 for and likes it. The meeting is being recorded with Heinz Fleur as professor for application of business analytics. He is the director of the Zero Hunger Lab, of which he will be telling in a short while. And he is a true ambassador of professional learning programs and the anonymous academy of data science. So Heinz, let me please go ahead and have a nice evening and have an inspirational session. Okay, thank you, Kierjean. And welcome to the audience. I really appreciate that you want to attend these kind of lectures and the Tilburg University knowledge sessions, as they are called. And that's always, let's say, the money earned with that that we can help some students who are, let's say, in difficulties due to the COVID situation. So what I would like to do tonight is show you a little bit the Zero Hunger Lab, but also explain why we are involved in COVID-19 research. And the idea is in fact quite simple. We have done a lot of zero hunger research. I will tell you a little bit about that, or I'll tell you quite a lot about that. I will also tell you about the COVID-19 research and how the two come together. This is research. It's going on. It's under construction. So no hard results yet. But we are seeing all kinds of interesting things. And that's what I would like to share tonight with you in this presentation. Let me introduce myself a little bit. I love math. And this is the math of maybe you recognize, math of the secondary school of my youngest. He also loves math. So what you see here is you see here an H. And an H is what we call a variable. A variable is something we don't know and we want to know or we want to optimize. But remember that there's only one H. You see H's over everywhere. I also love big data. And if you look to this picture, then you might not notice directly that two and a half billion data elements have been processed to make these seven graphs. And they are from a famous transporter, not being TNT. I did a lot of work with TNT, but from another transporter. And here they, let's say the experts in the company, they can really see a lot in these pictures. But it took quite some effort to make these things. And the final thing is I love to make the world, I love to make the world a better place. And this picture of this Yazidi girl really struck me. I was already quite some time working for United Nations World Food Programming as my students and research team. But this Yazidi girl, when she looks to you, she's hungry. And I cannot help her personally, but we can help maybe people like her in the same situations. And I'll explain how. So first of all, let me let me introduce you to the Zero Hunger Lab. The Zero Hunger Lab is quite, quite new. So, and I start with David Beasley. And David Beasley is at this moment the executive director of the World Food Program, and World Food Program is based with his headquarters in Rome. And he gave this speech a really thrilling speech to the United Nations on the 21st of April. And what he told me what he told the United Nations is that due to crisis like climate change, war and conflict, and especially grasshopper swarms at this moment in Africa, around this year, around 135 million people worldwide are really marching to the brink of starvation. That's how they are really in life, life danger. This is not talking about COVID. We'll come to that later. And this is really the situation before COVID. So let me give you a little bit of background how we started, let's say with this whole Zero Hunger Lab. From history, the research department in, and especially in Tilburg, we have become famous in applied research in logistics and in applying mathematics. And two times two years in a row in 2012 and 13, we have won the Franz Edelman Award. And Edelman Award is seen as the most prestigious prize worldwide for applying mathematics. And so it should not be something theoretical. It's something which has really been applied, which has really shown results. And I won it in 2012 with the TNT Express. Gia-Cian was also involved in that. And one year later, my colleague, Dr. Dikten-Hertog, Professor Dikten-Hertog, he has won it with the Dijkhaar project. And because of his work, we don't have to pay 7 billion euros in the Netherlands. Because our government wanted to raise the Dijk, which looking backward wasn't necessary at all. But this is not so, this was a little bit leading towards this work. Because some 10 years ago, around this time of this Franz Edelman Award for TNT, we were wondering whether data science or business analytics, whether it could be used in humanitarian context. And one of the great ideas came from Peter Bakker. And at that time, I was working for him, he was at that time CEO of TNT, the whole TNT group, which is now TNT Express and PostNL. But at this time, it was one company. And he asked me, in fact, this question. Because he was thinking of a kind of public-private relationship between TNT and the World Food Program. And he said, hey, when I see what kind of things you are doing here in TNT, can't we do that for humanitarian context? And I liked it immediately from the start. And especially if I had already been at headquarters of the WFP. And when you walk there through the corridors, you see all kinds of pictures of people in need or