Refining environmental risk factors to improve Soybean white mold management efficiency.

Commodities

• Agronomic: soybeans

Practices

White mold (a.k.a. Sclerotinia stem rot) causes annual losses of millions of bushels for North Central region soybean producers. Current disease management largely depends on fungicide applications, which are often mistimed due to a lack of accurate real-time risk assessment. As a result, fungicides are frequently used when not needed, or too late to be effective. This leads to substantial unnecessary input costs, environmental contamination, and accelerated selection pressure for fungicide resistance development.

This project addresses these challenges by identifying and refining environmental predictors that can be used to support precise and timely fungicide applications. We will identify and refine real-time environmental data, including above-and-below canopy temperature, light quality, humidity, leaf wetness, soil conditions, and canopy closure, with continuous monitoring of pathogen development and spore release. This high-resolution data will be correlated with soybean flowering, the most susceptible crop stage, to precisely map the environmental triggers for infection.

By deploying advanced weather sensors and time-lapse cameras across university research farms and commercial farms, we will identify the most predictive environmental variables for white mold outbreaks. The key outcome will be the identification of critical environmental drivers of disease. This will enable growers to make data-driven decisions on fungicide application timing, significantly reducing unnecessary chemical use while improving disease control effectiveness. This will enhance both economic viability and environmental sustainability in soybean production.

Project output and outreach effectiveness will be assessed through key metrics such as digital engagement metrics, growers' feedback and participation, field day performance, feedback from the advisory committee, and farmer corporates involved in the project, and citations and references to publications.

The outcomes of this project will be the measurable weather, soil and below canopy microclimate conditions, such as temperature, humidity, precipitation, light, leaf wetness, soil temperature, and soil moisture, that contribute to pathogen development. By understanding periods of high disease risk, we can help growers in making timely and informed fungicide application decisions.

A major outcome of the project is the reduction of unnecessary fungicide use. Currently, many growers apply fungicides without knowing if the disease will occur, just to be safe. This practice increases production costs, contributes to environmental stress, and accelerates the development of fungicide-resistant pathogen strains. By using weather-based predictions, growers will be able to avoid unnecessary applications and only apply fungicides when conditions are right for disease development.

Another important outcome is improved fungicide efficacy. Applying fungicides during periods of high risk, when infection is most likely, will improve disease control outcomes. Timely applications also reduce selection pressure, helping to preserve the long-term effectiveness of existing fungicides.

The project will be implemented across both university research fields and commercial farms, enabling comparisons of pathogen risk and management strategies under diverse conditions. This dual approach will help identify practical solutions for disease mitigation in real-world settings.

Overall, the project will refine weather-based risk factors that growers and advisors can use to optimize white mold management. This information will support more precise, efficient, and environmentally responsible decision-making by aligning disease control efforts with actual production field conditions.