Home

Dorothy AI Wiki

This page is a reference for all things related to the Dorothy-AI project, an open-source machine learning project for advanced weather forecasting and severe tornadic storm prediction.

Table of Contents

Introduction

Project Structure

Data Sources

Machine Learning Algorithms

Getting Started

Contributing

Introduction

Dorothy-AI is a machine learning project aimed at improving weather forecasting and storm prediction. By analyzing historical weather data and real-time weather data, the project aims to build models that can accurately predict severe tornadic weather events.

Project Structure

The project is organized as follows:

dorothy-ai/
├── data/
├── src/
├── models/
├── notebooks/
├── LICENSE.md
├── README.md
└── .gitignore

data: contains all the raw and processed data used in the project.

src: contains the source code for the project.

models: contains the trained machine learning models.

notebooks: contains Jupyter notebooks used for data exploration and model training.

LICENSE.md: the license for the project.

README.md: the project's README file.

.gitignore: contains a list of files and directories to be ignored by Git.

Data Sources

The project uses a combination of publicly available data sources such as NOAA's Integrated Surface Database (ISD), the National Centers for Environmental Prediction (NCEP) Reanalysis datasets, and private weather data from Storm Chasers. The data is cleaned and preprocessed to remove missing values and anomalies.

Machine Learning Algorithms

The project uses a variety of supervised and unsupervised machine learning algorithms, including:

• Random Forest
• Support Vector Machines
• Convolutional Neural Networks
• K-means Clustering
• Principal Component Analysis

In addition, time series analysis and anomaly detection methods are used to identify unusual or abnormal weather patterns.

Getting Started

To get started with the project, follow these steps:

• Clone the repository: git clone https://github.com/username/dorothy-ai.git
• Install the required dependencies: pip install -r requirements.txt
• Explore the data: see the Jupyter notebooks in the notebooks directory for examples of data exploration and visualization.
• Train models: see the src directory for source code used to train machine learning models.
• Evaluate models: see the models directory for pre-trained machine learning models.

Contributing

Contributions to the project are welcome! If you are interested in contributing, please see the CONTRIBUTING.md file for guidelines and instructions.