An IoT and Machine Learning Approach for Site-specific Irrigation in Residential Irrigation Systems

Abstract

Irrigation schedules on traditional irrigation controllers tend to disperse too much water by design and cause runoff, which results in wastage of water and pollution of water sources. Previous attempts at tackling this problem used expensive sensors that aren’t applicable to the residential landscape. In this thesis, we propose Weather-aware Runoff Prevention Irrigation Control (WaRPIC), a low-cost, practical solution that optimally applies water, while preventing runoff for each sprinkler zone. WaRPIC involves experiments conducted by homeowners on their landscape as part of a two-week data collection phase. The gathered data is used to build machine learning models that can accurately predict the Maximum Allowable Runtime (MAR) for each sprinkler zone given weather data obtained from a network of weather stations. We have also developed a low-cost module that can retrofit irrigation controllers in order to modify its irrigation schedule. We built a neural network-based model that predicts the MAR for any set of antecedent conditions, using data collected from a sprinkler zone. The model’s prediction is compared with a state-of-theart irrigation controller and the volume of water wasted by WaRPIC was only 2.6% of that of the state-of-the-art. We have deployed our modules at residences and estimate that the average homeowner can save 38,826 gallons of water over the course of May-Oct 2019, resulting in savings of $192.