Item

Abstract

Effective measurement and management of soil organic carbon (SOC) are essential for ecosystem function and food production. SOC has an important influence on soil properties and soil quality. Conventional SOC analysis is expensive and time-consuming. The development of spectral imaging sensors enables the acquisition of larger amounts of data using cheaper and faster methods. In addition, satellite remote sensing offers the potential to perform surveys more frequently and over larger areas. This research aimed to measure SOC content with colour as an indirect proxy. The measurements of soil colour were made at an agricultural site of the Czech Republic with an inexpensive digital camera and the Sentinel-2 remote sensor. Various soil colour spaces and colour indices derived from the (i) reflectance spectroscopy in the selected wavelengths of the visible (VIS) range (400–700 nm), (ii) RGB digital camera, and (iii) Sentinel-2 visible bands were used to train models for prediction of SOC. For modelling, we used the machine learning method, random forest (RF), and the models were validated with repeated 5-fold cross-validation. For prediction of SOC, the digital camera produced R2 = 0.85 and RMSEp = 0.11%, which had higher R2 and similar RMSEp compared to those obtained from the spectroscopy (R2 = 0.78 and RMSEp = 0.09%). Sentinel-2 predicted SOC with lower accuracy than other techniques; however, the results were still fair (R2 = 0.67 and RMSEp = 0.12%) and comparable with other methods. Using a digital camera with simple colour features was efficient. It enabled cheaper and accurate predictions of SOC compared to spectroscopic measurement and Sentinel-2 data.