refugees, people who are hungry, but you also see all kinds of pictures about operations. And I was immediately sold. But then when you enter the World Food Program, then you enter completely, yeah, let's say for me, at least in a completely new world, there's a lot of things I didn't know. So first of all, what you see here is the World Hunger Map. And this World Hunger Map is produced every year by WFP with file statistics. And what you see is, let's say, how many people in the country are really, really hungry. So when you look worldwide, first of all, 821 million people, exactly that number that Beasley was mentioning, but that means one in nine in this world go to bed hungry every now, really every now. And then when you look to the World Map is what they do is with different colors, they identify how bad the hunger situation is. So in the blue countries, hunger is below 2.5%, but for example, here in this dark red, then more than one in three people fall into this definition of the 821 million people. So they go to bed hungry every now. So what we did there is, let's say, after some pre-work, the pre-work of convincing managers that maybe mathematics could help, which they didn't believe at all in the beginning. But what we did is we developed a mathematical model. And for tonight, I won't bother you with formulas, but I will try to explain it via this map. And so this is the World Hunger Map. And what you first do is you identify where the food is needed. And so let's, as an example, take these areas where you want to bring food. Then from all of their knowledge and databases, they also know where to procure food. Procure food in Europe and several places in the United States, in Brazil, Australia. And when you have mapped this out, then there are very many ways to transport it. So often it is sea transport and then combined with road transport in the end. And so there are very, very many possibilities. So think of what I explained in the beginning of this math of the secondary school, where you had one variable, which you want to know. Now, if you look to this kind of, let's say, pictures and you want to solve and you really want to find the best solution in this case, so the best transport solution from, let's say, a procurement to the place where the food is needed. You need really 100,000 to millions of variables. But there's modern mathematics that can be done and it can be solved. And then you get something like this. And so this is then, for example, the optimal plan. And the optimal plan balances the cost of procurement, of transportation, and of handling. So this is the cheapest way to feed all the people in the yellow notes by procuring in the red notes. And you can assure that the total sum of procurement and transportation cost is minimal. And you also see that at some places no food is bought. But when I've drawn it right, every place should at least receive food. And some places receive food from different directions. That is all possible. But when we were working on this project, this is what we call optimizing the supply chain, then we were thinking of something else. And this was really a fundamentally new idea. And when you hear it, you think, hey, why didn't they think of it before? But what we realized is that in the picture Richard just showed you that it was specified beforehand what kind of food people would get. So they get, let's say, 100 grams of wheat, 202 grams of lentils, 300 grams of beans, and 200 meters of vegetable oil per day. And then they multiply it with, let's say, 30 or 31 days in a month. And they multiply it with the number of refugees. And then they get an awful lot of tonnages. But when we were thinking about this, then we said, hey, people don't need lentils or beans, people need nutrition. So what we did is we changed the traditional fixed commodity, which was pre-specified, and we constructed the so-called flexible food basket. And we included that in the supply chain. And the result is that we not only optimized the supply chain, but also came to an optimal food basket. And to give you an idea, for example, in the traditional way, they prescribed that beans were necessary and the beans were bought in Brazil. But when you look from a nutritional perspective, then you can, for example, beans replace them with lentils, more or less the same, not completely, but more or less the same nutrients. But these nutrients, you might get them from Turkey, for example. Now, from Turkey to Africa, to Northern Africa, for example, is much cheaper in transport than beans from all the way from Brazil to Northern Africa. And so what you see here is that we have what our research delivered is a kind of interplay between the supply chain and the optimal food basket. And now that has been worked out in a tool, and the tool is called Optimus. And when you look to that, an Optimus is really developed by my students who were doing their master thesis in a row. I had five of these students in a row, and especially the third student, Kuhn-Peters, and he's still working for WFP. He designed this model, which I'm just described. And what you can see is here that a lot of inputs are needed because you need all kinds of nutritional data, you need procurement data, how expensive is it to buy one ton of lentils