Title: Designing Technology for Different Scales of Irrigation Scheduling

Name: Paul Consalvo
Mentor: Dr. Alfonso Torres-Rua

Changes in water availability are a significant challenge to the agriculture industry; farmers depend on novel uses of sensors and data to maximize water efficiency. Documented studies have scheduled irrigation based around the approach of a threshold limit on crop water stress. This scheduling uses different parameters to determine the moment of crop water stress due to available water in the soil. However, soil moisture and matric potential, which continuously tracks water available to plants, have the potential to train machine learning algorithms to forecast water stress based on previous measurements. This project trains a learning machine with soil moisture and home-brew tensiometer information. To create a system of water management that avoids exposing crops to stress, the learning machine uses previous soil water conditions to forecast crop water demand; the forecast informs the farmer of the moment maximum water depletion will occur, providing the farmer opportunity to irrigate in advance of crop water stress conditions. Additionally, the value of soil moisture, matric potential, and trained machine learning is evaluated by implementing a home-brew, web-app connected platform that can transfer data continuously and wirelessly using web-Bluetooth protocols and solar charging. This web platform interfaces with machine learning functionality and provides irrigation guidance to the farmer. The short-term achievements of this project will provide additional value to existing water availability measurements. Soil moisture and water availability both have the potential, tested through this project, to forecast water stress through previously measured soil water condition. The long-term impacts of this project will be an investigation into the suitability of sensor-machine learning-web application integrations that will allow farmers to access data and receive irrigation guidance across multiple farms. These impacts will allow farmers to further maximize crop yield and quality with their limited water availability.