in the last two years? ACLED, an organization that records violent incidents around the world, puts it at exactly 5,000. For us, ACLED is a great resource, because food security and conflict are closely related. But numbers like these make my hairs stand on end.

THURSDAY Eelke 2:13 PM

Julius and I don’t have the same view of things. I mean that in a positive way. Today, we’ll look at each other’s chapters and treat each other to all kinds of suggestions. It doesn’t feel uncomfortable, because we both want our report to be the best it can be and are happy to complement each other. That’s one of the great things about the Zero ­Hunger Lab. Everyone here respects each other’s abilities.

Julius 5:01 PM

Eelke once again has been keeping me super sharp today regarding the proper use of data. As a social scientist, in turn, I try to keep an eye on what we lose when we reduce reality to numbers. An example from my time in ­Myanmar: Western organizations had set up a large project there to help people with the number one problem on the ground: crime. But when relief workers went out into the neighborhoods, they discovered that no one

cared. To them, there was something else that was more problematic about which there were no figures: dirty drinking water. We managed to shift the focus of our resources to changing the water. Unfortunately, h ­ umanitarian interventions sometimes miss the mark because of a lack of attention to ­local realities.

FRIDAY Eelke 4:44 PM

I stared at Google Maps for a long time during my breaks today. Now that the article and training sessions are nearly complete, I am thinking more often about my next challenge. I want to bike to Asia. In 2019, I rode to Copenhagen by myself; last year I cycled through Switzerland. And soon I will first bike to Istanbul. There I’ll meet up with a Belgian girl, and we will continue our journey together through Iran to Tajikistan. I haven’t really trained yet, but that’s not a problem. Months of cycling will naturally improve your cycling fitness. I hope.

Julius 6:12 PM

A blank canvas. That’s where we started. I’ve sometimes wondered: can we fill it as is ­expected of us? But now, when I see how our efforts have come together in sixty pages of analysis and recommendations, I feel proud. At the same time, I now know how many ­people are committed to making the world better little by little, yet the challenges we all face remain undiminished. Sometimes they even seem to increase. I think we must ­abandon the illusion that our work will someday be finished. But that doesn’t change my desire to complete great projects that truly benefit people. Hopefully, this was one of those projects. Special Zero Hunger Lab | New Scientist | 15


Text: Eline Kraaijenvanger Photos: Bram Belloni

Using data models to contribute to more robust food systems in crisis areas is what the Zero Hunger Lab (ZHL) and the ­Wageningen Centre for Development ­Innovation (WCDI) are working on ­together. While Frans Cruijssen of the ZHL is looking into complicated data analyses, Gerrit-Jan van Uffelen of the WCDI is mainly concerned with the local situation

in the Horn of Africa. Together, they are striving to find a long-term solution to the food problems that exist there. And that is much needed, says Van Uffelen: “We now have the highest number ever of people in a food crisis or worse. That’s the unpleasant truth. The way we as an international community intervene in these kinds of ­areas falls short.” That sounds serious. Can you elaborate? Van Uffelen: “Humanitarian aid is neutral.

It helps the individual survive but makes

no judgements about the cause of the ­crisis. As soon as you talk about warring parties and questions of blame, you lose the ability to provide impartial aid. This is a strength of the humanitarian system, but also a weakness. It means that we give countries aid year after year, but we cannot look at the structural causes of why that emergency aid is needed.” Cruijssen: “In fact, emergency aid means you’re too late. Yes, the help is desperately needed, but in doing so you ignore the fact that you could often have made smart

“We can contribute more to a better world” Providing emergency aid to people in a food crisis is badly needed – but far better is it to try to prevent such disasters by looking at structural causes and improving food systems, say Frans Cruijssen and ­Gerrit-Jan van Uffelen.

“With this approach, we ensure that people’s realities are the main focus again” ­ ecisions to avoid the disaster in the first d place. That’s what we should be investing in. Calculations have been done: every ­dollar you invest in measures to improve food systems and prevent problems equals six dollars that you will have to spend on emergency aid once the problem materializes. That realization is slowly beginning to sink in now.” So, you are working with a relatively new method: the food system approach. Van Uffelen: “Yes, we are using this to look

at all parties together: emergency aid, development aid, and peace aid. It allows us to approach food insecurity as a whole. This is important, because for people in food crisis, it is one and the same reality. Twice a year, we are given an overview of the food security situation for those areas where we know food security is problematic. This allows us to see where things are

going quite well, where and which groups of people are living in high levels of food insecurity, and which people are facing ­severe famine. It gives us a reasonable ­understanding of how food systems work and how they are changing. Based on that, we draw lines to the future: what will it take to make those food systems more robust?” How far along are you in that process? Van Uffelen: “We are still at the beginning.

An important starting point is to understand what food systems are and how they work. For us, this project is also a search for new interventions that do justice to the ­reality of the local people. Interventions that connect to what people in crisis situations contribute to food systems themselves. That’s very important. I think that – when you look at how we have intervened internationally – we have lost sight of local reality. With this systems approach, we can put it back on the map, and make people’s realities the main focus again. That sounds very ambitious...” Cruijssen: “...but you can also make it smaller. For example, there are your model gardens in the Horn of Africa. People from the region come there to see how to grow vegetables under different conditions. This way they learn to put together a diverse diet with what they grow themselves. That’s what I like about our collaboration: it lends the sets of figures and models that we work with in Tilburg so much more color.” So, that’s where the Zero Hunger Lab and Wageningen University & Research come together very well. Cruijssen: “Certainly. Data analysis is more


Frans Cruijssen (1979) is a researcher at Tilburg ­University’s Zero Hunger Lab. He received his PhD, also in ­Tilburg, in the field of business economics.


