Researchers have created a novel method for monitoring soil moisture that uses artificial intelligence and machine learning to save energy and money. When compared to existing industry standards, the software learns over time how to make the best use of available network resources, resulting in more power-efficient systems at a lower cost for large-scale monitoring.
Soil moisture is an important variable in both forested and agricultural ecosystems, especially during drought conditions such as those experienced in Maine over the summers. Regardless of the robust soil moisture monitoring networks and large, freely available databases, the high costs of using such technologies may be prohibitive for researchers, farmers, or foresters investigating these issues.
Because of the existing combination of softwares, collection systems, and computing environments that require increasing amounts of energy to power, monitoring and measuring forest ecosystems is a complex challenge. The University of Maine’s Wireless Sensor Networks (WiSe-Net) laboratory has developed a novel method for using artificial intelligence and machine learning to make soil moisture monitoring more energy and cost efficient – a method that could be used to make measuring more efficient across Maine’s broad forest ecosystems and beyond.
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.
Ali Abedi
Soil moisture is an important variable in both forested and agricultural ecosystems, especially given the recent drought conditions in Maine summers. Despite robust soil moisture monitoring networks and large, freely available databases, the cost of commercial soil moisture sensors and the power required to run them can be prohibitively expensive for researchers, foresters, farmers, and others tracking the health of the land.
UMaine’s WiSe-Net team collaborated with researchers from the University of New Hampshire and the University of Vermont to create a wireless sensor network that uses artificial intelligence to learn how to be more power efficient in monitoring soil moisture and processing data. The research was supported by a National Science Foundation grant.
“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, principal investigator of the recent study and professor of electrical and computer engineering at the University of Maine.
The software learns over time how to make the best use of available network resources, which helps produce power-efficient systems at a lower cost for large-scale monitoring compared to the existing industry standards.
WiSe-Net also collaborated with Aaron Weiskittel, director of the Center for Research on Sustainable Forests, to ensure that all hardware and software research is informed by the science and tailored to the research needs.
“Soil moisture is a primary driver of tree growth, but it changes rapidly, both daily as well as seasonally,” Weiskittel says. “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 study was published in Springer’s International Journal of Wireless Information Networks.
Although the researchers’ system focuses on soil moisture, the same methodology could be extended to other types of sensors, such as ambient temperature, snow depth, and others, as well as scaling up the networks with more sensor nodes.
“Different sampling rates and power levels are required for real-time monitoring of various variables. Instead of sampling and sending every single data point, which is inefficient, an AI agent can learn these and adjust the data collection and transmission frequency accordingly” According to Abedi.
