Catastrophe Forecasting

Visual Representation of the Predicted model

Inspiration

I got the inspiration from Dr.Ryan's project to predict Crime Rates in the United States. The model predicted how high crime rates will be during the year or in future years. Due to the high frequency of hurricanes in the Houston area(i.e where I live), it will be very useful to predict and prevent hurricanes. This will save a lot of money and even lives.

What it does

It analysis the data and forecasts future catastrophes and the month they most likely occur. I used the Atlantic ocean's dataset of events as an input and the output is the predicted events. It uses the facebook prophet to forecast future events.

How I built it

I used python as the main programming language, pandas to explore the data, matplotlib to plot and visualize the data, seaborn to visualize the output and Facebook Prophet to train the model.

Challenges I ran into

The biggest challenge I ran into was data preparation. The data was downloaded from kaggle and had a lot of issues to handle. Next, it was challenging to learn facebook prophet and implement it efficiently.

Accomplishments that I'm proud of

I'm very proud to complete the project and learn how to use Facebook tools to do Machine Learning. Additionally, I had amazing mentors to help me to accomplish this task.