Earthquake Magnitude Prediction Using AI in Light of Environmental Factors

Authors

  • Moeez Ahmed University of Sialkot https://orcid.org/0009-0004-6711-4851
  • Aysha Saddiqa University of Sialkot
  • Saqib Ali University of Sialkot
  • Zeeshan Saleem University of Sialkot
  • Adeel Ashraf University of Sialkot

DOI:

https://doi.org/10.33411/IJIST/1987

Keywords:

Earthquake Magnitude Classification, Environmental Factors, Feed-Forward Neural Network, Temporal Validation, Class Imbalance, Explainable Artificial Intelligence

Abstract

Earthquake magnitude-category modelling is difficult because damaging events are uncommon, catalogue observations are temporally dependent, and environmental associations may be weak. This study integrates daily United States Geological Survey (USGS) earthquake records with mean temperature and precipitation from seven Alaska Climate Research Center (ACRC) stations for 1960–2023. A reproducibility track retained the submitted random 80/20 split, whereas a reviewer-driven chronological protocol used five expanding-window validation years (2017–2021) and an untouched 2022–2023 holdout. On the submitted split, the original FFNN achieved 75.30% accuracy, macro precision of 73.13%, macro recall of 71.01%, and macro F1 of 68.54%; its Major-class precision, recall, and F1 were 71.32%, 45.83%, and 55.80%, respectively. Relative to the strongest non-FFNN baseline, this was +0.41 percentage points in accuracy and +1.63 points in macro F1, although stacking gave a slightly higher Major F1 (56.65%). “Under chronological validation, the compact FFNN averaged 65.72% accuracy and 40.57% macro F1. On the untouched holdout, the decision tree produced the highest Major F1 (14.67%). A paired environmental ablation showed modest lagged-feature gains: holdout Major F1 increased from 9.86% to 14.57% for FFNN and from 15.22% to 21.40% for LightGBM. However, the confidence intervals crossed zero and Holm-adjusted tests were not significant. SHAP analysis ranked depth and year above temperature and precipitation. The evidence therefore supports environmental variables as secondary, model-dependent signals rather than dominant or causal predictors.

Author Biographies

Moeez Ahmed, University of Sialkot

Lecturer

Department of Computer Science

University of Sialkot

Aysha Saddiqa, University of Sialkot

Lecturer

Department of Software Engineering

University of Sialkot

Saqib Ali, University of Sialkot

Student, MS Computer Science

Zeeshan Saleem, University of Sialkot

Lecturer

Department of Software Engineering

University of Sialkot

Adeel Ashraf, University of Sialkot

Student, MS Computer Science

References

“What is an earthquake and what causes them to happen? | U.S. Geological Survey.” Accessed: Aug. 03, 2026. [Online]. Available: https://www.usgs.gov/faqs/what-earthquake-and-what-causes-them-happen

“Continental Movement by Plate Tectonics | manoa.hawaii.edu/ExploringOurFluidEarth.” Accessed: Aug. 03, 2026. [Online]. Available: https://manoa.hawaii.edu/exploringourfluidearth/physical/ocean-floor/continental-movement-plate-tectonics

A. M. Dayal, “Basin Structure, Tectonics, and Stratigraphy,” Shale Gas Explor. Environ. Econ. Impacts, pp. 55–63, Jan. 2017, doi: 10.1016/B978-0-12-809573-7.00004-4.

“Plate tectonics.” Accessed: Aug. 03, 2026. [Online]. Available: https://www.nature.com/collections/fchjaacifj

“Valdivia Earthquake Strikes Chile.” Accessed: Sep. 16, 2026. [Online]. Available: https://education.nationalgeographic.org/resource/valdivia-earthquake-strikes-chile/

L. Dal Zilio and J. P. Ampuero, “Earthquake doublet in Turkey and Syria,” Commun. Earth Environ. 2023 41, vol. 4, no. 1, pp. 71, Mar. 2023, doi: 10.1038/s43247-023-00747-z.

W. L. Yeck et al., “Rapid Source Characterization of the 2023 Mw 6.8 Al Haouz, Morocco, Earthquake,” Seism. Rec., vol. 3, no. 4, pp. 357–366, Oct. 2023, doi: 10.1785/0320230040.

