Smart irrigation model predicts rainfall to conserve water

From the Cornell Chronicle (By Melanie Lefkowitz, July 16, 2019)

More than 70% of fresh water is used for agriculture. However, irrigation technologies are not often smart and water is often overconsumed. Chao Shang, Wei-Han Chen, Abraham Duncan Stroock, and Fengqi You have developed a robust predictive model of irrigation that could save 40% of the water consumed.

Previously, Stroock’s group developed sensors to determine when plants are thirsty. But sensors alone are insufficient because growers don’t need to irrigate if rain is on the way. Considering the weather prediction is better but not ideal, Chao said, because forecasts are often wrong, and the uncertainty of a forecast may be greater than the expected rainfall.

The researchers’ method uses historical weather data and machine learning to assess the uncertainty of the real-time weather forecast, as well as the uncertainty of how much water will be lost to the atmosphere from leaves and soil. This is combined with a physical model describing variations in the soil moisture.

Integrating these approaches, they found, makes watering decisions much more precise.

Chao Shang, Wei-Han Chen, Abraham Duncan Stroock, Fengqi You. Robust Model Predictive Control of Irrigation Systems With Active Uncertainty Learning and Data Analytics. IEEE Transactions on Control Systems Technology, 2019; 1 DOI: 10.1109/TCST.2019.2916753