or beans? You have all kinds of transportation and shipping modalities. They all have that cost. Sometimes it's expensive, sometimes it's very cheap. And of course, and very important, you have funding. And because the WFP is funded by governments like the Netherlands, and Sweden, and Japan, and the United States. When we have gathered all this data, then it goes into this Optimus engine. And this Optimus engine does exactly what I just described. Of course, there's a lot of practical constraints that the harbor has a certain capacity that certain people have never seen rise, so you cannot ship rice to them. And field experts, they look at the solution, and then finally you get these kinds of plans. You see it on the map, how it should be transported, where it should go, you can see when it arrives, and you can compare all kinds of scenarios. In this way, and that was something which really struck me, is every time that we have applied Optimus in all the big operations in Yemen, Iraq, Libya, Sahel, we find improvements of 15 to 20%. And that is really enormous, this enormous amount. And I've worked a lot in these restaurant supply chains, and what I showed you in the beginning. But there you always see around 10%, if you do your best. But here, really due to the combination of this food basket and the supply chain, we could come higher than the 10%. And the nice thing is, at least the nice thing for us is that Optimus is now rolled out worldwide to all the 80 country offices of the WFP. And from next year onwards, they want to apply it worldwide. But looking at this and thinking it further, because we are researchers, as you can imagine, we thought, hey, when you look to the World Food Program, then what you see is they serve around 100 million people every year, 100 million. But what we have seen in the 100 map, which I showed you in the beginning, is that more than 800 million people are hungry. So there's a big gap between the two, still 700 million people to go, nearly one in 10 people on Earth. So what we decided, what we were thinking one afternoon is, hey, why? Based, of course, on the results which we got at the World Food Program, which is called emergency relief. You help them in case of emergencies, whether it can be floods or earthquakes or drought, or these crosshopper swarms. But we've been thinking also on the other side, maybe we can also do something for more sustainable development, that people can feed themselves. And when you start to think about that, when people need to feed themselves, then you need to think of what kind of crops do people need to grow in Africa? And then when you think a little bit further, then you see it is more or less the same, from a data science perspective, of course, it's more or less the same problem as what we solved in the relief situation for the U of P. And so the idea was that in the zero overlap, with better decisions, with data science, we might help both. And so we might help organizations who work on emergency relief, like the United Nations, but also organizations which work on sustainable development, who really try to work with local farmers in Africa, or in 1000 million. And that was, in fact, the idea of the Zero Hunger Lab. Now, the Zero Hunger Lab is a kind of platform. I won't explain too much about it, but we want to be a platform where everybody meets everybody and where we can really, really help each other. And so what you see here is the United Nations kind of organization. What you see here is the organizations with whom we work, they are all working in different versions on reducing hunger. And we are also working with these Wageningen, of course, Tilburg, also some connections with MIT in Boston. And of course, we also want to go to Africa, work together with African universities, with African business, and with African governments. And there we hope to work together via the World Bank because they have very good connections there. Now, this idea of the Zero Hunger Lab, the Ministry of Foreign Affairs was very much interested in it because our ministry gives a lot of money to WFP. And of course, they were proud that the Dutch could help WFP a lot. So what they have decided is to give us a kind of startup subsidy if the university would help. And now there's kind of co-financing at this moment. So the university also partly finances this initiative. Together with the university fund also helps. And these three together are our, let's say, initial start funding that we can do this work. Then over to COVID-19 research. And I go back to David Beasley again because a few sentences further on what I just showed you, David said to the United Nations Council, due to the COVID-19, an other 130 million people will walk the same way as these people who are, let's say, at the brink of starvation. And he added to that that will already happen this year. And that means that when his analysis of the WFP, when that analysis is right, that after the summer, maybe 300,000 people will die per day because of hunger, not because of COVID, but because of hunger. So if you look at the total COVID crisis at this moment, I believe, around 350,000 deaths, that will be reached in one or one and a half day in the hunger scene in Africa, in South America, and in Asia. And so really