In recent years, research has been conducted in scientific institutions of the Ministry of Agriculture of the Russian Federation and the Russian Academy of Sciences on the introduction into practice of new technologies for the use of aerospace information in agriculture. The article, using the example of the Stavropol Territory, considers the possibility of using cloud services such as google earth engine (GEE) and Kaggle machine learning systems for mapping agricultural (agricultural) fields using deep learning methods based on remote sensing data. Median images of the Sentinel 2 space system for the 2022 growing season were used as data for the selection of training and validation samples. The total volume of the prepared training and training samples was 3998 images. One of the problems for researchers and manufacturers in the field of agricultural is the lack of centralized and verified sources of geospatial data. Deep learning methods are able to solve this problem by automating the task of digitizing the geometries of agricultural fields based on remote sensing data. One of the limitations in the widespread use of deep learning is its high demand for computing resources, which are not yet always available to a researcher or manufacturer in the field of agricultural. The paper describes the process of preparing the necessary data for working with a neural network, including correction and obtaining satellite images using the Google earth engine platform, their further standardization for training a neural network in the Kaggle service, and its further use locally. As part of the study, a neural network of the U-net architecture was used. The final classification quality was 97%. The threshold of division into classes according to the classification results was established empirically and amounted to 0.62. The proposed approach made it possible to significantly reduce the requirements for the local use of PC computing power. All the most resource-intensive processes related to the processing of satellite images were performed in the GEE system, and the learning process was transferred to the resources of the Kaggle system. The proposed combination of cloud services and deep learning methods can contribute to a wider spread of the use of modern technologies in agricultural production and scientific research.