University of Twente Student Theses

Login

Analysis and Prediction of Earthquakes using different Machine Learning techniques

Mondol, Manaswi (2021) Analysis and Prediction of Earthquakes using different Machine Learning techniques.

[img] PDF
827kB
Abstract:A reliable and accurate method for earthquake prediction has the potential to save countless human lives. With that objective in mind, this paper looks into various methods to predict the magnitude and depth of earthquakes. In this paper, real-world earthquake data is analysed to identify patterns and gain insight into this natural calamity. This data is then used to train four machine learning models namely Random forest, linear regression, polynomial regression, and Long Short Term Memory for predicting the magnitude and depth of earthquakes. The performances are compared to find the most effective model. It is very difficult to accurately predict the magnitude of earthquakes however, in this paper it can be seen that polynomial regression shows the best overall results. Also, Random forests are incredibly effective in predicting the depth of an earthquake.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Business & IT BSc (56066)
Link to this item:http://purl.utwente.nl/essays/87313
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page