SoilSound: Smartphone-based Soil Moisture Estimation

2025-09-11

AI Summary

Existing soil moisture monitoring relies on invasive probes or specialized instrumentation, which disturbs soil integrity and hinders widespread adoption. This paper introduces the first non-invasive, calibration-free smartphone-based method for soil water content estimation via acoustic reflectometry: a vertically directed chirp signal is emitted by the device’s speaker, and the ground-reflected waveform is captured by its microphone; surface roughness is explicitly modeled, and a lightweight convolutional neural network enables real-time on-device inference. Our approach establishes, for the first time, a principled linkage between acoustic reflection physics and soil surface microstructure, ensuring cross-device compatibility and robustness across diverse soil types and environmental conditions. Evaluated across ten field scenarios, the method achieves a mean absolute error of 2.39% over a moisture range of 15.9%–34.0%, with low power consumption and minimal latency—making it suitable for home gardening and resource-constrained agricultural applications.

Technology Category

• Intelligent Robots: State Estimation
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Machine Learning: Hardware-aware ML

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Soil moisture monitoring is essential for agriculture and environmental management, yet existing methods require either invasive probes disturbing the soil or specialized equipment, limiting access to the public. We present SoilSound, an ubiquitous accessible smartphone-based acoustic sensing system that can measure soil moisture without disturbing the soil. We leverage the built-in speaker and microphone to perform a vertical scan mechanism to accurately measure moisture without any calibration. Unlike existing work that use transmissive properties, we propose an alternate model for acoustic reflections in soil based on the surface roughness effect to enable moisture sensing without disturbing the soil. The system works by sending acoustic chirps towards the soil and recording the reflections during a vertical scan, which are then processed and fed to a convolutional neural network for on-device soil moisture estimation with negligible computational, memory, or power overhead. We evaluated the system by training with curated soils in boxes in the lab and testing in the outdoor fields and show that SoilSound achieves a mean absolute error (MAE) of 2.39% across 10 different locations. Overall, the evaluation shows that SoilSound can accurately track soil moisture levels ranging from 15.9% to 34.0% across multiple soil types, environments, and users; without requiring any calibration or disturbing the soil, enabling widespread moisture monitoring for home gardeners, urban farmers, citizen scientists, and agricultural communities in resource-limited settings.

Problem

• Estimating soil moisture non-invasively using smartphones
• Eliminating need for specialized equipment or soil disturbance
• Providing accessible moisture monitoring for agricultural communities

Innovation

• Smartphone-based acoustic sensing system
• Vertical scan mechanism without calibration
• Convolutional neural network for on-device estimation