Urban land utilization simulation cellular automaton method based on space errors

Abstract

The invention relates to an urban land utilization simulation cellular automaton method based on space errors, which comprises: 1) classifying remote sensing images to obtain an urban land utilizationgraph and a driving factor; 2) performing system sampling on the urban land utilization map and the driving factor to obtain sample data; 3) training the sampling data by using SEM, and establishinga CA conversion rule; 4) evaluating the fitting performance of the conversion rule by adopting the log likelihood value and the AIC, and checking the effect; 5) establishing a CASEM new model, and calculating to generate an urban land transition probability graph; 6) predicting the number of urban cells at each time point in the future based on historical land utilization data of remote sensing classification; 7) using CASEM to simulate and predict an urban spatial pattern and an expansion process; and 8) performing, outputting and saving comprehensive evaluation of the simulation results using multiple types of indicators. Compared with the prior art, the urban land use simulation cellular automaton method based on the space error has the advantages that the space autocorrelation in the model error can be eliminated, and the simulation precision is improved.

Description

technical field [0001] The invention relates to an urban land use simulation method, in particular to a spatial error-based urban land use simulation cellular automata method. Background technique [0002] A cellular automaton (CA) model consists of spaces, discrete finite state elements, neighborhoods, and transition rules. The CA model uses local interactions to simulate the evolution of complex systems, which is highly consistent with the complexity of urban land use. In the past two decades, most works have adopted classical statistical methods, artificial neural networks, and meta-heuristic algorithms to obtain transformation rules. There is not only multicollinearity but also spatial autocorrelation among spatial drivers, which makes these methods not fully quantify the impact of spatial drivers on urban land use change. The parameters of the fuzzy logic method are subjective, while the parameters obtained by the artificial intelligence method often lack physical mea...

AI Technical Summary

Problems solved by technology

However, heuristic methods usually only provide local optimal solutions at a reasonable computational cost, and changes in the search range may lead to different results and a sharp increase in computational cost

[0003] There are both spatial heterogeneity and spatial dependence in the process of urban land use, and the complex geographical process brings great challenges to model construction

Logistic regression models (logit) can only provide global best-fit relationships and thus cannot account for multicollinearity, autocorrelation effects, and spatial heterogeneity in complex geographic processes

Images