Researchers at Colorado State University, Fort Collins, are working with farmers to improve irrigation using sensors, satellite imagery and deep learning technology.
The project is led by Sangmi Pallickara, PhD, a professor in the computer science department at CSU. It is funded by a $1.2 million National Science Foundation grant.
It focuses on optimizing center pivot irrigation systems used in the western U.S.
“The goal is to forecast crop water needs using novel deep learning algorithms and game theoretic methods,” says Pallickara. “Better water use and placement would prevent erosion and nutrient runoff from overwatering while also improving yields. The growers also still retain control in this system to make decisions and consider how variables such as water rights and usage rates may come into play in a given year.”
According to the United States Geological Survey, irrigation accounted for 42% of the U.S.‘s freshwater withdrawals in 2015. The CSU team is exploring the use of sensors and satellite data to determine specific water needs across varying terrains. Additionally, deep learning, a subset of machine learning, will play a role in analyzing vast amounts of data to refine irrigation practices.
The team is collaborating with agricultural company Simplot and the University of Nebraska-Lincoln for data collection.
Researchers on the project include Sangmi Pallickara, Shrideep Pallickara, Jay Breidt, Jeffrey Niemann and Allan Andales.
Share on social media:
