Web Application of Earthquake Prediction Based on Machine Learning

Rabendra Shrestha

Master's thesis

Abstract:

This is the application base project and the complete package for the end users so they can use in their devices. There are the methods and modules are used to complete this project. Using moving average (MA) method based on time series data and analysis the trend that which is going towards make it easy to predict. The forecasting is the short time period. In this project forecasting is five next days periods. The data is the real direct attached from the USGC. This application is like the pre alarm that inform the earthquake might happen in next five days in where and how much magnitude might be face.But that does not mean it ring the bell to the email or get the notification to the mobile devices. It just provides the pre inform and possible danger to the places and try to make prevention activities by users own.Since this is the based-on machine learning, so data is the time series data. Before the application there is the machine learning analysis and the data visualization to see the trend of the flow of earthquake. After that applied model and methods, test accuracy and only than the code converted into the web application.

Keywords

Earthquake prediction, Artificial neural networks, Time series, Machine learning, Web Application, Data Analysis, Data Visualization.

Language used: English

Date on which the thesis was submitted / produced: 7. 4. 2020

Thesis defence

• Supervisor: doc. Ing. Vojtěch Merunka, Ph.D.

Czech University of Life Sciences Prague

Faculty of Economics and Management

Master programme / field:
Systems Engineering and Informatics / Informatics