Researchers at South Dakota State University's Geospatial Sciences Center of Excellence have developed a groundbreaking algorithm for crop monitoring, offering real-time insights into crop health and development, which could revolutionize farmers' field management by providing real-time information.
Two years ago, Yu Shen and Xiaoyang Zhang at GSCE aimed to improve crop monitoring efficiency by reducing the time-consuming and subjective visual assessments of plants, which have traditionally been the primary method for tracking crop progress.
Around 5,000 U.S. reporters conduct weekly surveys using visual observations of fields, providing valuable information on crop progress and conditions, but the process is labor-intensive, costly, and subjective.
Shen and Zhang proposed a more efficient method by using satellite remote sensing data to develop a near-real-time crop monitoring system, a concept not yet extensively explored for real-time monitoring of crop phenology.
The research team combined 30-meter spatial observations from polar-orbiting satellites like Landsat and Sentinel-2 with temporal data from geostationary satellites. This fusion allowed them to calculate high-resolution crop greenness development, offering near-real-time insights into crop growth.
Their new algorithm can monitor crop growth at a 30-meter field scale, accurately calculating key dates in development like planting, emergence, maturity, and harvest. The accuracy was validated by comparing predictions with ground-level measurements from the 2020 Iowa corn and soybean growing season, aligning with USDA progress reports.
This breakthrough enables near-real-time monitoring of crop phenology on a spatially distributed scale, improving upon state-based National Agricultural Statistics Service crop progress reporting.
Farmers stand to benefit significantly from this technology. It provides crucial information for crop management decisions, such as irrigation scheduling and yield estimation.
Zhang plans to integrate an algorithm into existing systems to monitor crop progress and conditions, allowing users to access crop conditions through an interactive map. Future research will focus on improving the algorithm's short-term prediction accuracy for global food security evaluation.
Funding for this project was provided by grants from the U.S. Department of Agriculture and the National Aeronautics and Space Administration.
Photo Credit: gettyimages-prostock-studio
Categories: South Dakota, Crops