Decision-making algorithms for the identification of crops based on remote sensing data

Abstract

The article presents an algorithm for collective management decision-making. The developed algorithm is based on Bayesian mechanisms for resolving contradictions when choosing methods for processing of decisions. The algorithm is used for phased processing of Earth remote sensing data in order to identify agricultural crops. Functional satellite images created using the algorithm increase the accuracy of identifying plant objects. With the help of GPS navigator observation points linked by geographical coordinates, reference points have been created, according to which the classification of functional satellite images is accomplished, with the most accurate results of the distribution of pasture crops in contrast to the original image. The classification was performed according to four types of vegetation in the studied territory of Northern and Southern Nuratau of the Republic of Uzbekistan. Based on the results obtained, field work was carried out in order to test the remote sensing data obtained in relation to the identification of agricultural crops of pasture territories.