abstract and further removed from the people it concerns. This is what we can and do contribute well, but with this collaboration we can also do justice to local contexts. There, we can implement the interventions we come up with here. This helps us to make better predictions, which in turn enables the humanitarian world to make better decisions. We are also committed to accessible training of the people there, so that they learn what it takes to do

Gerrit-Jan van Uffelen (1965) is Senior Advisor at the Wageningen Centre for ­Development and Innovation, part of Wageningen University & Research. There, he directs several projects on food ­s­ecurity.

simple food analyses. We’ve already developed these online training courses here, and we want to offer them to universities and governments there, in the hope that they will use them to come up with better programs and interventions.” What do you yourself learn from this work? Cruijssen: “There is no single answer to

the food problem; it is not ‘one size fits all’. You have to look at a particular country, a particular town or village. What’s going on there? And what can we do to address that?” Van Uffelen: “We live in one of the richest countries in the world, but we spend a lot of time worrying about ourselves. That’s a shame, because I think we can contribute more to a better world, where people don’t have to go hungry – at least not as much as they do now. This is also the primary motivation and challenge that drives us at the WCDI and the ZHL. This food systems ­approach has the potential to contribute to a different way of seeing and doing things in a fundamental way.” Special Zero Hunger Lab | New Scientist | 17


The world hunger problem is immense. According to the United Nations, as many as 811 million people will go to bed hungry tonight. Every ten seconds, somewhere in our world a child dies of starvation and malnutrition. The Zero Hunger Lab helps to achieve global food security using

­ athematics. We call it ‘bytes for bites’. m Our mission is to make people independent of food aid so that they themselves can ensure sustainable food security. We do this not only in Africa, Asia, and the Middle East, but also in the Netherlands, where more than 150,000 people

­ epend on food banks for their “daily d bread”. Reducing the world’s hunger ­problem requires not only more efficient and effective (emergency) food aid. Even more important is to increase local capacity so that farmers, businesses, and ­communities can provide sustainable

HOUTEN, the Netherlands From Houten, the activities of 171 food banks in the Netherlands are supported. ZHL researchers are helping the volunteer organization come up with smart solutions to help even more people more successfully.

PANAMA This is the work location of the Red Cross regional coordinator who coordinates emergency aid for the Americas and, through the Giro555 network, ­advises our researchers on the applicability and ­impact of ZHL solutions.

GHANA Tens of thousands of palm oil farmers have worked with Solidaridad experts over the past four years on productivity, sustainability, and resilience. ZHL helps with smart dashboards to increase scale and impact globally quickly and properly.

BURUNDI ZOA has invested heavily to help returning refugees in Burundi build new lives. We help ZOA’s experts ­analyze their CASH programs to make ever better choices in the best interest of refugees.

18 | New Scientist | Special Zero Hunger Lab


food security themselves and become independent of aid. That’s why Zero ­Hunger Lab researchers work not only from the campus in Tilburg, but especially on site with organizations that have safe access to people in need, that have a good understanding of how to make

communities resilient and their food ­systems sustainable, and that co-create solutions with sustainable impact ­together with those same communities. More than twenty researchers from ­Tilburg University work within the lab. They collaborate on more than forty

r­ esearch projects with numerous partners, including the World Food Programme, Voedselbanken Nederland, ­Solidaridad, Welthungerhilfe, Oxfam, ZOA, World Bank, INSEAD Humanitarian Research Group, Wageningen University & ­Research, Nuffic, and Giro555.

SUMATRA When 70 percent of the roads are unknown, how do you efficiently get relief supplies from A to B? We used GPS tracks to map infrastructure and ­provide advice.

SOMALIA With specialists from Wageningen University & ­Research and FAO, and with Somali students, we are developing data science trainings so that ­people in the Horn of Africa can develop and ­implement their own ZHL tools.

MOZAMBIQUE Using data from recent natural disasters in, for ­example, Mozambique and the humanitarian ­experts at Welthungerhilfe, we have conducted ­research to ensure that relief supplies reach people in need faster and more successfully.

SOUTH SUDAN The World Food Programme (UN) organizes food aid in South Sudan. Together with the emergency aid experts, we have ­developed an innovative solution that allows 20 percent more people to be helped for the same money; not only in Bentiu, but soon in eighty countries where the WFP provides aid. Special Zero Hunger Lab | New Scientist | 19

Meike Reusken

Pieter Nijman

Logistics under the microscope Every week, some 150,000 people can turn to one of the Dutch food banks. How can all the food ­distributed there be delivered to its destination in the most e ­ fficient way possible?

Text: Laura Bergshoef Photos: Bram Belloni


ith his phone in his hand and folders under his arm, Pieter Nijman quickly walks into the cafeteria of the food bank and distribution center in Tilburg. “Sorry I’m late,” he says. “I just had to rescue a sea container full of mackerel. They were about to be destroyed, due to regulations, but the fish themselves are in fine condition. Isn’t 20 | New Scientist | Special Zero Hunger Lab

that bizarre? I just put in a quick call. If it works out, every food bank customer will soon have a fish.” Food waste and food shortage are important issues for Nijman. For some two and a half years, he has been a board member of the logistics department of the Association of Dutch Food Banks. In the Netherlands, more than one million people live below the poverty line. People who cannot afford groceries temporarily receive a supplemental food package once a week. How does that work? And what could be improved?

