Major Earthquake Event Prediction Using Various Machine Learning Algorithms

Abstract

According to the extent or time period taken to foretell the occurrence of an earthquake, two primary classifications of methods are used. In other words, short-term maps are generated over the course of the few hours or, at most, days while maps that are made months or even years in advance are referred to as forecasts. The majority of research is aimed at the predictions that take into account the history of the earthquake in the given regions or countries. The objective of the present investigation is to identify if an earthquake event is positive or negative using different algorithms. The implementation of Random Forest, Naïve Bayes, Logistic Regression, Multi-Layer Perceptron, AdaBoost, K-Nearest Neighbors, SVC using Support Vector Machine, and Classification and Regression Trees has been performed to a real earthquake data set. Different hyperparameters for each algorithm were selected and the accuracy of each of them was compared based on several measures. The features were identified to have average values of 0.89, 0.89 and 0.83 for significant earthquake activities by three of the models. Some of the other algorithms that have been used in conjunction with the proposed approach are Random Forest, Naïve Bayes, Logistic Regression, AdaBoost, KNN, Support Vector Machine and Multi-Layer Perceptron Classifier.

Introduction

1. Introduction & Problem Statement:

Earthquakes are highly destructive and unpredictable natural disasters, often resulting in massive structural damage, economic loss, and human fatalities. Traditional earthquake prediction methods—based on historical geological data and statistical models—lack sufficient accuracy. These include:

• Short-term predictions (hours to days): Based on tremor frequency, intensity, and location.

• Long-term predictions (months to years): Based on geological patterns and fault line studies.

Despite progress, accurate prediction remains difficult due to the complexity of seismic processes. There's a growing need to explore machine learning (ML) to improve prediction accuracy.

2. Role of Machine Learning:

Machine learning models can process large seismic datasets and identify complex patterns that are difficult for traditional methods to capture. This research explores various ML algorithms to classify the likelihood of earthquake occurrence based on historical data.

Key Algorithms Used:

• Random Forest

• Naïve Bayes

• Logistic Regression

• AdaBoost

• K-Nearest Neighbors (KNN)

• Support Vector Machine (SVM)

• Multi-Layer Perceptron (MLP)

• CART (Classification and Regression Trees)

These models aim to classify whether an earthquake will occur and improve preparedness in high-risk regions.

3. Literature Survey:

Numerous studies have attempted to enhance earthquake prediction:

• Short-term prediction has gained focus with ML, analyzing seismic signal patterns.

• Algorithms like Random Forest, Naïve Bayes, Logistic Regression, and MLP have shown promising results.

• Combining models (ensemble learning) often yields better performance than using a single method.

Despite progress, challenges remain due to the uncertainty and variability in seismic activity.

4. Methodology:

The study proposes a system that integrates multiple ML algorithms for earthquake prediction using real historical datasets. It includes:

• Data preprocessing: Cleaning, normalizing, encoding categorical variables, and selecting relevant features.

• Training and testing of models using labeled earthquake event data.

• Performance evaluation using metrics like accuracy, precision, recall, and F1-score.

5. Implementation Details:

Dataset:

• Sourced from geological surveys and scientific institutions.

• Includes attributes like time, location, depth, and magnitude of earthquakes.

• Data is cleaned, normalized, and split into training and testing sets.

Model Training:

• Logistic Regression: Useful for binary classification (event/no event), outputs probabilities.

• Random Forest: An ensemble of decision trees using bagging, robust against overfitting, and good at handling missing data and high-dimensional datasets.

Each algorithm is optimized using hyperparameter tuning for better prediction accuracy.

Conclusion

Different aspects of application machine learning techniques study for predicting future earthquakes are related to the study and application of different machine learning techniques in predicting the future earthquakes\' occurrence. The specific aspect here refers to the capability to differentiate real or positive occurrences of earthquakes from fictive or negative occurrences. Algorithms implemented include Random Forest, Naïve Bayes, Logistic Regression, Multi-Layer Perceptron, AdaBoost, K-Nearest Neighbors, Support Vector Classifier, and Classification and Regression Tree. All of these algorithms have braced well to reasonable performances on some real earthquake datasets. This is given in terms of performance assessment on accuracy and other evaluation metrics by appropriate choice of hyperparameters for each one\'s models. Performance turned out good as some models averaged an accuracy of 0.89 for significant earthquake events. Thus, in addition, this spices it up to the usage of machine learning techniques into the problem of earthquake prediction, again with a solid feature selection and tuning of hyperparameters toward better prediction accuracy. Though further advances in the usage of real-time input data would still be beneficial for making predictions more credible. Future works may therefore focus on seeking the generalizations of the models towards the complex conceptual designs of geological and environmental determinants for their accurate earthquake predictions and effectiveness in time.

