Title: Interactive Irrigation Scheduling Enhanced by Field Measurements and Machine Learning
Real-time irrigation schedules have been shown to outperform predetermined irrigation schedules that do not consider the present water requirement and water availability for a crop. However, implementing real-time irrigation scheduling requires reliable present soil-crop-atmosphere dynamics and future weather predictions; moreover, how to enable the model recommended day-to-day water application to be used by farmers remains a challenge since they usually make the choice based on their own experience and knowledge. Farmers and computer-based tools are rarely connected in a closed loop since farmers' feedbacks are usually not incorporated into a real-time modelling procedure. I am introducing a real-time irrigation scheduling tool (RTIST) to resolve these critical issues based on weather forecasts, field observations, and human-machine interactions. RTIST integrates a simulation & optimization model, a data assimilation technique, and a human-computer interaction method, enabling the tool's optimality, accuracy, and applicability. However, due to the high computational burden, equation-based simulations can limit the application of such model-based tools. I am also introducing a surrogate data-driven model that enables conducting reliable simulations with minor computational costs. The optimization and simulation are validated by running the tool on two crop fields, showing the accuracy of present estimation and future prediction of soil moisture and leaf area index, taking advantage of field observation and data assimilation. The applicability of RTIST is tested via virtual irrigation exercises (VIEs) with a group of farmers for a corn field in Eastern Nebraska. It is found that RTIST with farmers’ direct engagement results in increased crop yield, profit, and water saving in comparison to traditional practices. Especially, farmers’ feedbacks show interest in using the tool in real-world irrigation scheduling, as well as meaningful suggestions to improve the tool for real-world application.
Alaa Jamal is a Postdoctoral Associate in the Department of Civil and Environmental Engineering. He completed his BSc and graduate studies from the Technion - Israel. His fields of expertise are optimization, data assimilation, and machine learning. In his postdoc, he developed an irrigation scheduling tool for two USDA projects.