Analysis of Ust-Kamenogorsk Soil Radioactive Contamination Data Using Machine Learning Algorithms

Radioactive contamination of soil is one of the most important environmental problems affecting natural and anthropogenic ecosystems. The study of radiation background and radionuclide content in soil is necessary to assess their impact on the environment and human health and to develop mitigation strategies. Within the framework of the article the results of analysis of data of radioactive contamination of soils of Ust-Kamenogorsk city with the help of machine learning algorithms are obtained. The aim of the study is to analyze alpha, beta, Ra226 and Th232 indicators of the database of radioactive contamination of the soil of Ust-Kamenogorsk city with the help of statistical methods and machine learning algorithms. Models of comparison of experimental and calculated data of laboratory tests of samples taken for chemical, radionuclide and mineralogical composition were created, general correspondence of observations was studied