Сluster analysis of long-term crop yield data in crop rotation

Abstract

Today, cluster analysis is one of the most effective tools for processing large amounts of information and is used wherever computing technology is used, since data and the results of their analysis play an increasingly important role in modern information society, and clustering allows for a better understanding of this data. Whenever it is necessary to classify a large amount of information of this kind and present it in a form suitable for further processing, cluster analysis turns out to be very useful and effective. The analysis of 48-year observations on 107 variables (crop yield, crop rotation by tillage techniques and means of intensification, crop contamination, soil moisture content under sowing during the growing season, the sum of non-vegetative precipitation, the sum of decadal precipitation and average decadal air temperatures during the growing season) using clustering by the Ward method allowed us to group observations into 6 clusters and use them to analyze the studied variables. An average positive relationship of soil moisture content before sowing with the amount of non-vegetative precipitation and a negative one with air temperature in May has been established. Linear regression equations of the positive relationship of yield with the consumption of soil moisture during the growing season, precipitation in June-July and negative clogging and average air temperature in May-July were selected.