Soil carbon is a critical factor in maintaining soil health and combating climate change. Understanding and managing soil carbon levels is essential for sustainable agriculture and environmental protection. However, current methods for measuring soil carbon are time-consuming and costly, hindering efforts to monitor soil health and increase carbon sequestration. In this paper, we propose Scarf, a novel soil carbon sensing approach that combines widely accessible radio frequency (RF) and optical signals to detect soil carbon contents without dedicated hardware. Our key insight is that soil carbon content closely correlates with two indicators: the effective permittivity derived from RF signals and soil lightness determined from soil surface images. We mathematically model the correlations and leverage the non-linear correlation between the two signal modalities to compute soil carbon content. We employ machine learning to model relationships that cannot be captured by traditional mathematical equations. Our experimental results indicate that Scarf can achieve high soil carbon prediction accuracy that is comparable to the state-of-the-art soil carbon sensing techniques which cost US$1000s.

Soil carbon is a key soil property for soil health management and a crucial part of the global carbon cycle. Existing methods for soil carbon determination are too expensive and time-consuming. This paper introduces Scarf, a novel soil carbon sensing technique that leverages Wi-Fi and images and eliminates the need for specialized hardware. Our analysis reveals a strong correlation between soil carbon content and both the soil permittivity obtained from Wi-Fi signals and the soil lightness captured in soil surface images. We develop mathematical models to quantify the relationships between soil carbon content and the two signal modalities, and use the models to estimate soil carbon. We apply machine learning to help handle relationships that mathematical models do not capture. Our experiments demonstrate that Scarf delivers highly accurate soil carbon estimations.