Extraction of gravel characteristics and spatial inversion for ecological restoration monitoring in the Northern Tibetan Plateau

Previous studies have often focused on monitoring grassland growth as the primary target of remote sensing investigations on grassland ecological restoration in the northern Tibetan Plateau, overlooking the crucial role played by gravel in the ecological restoration of these grasslands. This study utilizes supervised classification and segmentation techniques based on machine learning to extract gravel morphology profiles from field-sampled plot images and calculate their characteristic parameters. Employing a multivariate linear approach combined with Principal Component Analysis (PCA), a model for inferring gravel characteristic parameters is constructed. Statistical features, particle size characteristics, and spatial distribution patterns of gravel are analyzed. Results reveal that gravel predominantly exhibit sub-rounded shapes, with 80% classified as fine gravel. The coefficients of determination (R²) between gravel particle size and coverage, perimeter, and area are 0.444, 0.724, and 0.557, respectively, indicating linear relationships. The cumulative contribution rate of the top five remote sensing factors is 95.44%, with the first geological factor contributing 77.64%, collectively reflecting the primary information of the 20 factors used. Modeling shows that areas with larger gravel particle sizes correspond to increased perimeter and coverage. Gravels in the Nagqu Prefecture of northern Tibet have a particle size range of 4-8 mm, primarily comprising fine gravel which accounts for 94.61%. These findings provide a scientific basis for extracting gravel characteristic parameters and understanding their spatial distribution variations in the northern Tibetan Plateau.