Search

Soil moisture content (SMC) is a basic condition for crop growth, and a key parameter for crop yield prediction and drought monitoring. An advantage of large-scale synchronous observation using remote sensing technology is that it provides the possibility of dynamic monitoring of soil moisture content in a large area. This study aimed to explore the feasibility of accurately estimating soil moisture content at a regional scale by combining ground hyper-spectral data with multispectral remote sensing (Sentinel-2) data. The results showed that the different mathematical transformations increased the correlation between soil spectral reflectance and SMC to varying degrees. Hyper-spectral optimized index normalized difference index (NDI) ((B769~797 – B848~881/B769~797 + B848~881); (B842 – B740/B842 + B740)) derived from the transformed reflectance (the first-order derivate of reciprocal-logarithm (Log (1/R))′, second-order derivate of reciprocal-logarithm (Log (1/R)) ′′) showed significant correlation (correlation coefficient (r) = 0.61; r = 0.47) with SMC, and the correlation coefficient values higher than difference index (DI) and ratio index (RI). From the performance of 12 prediction models which were taken optimized indices as independent variables, the central wavelength reflectance model (Log (1/R))′′ and the average wavelength reflectance model ((Log (1/R)) ′ presented higher validation coefficients (coefficient of determination (R2) = 0.61, root mean square error (RMSE) = 4.09%, residual prediction deviation (RPD) = 1.82; R2 = 0.69, RMSE = 3.48%, RPD = 1.91) compared with other models. When verifying the accuracy, the model yields R2 values of 0.619 and 0.701. These results indicated that the two-band hyper-spectral optimized indices (NDI) as an optimal indicator for quickly and accurately soil moisture content estimation. Combining the ground hyper-spectral data and satellite remote sensing image regional scale soil moisture content prediction provides a scientific reference for land-space integrated soil moisture content remote sensing monitoring. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV)-based hyperspectral remote sensing is an important monitoring technology for the soil moisture content (SMC) of agroecological systems in arid regions. This technology develops precision farming and agricultural informatization. However, hyperspectral data are generally used in data mining. In this study, UAV-based hyperspectral imaging data with a resolution o 4 cm and totaling 70 soil samples (0–10 cm) were collected from farmland (2.5 × 104 m2) near Fukang City, Xinjiang Uygur Autonomous Region, China. Four estimation strategies were tested: the original image (strategy I), first- and second-order derivative methods (strategy II), the fractional-order derivative (FOD) technique (strategy III), and the optimal fractional order combined with the optimal multiband indices (strategy IV). These strategies were based on the eXtreme Gradient Boost (XGBoost) algorithm, with the aim of building the best estimation model for agricultural SMC in arid regions. The results demonstrated that FOD technology could effectively mine information (with an absolute maximum correlation coefficient of 0.768). By comparison, strategy IV yielded the best estimates out of the methods tested (R2val = 0.921, RMSEP = 1.943, and RPD = 2.736) for the SMC. The model derived from the order of 0.4 within strategy IV worked relatively well among the different derivative methods (strategy I, II, and III). In conclusion, the combination of FOD technology and the optimal multiband indices generated a highly accurate model within the XGBoost algorithm for SMC estimation. This research provided a promising data mining approach for UAV-based hyperspectral imaging data. [ABSTRACT FROM AUTHOR]