Fusion of hyperspectral and ground penetrating radar to estimate soil moisture
This work addresses soil moisture monitoring for agricultural or environmental applications, but it is incremental as it builds on existing multi-sensor fusion methods.
The study tackled soil moisture estimation by fusing hyperspectral and ground penetrating radar (GPR) data, finding that this combination significantly improved estimation performance, while simulated soil-moisture data with hyperspectral data performed worst.
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.