Sunscope is an innovative tool designed to forecast sunflower yield per acre in the United States under different emissions scenarios. Utilizing cutting-edge explainable AI (XAI) and machine learning (ML) techniques, Sunscope identifies key climate variables influencing yield and aids in developing effective adaptation strategies. The project leverages data from USDA and NOAA databases, as well as the WorldClim repository, and employs R programming language and ArcGIS Pro software for comprehensive data processing and analysis.
- Yield Forecasting: Predict sunflower yield per acre under various emissions scenarios using advanced ML models.
- Climate Variable Analysis: Identify and analyze key climate variables that influence sunflower yield.
- Adaptation Strategies: Provide insights for developing adaptation strategies to mitigate the impact of climate change on sunflower yield.
- Data Integration: Utilize data from reputable sources like USDA, NOAA, and WorldClim for accurate and reliable analysis.
- User-Friendly Interface: Easy-to-use interface for accessing and visualizing yield forecasts and climate variable insights.
The app is deployed here
To use Sunscope locally, follow these steps:
- Launch the application from your R environment.
- Select the desired emissions scenario and input parameters.
- View the yield forecasts and climate variable insights.
- Explore adaptation strategies based on the analysis.
Contributions to Sunscope are welcome! If you have suggestions for improvements or new features, please open an issue or submit a pull request.
Sunscope is released under the MIT License.
This project would not be posssible without the valuable data provided by USDA, NOAA, and WorldClim.