Contactless estimation of soil moisture using leaky Rayleigh waves and a fully convolutional network

Abstract

Soil moisture is a key factor that influences various aspects of ecosystem functioning. Measuring soil moisture without installing any objects in the soil is desirable because it allows for accurate characterizations of soil moisture while minimizing impacts on soil structure and ecology. In this study, we explored the potential of leaky Rayleigh waves as a proxy to contactlessly estimate soil moisture. We developed an ultrasonic system containing a transducer, receivers, and acoustic barrier. The specimens of sand, silt, and clay were utilized. Experiments were conducted over 4 months. We used a widely used soil-embedded moisture sensor to compare and develop relationships between leaky Rayleigh waves and soil moisture. Our results showed that as soil moisture increased, the velocity and amplitude of leaky Rayleigh waves decreased because water molecules attracted to the soils led to their attenuation. However, their magnitudes were not considerable except for very dry soils. To overcome these limited relations to estimate soil moisture from leaky Rayleigh waves, we constructed authentic images based on the observed leaky Rayleigh waves and used them as inputs for a fully convolutional network. We found that the combination of the ultrasonic system and deep learning approach developed in this study were suitable for estimating soil moisture without soil disturbances (RMSE = 0.01 m3 m-3). This study suggests that leaky Rayleigh waves have the potential to serve as a reliable proxy for determining soil moisture without the need for physical contact. Leaky Rayleigh waves are dependent on soil moisture, but their magnitudes vary depending on soil types.Developed ultrasonic system and deep learning are suitable for measuring soil moisture without soil disturbances.The proposed method has good performance in estimating soil moisture under sand, silt, clay, and soil mixture.