Commodity RF Sensing of Belowground Tuber Growth

2026-01-31

AI Summary

This study addresses the long-standing challenge of non-invasive, low-cost monitoring of subterranean root crops. The authors propose a novel approach that eliminates the need for buried sensors by deploying radio-frequency antennas on the soil surface to collect swept-frequency channel responses and cellular link quality metrics in the 2.0–3.5 GHz band. Under non-line-of-sight conditions, spectral attenuation and fluctuation characteristics are leveraged to classify growth stages and localize sweet potato tubers. This work presents the first experimental validation that commercial off-the-shelf RF signals can effectively monitor underground crops, with robustness significantly enhanced through the fusion of multi-source RF features. Experimental results demonstrate 87.5% accuracy in growth-stage classification across varying soil types and moisture levels, and, when combined with link-quality indicators, achieve tuber localization at 5 cm grid resolution with 95.0% accuracy.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Belowground yield-forming organs of root and tuber crops are difficult to measure during growth, and management therefore relies on aboveground proxies and destructive sampling. Aboveground wireless links could provide a low-cost, non-invasive alternative, but strong attenuation and soil-dependent variability make repeatable subsurface sensing challenging. In a controlled greenhouse pot study of sweet potato, we deploy aboveground antennas in a line-of-sight-suppressed geometry and collect daily swept-frequency channel spectra together with standardized cellular link indicators, revealing consistent frequency-dependent attenuation and rippling as tubers develop. Here, we show that swept-frequency measurements in the 2.0-3.5 gigahertz band yield four interpretable spectral features that classify day-indexed growth stages with up to 87.5% accuracy across two soil recipes and two moisture regimes, and that fusing cellular link-quality indicators enables 5-centimeter-grid tuber localization with up to 95.0% accuracy, providing a proof-of-concept for subsurface crop monitoring without buried sensors, and motivating validation across cultivars and larger soil volumes.

Problem

• RF sensing
• belowground tuber growth
• non-invasive monitoring
• subsurface sensing
• root and tuber crops

Innovation

• RF sensing
• subsurface crop monitoring
• swept-frequency spectroscopy
• non-invasive agriculture
• tuber localization