 We would like to present some of our results of the last year. So all these years, we've been working with Globium. And I think we've come up some interesting stuff when we tried to model the regional distribution of Russian crop production with Globium to see how the greenhouse gas emissions do at different levels of our regions, how do they respond if there is some intensification processes or land expansion processes. So the reason why we were interested in this topic, so this first picture is kind of a historical background on the Russian development. So the blue bars is the crop production, which has been increasing in the last few years. And the green line is the respective greenhouse gas emissions from crop production and from land expansion. And for some years, for example, 2011, you would see that it's kind of jumping since the additional burst of greenhouse gas. So according to Russian national GEG inventories, when you expand the crop land, even if it's relatively small amount, you would get very high emissions because of the certain carbon content, because you turn the land once again. But the Russian national GEG inventories, they don't give the picture for particular regions of Russia. That's why we wanted to see what could be, let's say, the parts of Russia where this problem could be critical. So we just call it relatively simple to evaluate the carbon footprint from a crop production. We wanted to understand what regions are sensitive for crop land expansion. And for this, we had three objectives. So first of all, we wanted to put the official data for Rostat, Russian statistical agency, into global biome. So for those crops which are in global biome, the harvest area and the production area, and since global biome consists of these squares called fluids, we want to correctly redistribute the Russian regional production into the proper fluids. After that, we run the model. We look at what kind of emissions the crop production, the increase of crop production produces. It could be crop emissions. It could be land use changing emissions. And after that, we create an additional variable. We divide the crop emissions to the production amounts. We call it the grain equivalent. And also another important issue is that we calibrated the historical data for 2011 and 2017. So this grain equivalent, you can see it under this picture at the top. So for example, it's kind of the coefficient which the Russian Ministry of Agriculture created to turn every type of crop production into some equivalent where you can compare. So some closer to one, like wheat and barley, some are less than one. And high protein crops like sunflower, soy, they have more than one with its end. So since emissions are all calculated in CO2 equivalent, we needed this equivalent to properly calculate this carbon footprint. And for example, at the bottom of this page, you would see that actually when we tried to model this with Glow-Bind, we managed to do it more or less correctly all the production amounts in the harvest. And here we see that since there was actually some cropland expansion, you would have a lot of emissions from this cropland, particularly 46 millions, as the model calculates. So this picture is a little bit technical because we did a lot of changes in the model, in the coding to redistribute the Russian region production to the particular leads. So if you ever worked with Glow-Bind, it has a certain variables for crop area, for crop data, which my colleague Vladimir worked on. Maybe it's also important to mention that right now, Glow-Bind covers I think 65% of Russian crop area, most of the crops which were worked with wheat, corn, rice, rapeseed, barley, potatoes, sunflower, soya, for other crop types, it's kind of a little bit small. And also Russia has this specific area of feed stuff, grass feed stuff for, it is considered a cropland, but in Glow-Bind, it's kind of not the catalyst on the pastures. And also some procedures were done to calculate the shadow price. Also it helped us to redistribute this production amounts and harvest more or less close. So this picture, the next one, could be a little bit more interesting because here we have all these eight crops and the respective Russian regions, Russia is divided into 80 regions, something like this. And we just put them on this line to see how the model resorts closely match the official data. So for some crops, we actually had success like sunflower and wheat, for most of the region, the model managed to estimate more or less precise, but for some crops with very small fields like potato and rapeseed, the model still gives some deviation. So by now we couldn't make it any more precise. So now how does this look into, let's say terrestrial distribution? So on this picture, we have two pictures. At the bottom of the picture, it's kind of the crop production and this grain equivalent that we have. So most of the crop production is concentrated at what we call the southwest of Russia or the Black Sea basin closer to the sea where the most favorable climate conditions, the best soils. And if we move a little bit northern, you would have less red color because there is some production there, but not much compared to this region. But at the top of the picture, you would see the emissions from the nitrogen use and from land use change emissions. You would see that there is much more red regions which have emissions more than three or four million per one region, a million tons of CO2. So we see that some regions which don't have as much production as in Black Sea, they still cause a lot of emissions. And that's why we wanted to see this carbon footprint. And so this was the main picture that we wanted to do. So here we have... So the average carbon footprint for Russia will be 0.5 CO2 equivalent. If you compare it with one ton of grain equivalent, the blue regions on this picture is the ones with, let's say, more favorable conditions and they give less carbon footprint. It's less than 0.5. It's a lot of regions in Siberia, in the Volga region and the Southwest of Russia. But all the ones with the red color and the black color, they cause large amounts, well, particularly for Russia, it's large amounts of carbon footprint. It could be two, three, four, five tons of CO2 equivalent per one ton of grain. And for some regions here, it is caused actually by cropland expansion. Like, for example, in the center, you see this what we call Far Eastern District because they had a dramatic decline of the cropland in the beginning of 2000 and they started plowing this land back. And although the national statistics doesn't report it, we think that it could cause large greenhouse gas emissions and they were not compensated by large yields. So that's why we think it could have been a historical problem. And also another important thing, the last picture, is we wanted to compare our results with, let's say, some kind of soil sciences. And we found the paper of Dmitry Shepachenko, he works in the ASA. So he did a paper with his colleagues about the carbon content and different parts of Russia. So on this picture, you would see, let's say, in the Southwest of Russia, let's say the bright parts where the carbon content is relatively small in the soil. And then when you move to the North or to the Far Eastern, it becomes more darker. So you would have more carbon in this area. And we think it's kind of more fragile territories. And we think it's more or less close to what our results of the global model. I don't know if global uses Shepachenko maps or not. I couldn't find out that, but anyway, we think that our results could be close to this kind of other soil research. So that's what we needed. That's what we wanted to share. Thank you. Any big questions?