The spatiotemporal distributions of wildfire areas and FRP values for the territory of Russia and its large regions (the European part of Russia, as well as the Ural, Siberian, and Far Eastern Federal Districts) during 2001–2022 were analyzed using satellite data. For the territory of Russia, there was a decreasing trend in annual burned areas and a small increase in average hotspot FRP. At the same time, the largest annual burned areas in the territory of Russia were recorded in 2008 (295.2 thous. km²), 2002 (272.4 thous. km²), 2006 (261.2 thous. km²), and in 2012 (258.4 thous. km²). It was found that during the studied period, 90% of fire hotspots in Russia had a maximum FRP < 100 MW. The most intense wildfires (FRP > 1500 MW) amounted to only 0.1% and were detected mainly in the Siberian and Far Eastern Federal Districts. Interconnections between large wildfires and meteorological factors, including blocking activity in the atmosphere, were revealed.

Research was conducted using satellite data to study variations in parameters of various geophysical fields manifested in the lithosphere, atmosphere, and ionosphere during the preparation and occurrence of destructive earthquakes of 6 ≤ M ≤ 7.8 in Türkiye in February 2023. Precursor manifestations of these seismic events were satellite-detected in the form of anomalies in parameters of various geophysical fields, including: lineament systems, surface skin temperature and surface air temperature, relative humidity, latent heat flux, integrated flux of outgoing longwave radiation, altitude changes in ionospheric electron density, total electron content of the ionosphere, as well as aerosol optical depth. It was found that the anomalies of all studied geophysical fields detected using satellite data manifested most intensively during the period 3–13 days before the onset of seismic events.

Machine learning models based on regression analysis methods have been selected to identify areas of maximum risk for major seismic events. The performance of nine linear and nonlinear models was evaluated, resulting in the selection of the Random Forest model. The quality of training for the Random Forest model was improved through hyperparameter tuning as well as the use of clustering and polar coordinates. It allowed the improvement of quality of model training, increasing the value of the coefficient of determination to 0.86. An analysis was conducted on the applicability of two neural networks with deep learning: Multi-layer Perceptron (MLP) and Long Short-Term Memory (LSTM), using training parameters that were selected for the Random Forest model. Using this model and selected neural networks with deep learning, areas of maximum risk for seismic events were predicted for the entire globe, with a detailed analysis of predicted areas for the territory of the Russian Federation. As a result of the conducted research, the use of neural networks with deep learning made it possible to identify a greater (~40%) number of zones of maximum seismicity (with M>6) compared to the improved Random Forest model.

Changes in the altitude profiles of the ionospheric electron density (Ne) and the total electron content (TEC) were detected using satellite navigation system data during the preparation and occurrence of a powerful M8.8 earthquake (July 29, 2025, UTC) and other strong earthquakes of M ≥ 6 that occurred near the Kamchatka Peninsula in June–September 2025. A 9–18% decrease in the ionospheric electron density was detected, occurred 1–5 days before the M8.8 earthquake. A gradual decrease in the total electron content (TEC) began 3 months before the earthquake, ceasing 15 days before the event. Using the Long Short-Term Memory and Autoencoder neural networks, anomalies were identified in the time series of normalized values of the total electron content (NTEC) of the ionosphere during the preparation of earthquakes of M ≥ 6 that occurred in June–September 2025 near the Kamchatka Peninsula. The pattern of the anomalous variations in ionospheric parameters identified in this research corresponds to the characteristics of ionospheric anomalies during the preparation and occurrence of strong seismic events presented in earlier works.