How much can temporally stationary factors explain cellular automata-based simulations of past and future urban growth?

Abstract

Driving factors are usually assumed temporally stationary in cellular automata (CA) based land use modeling, hence the persistence of their relationships. Therefore, major questions as to how much do the temporally stationary factors explain the past and future urban growth, and how long can these factors justify the projection of urban scenarios in the future, are worth further study. We selected seven explanatory driving factors to calibrate a DE-CA (differential evolution-based CA) model to simulate urban growth in Ningbo of China during 2000–2015 and project nine scenarios of urban growth from 2015 to 2060. We evaluated the effects of factors on urban growth using generalized additive models (GAM) based on fitting statistics such as accumulative deviance explained (ADE). Our results show remarkably temporal change in factor effects on the future urban growth – the ADE peaks with 34.7% in 2045 for the total projected urban growth since 2015 while that for every five years decreases continuously from 26.5% during 2000–2005 to 1.9% during 2050–2055, but slightly increase to 3.0% during 2055–2060. These indicate that the stationary factors have less strong explanatory power to the new urban areas that are farther away from the existing built-up areas. The results suggest that a 30-year period in the future is most suitable to project the urban growth scenarios, where the new urban area approximates the initial urban area. The specific best period for scenario projection elsewhere can then be identified using the method presented in this study.