Karst Rocky Desertification in Guizhou,China

Building a high-precision, stable, and universal automatic extraction model of rocky desertification information is the premise for exploring the spatiotemporal evolution of rocky desertification. Taking Guizhou province as the research area and based on MODIS and continuous forest inventory data in China (NFCI), we used a machine learning algorithm (SVM) to build a rocky desertification model with bedrock exposure rate, temperature difference, humidity, and other characteristic factors and improved the model accuracy from the spatial and temporal dimensions.