Bottlenecks “The logistics behind the food banks is very complex,” Nijman says. The food banks get their food from such sources as businesses, supermarkets, and fundraisers. That food is first distributed to ten distribution centers. From there, it goes to 171 food banks, and most food banks have multiple distribution points. There, some 150,000 customers pick up a food package once a week. “We want to distribute all the food, which is often fresh, as fairly as possible among various customers throughout the

Netherlands with as little waste as possible and as few kilometers to cover as possible,” says Nijman. “We never know exactly how much food we will be getting, and the number of clients per food bank varies over time.” To clarify and optimize the logistics, Meike Reusken of the Zero Hunger Lab developed two mathematical models with master’s students last summer. “Big companies like supermarket chain Albert Heijn have a lot of data available. Mathematical models can make predictions using that data,” says Reusken. “Albert Heijn, for example, knows in advance each day how many people will come to shop at each location and what food they need to have ready on their shelves. I want to help the food bank with similar models.” Reusken’s first model can predict the number of future customers, just like Albert Heijn’s model. “In the early 2020s, the food banks were worried that the number of customers was going to skyrocket because of the covid pandemic, but they had no idea how big the increase would be,” Reusken says. “That uncertainty made it impossible to prepare properly.” The second model calculates the bottlenecks in logistics, including where there are insufficient means of transport and where means of transport could run more efficient routes. “What stood out, for exam-

The Tilburg Regional Distribution Center of Voedselbanken Nederland was recently renovated.

ple, was that food, nationwide, could be distributed more efficiently if the Food Bank increased the transit warehouses at certain distribution centers.”

Twelve hundred loaves of bread In Tilburg, Nijman walks down a steep flight of stairs into the distribution center’s gigantic warehouse. Towering metal shelving units are filled with cardboard boxes of all sizes. Volunteers in orange-and-black food bank fleece vests shout things at each other, others drive around in forklifts. “This really is a gem,” Nijman says proudly. “The warehouse has just been renovated. We were running out of space.” Another board member, Will de Laat, nods affirmatively. “And the space is now more efficiently laid out as well.” He points to one of the shelving units in the front. “All this food has to go within a week, because this is all fresh.” In one corner of the warehouse, a young man is concentrating on cutting fresh loaves of bread with a glistening slicing machine. “Twelve hundred a day,” says De Laat. A little further down, large doors are open. “That’s where the trucks load and unload; sometimes they’re up to 18 meters long. Here in Brabant, there are 29 food banks that come to collect food with their own means of transport.” But that number will be reduced. The model calculated that

“Mileage can be reduced if different food banks share transport resources” the number of kilometers could be reduced if the various food banks shared means of transport. So, instead of 29 separate trips, 5 trips will be made with different food banks as stops. “I think that’s perhaps the best thing about the model,” Nijman says. “It allows the 171 individual food banks to work together better. Instead of asking what is most convenient for each individual food bank, the model looks at what works best for all of the Netherlands.” Reusken: ­“Consulting with 171 individual food banks is difficult. The model looks for possible regional collaborations from the top down.”

Mathematical tricks Before Reusken got started with mathematics and computers, she first collected data about the food banks. “That was a huge job. The food banks don’t have as much data as, say, Albert Heijn. First, we prepared a survey with a hundred questions about logistics. Then I used that data to build the logistics model. This amounts to translating the data into mathematical ­formulas. The models then calculate how to optimize the logistics, for example, by reducing mileage as much as possible. The other model, which predicts how many customers the food banks will have in the future, uses mathematical tricks to find patterns in old data. Should there ever be another pandemic, the model now has data from the current pandemic, so we can prepare for the next one.” In the warehouse in Tilburg, Nijman and De Laat walk through the door of the freezer. A crackling cold wind blows at them. De Late checks the room and grabs a stack of empty cardboard boxes. “I have to get going,” he calls after us as he quickly walks away. “I’m going to pick up food from a school.” Special Zero Hunger Lab | New Scientist | 21

From oddity to household name Koen Peters spearheaded the OPTIMUS program, which is part of a digital revolution within the World Food Programme. The resulting savings have generated enough money to provide food for 2 million people for a year. Text: Mirna van Dijk


s an econometrics student, Koen Peters already knew that solving logistics problems would be in his future. But that he would cash in on his head for mathematics in the business world was something he doubted more and more with every class. “The ­focus was very often on the same kind of business examples: logistics, transport, ­investments, how to set up a pension ­system.... You learn to solve things like that using data and mathematics, but I didn’t find the topics all that exciting.” That’s why Peters looked outside the box for fields of work that were a little less ­obvious. At a conference on food insecurity, the penny dropped. “There, a former agriculture minister told us that there are 800 million people who don’t have enough to eat, even though there is enough food available worldwide. That sounded like the kind of problem I wanted to tackle: how do you get those products to the right place at the right time?”

Koen Peters: “It took several years to convince everyone in the organization of what you can do with data science and analytics.”

22 | New Scientist | Special Zero Hunger Lab


Thirty specialists Within Tilburg University, Peters began looking for thesis options. This led him to Hein Fleuren, now director of the Zero Hunger Lab. With Fleuren’s help, he ­arranged a master’s internship with the UN World Food Programme (WFP). During his internship in 2014, Peters spearheaded the creation of the ingenious

User-friendly solutions

software program OPTIMUS, a model for assembling and distributing food packages that can handle every conceivable ­variable, requirement, and constraint. The model is part of an organization-wide digital revolution within the WFP, in close collaboration with the business community and tech-savvy universities like Tilburg. This has already led to a total savings of about $150 million for the organization – enough to provide 2 million people with enough food for a year. However, as a data researcher, Peters was still quite an oddity during his internship within the world of humanitarian aid. Together with just two colleagues, he faced the challenge of getting a prototype of ­OPTIMUS working for the supply chain of a WFP food program in Syria. Now, WFP has a team of thirty data specialists: the Supply Chain Planning & Optimization team.


