The effects of sample size and sample prevalence on cellular automata based urban growth simulation

This dataset is used in the research of "The effects of sample size and sample prevalence on cellular automata based urban growth simulation".
Abstract: In this paper, we take cellular automata (CA) models based on an artificial neural network (ANN), logistic regression (LR), and support vector machine (SVM) as examples. The effects of the sample size and sample prevalence on the CA simulation are investigated by simulating the urban growth of the city of Wuhan in China and the Wuhan Metropolitan Area under different sampling schemes. The results of the CA models based on the ANN, LR, and SVM methods are generally consistent, and show that sampling schemes with a small sample size and low sample prevalence should be discarded because of the high uncertainty. The sample size determines the robustness of a CA model, whereas the sample prevalence affects the performance of a CA model when there are sufficient samples. In particular, the closer the sample prevalence is to the population prevalence, the higher the simulation accuracy and the lower the shape complexity and fragmentation of the simulated urban landscape. We show that the optimal sampling scheme has a sample rate of 1% and a sample prevalence that is the same as the population prevalence, and is independent of the population sizes represented by different study areas.