Modelling spatial patterns of urban growth in Africa.

摘要: The population of Africa is predicted to double over the next 40 years, driving exceptionally high urban expansion rates that will induce significant socio-economic, environmental and health changes. In order prepare for these changes, it important better understand growth dynamics in predict spatial pattern rural-urban conversions. Previous work on has been carried out at city level or global with a relatively coarse 5–10 km resolution. main objective present paper was develop modelling approach an intermediate scale identify factors influence patterns Africa. Boosted Regression Tree models were developed conversions every large African city. Urban change data between circa 1990 2000 available 20 cities across used as training data. Results showed land 1 neighbourhood accessibility centre most influential variables. obtained generally more accurate than results using distance-based model small, compact fast growing easier simulate lower densities rate. simulation method here allow production spatially detailed forecasts 2020 2025 Africa, are increasingly required by modellers.