S. M. Mousavi and G. C. Beroza, “Machine Learning in Earthquake Seismology,” Annu. Rev. Earth Planet. Sci., vol. 51, no. Volume 51, 2023, pp. 105–129, May 2023, doi: 10.1146/ANNUREV-EARTH-071822-100323/CITE/REFWORKS.

L. Mizrahi et al., “Developing, Testing, and Communicating Earthquake Forecasts: Current Practices and Future Directions,” Rev. Geophys., vol. 62, no. 3, p. e2023RG000823, Sep. 2024, doi: 10.1029/2023RG000823;SUBPAGE:STRING:FULL.

K. Dascher-Cousineau, O. Shchur, E. E. Brodsky, and S. Günnemann, “Using Deep Learning for Flexible and Scalable Earthquake Forecasting,” Geophys. Res. Lett., vol. 50, no. 17, Sep. 2023, doi: 10.1029/2023GL103909.

Y. Zhang, C. Zhan, Q. Huang, and D. Sornette, “Forecasting future earthquakes with deep neural networks: application to California,” Geophys. J. Int., vol. 240, no. 1, pp. 81–95, Nov. 2024, doi: 10.1093/GJI/GGAE373.

Y. Hu, Q. Zhang, H. Zhu, B. Wang, H. Xiong, and H. Wang, “Scalable intermediate-term earthquake forecasting with multimodal fusion neural networks,” Sci. Reports 2025 151, vol. 15, no. 1, pp. 9748-, Mar. 2025, doi: 10.1038/s41598-025-93877-7.

Y. H. Chen, C. H. Chan, C. C. Chang, and K. F. Ma, “A Deep Learning Framework for Peak Ground Velocity Prediction Using Multi-Station Velocity Waveforms: The Taiwan Transformer Shaking Alert Model (TT-SAM),” J. Geophys. Res. Mach. Learn. Comput., vol. 3, no. 3, p. e2025JH001005, Jun. 2026, doi: 10.1029/2025JH001005;SUBPAGE:STRING:FULL.

C. Maji, B. Sadhukhan, S. Mukherjee, S. Khutia, and H. Chaudhuri, “Impact of climate change on seismicity:a statistical approach,” Arab. J. Geosci. 2021 1424, vol. 14, no. 24, pp. 2725-, Dec. 2021, doi: 10.1007/S12517-021-08946-8.

B. Sadhukhan, S. Chakraborty, and S. Mukherjee, “Investigating the relationship between earthquake occurrences and climate change using RNN-based deep learning approach,” Arab. J. Geosci. 2021 151, vol. 15, no. 1, pp. 31-, Dec. 2021, doi: 10.1007/S12517-021-09229-Y.

M. Carpineti et al., “An Enhanced Seismic Activity Observed Due To Climate Change: Preliminary Results from Alaska,” IOP Conf. Ser. Earth Environ. Sci., vol. 167, no. 1, p. 012018, Jun. 2018, doi: 10.1088/1755-1315/167/1/012018.

Y. J. Hsu et al., “Hydrologically-induced crustal stress changes and their association with seismicity rates in Taiwan,” Earth Planet. Sci. Lett., vol. 651, p. 119181, Feb. 2025, doi: 10.1016/J.EPSL.2024.119181.

J. P. Huang, X. A. Wang, Y. Zhao, C. Xin, and H. Xiang, “Large earthquake magnitude prediction in Taiwan based on deep learning neural network,” Neural Netw. World, vol. 28, no. 2, pp. 149–160, 2018, doi: 10.14311/NNW.2018.28.009.

M. Nurtas, Z. Zhantaev, and A. Altaibek, “Earthquake time-series forecast in Kazakhstan territory: Forecasting accuracy with SARIMAX,” Procedia Comput. Sci., vol. 231, pp. 353–358, Jan. 2024, doi: 10.1016/J.PROCS.2023.12.216.

M. Yousefzadeh, S. A. Hosseini, and M. Farnaghi, “Spatiotemporally explicit earthquake prediction using deep neural network,” Soil Dyn. Earthq. Eng., vol. 144, p. 106663, May 2021, doi: 10.1016/J.SOILDYN.2021.106663.

A. Pandit and K. C. Biswal, “Prediction of earthquake magnitude using adaptive neuro fuzzy inference system,” Earth Sci. Informatics 2019 124, vol. 12, no. 4, pp. 513–524, Jul. 2019, doi: 10.1007/S12145-019-00397-W.

