 The study developed a method for automated detection of crop lands and natural grasslands using multi-year time series of the vegetation indices. This methodology is based on a new recognition feature which enables identification of all lands cultivated over a long period. This feature is calculated from time series of the Modi's vegetation indices and takes into account both inter-seasonal and inter-annual characteristics of the vegetation period for arable lands with spring and winter crops, as well as for natural grasslands. The methodology also includes procedures for obtaining time series of the NDVI and EVI vegetation indices for the period from March to November in the given years, generalizing the time series by land cover categories in agroclimatic zones, calculating the recognition feature in each zone, adapting the decision rules to the regional environmental conditions, threshold values for the agroclimatic zones, and classifying the data into crop lands and grasslands. The results of this study show that the developed recognition feature can be successfully used for crop land detection and can improve the accuracy of data interpretation when applied along with other features. This article was authored by M.A. Vanoff, S.S. Mokromova, O.P. Yermoliev, and others. We are article.tv, links in the description below.