Estimating aboveground biomass in desert steppe using UAV hyperspectral and machine learning

Grassland can provide the abundant forage and feed resources for the livestock industry, in order to maintain the ecological balance and biodiversity. One special types of the grassland, desert steppe is located at the transitional zone between grasslands and deserts, particularly with the relatively fragile ecosystem at risk of desertification. Aboveground biomass is one of the most important indicators to monitor the community structure and function in the grassland. However, the traditional estimation of aboveground biomass cannot fully meet the monitoring needs of desert grassland in a large area, due to the time-consuming, destructiveness and laborious. Satellite multi-spectral remote sensing can be expected to serve as such application against the clouds and resolution. In this study, non-destructive and accurate estimation was performed on the aboveground biomass in the desert grassland, in order to improve the monitoring level and utilization efficiency. The study area was taken from the desert grassland at Wulan Town, Etuoke Banner, Ordos City, Inner Mongolia, China. A drone was utilized to capture the hyperspectral data in the study area. Sample plots were established to collect the aboveground biomass data. A series of preprocessing was carried out on the hyperspectral datasets. Firstly, the average reflectance of each sample plot was precisely calculated to standardize the data. Subsequently, the advanced techniques of noise reduction were applied to eliminate any potential noise interference, particularly for the integrity and reliability of data. Principal component analysis (PCA) was then utilized to reduce the dimensionality. Three principal components were extracted successfully, including PC1, PC2, and PC3. These principal components were effectively condensed to highlight the key spectral features in the high-dimensional hyperspectral data. In parallel, 16 vegetation indices were calculated using the reflectance data. These indices were widely recognized in the field of vegetation research, in order to characterize the physiological and ecological status of the vegetation. After that, the correlation analysis was conducted among the principal components, vegetation indices, full-band reflectance data, and AGB. The relationships among these variables were then obtained to identify the most significant influencing factors on the AGB. A genetic algorithm was employed to further optimize the feature set. This algorithm was inspired by the principles of natural evolution, indicating the strong global searching. Finally, an optimal combination of optimal features was selected after continuous iteration and evaluation, including PC1, PC3, NDVI, NDRE. Among them, the specific bands were in the ranges of 536-557 nm, 673-690 nm, and 703-715 nm, respectively. According to these selected features, different estimation models of aboveground biomass were developed for the desert grasslands using Random Forest, BP Neural Network, and LASSO regression. A ten-fold cross-validation was applied to evaluate the performance of the improved model. The results demonstrate that the better performance of the improved model was achieved in the machine learning with the spectral features that selected by the genetic algorithm. Among them, the LASSO model exhibited the greatest performance, indicating R²=0.76, an increase of 65.2%, RMSE=0.05 kg/m², an improvement of 28.6%, MAE=0.04 kg/m², an increase of 20%, NRMSE=0.12, and an improvement of 36.8%. The BP Neural Network model performed the best, with R²=0.81, RMSE=0.04 kg/m², MAE=0.04 kg/m², and NRMSE=0.11. A consistence was found between the estimation and mapping of desert grassland AGB with the BPNN model and the actual distribution of vegetation. Therefore, the UAV-based hyperspectral data can be expected to construct an AGB estimation model for the desert grasslands. The finding can provide a scientific basis to formulate the grazing plans, in order prevent the overgrazing from the desertification in sustainable ranches.