The article presents a new scheme of zoning of modern gully erosion in a large region of the Russian Federation. Automated landscape zoning by means of artificial neural networks was carried out in order to determine the natural and anthropogenic conditions for the development of the gully network. Erosion zoning was implemented on the basis of large-scale geoinformation mapping of gullies by the method of visual interpretation of high- and ultra-high-resolution satellite images for 2017–2021. The basins of small rivers (1314 in total) with an average area of 91 km2 are taken as operational-territorial units. 22688 gullies (including their holes) were identified in the study area, the average length of which is 65 m, and the total length of the gully network is about 1500 km. The density of the gully network averages 12 m/km2, reaching a maximum of 301 m/km2. The density of gully dissection is used as an indicator for the zoning of gully erosion, this indicator indirectly reflects the intensity of gully formation in geo-space. The dominant (84% of basins) are areas either with no gully dissection or having weak or very weak gully erosion. The main reasons for the widespread damping of gully erosion are related to changes in land use and in the climate system, as well as an evolutionary factor – the transition of many gully forms to the balka stage of development.