Attention Based Time Series Analysis for Earthquake Prediction
Term effects on people's health, mental well-being, and economic well-being, are among nature's most damaging and unpredictable threats. More than 1100 devastating earthquakes have occurred in the last century, resulting in the deaths of over 1.5 million people around the world. Most seismic vulnerability assessments in India are conducted at the municipal or state level, and they are based on traditional methods. Delhi, the northeastern section of India, and much of Gujarat, as well as the West Bengal plain, are particularly vulnerable to earthquakes. As ML has advanced fast in recent years, it has the potential to significantly transform and increase the role of data science across a wide range of academic disciplines. Complex issues, computing efficiency, propagation and treatment of uncertainty, and ease of decision-making are some of the advantages of ML over traditional techniques. In addition, improvements in machine learning (ML) have had a substantial impact on a wide range of scientific and engineering domains, including material science, bioengineering, construction management and transportation engineering. Support Vector Regressor and LSTM model is used to evaluate earthquake vulnerability in this study. Mean Absolute error below 3 percent is achieved.
Keywords: Earthquake prediction, Machine learning, Time series analysis, Regression Analysis, LSTM, Support Vector Regressor.
How to Cite
This work is licensed under a Creative Commons Attribution 4.0 International License.
International Journal of Engineering Technology and Computer Research (IJETCR) by Articles is licensed under a Creative Commons Attribution 4.0 International License.