something needs to be done. And when the first lockdown in fact hit us in the Netherlands, we were still at that time physically together at the Zero Hunger Lab. And we were thinking, hey, can't we do something with our, let's say, mathematical skills? And can't we do something to help people, also in the Netherlands? And only later we realized that COVID might have, let's say, an enormous impact on hunger. We didn't realize it in the beginning, to be honest. And so we were just simply thinking of the Netherlands and then suddenly in the lockdown, people were sitting at home, you see the pictures, and people see each other via a crane and through the window, the economy went a little bit down, and in some sectors very much down. And so what we thought is, hey, can we help with data analytics? And we just decided to give it a go. And we reached out to, let's say, organizations in the front line, like the ETZ, that's the hospital interwork, RIVM, POTSHA, that's the United Nations Disaster Organization, and the organization, Lot C, who works for the Caribbean. And as you know, we have some islands still in the Caribbean, sometimes independent companies, sometimes municipalities, but they are also in danger. So what we did is we developed a model. I'm not going to explain this to you, but this is in fact our model, where we look to how COVID developed itself. And in a few pictures, I will try to explain you what we are doing. So what we have done is for the Netherlands, we have divided these 70 million individuals, we have spread them over age groups. And that is already a difference with the RIVM model, because it's for them, it's very difficult to look at different age groups in their model. And what we are also doing is we look to regions. And we have taken the so-called co-op regions, maybe you know, for statistical purposes in the Netherlands, our provinces are divided in the kind of sub-provinces, which are called co-op regions. And all our statistical analysis in the Netherlands takes place on co-op regions. And we have roughly 40 of them in the Netherlands. And so what we did is we looked at the co-op regions and we looked at the travel patterns in the Netherlands. And in this underlying model, we also need to know when people get affected, how this whole infection mechanism works. And when people get affected, they follow quite some stages. They are healthy and then they become infected, but they have no symptoms. They are also not contagious. But in a certain stage, they get symptoms or they get contagious, etc. And it might end up that you get cured, but it might also get that you end up in an IC or even don't survive it. And so that is what we do. What helped us a lot here is that we, people from virology, from the ETZ in hospital in Thunberg, they helped us to think about how these stages work. But still, it is very little is known about how this mechanism works. But what we try to do is to make this model, this corona model, and where we can ask questions what happens if we leave all the messages tomorrow? What happens if you stay in the lockdown from a health perspective? What happens if only people of a certain age can go out? Because in our model, we can work with different age strategies. For example, that you start an economy below the age of 40 or 45. And we can simply see what happens. Not that it is per se a good idea, but we can at least see what happens. And maybe also we can look to a kind of containment measures if only people in a certain region can go out. And when you look to this and when we were thinking about this more and more, it appeared to us that we needed not only for the Netherlands, but that we needed especially for our hunger lab. And that's where we bring the two research fields together. And here I quote another not David Bisley, but exactly the opposite side, an anonymous refugee. What he said to the newspapers, I don't fear the COVID fears. I will have died from hunger long before the virus reaches and I think, yeah, we could not have said it better. And that is what we try to identify. So what we do is, in fact, in our research or what we try at this moment is how we have the situation in the Netherlands. In the Netherlands, we have relatively good information. So what we do is in our model, we try to estimate the COVID-19 parameters. And this is COVID-19 parameters. We go to situations like refugee camps, like slums in big cities, like countries in Africa or Asia or South America. And there we try to forecast what happens and we try to find out how it relates to food security. Because when you think of, let's say, these kinds of situations, these are slums. And slums are around years of slum in Lagos. You see how crowded it is. You also see it here. A simple lockdown and the one and a half or two meter distance rule often doesn't work. And let's say the medical care is not what we are used to in Western Europe and US and Australia. And so people, there are no breathing mechanisms. And so we need to do something. And so what you can think of with our modeling is that, let's say, that you make in such a situation, you're left under, that you make a certain containment and that you try to restrict context between various parts of a refugee camp of a slum. And that you work with certain