Abstract
The article discusses the important geoecological problem of predicting the dynamics of thermokarst lakes in the Russian Arctic as intensive sources of natural greenhouse gas emissions, which is considered as one of the factors of current climate change. The purpose of the work is to consider the development of a system for forecasting the dynamics of lake areas using entropy-randomized machine learning algorithms and tools of the NextGIS Web geographic information system. The procedure for processing information to predict the dynamics of lakes is considered. Data from remote measurements of the areas of thermokarst lakes in the Arctic zone of Russia, obtained from Landsat satellite images over the past several decades, and climate data determined by reanalysis of meteorological data for the same period are used as retrospective information for forecasting. The system is implemented on the basis of the NextGIS Web geographic information system, which allows the inclusion of randomized modeling applications using the Python language.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call