A Bayesian method for estimation of plant soil water content with application to low-cost horticultural robotics

Abstract

Climate change represents a challenge to food security by interfering with the environmental conditions needed for productive plant growth. While technology can be used for partial mitigation, access to technology is inequitable. Low-cost microcontrollers, such as the ESP32, have recently lowered the barrier for entry into prototyping smart devices. ESP32s equipped with capacitive moisture sensors have been suggested for low-cost smart plant watering systems. However, measuring moisture in soil is complex, potentially destructive, and requires careful calibration in order to characterise the response curve mapping soil water content to sensor measurements. Here, we developed a Bayesian method for estimating the inverse response curve from capacitive moisture sensor data, known water doses, and prior uncertainty, bypassing the need for destructive gravimetry. This method constitutes the core calibration module of the open-source OpenHCult software system for low-cost horticultural automation.