Optimasi Akurasi Model Prediksi Magnitudo Gempa Bumi dengan Integrasi Clustering DBSCAN pada Ensemble Learning (Random Forest & XGBoost)
-
Akhmad Syaifuddin
*
Universitas Sebelas Maret, Kota Surakarta,
Indonesia
- Tito Prabowo Universitas Nahdlatul Ulama Blitar, Kota Blitar, Indonesia (*) Corresponding Author
Abstract
Earthquake prediction is crucial for risk mitigation, particularly in taking appropriate preventive measures in the face of disasters. The magnitude of an earthquake is influenced by various factors, including location, depth, and the history of seismic activity in a region. This study aims to develop an accurate earthquake magnitude prediction model by integrating clustering and ensemble learning techniques. Earthquake catalog data from BMKG Indonesia is processed and clustered using the DBSCAN algorithm based on geographical location. The prediction model is constructed using Random Forest and XGBoost, then integrated through stacking ensemble learning techniques. Evaluation results indicate that the stacking model delivers the best performance, with the lowest Mean Squared Error (MSE) of 0.108 and the highest R-squared (R²) of 0.892, compared to individual models. This accuracy improvement is attributed to stacking’s ability to combine the predictive strengths of Random Forest and XGBoost. The study demonstrates that integrating clustering and ensemble learning can enhance earthquake magnitude prediction models. However, further research is needed to explore more comprehensive data and features and to test model generalization in other regions.
Downloads
References
Aggarwal, C. C. (2017). Outlier Analysis. Springer.
Ari Wibowo. (2022). Prediksi Kekuatan Gempa menggunakan Machine Learning dengan Model XGBoost sebagai Langkah Strategis dalam Perencanaan Struktur Bangunan Tahan Gempa di Indonesia. MESA : Jurnal Teknik, 6, 18–29. http://www.ejournal.unsub.ac.id/index.php/FTK/article/view/1829
Cui, S., Yin, Y., Wang, D., Li, Z., & Wang, Y. (2021). A stacking-based ensemble learning method for earthquake casualty prediction. Applied Soft Computing, 101, 107038. https://doi.org/10.1016/J.ASOC.2020.107038
Fatima, S., Hussain, A., Bin Amir, S., Haseeb Ahmed, S., & Muhammad Huzaifa Aslam, S. (2023). XGBoost and Random Forest Algorithms: an in Depth Analysis. Pakistan Journal of Scientific Research, 3, 26–31. http://pjosr.com/index.php/pjosr/article/view/946
Fauzan, A., & Ahmad, D. (2023). Analisis Hasil Prediksi Magnitudo Gempa di Wilayah Kota Padang menggunakan Teknik Random Forest. Lebesgue: Jurnal Ilmiah Pendidikan Matematika, Mateatika Dan Statistika, 4. https://www.lebesgue.lppmbinabangsa.id/index.php/home/article/view/450
Fauzi, M., & Mussadun. (2021). Dampak Bencana Gempabumi dan Tsunami Pesisir Lere Kota Palu. Jurnal Pembangunan Wilayah Dan Kota, 17(1), 16–24. https://doi.org/10.14710/pwk.v17i1.29967
Furqon, M., & Muflikhah, L. (2016). Clustering the potential risk of tsunami using Density-Based Spatial clustering of application with noise (DBSCAN). Journal of Environmental Engineering, 3, 1–8. https://jeest.ub.ac.id/index.php/jeest/article/view/38
Husaini, M. (2023). Implementasi Machine Learning pada Prediksi Data Ketinggian Muka Air Laut Dengan Metode Fbprophet dan Pendeteksian Anomali dengan Metode Klasifikasi. Universitas Lampung. http://digilib.unila.ac.id/id/eprint/69128
Hutagaol, R., Lana, V., Dzunnurain, Z., & Kurniawan, R. (2024). Penerapan Machine Learning dalam Prediksi Klasifikasi Big Data Kedalaman Gempa Bumi di Indonesia Tahun 2015-2024. Prosiding Seminar Nasional Sains Data 2024. https://prosiding-senada.upnjatim.ac.id/index.php/senada/article/view/156
Jeena, R., M., K., A., Princy., & A., Tanya. (2023). Earthquake Location Forecasting In Map Using XGBOOST Algorithm. Journal of Cognitive Human-Computer Interaction, 5(1), 42–45. https://doi.org/10.54216/JCHCI.050104
Joshi, A., Vishnu, C., Mohan, C. K., & Raman, B. (2024). Application of XGBoost model for early prediction of earthquake magnitude from waveform data. Journal of Earth System Science, 133(1), 1–18. https://doi.org/10.1007/S12040-023-02210-1/FIGURES/12
Molnar, Christoph. (2022). Interpretable machine learning : a guide for making black box models explainable. 317.
