Earthquake time-series forecast in Kazakhstan territory: Forecasting accuracy with SARIMAX

Abstract

This research paper presents an analytical approach to earthquake time-series forecasting using the Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) models. The objective of this study is to investigate the effectiveness of the SARIMAX model in earthquake forecasting by considering relevant exogenous variables, such as historical seismic activity, geological characteristics, and geodetic measurements. We start introducing the SARIMAX models, explaining its mathematical formulation and the incorporation of exogenous variables. The research methodology involves collecting earthquake time-series data from seismological databases and preprocessing the data for analysis. Various SARIMAX models are constructed and evaluated using statistical measures, such as root mean square error and mean absolute error, to assess their forecasting accuracy. Additionally, the impact of different exogenous variables on the predictive performance of the models is analyzed. The results of this research contribute to the field of earthquake prediction by demonstrating the applicability and efficacy of the SARIMAX model in capturing the temporal patterns and dynamics of seismic events. The practical reason of the results provides valuable information for decision-makers and stakeholders involved in disaster preparedness and mitigation strategies.

More by Marat Nurtas

• Two-stage synthetic-to-real transfer learning for automated mammography report generation using vision-language modelsScientific Reports · 2026
• Macro-scale earthquake forecasting under class imbalance in Central AsiaJournal Of Big Data · 2026
• Enhanced Fine-Tuning Optimization for Real-Time Fire and Smoke Detection Using a YOLOv9 Architecture with a Comprehensive Ablation AnalysisEngineering Technology & Applied Science Research · 2026 · Citations: 1
• Spatially honest validation of machine-learning prospectivity maps for karst bauxite in KazakhstanResearch Square · 2026