Project collaborators
Damon Smith, Plant Pathology / Extension
Allison Kittinger, Open Source Program Office (OSPO)
David James Henry, Wisconet
Maria Oros and Iain McConnell, Data Science Institute (DSI)
Project start and end dates
August – December 2024
Project Summary
“There is a barrier of complexity of models that we can deliver to the masses. This code and tool help remove this barrier. They allow us to use very complex models, including advanced machine learning to improve accuracy, while keeping the usability and availability possible for the agricultural masses.”
—Damon Smith
This is a cool tool and I’m excited to use it this season. I would recommend it to others.
I like the idea of having all the forecasting tools in one place!
Overall, very intuitive and easy to use.
—Crop and Pest Management Workgroup survey responses
Emerging diseases pose a growing threat to crop yields. This creates a unique opportunity to support adaptation of agricultural practices using AI and machine learning solutions accessible to agricultural practitioners. Our open-source crop disease forecasting tool, API, and dashboard provide valuable insights for disease prevention and crop management, helping farmers protect their yields and profitability through data-driven decisions. A Wisconsin Idea Collaboration Grant supported the development of this tool.
The tool uses hourly weather data from Wisconet and IBM to identify weather conditions conducive to various crop diseases for any location in Wisconsin. Features include:
- An interactive weather map with disease risk visualization
- Dynamic data for different forecasting dates and diseases
- Downloadable reports
All of the data used to train and develop the models were obtained from public universities and supported by public grants, and it is fitting that the results of that work should also be open and public. Making these tools open source speeds up innovation and the ability to use them for the greater good. Private and public entities can also augment and add value to their own tools by accessing our open-source API. For example, the North Dakota Agricultural Weather Network (NDAWN) is using the open-source code from this project to power one of their disease forecasting models.