References

[1] S. B. Feroz, M. S. Sevas, N. Sharmin, and A. Chatterjee, Performance Analysis of Machine Learning and Deep Learning Architecture for Earthquake Magnitude Prediction,Proceedings of 2023 IEEE 9th International Women in Engineering (WIE) Conference on Electrical and Computer Engineering, WIECON-ECE 2023, pp. 70–75, 2023, doi: 10.1109/WIECON-ECE60392.2023.10456401. [2] F. Ahmed, S. Akter, S. M. M. Rahman, J. Bin Harez, A. Mubasira, and R. Khan, “Earthquake Magnitude Prediction Using Machine Learning Techniques,” 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024, 2024, doi: 10.1109/IATMSI60426.2024.10502770. [3] R. Mallouhy, C. A. Jaoude, C. Guyeux, and A. Makhoul, “Major earthquake event prediction using various machine learning algorithms,” Management, ICT-DM 2019, Dec. 2019, doi: 10.1109/ICT-DM47966.2019.9032983. [4] A. Gaba, A. Jana, R. Subramaniam, Y. Agrawal, and M. Meleet, “Analysis and Prediction of Earthquake Impact-a Machine Learning approach Technology for Sustainable Solution, Proceedings, Dec. 2019, doi: 10.1109/CSITSS47250.2019.9031026. [5] B. Arunadevi, M. Madiajagan, M. I. Hussain, R. Lakshmi, M. M. Ramakrishna, and K. Sengupta Das, “Risk Prediction of Earthquakes using Machine Learning,” 3rd International Conference on Electronics and Sustainable Communication Systems, ICESC 2022 - Proceedings, pp. 1589–1593, 2022, doi: 10.1109/ICESC54411.2022.9885674. [6] P. Chomchit and P. Champrasert, “Strong-motion Earthquake Prediction Model using Convolutional Extreme Learning Machine,” ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications, pp. 756–759, 2022, doi: 10.1109/ITC-CSCC55581.2022.9894973. [7] R. Kumar, M. Gupta, K. S. Bedi, A. Upadhyay, and A. J. Obaid, “Earthquake Prediction Using Machine Learning,” Proceedings - IEEE 2023 5th International Conference on Advances in Computing, Communication Control and Networking, ICAC3N 2023, pp. 195–198, 2023, doi: 10.1109/ICAC3N60023.2023.10541482. [8] S. Dhotre, K. Doshi, S. Satish, and K. Wagaskar, “Exploring Quantum Machine Learning (QML) for Earthquake Prediction,” 2022 2nd International Conference on Intelligent Technologies, CONIT 2022, 2022, doi: 10.1109/CONIT55038.2022.9848250. [9] S. Rath, A. B. Gurulakshmi, S. Aditya, V. R. Naik, A. Pawar, and V. Karoor, “A Comparison of Earthquake Prediction using Machine Learning Algorithms,” Proceedings of 5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024, pp. 1529–1533, 2024, doi: 10.1109/ICICNIS64247.2024.10823378 [10] M. Elbes, S. Alzu’bi, and T. Kanan, “Deep Learning-Based Earthquake Prediction Technique Using Seismic Data,” 2023 International Conference on Multimedia Computing, Networking and Applications, MCNA 2023, pp. 103–108, 2023, doi: 10.1109/MCNA59361.2023.10185869. [11] G. S. Manral and A. Chaudhary, “Prediction of Earthquake Using Machine Learning Algorithms,” doi: 10.1109/ICIEM59379.2023.10166658. [12] P. Shrote, P. Dasarwar, S. Dongre, and P. Khobragade, “Earthquake Prediction Through Machine Learning Approach,” Proceedings - 4th International Conference on Technological Advancements in Computational Sciences, ICTACS 2024, pp. 542–546, 2024, doi: 10.1109/ICTACS62700.2024.10840652. [13] R. Kail, E. Burnaev, and A. Zaytsev, “Recurrent Convolutional Neural Networks Help to Predict Location of Earthquakes,” IEEE Geoscience and Remote Sensing Letters, vol. 19, 2022, doi: 10.1109/LGRS.2021.3107998. [14] M. H. Al Banna et al., “Application of Artificial Intelligence in Predicting Earthquakes: State-of-the-Art and Future Challenges,” doi: 10.1109/ACCESS.2020.3029859. [15] Y. Zhao, S. Lv, and P. Liu, “Advances in earthquake prevention and reduction based on machine learning: A scoping review (July 2024),” doi: 10.1109/ACCESS.2024.3467149. [16] Q. Wang, Y. Guo, L. Yu, and P. Li, “Earthquake Prediction Based on Spatio-Temporal Data Mining: An LSTM Network Approach,” 10.1109/TETC.2017.2699169 [17] C. Yang, K. Zhang, G. Chen, Y. Pan, L. Zhang, and L. Qu, “Application of Machine Learning to Determine Earthquake Hypocenter Location in Earthquake Early Warning,” IEEE Geoscience and Remote Sensing Letters, vol. 21, pp. 1–5, 2024, doi: 10.1109/LGRS.2023.3348107

Copyright

Copyright © 2025 Dr. M. A. Manivasagam, M Ramya, K Sri Vidya, K Siva Rami Reddy, T Surya Narayana, S Surendra Naidu. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.