Koen Peters (1991) received his master’s degree in operations research & management science from Tilburg University in 2014. He is now head of ­optimization at the World Food Programme and an ­external PhD student at the Zero Hunger Lab.

Koen Peters works parttime as an external PhD student for the Zero ­Hunger Lab. His PhD work will ensure that valuable knowledge and ­experience from the ­World Food Programme can also be applied by NGOs and g ­ overnments within the same sector.

In addition, Peters is researching how technical education programs can better prepare their students for the ­day-to-day operations of the humanitarian world, a growing field of work for mathematicians and data scientists. He a ­ dvocates a curriculum with more ­focus

Step by step The humanitarian world is used to working in very complex situations, under ­unpredictable conditions with an incredible number of variables. Think of, for example, natural disasters that result in acute emergencies, conflict situations that create danger and uncertainty, and areas that are sometimes inaccessible to road traffic for months on end during rainy seasons or after floods. Systems that have long since been implemented and optimized in the business world were inadequate for food aid organizations due to the complexity of humanitarian logistics, even though they operate on the same mathematical principles. In addition to speed and cost, it was necessary to factor in local conditions and nutritional values in logistics planning. When Peters flew to Jordan with the OPTIMUS prototype for Syria’s annual planning workshop, he was full of excitement about whether the mathematical puzzle that had been solved in theory would yield a working system. “I started talking to the local experts and looking at all the data. What are the characteristics to consider? What products can be included? What do they currently cost? That’s how I puzzled it all together in a mathematical model.” The model did what it promised to do, the team in Syria saved money to feed more mouths, and Peters was not allowed to leave WFP. “One of the key success ­factors was the pragmatic approach. In this field, we often see that data specialists approach the problem very theoretically or want to take all the exceptions into ­a­ccount right from the start. We built

on the operational challenges that young mathematicians will face after developing a beautiful model. Peters: “They learn a lot about solving the puzzle, but there is little attention paid to the next steps t­ owards user-friendly software and its implementation.”

­ PTIMUS step by step based on the data O that was actually available to us.”

Long, bumpy road By now, some seven years later, after an extensive testing phase and an even longer implementation phase, the model has evolved to the point where any employee in the chain without knowledge of mathematics can work with it easily. With a few clicks, you can see what the options are if, for example, you need to add products containing iron to a package within an ­operation or want to purchase more food from local entrepreneurs. Peters has now well surpassed the programming stage. He mainly helps his colleagues worldwide with their data analytics questions. He is also the point of contact for other NGOs looking to optimize their humanitarian goals using data. “We can use our experience to apply the model and make it suitable for their particular puzzle.” The road to the – now – high level of automation and data-science-based ­operation within the WFP has been long and sometimes bumpy, Peters says. “For decades, humanitarians have worked from the experience that building on data can be dangerous, because the data was outdated, incomplete, and, therefore, unreliable. It took several years to convince everyone in the organization of what you can do with data science and analytics. Now it has become the operational culture. There was no doubt at the WFP about how to deal with a global crisis like covid. It is still wonderful to see how many people we can help every day. With mathematics of all things!” Special Zero Hunger Lab | New Scientist | 23


“We are the greaseman of food security” edge of professional fruit and vegetable growing to local farmers in the best ­possible way. We also ensure that Dutch organizations learn from people in developing countries, for example about the changing climate conditions that farmers face there. On the one hand, you see areas suffering from desertification and, on the other, more flooding in coastal areas. Areas where coffee was previously easy to grow are now experiencing diseases and pests normally found in warmer areas.”


Will we make it: no more world hunger by 2030?

The Netherlands Food Partnership connects parties involved in food security. Director ­Myrtille Danse: “The Zero Hunger Lab is taking a fresh look at the issue.” Text: Peter de Jong

What are the goals of the Netherlands Food Partnership?

“The NFP is an independent foundation created to optimize the Dutch contribution to food security. We have four ­challenges: equal access and distribution of food; healthy diet; resilient ecosys24 | New Scientist | Special Zero Hunger Lab

tems; and peace, justice, and stability. We help establish the right lines of communication between the parties here in the Netherlands and those in the developing world. We are the greaseman in the world of food security. For example, we put a seed breeding company like Rijk Zwaan in touch with knowledge institutes and farmers’ organizations in developing countries, so that such a company can transfer its knowl-

“We are the first generation to be able to achieve that goal. In addition, we want healthy food. Obesity is also a problem in developing countries because people eat too much cheap, unhealthy, fattening food. In that context, it is interesting that the new government wants to make healthy food cheaper.” What is the role of the Zero Hunger Lab?

“We have only been working together for a short time, since 2021, but the experience with the ZHL has been excellent. The humanitarian aid community could very well use their statistics and models. ZHL researchers are taking a fresh look at the food issue. They are pragmatic and like to think outside the box. With their data science, they help farmers in developing countries with digitization, so that knowledge transfer to and communication with farmers is as efficient as possible. If farmers there will soon be able to manage many things digitally, this will lead to higher and better production of food – and that, of course, is what it’s all about. Yes, it is very useful to have the ZHL in our network.”


“The frustrating thing is that hunger is not necessary” The Netherlands is making an effort to permanently help 32 million people out of a state of malnutrition, says Marriët Schuurman, ­director of ­Stabilization and Humanitarian Aid at the Ministry of Foreign Affairs. Text: Peter de Jong

What is the scale of worldwide famine?

