Application of machine learning methods to predict soil moisture based on meteorological and atmospheric data

Abstract

The purpose of this study was to develop and evaluate models for predicting soil moisture based on data from meteorological conditions and particle concentrations in the air. Two machine learning methods were used in the work: random forest and linear regression. The results of the study showed that the random forest model achieved 94% accuracy, while the linear regression model showed 92% accuracy. Air temperature, air humidity and the concentration of particles in the air turned out to be important factors affecting soil moisture. Both models offered good predictive capabilities, with an emphasis on the ability of a random forest to adapt to complex nonlinear dependencies, and linear regression to interpret the results. The developed models can be useful for optimizing agricultural processes, managing land resources and environmental monitoring.