Journal of Artificial Intelligence and Metaheuristics
Journal DOI
2833-5597ISSN (Online)
Volume 9 , Issue 2 , PP: 72-87, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Nima Khodadadi 1 *
Doi: https://doi.org/10.54216/JAIM.090205
Earthquakes represent one of the most destructive natural hazards because they cause consequential destruction to entire communities and fatal consequences for people. Research has continued for decades because scientists aim to develop better forecasting tools for seismic events, which unpredictably strike society with massive economic losses. Research methods from classical earthquake science and statistical and physical earthquake models do not effectively demonstrate earthquake data's complex spatial and temporal characteristics. ML methods generated widespread interest in prediction work because they extract understanding from extensive data collections to produce accurate results independently of physical rules. The presented work examines various ML models that predict earthquake magnitudes by assessing an open-access global earthquake dataset from 2023. The evaluation consists of five predictive models, including Light Gradient Boosting Machine (LightGBM) and Support Vector Regression (SVR), as well as k-nearest Neighbors (KNN), Ridge Regression, along Extra Trees Regressor. The training process included stratified cross-validation and model optimization of hyperparameters for every model. The assessment included a mixture of statistical and mathematical performance indicators that measured Mean Squared Error (MSE) alongside Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Bias Error (MBE), Coefficient of Determination ($R^2$), Nash–Sutcliffe Efficiency (NSE), Willmott Index (WI), Pearson's Correlation Coefficient ($r$) and Relative Root Mean Squared Error (RRMSE). LightGBM outperformed all evaluation models by attaining a minimum MSE value of 0.0474 and a $R^2$ score of 0.9241. LightGBM's leaf-wise tree-building approach, robust scalability, and native regularization features enabled it to apply very well to unknown data samples without reducing computational speed. The experimental outcomes validate LightGBM as a powerful tool for recognizing delicate patterns within high-dimensional seismic data collections for potential use as a predictive modeling instrument in earthquake-prone zones. ML-based forecasting systems have displayed the capability to change earthquake prediction processes according to research outcomes. When used together, LightGBM and alternative advanced ML systems enhance real-time early warning systems, which leads to shortened emergency response time bet, better planning decisions, and lower numbers of human and economic losses from earthquakes. This approach, along with open-access datasets, allows the goal of seismic risk mitigation to achieve broader transparency and collaborative innovation through reproducible modeling strategies.
Earthquake prediction , Seismic Data Analysis , Light Gradient Boosting Machine , Machine Learning Models
[1] Artem Vesnin, Yury Yasyukevich, Natalia Perevalova, and Erman S¸ ent¨urk. Ionospheric response to the 6 february 2023 turkey–syria earthquake. Remote sensing, 15(9):2336, 2023.
[2] Hua-Lun Huang. Natural hazards: Earthquakes. In Encyclopedia of Security and Emergency Manage- ment, pages 662–669. Springer, 2021.
[3] Mikhail B Gokhberg. Earthquake prediction. CRC Press, 2024.
[4] Munish Bhatia, Tariq Ahamed Ahanger, and Ankush Manocha. Artificial intelligence based real-time earthquake prediction. Engineering Applications of Artificial Intelligence, 120:105856, 2023.
[5] Assem Turarbek, Maktagali Bektemesov, Aliya Ongarbayeva, Assel Orazbayeva, Aizhan Koishybekova, and Yeldos Adetbekov. Deep convolutional neural network for accurate prediction of seismic events. International Journal of Advanced Computer Science and Applications, 14(10), 2023.
[6] Alexander N Safronov. Astronomical triggers as a cause of strong earthquakes. International Journal of Geosciences, 13(9):793–829, 2022.
[7] David Teh and Tehmina Khan. Types, definition and classification of natural disasters and threat level. In Handbook of disaster risk reduction for resilience: new frameworks for building resilience to disasters, pages 27–56. Springer, 2021.
[8] Mei-Yun Lin and Raluca Ilie. A review of observations of molecular ions in the earth’s magnetosphere- ionosphere system. Frontiers in Astronomy and Space Sciences, 8:745357, 2022.
[9] Denis Anikiev, Claire Birnie, Umair bin Waheed, Tariq Alkhalifah, Chen Gu, Dirk J Verschuur, and Leo Eisner. Machine learning in microseismic monitoring. Earth-Science Reviews, 239:104371, 2023.
[10] Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30, 2017.
[11] Luca Franceschi, Michele Donini, Valerio Perrone, Aaron Klein, C´edric Archambeau, Matthias Seeger, Massimiliano Pontil, and Paolo Frasconi. Hyperparameter optimization in machine learning. arXiv preprint arXiv:2410.22854, 2024.