age groups. And because what we can do here in the West is we can, at least for a short while, we can shut down our economy or partly shut down our economy until the virus has completely... But that is simply not possible in many countries in the world. Because you have a lot of people who earn their daily loan and the daily fee and then they go home and from the day they buy their food. When from one day to the other, let's say their fee stops, they can't buy food anymore. And so hunger is immediately an issue if they do a lockdown. And unfortunately, you see some of these governments in Africa, you see a kind of copy behavior of the Western environment. And so they do a lockdown. But that might have disastrous results. So what we hope is that we can help with our modeling, what to do in such a situation. And then we could also look to strategies which we don't have to look into. But for example, this age-based strategy where you say, okay, all people below 40, 45, 50, they do their normal daily thing. And they also don't keep the one and a half meter distance. And then they get probably a lot of them will get the virus. But they will survive because they are young. And when we look to the numbers in the West, and you see relatively very few young people die. Of course, there are examples. But not that very many. And these countries, they don't have the luxury to take other measures which we have. And so what we hope is to help is with our research. And we are not yet ready. We are fully investigating at this moment how it works. But we hope to answer these kind of measures, this kind of question. So what if no measures are taken? What if there's a lockdown? What if only people of a certain age group can go out? And maybe we can work this compartmentation. And these kind of things we want to answer by bringing these lines together. That's what I would like to convey to you tonight. And I would like to open the floor for questions. And I understood that the questions should go via chat to Hia-Chan. And then Hia-Chan will hand the question to me. All right. Do you hear me? Yeah. All right. So we have this one question came in from Barbara. And please, every other participant, please. Ah, there's some more questions coming in now. But Barbara, please, can you unmute your phone and ask a question yourself? Yes, of course. I hope you can hear me. Is Barbara Flüger from Switzerland? Yeah, great. Welcome, Barbara. Okay, great. I really like the presentation because of the content focus. And actually also, let's say, looking into resolutions and not, let's say, the problems and the issues. My question is to Hain, about what would you call the top three success factors to really be able, let's say, to scale the optimal solution into these 80 countries? So because it's not all about funding. It's not all about policymakers. So what would you say? What were the top three or what would be the top three success factors to really be able to do to achieve that scalability? Yeah, it's a very good question. And so we discussed that already a few times over the last week. And because here we can look back a little bit because because it is applied, the top three things are, and then first I start with management. We really have to convince management that these kind of, let's say, new techniques in data science that they really can help. And that people, let's say, trust the outcomes. Because literally when I came at WFP, they asked me, Hain, what are you doing here? And we are shipping taxes. And by playing games and these kind of things, at least we could do some research. Now, once the research results came out from the students, then they started to get, hey, this is very interesting. Maybe we came up with an alternative. So that is one, that is management. Then the second one, I think, is data. And what you see in humanitarian context, that there is not so much data. Old data, which is there, is towards, let's say, satisfying the donor. Because every NGO, every United Nations organization, they should give feedback, reports to the donors. And all the things they gather is towards the donors, and not so much towards their own operation. So they cannot, let's say, yeah, how do you call it? No. And the third one I would say is really work together with the organization. Because when you work as a data scientist, for many data scientists, it is a kind of natural habit to think, to listen a little bit, and then think, oh, I understand it. I go back to my office or my research lab, and I'm going to code. And I'm going to do all kind of data analysis. But then you probably end up with a solution that will never be used. So what we did is we worked a lot together with WFP, an every step, and that took quite a while. Every single step we discussed with them. And this is the assumption you make, these are the results we get. And that really helped, let's say, in making it work in the end, and getting it accepted. So these are would be my top three. Okay. Thanks a lot. I just want to comment on the humanitarian. So the second one, what you talked about, the focus on the benefactors, and rather not on the operational side. I opened up a project now for vulnerable groups, especially homeless people, and people that are facing home loss due to Corona, work