AI Tapped to Keep Maine's Trees Monitored with Low-Cost, High-Efficiency Soil Moisture Networks

A team of scientists from the University of Maine's Wireless Sensor Network (WiSe-Net) laboratory, alongside colleagues from the University of New Hampshire and University of Vermont, has turned to artificial intelligence (AI) to keep tabs on the state's forest health — by considerably boosting energy efficiency.

"AI can learn from the environment, predict the wireless link quality and incoming solar energy to efficiently use limited energy and make a robust low cost network run longer and more reliably," says Ali Abedi, professor of electrical and computer engineering and principal investigator of the study, of the team's findings.

"Real-time monitoring of different variables requires different sampling rates and power levels. An AI agent can learn these and adjust the data collection and transmission frequency accordingly rather than sampling and sending every single data point, which is not as efficient."

The team's study concentrated on a network of devices designed to monitor soil moisture, built to come in at a considerably lower per-unit cost than commercial off-the-shelf rivals while offering a big boost to energy efficiency by training an artificial intelligence system to run the sensors and communicate results on the most efficient schedule possible.

"Soil moisture is a primary driver of tree growth, but it changes rapidly, both daily as well as seasonally," explains Aaron Weiskittel, director of the Center for Research on Sustainable Forests, who collaborated on the project.

"We have lacked the ability to monitor effectively at scale. Historically, we used expensive sensors that collected at fixed intervals — every minute, for example — but were not very reliable. A cheaper and more robust sensor with wireless capabilities like this really opens the door for future applications for researchers and practitioners alike."

The team's work has been published in the International Journal of Wireless Information Networks; the researchers have indicated that the core concepts behind the study are applicable to a broader range of wireless sensor systems than just moisture sensors.