SHARE
- 7 minutes read
During the years from 2015 to 2019, soybean diseases were responsible for losses of around 9% of the production potential in the U.S., equaling $3.8 billion annually (Bi et al. 2020). Soybeans (Glycine max) are the primary host for Fusarium virguliforme, a soil-borne pathogen 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 other main soybean production areas (i.e. Argentina, Brazil), and continues to spread.
Challenges
Predictive Modeling for SDS
Crafting an advanced analytics model that can be used to predict SDS outbreaks.
Agronomic Data Integration
Synthesizing diverse data sets to model SDS spread accurately.
Data Standardization Challenges
Harmonizing large-scale agronomic data sets for analysis.
Decision-Support Development
Building data-driven tools for effective SDS management by soybean farmers.
Comprehensive Analysis Requirement
The requirement for software capable of processing extensive data on soybeans, including sanitation, weather conditions, irrigation patterns, crop rotation, and fungicide use.
Our Solution
In response to the pressing challenge of Soybean Sudden Death Syndrome (SDS), a novel approach was devised, leveraging the collective expertise of pathologists across North America and the cutting-edge data analysis tools provided by Agmatix. This solution aimed to harness the power of big data to predict and mitigate the impacts of SDS on soybean crops. The key elements of this strategic approach include:
Interdisciplinary Collaboration
A coalition of pathologists from five Midwest universities and the Ontario Ministry of Agriculture collaborated to study SDS, aiming to predict its occurrence and severity.
Comprehensive Data Analysis
Utilized data from 90 field trials across 5 U.S. sites and 1 Canadian site, incorporating management practices and weather conditions into an XGBoost machine learning model.
Standardization with GUARDS
Employed Agmatix's GUARDS protocol to standardize and harmonize trial data, ensuring data interoperability and accuracy in analysis.
Predictive Modeling Success
Achieved significant predictive accuracy with a mean absolute error of 7 for disease severity, demonstrating the model's capability in SDS management.
Results
SDS Severity Prediction
Achieving high accuracy in SDS severity forecasting.
Disease Classification Success
The model's effective disease severity classification.
Data Harmonization for Research
Standardizing trial data to enable comprehensive analysis.
Our collaboration with Agmatix and the adoption of their Trial Management platform has revolutionized our product trials processes. We’ve cut months off our data processing time, significantly accelerating product development and market readiness. We are excited about the prospect of bringing new products to market faster, enabling higher yields for our customers.
Dr Prashant Puri,
Head of R&D, Deepak
Conclusions
The initiative led by a coalition of extension pathologists and supported by Agmatix's data analytics and standardization tools has showcased the significant impact of leveraging big data in agriculture. As we review the progress and insights gained from this collaboration, here are the pivotal conclusions drawn from the study:
Predictive Modeling Insights
The essential role of data integration and standardization in SDS prediction accuracy.
Collaborative Analytics Impact
The potential of collaborative data analytics in advancing agricultural predictive modeling.
Interdisciplinary Approach Value
The effectiveness of combining various expertise in solving agricultural problems.
Tool Development for SDS Management
he future expansion of the model into a robust decision-support system for soybean producers.
Looking Ahead
Cultivating a More Efficient, Sustainable Agricultural Landscape
The collaboration focusing on Soybean Sudden Death Syndrome (SDS) is gearing up to enhance its predictive model with broader data collection and advanced machine learning techniques, aiming for greater accuracy in forecasting SDS outbreaks. Efforts to make the model more user-friendly and integrate real-time data will improve its applicability and responsiveness for farmers and agronomists.
Expanding collaborations and tailoring the tool for global use are key steps toward aligning with the needs of the agricultural community. By doing so, the initiative not only targets SDS more effectively but also promotes sustainable farming practices worldwide, showcasing the potential of data-driven solutions in agriculture.
