4 minute read
Hidden path
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.
Text: Laura Bergshoef Photos: Bob Bronshoff
Go 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 needs to know how the road runs and whether he can even use the road.”
How do you put the weather and the roads together in one model?
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 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?
Wagenaar: “When a disaster strikes somewhere, 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 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.”
What makes food such an attractive topic for you?
Stienen: “When I started studying econometrics 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 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.”