A. Joshi, C. Vishnu, and C. K. Mohan, “Early detection of earthquake magnitude based on stacked ensemble model,” J. Asian Earth Sci. X, vol. 8, p. 100122, Dec. 2022, doi: 10.1016/J.JAESX.2022.100122.

E. Abebe, H. Kebede, M. Kevin, and Z. Demissie, “Earthquakes magnitude prediction using deep learning for the Horn of Africa,” Soil Dyn. Earthq. Eng., vol. 170, p. 107913, Jul. 2023, doi: 10.1016/J.SOILDYN.2023.107913.

S. M. Mousavi and G. C. Beroza, “A Machine-Learning Approach for Earthquake Magnitude Estimation,” Geophys. Res. Lett., vol. 47, no. 1, p. e2019GL085976, Jan. 2020, doi: 10.1029/2019GL085976

Z. Bao, J. Zhao, P. Huang, S. Yong, and X. Wang, “A Deep Learning-Based Electromagnetic Signal for Earthquake Magnitude Prediction,” Sensors 2021, Vol. 21, Page 4434, vol. 21, no. 13, p. 4434, Jun. 2021, doi: 10.3390/S21134434.

M. A. Bilal, Y. Ji, Y. Wang, M. P. Akhter, and M. Yaqub, “An Early Warning System for Earthquake Prediction from Seismic Data Using Batch Normalized Graph Convolutional Neural Network with Attention Mechanism (BNGCNNATT),” Sensors 2022, Vol. 22, Page 6482, vol. 22, no. 17, p. 6482, Aug. 2022, doi: 10.3390/S22176482.

Y. Wang, X. Li, Z. Wang, and J. Liu, “Deep learning for magnitude prediction in earthquake early warning,” Gondwana Res., vol. 123, pp. 164–173, Nov. 2023, doi: 10.1016/J.GR.2022.06.009.

P. Hajikhodaverdikhan, M. Nazari, M. Mohsenizadeh, S. Shamshirband, and K. W. Chau, “Earthquake prediction with meteorological data by particle filter-based support vector regression,” Eng. Appl. Comput. Fluid Mech., vol. 12, no. 1, pp. 679–688, Jan. 2018, doi: 10.1080/19942060.2018.1512010.

Q. He, M. Wang, and K. Liu, “Rapidly assessing earthquake-induced landslide susceptibility on a global scale using random forest,” Geomorphology, vol. 391, p. 107889, Oct. 2021, doi: 10.1016/J.GEOMORPH.2021.107889.

Y. Lu, E. Sawada, and G. Chakraborty, “Earthquake Aftershock Prediction Based Solely on Seismograph Data,” 2019 IEEE Int. Conf. Big Data Smart Comput. BigComp 2019 - Proc., Apr. 2019, doi: 10.1109/BIGCOMP.2019.8679491.

R. F. Mereu, “A study of the relations between ML, Me, Mw, apparent stress, and fault aspect ratio,” Phys. Earth Planet. Inter., vol. 298, Jan. 2020, doi: 10.1016/J.PEPI.2019.106278.

A. Deniz and M. S. Yucemen, “Magnitude conversion problem for the Turkish earthquake data,” Nat. Hazards 2010 552, vol. 55, no. 2, pp. 333–352, May 2010, doi: 10.1007/S11069-010-9531-8.

R. Kumar, R. B. S. Yadav, and S. Castellaro, “Regional earthquake magnitude conversion relations for the himalayan seismic belt,” Seismol. Res. Lett., vol. 91, no. 6, pp. 3195–3207, Nov. 2020, doi: 10.1785/0220200204.

“Moment Magnitude Scale: Definition, Importance, Uses – Geology In.” Accessed: Aug. 03, 2026. [Online]. Available: https://www.geologyin.com/2023/10/moment-magnitude-scale.html

Downloads

Published

2026-09-19
CITATION
Published: 2026-09-19
Crossref Citation Count: Loading...

How to Cite

Ahmed, M., Aysha Saddiqa, Saqib Ali, Zeeshan Saleem, & Adeel Ashraf. (2026). Earthquake Magnitude Prediction Using AI in Light of Environmental Factors. International Journal of Innovations in Science & Technology, 8(7), 2768–2781. https://doi.org/10.33411/IJIST/1987