Landform classification based on landform geospatial structure – a case study on Loess Plateau of China

Landform classification, which is a key topic of geography, great significance to wide range fields including human construction, geological structure research, environmental governance, etc. Previous studies landform classification generally paid attention the topographic or texture information, whilst watershed spatial has not been used. This study developed new method based on geospatial structure. Via abstracting into internal and marginal structure, we adopted gully weighted complex network (GWCN) boundary profile (WBP) simulate Introducing various indices quantitatively depict conducted Northern Shaanxi Loess Plateau with watershed-based strategy established map. The classified distribution significant aggregation clear regional boundaries. Classification accuracy reached 89% kappa coefficient 0.87%. Besides, proposed positive response some similar landforms. In general, present first utilized conduct an efficient well universality, offering additional insights for mapping.