“At this moment, about 811 million people are suffering from hunger – that’s 10 percent of the world’s population. And that number is rising. Climate change is a ­

major cause of this. Extreme droughts and floods are devastating to agriculture. The world’s 100 poorest countries account for only 3 percent of carbon dioxide emissions, while they suffer the most from ­climate change. Conflict unfortunately remains a second cause of hunger in developing countries.

People are being starved and driven out. Even aid convoys are being attacked. And don’t forget covid. People in developing countries also have to stay indoors because of the virus, even though they are much more likely to work in the fields to earn a living. And they don’t have support ­packages for distressed sectors there, like we do here. The frustrating thing is that hunger is not necessary. In principal, there is enough food for all the people in the world. Climate, conflict, disease... ­Humanity itself is the cause.” What will the Netherlands do about it?

“By 2030, we want to have permanently helped 32 million people out of a situation of malnutrition. We want to increase local resilience, so that the people there can ­develop themselves and build a dignified existence. The Zero Hunger Lab is helping us do that.” What is the added value of the ZHL?

“Their algorithms allow us to purchase and distribute food packages more efficiently. Of course, we prefer to buy from local ­markets so that the farmers also benefit. Thanks to the ZHL, there was a 20 percent cost reduction in Syria, which allowed us to help an additional 1 million people. The lab also takes a critical look at what goes into the emergency food basket, so that people receive a healthy diet that fits in with their customs. ZHL’s data is also very useful in predicting humanitarian crises. 20 percent of them are predictable, half are foreseeable. Providing aid earlier is more humane and cheaper, leaving more money for other projects. As far as I’m concerned, the ZHL’s data science will be shared on an even larger scale within the United Nations so that we can help even more people.” Special Zero Hunger Lab | New Scientist | 25


Playing with food How do you optimize the food supply in a field, in a town or even in an entire country? Three Tilburg students built their own games to tackle these questions.

26 | New Scientist | Special Zero Hunger Lab

Text: Wouter Schreuder


n 1798, economist Thomas Malthus published an essay contrasting population growth with the growth of agricultural capacity. Because population grows ­exponentially and agricultural capacity grows linearly, an intersection would inevitably be reached after which population would be greater than food production could handle. Here, “intersection” is a mathematical euphemism for the start of a horrific famine. However, due to technological developments that Malthus had not taken into account, the disaster was ultimately avoided. Yet this issue is still relevant today. The ­United Nations estimates that the world’s population will reach approximately 10 billion by 2050. Meanwhile, due to climate change, the amount of available agricultural land is more likely to decrease than increase. So, Malthus could be proven right after all. To prevent his intersection in the 21st century as well, three econometrics and operations research students at Tilburg University are each developing a game for their bachelor thesis that focuses on an ­optimization problem in food supply. ­Under the guidance of Hein Fleuren, Mas van Gageldonk, Juliëtte Tillie, and Mark Smolenaers are each trying to find a mathematical optimum to feed as many people as possible with as few resources as possible. All three came across the Zero Hunger Lab through a guest lecture. Gageldonk: “I thought it was really cool that econometrics could also serve social purposes. The field is often fairly theoretical, with the goal of making as much money as possible. So, I thought it would be great fun to collaborate on an application that could really benefit people.”

Tricky trade-off Tillie is trying to make the imaginary ­African village of Agriville completely self-sufficient in its food production. Here,

the focus is also on the effects that a particular crop has on the rest of the ecosystem. For example, there must be bees to pollinate the crops. These insects have another benefit, which is that they scare away elephants. “The first step is to increase food production to ensure that Agriville residents simply get enough nutrients,” says Tillie. “Then we look at how to attract as many bees as possible without sacrificing the nutrients needed for the population. To attract bees, though, flowers must grow on about 25 percent of farmland. With a mathematical model, I am trying to find an optimal balance in this.”

“The goal of the games is to make it clear to players how complex the trade-offs involved in food production are” Van Gageldonk is looking at a higher level in terms of scale. His game focuses on food production across Nigeria. To do this, he has created a map of the African country, entering the soil type for each region. “The overarching goal of my game is to have as large a percentage of the population as possible get enough of all nutrients. You do this by growing different food types on each parcel of land. All parcels have their own soil type, so not every food type can be produced everywhere. Also, yield per hectare varies for each food type. In addition, all these food types contain their own nutrients, so there is not an equal need for each type. That ultimately creates a tricky trade-off of what to grow where to feed as many people as possible.” The game includes 29 food types, 18 soil types, and 19 nutrients. There is a recommended daily intake for each of the nutri-

ents. The score in the game is determined by how many people can get the recommended intake of each nutrient. So, if eighteen of the nineteen nutrients are ­produced in sufficient amounts, but one isn’t, you still have a poor score.

Inspiring project If you grow the same crop in a field every year, the soil will become depleted. The solution to this is to spread fertilizer, but that introduces new problems. For example, it poses significant environmental problems, known in the Netherlands as the nitrogen crisis. Also, the global supply of phosphate, a crucial ingredient of ­fertilizer, is in danger of running out ­during this century. In addition, this stock is highly concentrated in China and ­Morocco, which can create an uneasy ­dependency. Smolenaers is trying a different approach and is looking at how rotating different crops can prevent soil depletion. “By alternating between different types of crops, the soil remains healthy for longer,” he says. “Each crop type has a specific ­sowing date and a specific harvest date. If you optimize them, you can, for example, harvest one crop in May and sow another in June. Sticking to one crop type means waiting a year before you can sow again. In the game I’m creating, players have to maximize yields over a five-year period by growing crops in the right order.” It is not the intention to base policy on the games. “The goal of the games is to make it clear to players how complex the trade-offs involved in food production are,” Tillie says. Also, before the games can really be used as games, there is some work to be done on the graphics. Yet the project turns out to be very inspiring. Smolenaers: “When we had the interim presentation in October, a student from another group came over afterwards to ask if she might be able to do an internship at the Zero Hunger Lab. That just goes to show how excited ­people get about this.” Special Zero Hunger Lab | New Scientist | 27


“Every euro that farmers save on gasoline can be invested in feeding people” Valentijn Stienen and Joris Wagenaar are developing models to transport farmers to traders and food to disaster areas as quickly as possible. Now they have set their sights on reducing food waste. needs to know how the road runs and whether he can even use the road.”

