Fusion of hyperspectral and ground penetrating radar to estimate soil moisture

TL;DR

This paper explores combining hyperspectral data with simulated ground penetrating radar (GPR) or soil-moisture data to improve soil moisture estimation, highlighting the potential and challenges of multi-sensor data fusion.

Contribution

It introduces two simulation methods to extend multi-sensor datasets and demonstrates that fusing hyperspectral and GPR data significantly enhances soil moisture estimation.

Findings

Fusion of hyperspectral and GPR data improves soil moisture estimation.

Simulated GPR data via interpolation or machine learning enhances results.

Combining simulated soil-moisture with hyperspectral data performs poorly.

Abstract

In this contribution, we investigate the potential of hyperspectral data combined with either simulated ground penetrating radar (GPR) or simulated (sensor-like) soil-moisture data to estimate soil moisture. We propose two simulation approaches to extend a given multi-sensor dataset which contains sparse GPR data. In the first approach, simulated GPR data is generated either by an interpolation along the time axis or by a machine learning model. The second approach includes the simulation of soil-moisture along the GPR profile. The soil-moisture estimation is improved significantly by the fusion of hyperspectral and GPR data. In contrast, the combination of simulated, sensor-like soil-moisture values and hyperspectral data achieves the worst regression performance. In conclusion, the estimation of soil moisture with hyperspectral and GPR data engages further investigations.