Modeling urban encroachment on ecological land using cellular automata and cross-entropy optimization rules

Area of Science:

• Environmental Science
• Urban Planning
• Geographic Information Systems (GIS)

Background:

• Rapid urban expansion poses a significant threat to ecological lands and natural environments.
• Coastal areas are particularly vulnerable to urban encroachment.
• Predictive modeling is crucial for understanding and managing urban growth impacts.

Purpose of the Study:

• To develop and validate a novel cellular automata model (CA_CEO) for simulating and projecting urban expansion.
• To assess the extent of urban encroachment on ecological lands using a new optimization technique.
• To predict future urban expansion scenarios and their environmental consequences.

Main Methods:

• Development of the CA_CEO model integrating cross-entropy optimization (CEO) for parameterization.
• Calibration and validation of the CA_CEO model using historical urban expansion data from Wenzhou (1995-2015).
• Prediction of four distinct urban expansion scenarios (BAU, District, Road, Coast) for 2025 and 2035.

Main Results:

• The CA_CEO model achieved high accuracy in simulating past urban expansion (e.g., 94.4% overall accuracy for 2015).
• Predicted scenarios show substantial variations in urban encroachment and loss of ecological lands (farmland, forest, wetland, grassland).
• The model effectively distinguishes impacts based on different urban development strategies.

Conclusions:

• The CA_CEO model provides a robust tool for objective parameterization and multi-objective scenario prediction of urban expansion.
• Findings highlight the significant environmental risks associated with different urban development pathways.
• The model's outputs can inform adaptive urban planning and policy-making to reduce ecological land loss.