Text: Laura Bergshoef Photos: Bob Bronshoff

How do you put the weather and the roads together in one model?


o to a food ordering site and enter your postal code. Or: open Google Maps and find the nearest supermarket. In the Netherlands, you always know where to find food quickly, “because here all the roads are known,” says PhD student Valentijn Stienen. “But that’s not the case everywhere. Take ­Indonesia, for example. Many local farmers there have no idea how to transport their food in the most efficient way. In some ­areas, such as jungles, the road network is not fully mapped. And imagine if a disaster were to take place there. Tens of thousands of people would be without food. It is vital that aid stations know how to bring food there quickly.” To map the road network in Indonesia, Stienen is building a mathematical model. He is doing this with his dissertation supervisor Joris Wagenaar. Both are affiliated with the Zero Hunger Lab and the Tilburg School of Economics and Management. “Weather is also an important part of our model,” says Wagenaar. “Regularly, roads are completely flooded by rain. A farmer

Wagenaar: “The first step is to collect all

the roads in Indonesia in the model. We have attached GPS trackers to trucks that transmit their location every minute. Sometimes we see several trucks driving

Valentijn Stienen 28 | New Scientist | Special Zero Hunger Lab

off a familiar road, into the wilderness. So, apparently there is a road there that is ­unknown.” Stienen: “The second step is to link the road data to weather data. For example, with the data from the GPS trackers, we can calculate how fast trucks travel along a specific road under certain weather conditions. A road where trucks turn around en masse during

heavy rains is flooded from a certain amount of precipitation.” How will this model be used in the future? Stienen: “First and foremost, this model is

intended for local farmers, so that they can understand transport logistics and planning. For them, it is important to know the fastest route to traders. Every euro that they save on gasoline can be invested in feeding more people. As the model was being built, other applications such as disasters were added. For that, we built an additional model.” What kind of model was that?

now have twenty years of data regarding the distances between the hubs and the locations of disasters. With that, we can calculate the ideal spot for the seventh hub.” Stienen: “However, it is important to note that disasters are unpredictable. If all the disasters in the last twenty years took place near a certain location, you don’t want to have all your hubs in that location. After all, the next disaster could take place on the other side of the world. But that is ­precisely the beauty of computer models. In them, you can include that uncertainty and unpredictability. However, to do that, twenty years of data is not much.”

Wagenaar: “When a disaster strikes some-

where, aid workers bring food to the disaster area from places where food is stored for emergencies. These places are called hubs. There are six hubs scattered around the world that were built twenty years ago. We

What makes food such an attractive topic for you? Stienen: “When I started studying econo-

metrics in Tilburg, I never thought that I would ever do anything involving food. I

have always enjoyed solving problems with math and models and have worked on many different types of problems. A while back, I was working on models for the airline KLM that calculate how to reduce the number of delays. Now I’m working on food. The great thing about that is that you see immediate impact. As modelers, we work a lot with numbers and behind computers, far from the problem. But the goal of modeling, by definition, is to build the most realistic model of the real world ­possible. That’s why we work closely with people in the field, such as local aid organizations. So, you can see right away what the model does for them.” Wagenaar: “I also see more and more econometrics students who, like Valentijn, are interested in themes within sustainable development, rather than just in business.” Why is that? Stienen: “During my studies, the textbooks

“When I started studying econometrics in Tilburg, I never thought that I would ever do anything involving food”

were mainly about maximizing profits and minimizing costs for companies. But the younger generation is increasingly aware of the world’s major problems. Some ­students are looking for ways to apply their knowledge to those problems.” Will you continue to work with the food theme in the future? Wagenaar: “Definitely!” Stienen: “After this, we want to come up

with methods to quantify food waste, so that consumers know how much food is wasted for a particular product. Food waste really is ridiculously common.” Wagenaar: “A good example is french fries. I saw a machine the other day that peels potatoes and in order to fit into the machine, the potatoes had to be a certain shape. Potatoes that were too thin or too thick were discarded. In this case, it was about 30 percent of the potatoes. Bizarre. I want to put the amount of food waste per product on the packaging so that consumers can make conscious choices. The less food wasted, the less food shortage.”

Joris Wagenaar Special Zero Hunger Lab | New Scientist | 29

Virtual child growth monitor To detect malnourishment in time, researchers at the Zero Hunger Lab are working on an app that evaluates photos of children. As a bonus, this Child Growth Monitor collects data that is sorely lacking. Text: Mirna van Dijk Illustration: Maaike Putman

30 | New Scientist | Special Zero Hunger Lab


or Dutch parents it is a matter of course: if desired, professionals closely monitor the growth and ­development of your child from birth. Weighing and measuring are essential in this process. Because early detection of malnourishment – or rather obesity, a greater public health threat in rich countries – saves lives. That is why research is being conducted at Tilburg University in collaboration with German NGO Welt­ hungerhilfe under the banner of the Zero Hunger Lab to detect malnourishment ­remotely, via an app. An algorithm can

“The app generates data that can be used to deploy food aid much more effectively” ­ ther things, children’s height, girth, and o weight from a photograph. It sounds complicated – and it is, for starters because public data sets of children’s photos don’t exist, Postma says. “Collecting photos of half-naked children is a problem for understandable reasons, so we are looking for solutions to that. Among other things, we want to see if we can use deepfake technology to generate non-existent children with varying body characteristics. We can use those to train the AI systems.”

