Assessment of crop heterogeneities is one of the key conditions for predicting crop yield and increasing the economic efficiency of farming. The aim of the study is to develop methods for assessing in-field heterogeneities of soybean based on remote sensing data and to determine the relationship between soybean productivity indicators and soil characteristics. The work was carried out on meadow-brown heavy loamy soil, 10 plots of soybean field with a total area of 36.9 ha (Khabarovsk Krai) were selected for sampling in May and August 2023. The research was based on the results of remote sensing data processing (Sentinel-2 satellite, DJI Mavic3M quadrocopter), assessment of soybean productivity indicators, agrochemical, physical and chemical characteristics of soils and micro- and macroelement composition. The spatial distribution of NDVI modeled from Sentinel-2 data (early August) corresponded to the distribution of NDVI from DJI Mavic3M data. NDVI index values in August 2023 were found to be significantly correlated with soybean height (R = 0.64) and number of beans (R = 0.64). Soil moisture has a positive correlation with NDVI (R = 0.87) and soybean height (R = 0.68) for the entire growing season of the crop. NDVI was positively correlated with Hg (R = 0.79) and negatively correlated with pH (R = –0.79). The content of N-NO3 ranged from 2.51 to 6.84 mg/kg (V = 35.12 %), mobile forms of Р2О5 – from 2.47 to 6.07 mg/100 g (V = 33.13 %), К2О – from 4.98 to 9.37 mg/100 g (V = 20.07 %). The variability of N-NO3 and Р2О5 content decreased to 11.61 % and 21.99 % by August. No significant changes in soil bulk composition were observed between the first and second sampling. Variation of content of rare-earth elements (Sc, Y, lanthanides) in the selected sites did not exceed 5 %. By the date of the second sampling a significant decrease by 4–10.5 % (p 0.05) in the content of rare earth elements in soil was noted.