Transition from manual (visual) interpretation to fully automated gully detection is an important task for quantitative assessment of modern gully erosion, especially when it comes to large mapping areas. Existing approaches to semi-automated gully detection are based on either object-oriented selection based on multispectral images or gully selection based on a probabilistic model obtained using digital elevation models (DEMs). These approaches cannot be used for the assessment of gully erosion on the territory of the European part of Russia most affected by gully erosion due to the lack of national large-scale DEM and limited resolution of open source multispectral satellite images. An approach based on the use of convolutional neural networks for automated gully detection on the RGB-synthesis of ultra-high resolution satellite images publicly available for the test region of the east of the Russian Plain with intensive basin erosion has been proposed and developed. The Keras library and U-Net architecture of convolutional neural networks were used for training. Preliminary results of application of the trained gully erosion convolutional neural network (GECNN) allow asserting that the algorithm performs well in detecting active gullies, well differentiates gullies from other linear forms of slope erosion — rills and balkas, but so far has errors in detecting complex gully systems. Also, GECNN does not identify a gully in 10% of cases and in another 10% of cases it identifies not a gully. To solve these problems, it is necessary to additionally train the neural network on the enlarged training data set.

Quantitative assessment of the potential soil loss on arable lands in the European part of Russia (4 million km²) was performed at the regional level of generalization corresponding to the scale of 1 : 500 000. Mathematical modeling based on the use of the equation for calculating potential soil loss from erosion developed in the research Laboratory of Soil Erosion and Channel Processes of Moscow State University was applied for this purpose in combination with geoinformation technologies. The calculations were performed for a raster model of representation of spatial data, including slope gradients, slope lengths, soil properties, rainstorm precipitation, layer of snowmelt runoff, intra-annual distribution of rainfall, and land use types. New data were obtained on the erosional soil loss during the periods of snowmelt runoff and rainstorm runoff and on the total annual loss. An electronic map of erosional soil loss on the arable lands of the European part of Russia was developed. The average soil losses reach 11 t/ha per year under black fallow and 3 t/ha per year under crops with their soil-protective capacity. About a half of the territory is located under conditions of the potential soil loss of less than 0.5 t/ha per year, whereas soil loss of 10 to 15 t/ha per year predominates on the rest of the territory. The rates of soil erosion on arable lands in the European part of Russia decrease from the taiga-forest to the steppe landscape zones. The belt of maximum erosion intensity extends in the sublatitudinal direction within the subzone of mixed and broadleaved forests with a very high percent of plowed land. In addition, potential soil loss from water erosion was determined for 50 subjects of the Russian Federation in the studied area for black fallow and agrocenoses.