Avoidable cases

“see” from images whether a child is malnourished or at risk of malnourishment. The Child Growth Monitor, as the app is called, can be thought of as a virtual detection of malnutrition. A prototype developed by Welthungerhilfe is already being used by professionals in the field. Ultimately, ­parents should be able to use the app themselves to send a picture to a medical team so that malnourishment can be ­detected and treated more quickly. PhD student Hezha MohammedKhan and professor of artificial intelligence Eric Postma are working with Marleen Balvert, assistant professor of operations research, and Çiçek Güven, assistant professor of cognitive science & AI, on algorithms for detecting malnourishment from images or videos. They are developing a deep-­ learning system that estimates, among

With an alternative data set, consisting of 3D scans of adult bodies, the team has ­already achieved promising results upon which it is now building. There is a ­partnership with pediatricians at the ­Elisabeth-TweeSteden Hospital in Tilburg. These doctors are enthusiastic about the idea and are sharing their thoughts on it, MohammedKhan says. “The next step in our research is to train our model on different datasets. The model needs hundreds of thousands of images to learn to recognize new images. We now have a dataset that is more varied from the previous one in terms of color, body shape, lighting, and distance from the camera. These are all ­aspects that contribute to how the algorithm works in practice. Eventually, our model will need to be tested on images of real children, but we’re not there yet.” 240 million children are starving, and more than 3 million children die every year from malnourishment that could have been prevented by early detection. These are outdated figures, as less can be measured in the field during covid. Moreover, the pandemic will significantly increase this number. Not only can the app save millions of lives, but it can also collect data in the field that is now sorely lacking, MohammedKhan says. “The current method for remote areas, for example, is to estimate how

much malnourishment there is, because recent data is often unavailable. People know that there are millions of malnourished children, but not always exactly where they are. The app meets this need as well. It generates data that can be used to deploy food aid much more effectively.”

Human in the loop MohammedKhan is a mother of a little boy of one and a half. She has also been committed to various humanitarian initiatives since childhood. In addition, she is an ­active speaker – including giving TEDx Talks – in the areas of war, poverty, and ­minority empowerment. She grew up ­during a period of war and occupation and suffered hunger as a child. This is partly why she is so passionate about her work, she says. “Working at the Zero Hunger Lab is a perfect fit for me. I want to dedicate my life and career to ­societies like the one I come from, Iraqi Kurdistan, which lacks just about everything. The impact of this project is huge; I say that as a mother, too. In the Netherlands, my child is being monitored and I am incredibly grateful for the confirmation that he is growing well and is healthy. And I’m highly educated. If you haven’t had any education, it’s very difficult to know if your child is healthy and what good nutrition is.” Postma emphasizes that the monitor should be seen as a tool; not as something that will replace people. “Recognizing a specific pattern is typically something in which a powerful machine is superior to a human because, for example, it never gets tired. But a machine understands nothing of our world and doesn’t look at it as a human does. That’s the big difference between artificial and natural intelligence. They complement each other and that’s why there should always be a human in the loop who understands the context.” Special Zero Hunger Lab | New Scientist | 31

Three young ­ do-gooders Franka Schellekens, Laurentiu-Cristian Ciobotaru, and ­Romée Geelen all wrote their graduate thesis at the Zero Hunger Lab. They look back on their projects and reflect on their motives. Text: Peter de Jong Photos: Bram Belloni

“Being able to help people makes me feel good”

32 | New Scientist | Special Zero Hunger Lab

Franka Schellekens (24) studied econometrics at Tilburg University from 2015. It made sense with so much mathematical blood in the family, she says. “My mother, my aunt, and my grandmother are mathematicians. It was a very enjoyable study program. I like solving difficult ­puzzles, and econometrics does that just fine. After graduating in August 2021,

I started working at Rhythm, a company specializing in healthcare logistics. I’m currently working on an assignment for which I am laying out a hospital ward as efficiently as possible. I can recommend that any student write their thesis at the Zero Hunger Lab. Everyone is ready to help you; there is a real team spirit. My thesis is about absorption capacity. Simply put, what amount of relief

supplies can be distributed, practically speaking, to victims after a disaster has occurred? I learned a lot about humanitarian aid at the ZHL. Did you know that organizing disaster relief is similar to ­organizing a festival? Think about it: all at once there are a lot of people in one place who all need to eat, drink, sleep, and go to the toilet. Also noteworthy are the global differences between the networks that provide

local responders in the event of a disaster. In Africa it is often the church, in South America it is the soccer fans, and in some parts of the world there are even gang members who ensure fair distribution.” And is she a do-gooder? “I find it hard to say. Hein Fleuren and Perry Heijne of the ZHL certainly are. In any case, being able to help people makes me feel good.”

