Crop Yield Prediction Using Remote Sensing Data

Overview

This project is a comprehensive solution for Crop Yield Prediction using state-of-the-art machine learning techniques and remote sensing data. It empowers farmers, agricultural experts and stakeholders with valuable insights into crop yield forecasts, allowing for better planning and decision-making in the agricultural sector.

Data Sources

• GridMET Weather Data: We have utilized weather data from the GridMET dataset spanning from the year 1980 to 2020 to enhance our predictive models.

  • https://www.climatologylab.org/gridmet.html

• USDA Quick Stats: We also incorporate data from USDA Quick Stats for crop yield information, providing a valuable additional source for our predictive models.

  • https://www.nass.usda.gov/Quick_Stats/index.php

Python Package Deployement

• netcdf-unpacker: To simplify working with NetCDF files, we've developed and deployed an open-source library called netcdf-unpacker, which is available on PyPi.
  • https://pypi.org/project/netcdf-unpacker/
  • https://github.com/Ananya0703/NetCDF_Unpacker

Project Focus

This project primarily focuses on accurate crop yield predictions for two major crops:

• Corn: Providing detailed and reliable predictions for corn crops.

• Soybean: Offering insights into soybean crop yield predictions.

Project Highlights

• State-Wise Crop Yield Prediction for the US Corn Belt: Our models have been designed to provide accurate crop yield predictions for the US Corn Belt states.

• Ongoing Project: We're continuously improving and expanding this project, with the next goal being county-wise crop yield prediction.

• Streamlit Web Application: The model has been deployed as a user-friendly web application using Streamlit, making it easy for users to obtain real-time crop yield predictions and visualize the results.

Streamlit Web Application

Explore crop yield predictions and visualize insights with our user-friendly Streamlit web application. Get real-time forecasts and gain valuable information for better agricultural planning and decision-making.

• streamlit app: https://satellite-harvest.streamlit.app/
• github link: https://github.com/atishay-gwari/Satellite-Harvest

Contributing

We welcome contributions from the community. If you'd like to enhance the models, improve the user interface, or add support for new data sources and features, please consider contributing to this project. Check our Contribution Guidelines for more details.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contact

For questions or further information, please contact:

• Ananya Giliyal
• Isha Paranjpe
• Atishay Gwari
• Mansi Katgire

---

Note: This project is under active development, and we encourage you to check back for updates and improvements.