Application of Machine Learning Methods for Classification of Agricultural Crops

Abstract

The article demonstrates the significant role of the impact of training samples on the processing of satellite images for the accurate classification of crops. To achieve the goal of the study, three machine learning methods are tested by classifying various satellite data with high spatial resolution. As a result of the application of machine learning methods, the results are compared and a method with a high classification accuracy is selected. Based on the obtained data, crop maps have been developed and an assessment of the vegetation state for the research period is carried out.