- 🔭 This project aims to develop a big data analytics solution for earthquake prediction using various big data technologies, including PySpark, MLlib, Power BI, and MongoDB. By leveraging these tools, our goal is to establish a comprehensive framework for processing earthquake data, training predictive models, and visualizing insights through reports and dashboards.
The primary objective of this project is to create a predictive model to forecast the likelihood of earthquakes based on historical earthquake data spanning from 1965 to 2016
We will initially work with sample data to develop and validate the model .The process encompasses the following steps:
Data Preprocessing: Transforming raw earthquake data into summary tables suitable for model training.
Model Training: Utilizing MLlib to train predictive models based on historical earthquake data.
Prediction: Using trained models to predict future earthquakes.
Data Storage: Writing the final datasets to MongoDB for storage and retrieval.
Data Analysis and Visualization: Building reports and dashboards in Power BI Desktop to analyze and visualize insights derived from the earthquake data.
Documentation link : EarthQuake Analysis