The project is led by Xiaolei Huang, a computer science professor at the University of Memphis.
Also Read: Soybean sowing gains pace, acreage seen surpassing last year
It brings together researchers from the University of Missouri, Kennesaw State University, Indian Institute of Technology Delhi, Sher-e Kashmir University of Agricultural Sciences and Technology of Jammu and Kashmir, and the Indian Council of Agricultural Research National Soybean Research Institute.
The National Science Foundation (NSF) has awarded funding of USD 528,137 for a three-year project which will begin on October 1 and continue till September 30, 2029.
The project will create a smart sensor network, NextG-enabled wireless communication, and advanced AI tools to monitor crops and soil conditions, the NSF said.
It said the system will help soybean breeders understand crop status and make better decisions.The project is a collaboration between the NSF and India’s Ministry of Electronics and Information Technology.
“It is especially encouraging that this work is being done in collaboration with the government of India, which pioneered ‘the green revolution’ in the 1960s and averted future famines,” Congressman Steve Cohen from Tennessee said in a statement.
Also Read: Monsoon revival boosts summer crop planting in India
He said the project will improve soybean yields and productivity, which will help feed the ever-growing population of our planet.
According to the NSF, the project will address major challenges faced by soybean farmers in both the US and India, including pests, crop diseases, and increasingly unpredictable weather.
Researchers plan to combine sensor networks, drone-based data collection, passive sensing technologies, and AI-powered analytical tools to provide more accurate insights into crop performance.
The project has three main research areas. The first involves developing sensor arrays to measure soil nutrients, moisture, and environmental conditions.
The second focuses on creating energy-efficient wireless communication systems using drones and passive sensing for large-scale field monitoring.
The third area aims to develop multimodal large language models that combine sensor data, drone imagery, and environmental information to support crop phenotyping, pest management, and yield forecasting.
The project will integrate these thrusts into a toolkit that combines sensing, wireless communication, and AI to support data-driven agricultural insights.