loss, home loss. There are many people in Europe into Germany, but also even Switzerland, that are not being able to finance anymore their rent for the apartment, but need to really go into a shared room facility or apartment facility as an adult, as a working adult. So where there's a lot of issues also on dignity acknowledgement and support. And I'm looking here into a new kind, also, let's say methods based on engaging the ecosystem. So engaging the local cells, how I call it. And that's what I hear also a bit from, or what I also hear from you, right? So, yeah, to look into that into the operational aspect, and how to really, let's say, gain reachability. And that's very important because what you see often is these organizations are sometimes largely run by volunteers. Yes. The best ideas is the best attitude. But sometimes it's not enough, especially in very complex situations. And there are these data science solutions. And when you want to involve them so that it's not a kind of black box, but when you involve them, that can really help them. Yeah, because we have a couple of hundred volunteers, just even solely in the US, for example. And we are now looking into what I call ecosystem thinking that's the message I developed over the past 10 years. And because otherwise, it looks more into, let's say funding, I would not say disappear, but funding gets spread into tiny little actions, but will not, let's say, support the overall momentum of diminishing poverty and homelessness, right? Or also, let's say, helping the health care sector, right? Yeah. Okay. Thank you. Yeah. Thank you. Thank you. There was a question of Hanukkah asking if the slides were going to be or the presentation was going to be provided afterwards. And yes, I can confirm that the entire PowerPoint that will be sent to you after presentation tomorrow. So that was the question of Hanukkah. And then we have Renz asking a question. Renz, are you still on board? Can you please unmute Renz? I'm not sure if Renz, let me pose the question because you wrote it down. Did you assess and include the impact of the need in the street on the world hunger problem? His microphone doesn't ah, his microphone doesn't work, it doesn't function tomorrow. So that's why you're asking me to pose the question. So the question is, did you assess and include the impact of the need in the street on the world hunger problem? Yes, that is a very, very big and important issue. And we are not so much involved at this moment in that kind of research. You see this kind of research in Wagening. And I was, lately I was at the commission in Wageningen and there they looked really into the effect of going to a more vegetarian or even vegan diet worldwide and the effects. So this is not our own research, this is Wageningen University research. And what they found out that the effects on, especially on water usage and depletion and the use of grounds is enormous if we could reduce the meat industry a little bit. Because the meat industry, what you now see happening in South America is large, really large amounts of the country and forest is destroyed simply because we want to have our cattle there. But we also need grounds to feed our cattle. So if you, if you really look to the total picture, then in cattle, yeah, it is there for at least sometimes a few years, sometimes half a year, depending on the type of meat you have. And so year after year, you'll even have to do that. And also the water use is huge to produce. I just, some time ago, I read the study that if you reduce your meat consumption in a year by only one kilogram, one kilogram over a whole year, then you can take, you can shower as long as you want that year. But that's the same effect. And it's only reducing one kilogram of meat. So there's a lot to say. But yeah, on the other hand, a lot of people like meat. So there are a lot of cultural aspects to it, especially in South America. People see it as a kind of well-being, healthy thing. And so there's a lot, a lot to do to change that behavior. And so yeah, but it has, it has an enormous footprint that that is clear. Thank you. Well, thank you. I hope that answers your question. If not, please let me know. Again, by chat. I didn't get any other questions in the meantime. So if there are any other questions, please post them now. In the meantime, hey, let me ask you a question myself. Because you were talking about the model that was used for WFP. And I was just wondering, yeah, because you, you show examples of using the model for the food hunger program. But can this model also be applied to other sectors, maybe pride by organizations or other, or where would this model be very useful in what kind of sectors or what kind of issues that private companies are facing? Yeah, so what we asked, and we have also been thinking about this, but not that much, to be honest, because as you have seen there, the hunger problem is so big that the problem is a little bit that the model is developed by WFP because we have done the initial work and they have worked, they have taken it further and they indeed have really invested a lot of time in it. So it is not easily available for other organizations, but I think if you could push a little bit towards it, then it could be made