Urban expansion simulation prediction method integrating firefly algorithm and cellular automaton

Abstract

The invention relates to an urban expansion simulation prediction method integrating a firefly algorithm and a cellular automaton. The method comprises the steps: carrying out the supervision and classification of a remote sensing image, and obtaining an urban land utilization classification map; obtaining urban land utilization change driving factor data, and performing preprocessing; obtaining effective sample points of the land utilization map and the driving factor through a random stratified sampling method; determining boundaries of the parameters based on logistic regression, and training the effective sample points by using a firefly algorithm to obtain a conversion rule of the cellular automaton; obtaining an urban land utilization conversion probability according to a CA conversion rule; establishing a model based on the CAFFA; carrying out simulation application and verification analysis on urban land utilization by utilizing a CAFA model, and evaluating the precision; oUTPUTTING AND STORING SIMULATION RESULTS. Compared with the prior art, the method has higher simulation precision and better urban land utilization change simulation capability. Compared with the prior art, the method has the advantages of high simulation precision, high efficiency, good simulation effect, good universality and the like.

Description

technical field [0001] The invention relates to a cellular automata method for simulating urban land use changes, in particular to a method for simulating and predicting urban expansion by combining firefly algorithms and cellular automata. Background technique [0002] The rapid increase in urban population density and demand, traffic congestion, insufficient urban water supply, air pollution, high energy consumption, and waste disposal have become increasingly prominent, posing huge challenges to urban planning, resource protection, and ecological diversity. The model based on Cellular Automata (CA) has been gradually applied to the simulation of urban expansion. Its ability to simulate complex systems, self-organization characteristics, and flexibility and compatibility with grid data structures make it a It has significant advantages in the dynamic simulation of urban complex systems. But for the existing cellular automata models, it is still a challenge to determine th...

AI Technical Summary

Problems solved by technology

Although these methods can handle autocorrelation effects among spatial variables well, there are some limitations

The artificial neural network has a certain black-box nature, and cannot provide clear and interpretable weights for spatial variables, and there are problems such as falling into local minima and data overfitting.

Support vector machines have good nonlinear classification capabilities, but it is difficult to implement training on large-scale samp

Images