Early Earthquake Prediction Using a Hybrid Feature Selection and Ensemble Learning Approach

Abdul Khaliq; Muhammad Muttaqin

doi:10.61306/ijecom.v3i2.83

Authors

Abdul Khaliq Universitas Pembangunan Panca Budi
Muhammad Muttaqin Universitas Pembangunan Panca Budi

DOI:

https://doi.org/10.61306/ijecom.v3i2.83

Keywords:

Earthquakes,, Voting Classifier

Abstract

Earthquakes are extremely dangerous natural disasters that can cause severe damage to infrastructure and loss of life. These disasters often occur suddenly, making mitigation efforts difficult. Therefore, earthquake prediction is very important for human safety. The scientific community continues to be interested in this topic, and our understanding of this complex natural phenomenon will be improved if we can develop accurate earthquake prediction models using machine learning methods. These models will help save lives and reduce damage. In this study, we propose a new feature selection approach that combines two filtering approaches: normalization on analysis of variance, Chi-square technique, and correlation based on Logistic Regression to analyze the correlation between features and select the main features before feeding them into the classification model. Four commonly used algorithms are applied to help find patterns in the obtained data. Our method, which relies on a soft voting classifier that combines the best three models to produce a single model that carries the strengths of the combined models, is able to predict earthquakes early. The proposed methodology outperforms previous studies, achieving accuracy, F1_score, recall, and precision of (0.994, 0.99, 1, 0.98), respectively.

References

R. Tehseen, M. S. Farooq, and A. Abid, “Earthquake Prediction Using Expert Systems: A Systematic Mapping Study,” Mar. 19, 2020, Multidisciplinary Digital Publishing Institute. doi: 10.3390/su12062420.

J. Chen, Z. Yan, L. Xu, Z. Liu, Y. Liu, and J. Tian, “Gray System Prediction in the Alpine–Himalayan Earthquake Zone,” May 01, 2021, IOP Publishing. doi: 10.1088/1755-1315/772/1/012009.

G. S. Baveja and J. Singh, “Earthquake Magnitude and b value prediction model using Extreme Learning Machine,” Jan. 01, 2023, Cornell University. doi: 10.48550/arxiv.2301.09756.

N. Altay and A. Narayanan, “Forecasting in humanitarian operations: Literature review and research needs,” Sep. 09, 2020, Elsevier BV. doi: 10.1016/j.ijforecast.2020.08.001.

N. M. S. I. Arambepola, Md. A. Rahman, and K. Tawhid, “Planning Needs Assessment for Responding to Large Disaster Events in Cities: Case Study from Dhaka, Bangladesh,” Jan. 01, 2014, Elsevier BV. doi: 10.1016/s2212-5671(14)00991-5.

A. Mosavi, P. Öztürk, and K. Chau, “Flood Prediction Using Machine Learning Models: Literature Review,” Oct. 27, 2018, Multidisciplinary Digital Publishing Institute. doi: 10.3390/w10111536.

Y. Chiu, H. Omura, H. Chen, and S. Chen, “Indicators for Post-Disaster Search and Rescue Efficiency Developed Using Progressive Death Tolls,” Oct. 08, 2020, Multidisciplinary Digital Publishing Institute. doi: 10.3390/su12198262.

E. J. Fielding et al., “Rapid Imaging of Earthquake Ruptures with Combined Geodetic and Seismic Analysis,” Jan. 01, 2014, Elsevier BV. doi: 10.1016/j.protcy.2014.10.038.

D.-K. Nguyen, C.-H. Lan, and C. Chan, “Deep Ensemble Learning Approaches in Healthcare to Enhance the Prediction and Diagnosing Performance: The Workflows, Deployments, and Surveys on the Statistical, Image-Based, and Sequential Datasets,” Oct. 14, 2021, Multidisciplinary Digital Publishing Institute. doi: 10.3390/ijerph182010811.

P. Y. Taşer, K. U. Birant, V. Radevski, A. Kut, and D. Birant, “Comparative analysis of ensemble learning methods for signal classification,” May 01, 2018. doi: 10.1109/siu.2018.8404601.

K. Pham, D. Kim, S. Park, and H. Choi, “Ensemble learning-based classification models for slope stability analysis,” Sep. 09, 2020, Elsevier BV. doi: 10.1016/j.catena.2020.104886.

S. Chaves, E. Ogasawara, P. Valduriez, and F. Porto, “StreamEnsemble: Predictive Queries over Spatiotemporal Streaming Data,” Sep. 30, 2024, Cornell University. doi: 10.48550/arxiv.2410.00933.

Qi and X. Tang, “A hybrid ensemble method for improved prediction of slope stability,” Jul. 09, 2018, Wiley. doi: 10.1002/nag.2834.

K. M. Asim, F. Martínez‐Álvarez, A. Basit, and T. Iqbal, “Earthquake magnitude prediction in Hindukush region using machine learning techniques,” Sep. 08, 2016, Springer Science+Business Media. doi: 10.1007/s11069-016-2579-3.

S. Dhotre, K. Doshi, S. Satish, and K. Wagaskar, “Exploring Quantum Machine Learning (QML) for Earthquake Prediction,” Jun. 24, 2022. doi: 10.1109/conit55038.2022.9848250. Akbar, A., Sulistianingsih, I., Kurniawan, H., & Putri, R. D. (2022). Rancangan Sistem Pencatatan Digital Sensus Penduduk (Sensudes) Berbasis Web di Desa Kota Pari. Brahmana: Jurnal Penerapan Kecerdasan Buatan, 4(1A), 23–27.

Hariyanto, E., Lubis, S. A., & Sitorus, Z. (2017). Perancangan prototipe helm pengukur kualitas udara. KOMIK (Konferensi Nasional Teknologi Informasi Dan Komputer), 1(1).

Hariyanto, E., & Wahyuni, S. (2020). Sosialisasi Dan Pelatihan Penggunaan Internet Sehat Bagi Anggota Badan Usaha Milik Desa ( Bumdes ) Mozaik Desa Pematang Serai. Jurnal ABDIMAS BSI, 3(2), 253–259.

Hariyanto, E., Wahyuni, S., & Iqbal, M. (2019). Aplikasi Rekam Medis Pada Klinik Pratama Darul Amin Berbasis Web. 1, 697–701.

Hermansyah, H., Wijaya, R. F., & Wahyuni, S. (2024). Desain Aplikasi Cinta Mangrove Berbasis Mobile Di Desa Kota Pari Dengan Metode Waterfall. Senashtek 2024, 2(1), 42–48.

Lubis, A., Hariyanto, E., & Harahap, M. I. (2022). Wireless Controller Menggunakan Capsman di Jaringan Laboratorium Komputer Perguruan Panca Budi Medan. INTECOMS: Journal of Information Technology and Computer Science, 5(2), 97–103.

Marlina, L., Wahyuni, S., & Sulistianingsih, I. (2023). The Information System for Promotion of Products for Micro, Small, and Medium Enterprises in Hinai Village is Website-Based With a Membership Method. International Journal Of Computer Sciences and Mathematics Engineering, 2(2), 141–151.