Machine learning for predicting earthquake magnitudes in the Central Himalaya - Article

Aug 3, 2026

Uploaded by Miles

Earthquakes cannot be stopped by human intervention, but machine learning can extract patterns from seismic datasets to improve forecasting capability. The study applies Random Forest Regressor (RFR), Multi-Layer Perceptron Regressor (MLPR), and Support Vector Regression (SVR) to predict magnitudes exceeding 6 mb for 2015 earthquakes in the Central Himalaya. Results show RFR best matches key events including the 6.9 mb Gorkha and 6.7 mb Kodari earthquakes, using MAE, MSE, and RMSE. Findings indicate RFR produces predictions closest to observed magnitudes, demonstrating stronger performance than competing models.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Introduction

Random Forest

BIBECHANA Vol. 22, No. 1, April 2025, 22-29 ISSN 2091-0762 (Print), 2382-5340 (Online) Journal homepage: [http://nepjol.info/index.php/BIBECHANA](http://nepjol.info/index.php/BIBECHANA)[ ](http://nepjol.info/index.php/BIBECHANA)Publisher:Dept. of Phys., Mahendra Morang A. M. Campus (Tribhuvan University)Biratnagar | Machine learning for predicting earthquake magnitudes in the Central Himalaya
Ram Krishna Tiwari 1 , Rudra Prasad Poudel 1 ,2 , Harihar Paudyal 1
1 Birendra Multiple Campus, Tribhuvan University, Bharatpur, Chitwan, Nepal
2 Central Department of Physics, Tribhuvan University, Kirtipur, Kathmandu, Nepal
∗ Corresponding author. Email: [ram. tiwari@bimc. tu. edu. np](ram. tiwari@bimc. tu. edu. np)
Abstract
Human intervention cannot halt natural disasters like earthquakes, but machine learning applications expertise can be utilized to detect patterns in data and increase understanding and predictive power. Recent development of machine learning models has increasingly developed interest in forecasting and predicting the magnitude of earthquakes. In this work, Random Forest Regressor (RFR), Multi-Layer Perceptron Regressor (MLPR), and Support Vector Regression (SVR) models were employed to predict the magnitude of greater than 6 mb earthquakes that occurred in the year 2015 in the central Himalaya. We noticed RFR method had been able to predict the magnitude of the Gorkha earthquake (6.9 mb), the Kodari earthquake (6.7 mb), and 6.5 mb magnitude earthquake (aftershock of Gorkha earthquake) in comparison with the other two models. We also checked the performance of these models by three parameters Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) and noticed the better performance of RFR model. The findings illustrate that RFRis achieving better performance than the other two algorithms, as the predicted magnitudes are close to the actual magnitudes.
Keywords
Machine Learning, Earthquake, Regressor, Prediction. | | --- | | Article information
Manuscript received: October 6, 2024; Revised: January 7, 2025; Accepted: January 12, 2025
DOI [https://doi.org/10.3126/bibechana.v22i1.70637](https://doi.org/10.3126/bibechana.v22i1.70637)
This work is licensed under the Creative Commons CC BY-NC License. [https://creativecommons](https://creativecommons). org/licenses/by-nc/4.0/ | 1 Introduction An earthquake is a natural disaster that strikes suddenly, between seconds to minutes, and shakesa large area of landmass, potentially killing people and damaging property. Nepal, which is posi- tioned in the center of the Himalayan arc, saw many small and large earthquakes in last millennia [1–5] . The seismic activity in the Himalayan region is impacted by the buildup of strain energy that happened roughly 50 million years ago during the Indian plate's thrust beneath the Eurasian plate [6–8] . The region has had more recent earthquakes in the past 70 years, including the 1988 Udayapur earthquake of magnitude 6.6 Mw, 2011 Sikkim earthquake of magnitude 6.9 Mw, 2015 Gorkha earthquake of magnitude 7.9 Mw, Dolakha (Kodari) earthquake of magnitude 7.3 Mw, Doti earthquake of magnitude 6.6 ML, and the 2023 Jajarkot earthquake of magnitude 6.4 ML [8–10] . Human intervention cannot halt natural disasters like earthquakes, but machine learning application expertise can be utilized to detect patterns in data and increase understanding and predictive power [11–13] . Most of the machine learning (ML) algorithms fall into one of two categories: Supervised Learning (SL) and Unsupervised Learning (USL) (Figure 1) . Figure 1: Basic idea of selecting the ML algorithms. Unsupervised ML for unlabelled data, and supervised ML for labelled data. In SL, the computer is instructed or trained with the labeled data. SL algorithms construct two types of predictive models, Regression and Classification models which approaches data in a different way. For forecasting a numerica

FAQs

Which machine learning models are used to predict earthquake magnitudes in the Central Himalaya?

The work uses Random Forest Regressor (RFR), Multi-Layer Perceptron Regressor (MLPR), and Support Vector Regression (SVR).

What earthquakes and time period are used for the prediction task?

The models predict magnitudes greater than 6 mb for earthquakes that occurred in 2015 in the Central Himalaya.

How is model performance evaluated in this study?

Performance is assessed using Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE).

Which model performs best and what is the main reason?

RFR performs best because predicted magnitudes are closest to the actual magnitudes, including events like the Gorkha and Kodari earthquakes.

Aug 3, 2026

Uploaded by Miles