Natras, R., Soja, B., & Schmidt, M. (2022). Ensemble machine learning of random forest, AdaBoost and XGBoost for vertical total electron content forecasting. Remote Sensing, 14. https://doi.org/10.3390/rs14153547
Noor, A. (2018). Perbandingan Algoritma Support Vector Machine Biasa dan Support Vector Machine berbasis Particle Swarm Optimization untuk Prediksi Gempa Bumi. Jurnal Humaniora Dan Teknologi, 4. https://www.academia.edu/download/86328513/43.pdf
Rachman, A., & Widodo, A. (2017). Penentuan Magnitudo Gempa Bumi Dengan Menganalisis Amplitudo Anomali Manetik Prekusor Gempa Bumi Dan Jarak Hypocenter. Jurnal Teknik ITS. http://ejurnal.its.ac.id/index.php/teknik/article/view/27583
Rahayu, T., & Purwoko, A. (2020). Pendekatan Empiris untuk Estimasi Kerugian Ekonomi dan Dampak Kerusakan Lingkungan akibat Gempabumi di Deli. KAKIFIKOM, 02(01).
Ridzwan, N. S. M., & Yusoff, S. H. M. (2023). Machine learning for earthquake prediction: a review (2017–2021). Earth Science Informatics, 16(2), 1133–1149. https://doi.org/10.1007/S12145-023-00991-Z/TABLES/5
Risman, Syaripuddin, & Suyitno. (2019). Implementasi Metode DBSCAN pada Pengelompokan Kabupaten/Kota di Pulau Kalimantan berdasarkan Indikator Kesejahteraan Rakyat. Prosiding Seminar Nasional Matematika Dan Statistika, 22–28. https://jurnal.fmipa.unmul.ac.id/index.php/SNMSA/article/view/522
Sidik, I., Saroji, S., & Sulistyani, S. (2024). Implementation of machine learning for volcanic earthquake pattern classification using XGBoost algorithm. Acta Geophysica, 72(3), 1575–1585. https://doi.org/10.1007/S11600-023-01154-W/FIGURES/7
Sudarto, S., & Kusrini, K. (2024). Klasifikasi Tsunami Gempa Bumi dengan Teknik Stacking Ensemble Machine Learning. JIP (Jurnal Informatika Polinema), 10. http://jurnal.polinema.ac.id/index.php/jip/article/view/5655
Tantyoko, H., Sari, D. K., & Wijaya, A. R. (2023). Prediksi Potensial Gempa Bumi Indonesia Menggunakan Metode Random Forest Dan Feature Selection. IDEALIS: Indonesia Journal Information System, 6, 83–89. https://jom.fti.budiluhur.ac.id/index.php/IDEALIS/article/view/3036
Xu, G., Liu, M., Jiang, Z., Söffker, D., & Shen, W. (2019). Bearing fault diagnosis method based on deep convolutional neural network and random forest ensemble learning. Sensors, 19. https://www.mdpi.com/1424-8220/19/5/1088
Yavas, C. E., Chen, L., Kadlec, C., & Ji, Y. (2024). Improving earthquake prediction accuracy in Los Angeles with machine learning. Scientific Reports, 14(1), 24440. https://doi.org/10.1038/S41598-024-76483-X
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Optimasi Akurasi Model Prediksi Magnitudo Gempa Bumi dengan Integrasi Clustering DBSCAN pada Ensemble Learning (Random Forest & XGBoost)
Pages: 424-431
Copyright (c) 2024 Akhmad Syaifuddin, Tito Prabowo
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
