Modelling and Understanding Multi-temporal Land Use Changes

Understanding temporal urban growth is very crucial to the interpretation of urban morphology and a key challenge for the study of rapid urbanization in contemporary China. Previous land use change modelling approaches only consider the spatial complexity that may be indicated by spatial dependence and landscape fragmentation, ignoring the temporal complexity inherent in the process of urban growth. Multi-temporality is a typical characteristic of urban growth and multi-temporal data availability has been much improved due to great advance in geospatial technology particularly remotely sensed imagery. This paper proposes an innovative application of a machine learning method – Maxent for analysing the urban morphology of a fast growing city –Wuhan, China. Multi-temporal data sets for 1955, 1965, 1993 and 2000 were processed from remotely sensed imagery. The results demonstrate that Maxent is an effective exploratory method and tool for understanding urban morphology.