[12] Gautam Kunapuli. Ensemble methods for machine learning. Simon and Schuster, 2023.
[13] Davide Chicco, Matthijs J Warrens, and Giuseppe Jurman. The coefficient of determination r-squared is more informative than smape, mae, mape, mse and rmse in regression analysis evaluation. Peerj computer science, 7:e623, 2021.
[14] Gaurav Singh Manral and Alka Chaudhary. Prediction of earthquake using machine learning algorithms. In 2023 4th International Conference on Intelligent Engineering and Management (ICIEM), pages 1–5. IEEE, 2023.
[15] Nada Badr Jarah, Abbas H Hassin Alasadi, and Kadhim Mahdi Hashim. Earthquake prediction technique: A comparative study. IAES Int. J. Artif. Intell.(IJ-AI), 2252:1027, 2023.
[16] Ewnetu Abebe, Hailemichael Kebede, Mickus Kevin, and Zelalem Demissie. Earthquakes magnitude prediction using deep learning for the horn of africa. Soil Dynamics and Earthquake Engineering, 170:107913, 2023.
[17] Mustafa Abdul Salam, Lobna Ibrahim, and Diaa Salama Abdelminaam. Earthquake prediction using hybrid machine learning techniques. International Journal of Advanced Computer Science and Applications, 12(5):654–6652021, 2021.
[18] Anushka Joshi, Balasubramanian Raman, C Krishna Mohan, and Linga Reddy Cenkeramaddi. Application of a new machine learning model to improve earthquake ground motion predictions. Natural Hazards, 120(1):729–753, 2024.
[19] Victor Manuel Velasco Herrera, Eduardo Antonio Rossello, Maria Julia Orgeira, Lucas Arioni, Willie Soon, Graciela Velasco, Laura Rosique-de La Cruz, Emmanuel Z´u˜niga, and Carlos Vera. Long-term forecasting of strong earthquakes in north america, south america, japan, southern china and northern india with machine learning. Frontiers in Earth Science, 10:905792, 2022.
[20] Papiya Debnath, Pankaj Chittora, Tulika Chakrabarti, Prasun Chakrabarti, Zbigniew Leonowicz, Michal Jasinski, Radomir Gono, and ElË™zbieta Jasi´nska. Analysis of earthquake forecasting in india using supervised machine learning classifiers. Sustainability, 13(2):971, 2021.
[21] Rayan Abri and Harun Artuner. Lstm-based deep learning methods for prediction of earthquakes using ionospheric data. Gazi University Journal of Science, 35(4):1417–1431, 2022.
[22] Bharat Bhargava and Sumanta Pasari. Earthquake prediction using deep neural networks. In 2022 8th in- ternational conference on advanced computing and communication systems (ICACCS), volume 1, pages 476–479. IEEE, 2022.
[23] Mohsen Yousefzadeh, Seyyed Ahmad Hosseini, and Mahdi Farnaghi. Spatiotemporally explicit earth- quake prediction using deep neural network. Soil Dynamics and Earthquake Engineering, 144:106663, 2021.
[24] Yao Li, Peng Cui, Chengming Ye, Jos´e Marcato Junior, Zhengtao Zhang, Jian Guo, and Jonathan Li. Ac- curate prediction of earthquake-induced landslides based on deep learning considering landslide source area. Remote Sensing, 13(17):3436, 2021.
[25] Pan Xiong, Lei Tong, Kun Zhang, Xuhui Shen, Roberto Battiston, Dimitar Ouzounov, Roberto Iuppa, Danny Crookes, Cheng Long, and Huiyu Zhou. Towards advancing the earthquake forecasting by ma- chine learning of satellite data. Science of the Total Environment, 771:145256, 2021.
[26] Yiyi Zhao, Shuai Lv, and Pengfei Liu. Advances in earthquake prevention and reduction based on ma- chine learning: a scoping review (july 2024). IEEE Access, 2024.
[27] M Apriani, SK Wijaya, et al. Earthquake magnitude estimation based on machine learning: Application to earthquake early warning system. In Journal of Physics: Conference Series, volume 1951, page 012057. IOP Publishing, 2021.
[28] Earthquakes 2023 global. https://www.kaggle.com/datasets/mustafakeser4/ earthquakes-2023-global, 2023.
[29] Cheng Fan, Meiling Chen, Xinghua Wang, Jiayuan Wang, and Bufu Huang. A review on data prepro- cessing techniques toward efficient and reliable knowledge discovery from building operational data. Frontiers in energy research, 9:652801, 2021.
[30] Andrea Barucci, Stefano Diciotti, Marco Giannelli, and Chiara Marzi. Data preparation for ai analysis. In Introduction to Artificial Intelligence, pages 133–150. Springer, 2023.
