Development of an Intelligent System for Forecasting the Dynamics of Changes in the State of the Earth’s Surface Using the Amur River As an Example

Abstract—The paper considers a model of an intelligent system that provides forecasting of the dynamics of changes in the state of the observed areas of the Earth’s surface, using the example of the Amur River coastline. An integrated method is proposed that takes into account short-term dynamic changes in the surface and long-term time dependencies that describe seasonal changes in the observed process. To implement this method, satellite data is collected and preprocessed, and then fed into the base and time models of machine learning. To improve the accuracy of the forecast, a metamodel of linear regression is used, which receives predictions from the time and base models. The results of the intelligent system are evaluated using various metrics. An experimental evaluation based on real data shows an improvement in prediction quality compared to individual model predictions.