available. So what I see in the first thing is that we are going to help other organizations by so that they can apply more or less the same model, for example, well, for also a very big organization. That's one thing that the other thing where you might apply it is what I showed you in the difference between relief value after disasters and let's say more development side. And what we see is that we can use more or less the same kind of models there. So what we hope is that we can help a lot of development organizations and local governments, for example, the government in Nigeria, of Liberia or Yemen, and that we can help them with these models to find out what kind of crops they should grow in their country or neighboring countries to feed their own population. Now, I think if we are there, then we have really done a good job. But there you will see that there's also a lot of politics involved in these kind of things. And still, yeah, the model can also be used, for example, maybe you're pointing to that for medicine distribution. But we have never looked into that. So another question came in from Leendert de Jong. Leendert, are you still on Please unmute your microphone. Leendert, you know one another. You're on mute, Leendert. Please unmute on the left hand side. Left hand side down. Here I am, Hi Heijn, and here John. Hi Elendert. And all the others. My question is, WFP is a corporation of many different organizations with different targets, different goals. It seems to me that it's very difficult to bring them together. Could you tell something about that cooperation and how it works? Yes, I can. I hope this is not recorded. I will say it politically. WFP is doing a fantastic job. You cannot say otherwise. They are doing, they are serving 100 million people on this planet. They are simply the biggest transportation company on earth. Bigger than UPS intelligence is bigger than FedEx from the numbers I've seen. But on the other hand, there's also a lot of criticism. Because by bringing food to people, they become dependent on that. And what you see is these organizations tend to become very big. And when they tend to become very big, then you know what happens. You get all the, like in every big organization, it's not specifically WFP, but you get all kind of political things in it. You get power games, you get ego things. And yeah, to be honest, that was from time to time, it was quite heavy. It was quite heavy to deal with it. But yeah, what we have done is simply step by step, we have gone through it. Because the research I've told you about this evening started in 2011, 2012. And we are now talking 2020. And we are now rolling it out. But that is eight or nine years work. And that's not because the things I explained about that the model is so difficult, or that the data, the data is indeed, it takes quite some time and takes you a few years to get the data. But a large part of the time has been spent on that people didn't believe in it. And then suddenly a manager changed and he believed very much in it. And now this this kind of yeah, of processes happen. Thank you. Thank you. So another question came in from Mark Damon. Mark, are you still on? Hi. My question is as follows. The model that you're developing for COVID at the moment, together with your group, of course, will probably have a very big perhaps huge impact on decisions that countries or ministers, whoever, decide to take there. My question is, what is your approach in validating your model in this still developing world with all of these uncertainties? And how do you deal with these uncertainties? Yeah, it is a very good question. Thank you, Mark. That is one of the things. But what we see happening, first of all, in COVID, there are so many uncertainties. But some data is quite accurate. For example, the IC hospitalizations are quite accurate. The number of deaths is relatively accurate. And we have some numbers. And what we see is when we try to combine these numbers in one model, we don't get it, we can't make the fit. And so there and that is already quite interesting. And so and that is what we want in a few weeks time we want to publish about. And that's the numbers which we have right now, because many research groups that they focus on a particular thing, which they want to find out. For example, how long it is that somebody is contagious before he gets symptoms. And what we see is from the numbers of the literature, because we have looked at all these papers, we can't make it work. So there must be some numbers must be wrong. And that's the uncertainty which you are pointing out. And what we do what we try to do is to identify which of the parameters are the most important for the spread and the prediction of COVID. And some parameters might might not be that important and others might be very important. And we try to figure out which which are the most important let's say three to five. And with this we were also in let's say in developing countries until and that's what we do in parallel until new information becomes available. Suppose that people from virology or epidemiologists just that they find out new and new things. Then we try to include them in the model and make new estimations and then hopefully a more accurate estimations. I bet you are