Forecasting seismic activity using machine learning algorithms

¹ Bauman Moscow State Technical University, 105005 Moscow, Russia
² Reshetnev Siberian State University of Science and Technology, 660037 Krasnoyarsk, Russia
³ RSAU-MAA Named after K.A. Timiryazev, 127434 Moscow, Russia

^* Corresponding author: sofaglu2000@mail.ru

Abstract

In this paper, the possibility of using the random forest method to predict earthquake locations based on historical data was studied. The aim of the work was to develop a model capable of accurately predicting the geographical coordinates of earthquakes in India and adjacent regions. The model showed high accuracy of predictions, which is confirmed by low values of the mean quadratic error (MSE) and high coefficients of determination (R²). Analysis of the results showed that the model successfully captures patterns in the data and is able to accurately predict earthquakes in regions with high seismic activity. At the same time, areas with deviations were identified, which highlights the need for further research to improve the model and increase its accuracy. This study demonstrates the promise of machine learning methods in seismological forecasting tasks and can serve as a basis for creating more accurate earthquake early warning systems.