New Systems Monitor Conditions and Provide Early Warning to Keep Crops Healthy
Outcome/Accomplishment
Researchers have created a new integrated system that combines close and remote sensing to monitor plant health and growth, as well as to detect the symptoms and causes of potential harm by external or internal factors. This innovation was developed with support from the NSF-funded Internet of Things for Precision Agriculture (NSF IoT4Ag) Engineering Research Center (ERC), which is headquartered at the University of Pennsylvania.
Impact/Benefits
Plant health and growth are subject to a wide array of environmental and physical challenges, ranging from weather and man-made problems (e.g., overwatering, chemical exposure) to diseases and pests. This new system uses monitoring sensors and artificial intelligence (AI) detection models to improve the efficiency of conventional data collection for crop models and decision support systems. This information will be used to inform and optimize precision crop management.
Explanation/Background
The NSF IoT4Ag researchers built and trained AI models to detect diseases in cotton plants and set up systems so these models can run automatically on small, field-based computers. They also filed a provisional patent for a drone port that allows drones to monitor crops remotely and autonomously. In addition, they tested a waterproof, solar-powered “sentinel” device in the field that observes crops using 3D imaging and communicates data via Wi-Fi and long-range networks. This work also contributed to a study to measure peanut crop damage from disease using drones and multispectral imagery to detect things not visible to the naked eye.
Location
Philadelphia, Pennsylvaniawebsite
Start Year
Microelectronics and IT
Quantum, Microelectronics, Sensing, and IT
Lead Institution
Core Partners
Fact Sheet
Outcome/Accomplishment
Researchers have created a new integrated system that combines close and remote sensing to monitor plant health and growth, as well as to detect the symptoms and causes of potential harm by external or internal factors. This innovation was developed with support from the NSF-funded Internet of Things for Precision Agriculture (NSF IoT4Ag) Engineering Research Center (ERC), which is headquartered at the University of Pennsylvania.
Location
Philadelphia, Pennsylvaniawebsite
Start Year
Microelectronics and IT
Quantum, Microelectronics, Sensing, and IT
Lead Institution
Core Partners
Fact Sheet
Impact/benefits
Plant health and growth are subject to a wide array of environmental and physical challenges, ranging from weather and man-made problems (e.g., overwatering, chemical exposure) to diseases and pests. This new system uses monitoring sensors and artificial intelligence (AI) detection models to improve the efficiency of conventional data collection for crop models and decision support systems. This information will be used to inform and optimize precision crop management.
Explanation/Background
The NSF IoT4Ag researchers built and trained AI models to detect diseases in cotton plants and set up systems so these models can run automatically on small, field-based computers. They also filed a provisional patent for a drone port that allows drones to monitor crops remotely and autonomously. In addition, they tested a waterproof, solar-powered “sentinel” device in the field that observes crops using 3D imaging and communicates data via Wi-Fi and long-range networks. This work also contributed to a study to measure peanut crop damage from disease using drones and multispectral imagery to detect things not visible to the naked eye.