“I am inspired by the story of poverty reduction. Romania also has poverty” The Zero Hunger Lab also has foreign ­students. One is Romanian Laurentiu­Cristian Ciobotaru (24). In 2019, he enrolled for the master’s program in econometrics and mathematical economics at Tilburg University. “I had ­always planned to study in another coun-

try. It’s good for your development as a person if you spend some time abroad. The Netherlands is a nice, open society with good educational quality. Whether there are differences? I’ll mention two: Dutch people are more direct than Romanians. And the Dutch eat mainly to get

energy; for us it’s mainly a social event. In other words: Romanians live to eat; Dutch people eat to live. For my thesis at the Zero Hunger Lab, I researched cash transfers in Burundi, ­Sudan, and Nigeria. This is the donation of cash to affected citizens so that they

Special Zero Hunger Lab | New Scientist | 33

can make a living as they see fit. This not only has a positive effect on people’s food security, but it is also very good for their self-worth. Furthermore, it has been shown that it doesn’t matter for the success of the cash transfer whether a man or

a woman is the head of the family, when you might expect women to be a little more efficient with the money. I had a great time at the Zero Hunger Lab. Everyone is very enthusiastic. It’s like a little family; “gezellig,” as you say. I am

inspired by the story of poverty reduction. Romania also has poverty. There were families where only one of the children could attend school. That made an ­impression on me. Yes, I would like to make the world a better place.”

“The knowledge we gain here, can also be applied in the third world” Romée Geelen (24) is here to stay at the Zero Hunger Lab. After completing her studies in econometrics, she was asked to participate in a PhD program. The final grade that she received for her thesis, a nine, must have contributed to that. “I’m going to be working on the Zero Waste Project. It’s about reducing food waste in Europe,” she explains enthusiastically. “Here, of course, there is less ­starvation than in the Third World, but the knowledge that we gain here can be ­applied there later. My thesis at the ZHL is 34 | New Scientist | Special Zero Hunger Lab

about dietary ­optimization. It suits me; I’m always into healthy eating. I researched the cheapest diets for Indonesia, using local products such as cassava, corn, tofu, and peanuts. With people getting enough protein, minerals, and vitamins, of course. An average household of eight people spends about 66,000 rupees a day on this; converted, that’s about 4 ­euros. A vegetarian diet is slightly more expensive. Whether it was fun at the ZHL? I must say that because of covid I was only at the

university at my graduation, but the ­atmosphere was very relaxed. Students sometimes complain about the super­ vision during internships, but mine was ­top-notch. I was provided with a clean ­dataset and was able to get started right away. I was given a lot of freedom in my research; it made me more independent.” And, when she has her PhD, off to the whole wide third world? “Who knows? I love to travel and explore.”

opinion commentary

Use analytics for other sustainable ­development goals as well Thanks to analytics, ­millions more people can be fed, as demonstrated by the Zero Hunger Lab. Time to unleash that same approach on other humanitarian goals, argues Professor Dick den Hertog.


he use of data and algorithms to make better decisions has increased dramatically over the past few decades. Today, analytics is essential to many companies’ success. It is noteworthy that the use of analytics by NGOs is still very low. There are many untapped opportunities here, namely, to leverage analytics for the United Nations’ Sustainable Development Goals (SDGs). This is exactly what Tilburg University’s Zero Hunger Lab (ZHL) is doing: using analytics to contribute specifically to the second SDG: zero ­hunger. The ZHL has already demonstrated in several projects that improvements like those that benefit commercial companies are also possible for SDG-2 applications. A good example is the World Food Programme’s Food ­Supply Chain Optimization project. In it, the ZHL demonstrated that by using analytics, millions more ­people can be fed. What are the reasons for the ZHL’s success? I see at least three. The first reason is that the ZHL is an expert in all three essential components of analytics: descriptive, predictive, and prescriptive. And all three

According to Dick den Hertog, the methods of the Zero Hunger Lab can also be applied to other Sustainable Development Goals, such as clean water and sanitation for all. ISTOCK

There is a rapidly increasing need among young people to do meaningful work components are important for the successful application of analytics. The second important ­reason is that ZHL researchers have extensive experience with the successful application of analytics. Many ­universities are conducting research in areas such as humanitarian logistics. ­Consequently, hundreds of scientific articles have been written on this subject. But only a small proportion of these articles have had a practical impact. Many

researchers at universities have little expertise in implementing analytics. Moreover, they are often primarily focused on writing scientific publications. The ZHL, on the other hand, is focused on practical impact. The third reason is that the ZHL knows how to connect with a rapidly increasing need among young people to do meaningful work. There is a huge shortage of analytics experts, but the ZHL is in high demand by talented young students and researchers. The reason is that, for these young people, using analytics to help make the world a better place – to reduce world hunger – is meaningful work and very fulfilling. It is high time to apply the ZHL’s formula for success to

the other SDGs. Inspired by the ZHL, we therefore established an Analytics for a ­Better World Institute at the University of Amsterdam, in collaboration with the ­company ORTEC and the Massachusetts Institute of Techno­logy. With this institute, we want to use analytics for the other SDGs.

Dick den Hertog is professor of operations research at the Faculty of Economics and Business at the University of Amsterdam.

Special Zero Hunger Lab | New Scientist | 35

facts & figures


According to the UN 811 million people will go to bed hungry tonight.





We think it is important that many people hear about the possibilities of data science in working towards a better world.




Every ten seconds a child dies somewhere in the world due to hunger and malnutrition.

zero hunger





Our solutions have greater impact when we work together in consortia with also other expertise involved.

ZERO HUNGER LAB There is only one Zero Hunger Lab that uses mathematics to help ­realize global food security.


Won with WFP for our joint project ­Towards Zero Hunger with Analytics. This award recognizes and rewards ­outstanding operations research, ­management science and advanced analytics.



Our partners are key in solving problems with data science, but also in helping to find problems and to find necessary knowledge.



Our students are involved in a wide range of SDG-2research projects and deliver new insights for our partners and often serve as a great stepping stone for future Zero Hunger Lab-research.

Articles from Zero Hunger Lab special (English)

3 min read

Improve helping

Perry Heijne and Hein Fleuren spearheaded the Zero Hunger Lab.