right. This is the state of things we know now. It is quite uncertain. It's quite uncertain. But at least already now we see that certain figures can't be true. They don't make this sure. Okay. Thanks. Thank you Mark. So that's a final question also getting the time. There's five minutes left. So this is a question from Constantine. His mic is also working. So I'm going to present to you. I'm going to read it out to you. To follow up on the meat discussion. Who makes the session on which nutrient or protein source to transport lentils or beans is a big protein source. Why not chicken meat as an example? On what or who is that determined in the model? And the decision to go to lentils and start with something else has a high impact for some companies like land for producers. And is there a question or a question basically? It's not not completely clear partly because I couldn't hear you well, but taking on on the meat discussions and replacing it with chicken, maybe it's good to realize that let's say in the WFP situation we are not talking about meat at all. And because these are very, very basic diets to let people survive. And of course these diets, they contain the most necessary ingredients. They have the necessary energy content, they have the necessary proteins, they have the necessary fat and they have the most important vitamins. Meat is in no way in these diets because you should imagine that these tonnages, they should be shipped. They are shipped over thousands of miles and they are really underway for more than three, four, five weeks. Now things like meat or fresh products, they cannot be shipped in that way. So this is really to let people survive and it's all composed of commodities which you can keep already for a long time, which you can store let's say for two, three months. And looking to this question in general, because I think it's a fair question, is yeah we should, or Wageningen or other research group and I think they are also working on that. What if people don't eat meat from cows and horses and pigs anymore, a bit more from chicken and also from the sea and these kind of things. I know that this is being investigated, but I don't know results by heart. Okay, thank you very much. Hopefully that answered your question on something. And with that I'd like to nearly close the session, not before asking if anybody has any more questions or wants to continue to some way or another to the zero hunger line. How can they reach out to you? In the presentation at the end of the last slide is my contact card. My contact details are in there. And what I really hope is that, of course, that you like this presentation, but also that you like the work. And if you know people who would like to support this work or have questions, they can simply reach out to me and my email is there and I will try to answer as soon as possible. Okay. Thank you very, very much for this very interesting and inspirational session. I'd like to ask everybody not to close down and to leave the session, but to look at the short video of Redery Knut, our director of observations after this presentation. But after this video, the session will be shot and will be closed. So once again, thank you very much. If you liked the session, please let us know through the chat while you're watching the video. And hopefully looking forward to meeting you for our next session, which will take in a week's time. Thank you very much and have a nice evening. Thank you. Good evening. I really hope you enjoyed today's content, today's webinar. It was offered to you by TS School for Business and Society in cooperation with the professional learning program of Tilburg University. And I hope it was exciting and that you learned something. And that's what we are as a university. We're supposed to learn you something and inspire you. And my name is Redery Knut. I just wanted to tell you a little bit about our students. I'm director of alumna relations. I'm also director of the Tilburg University Fund. And there is something that's concerning me and I wanted to share that concern with you. A lot of our students, especially international students, are having a really hard time. Many of them lost their jobs in bars and restaurants. So they have no access to funds. Many of them have lost the support of their parents because the parents became unemployed. So they struggle financially. And we all know if you struggle financially, it's really hard to concentrate on your studies. And that's why the Tilburg University Fund has decided to allocate funds to help these students. And today, I would like to ask you for your support. If you enjoyed this webinar today, I'm really hoping that you would like to show your appreciation by donating to the fund to help our students. We'll be taking the liberty to send you a SMS, a ticky, with a request for a donation. And obviously, if you don't like this, please delete it. No obligations. But if you share your my concern for our students, then please consider donating. And that would not only make me very happy. But obviously, it would really help our students and make them happy and make them able to concentrate on studies and finish this year successfully. Thank you so much. Hope to see you again next webinar. And have a nice evening.