Analysis of Earthquake Occurrence and Generating an Alert System Using Machine Learning Models

View at publisher Summarise with VIRAT
Authors: Punniyakotti Varadharajan Gopirajan, Bharathi S. Dhina, Surisetty Yeshwanth
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The challenge of predicting earthquakes stems from their nonlinear seismic characteristics. An assessment of machine learning methods investigates their ability to enhance predictive accuracy through the combination of earthquake historic records with geological data together with real-time sensor information. Feature engineering alongside training neural networks and support vector machines along with ensemble methods helped produce better pattern detection. The research demonstrates that machine learning detects early warning indicators which traditional methods frequently overlook yet require both cross-domain information integration and model improvement to create dependable predictions. A Neural Network (NN) model was designed to conduct midterm earthquake forecasts which emphasized intensity prediction capabilities. The evaluation of earthquake data through visualization methods uncovered predictive patterns that demonstrate machine learning systems’ potential to enhance seismic forecasting capabilities.

Fields of Study & Subjects

Seismology and Earthquake Studies Earthquake Detection and Analysis earthquake and tectonic studies

Publication details

Journal / source
CRC Press eBooks
Pages
32–37
Publication date
31 March 2026
Language
EN
Document type
Book chapter