XRF / 3rd Parties, Acdemy / Coffee

ISU is developing big-data models of soybean SDS with agmatix

ISU is developing big-data models of soybean SDS with agmatix

Fungi, the most common cause of disease in plants, are responsible for up to 30% of plant diseases today. 1 According to Jain and colleagues at the Zunyi Medical University in China, the most common sources of fungi are infected seeds, soil, crop debris, neighboring crops, and weeds. They are spread by wind and water and through contaminated soil, animals, machinery, seedlings, and farm workers. An infection can be established when they enter plants through their natural openings, including stomata, and through wounds resulting from pruning, harvesting, insects, and mechanical damage. 1 In recent years, infection by the Fusarium species has been on the rise in many plants, including soybeans, which serve as an affordable source of protein across the globe. Fusarium virguliforme is responsible for soybean sudden death syndrome (SDS), which has become a leading cause of the decline in soybean crop yield in North America. First seen about 40 years ago, SDS is currently detected in most soybean-growing areas in the United States and in Ontario, Canada, and continues to spread to other parts of the New World.

Challenge

To prevent the continued decline in soybean yield, growers must be able to predict the location of SDS outbreaks and their severity. This points to a need for an agricultural predictive modeling tool that can be used to explore relationships among key factors contributing to the spread of SDS and facilitate the development of data-driven agricultural solutions. This task is complicated, however, by the large number of factors that must be taken into consideration, including sanitation; weather conditions; patterns of irrigation (which can induce spore release) and crop rotation (which can affect soil infection); planting time, spacing, and overlapping crops; and the plant’s natural resistance to fungi versus fungicides. Additionally, growers must remember that other disorders cause symptoms similar to those of SDS and that when SDS symptoms appear, it may already be too late to stop the progression of disease. Thus, soybean growers require agronomic analysis software that can handle large amounts of data on soybeans as well as crops with which they are rotated, crops that are grown in adjacent fields, and–because fungi can remain dormant in the ground until conditions favorable for their growth arrive–crops that were previously grown in the same field.

Our Solution

Iowa State University of Science and Technology (ISU) is one of five universities participating in a study of SDS outbreaks to determine how to predict where they are most likely to occur and the severity of their occurrence. Their findings may allow soybean farmers to make optimal decisions regarding the time for planting, use of hybrids, population density, and other factors to prevent this disease. The ISU study was based on data derived from six studies of a total of 90 SDS field trials carried out over 10 years in six locations in the United States (5) and Canada (1). The original data were collected during weekly observations of plant-related conditions, including the weather, and monitored using the open-source software library XGBoost (an ensemble of decision trees). The challenge of standardizing the terminology, measurements, etc., of such a large amount of data was met using the agmatixTM protocol GUARDS (Global Universal Agronomic Data Standard), an agronomy data standardization tool in which trial-specific definitions and data measurements are standardized and anomalies that could skew analytical results are identified. Thus, they were able to transform trial-related data into a language that can be understand by researchers around the world.

Results

The researchers were able to predict disease severity with an 11% margin of error and, thus, predict which crops would have no disease , moderate disease, or severe disease with 80% accuracy. They also found that (1) seed hybrid predicted plant sensitivity to F virguliform to a greater degree than any of the other parameters originally considered by the team; and (2) population density during the early stages of plant growth—which had not been considered—was an accurate predictor of SDS severity.

CONCLUSION

Given more data, this preliminary analysis could be transformed into an agricultural predictive modeling tool that soybean growers can use to manage the occurrence of SDS in their fields.