ORIGINAL RESEARCH
Rural Landscape Spatial Change Prediction
and Environmental Optimization
Based on CA-Markov Model
			
	
 
More details
Hide details
	
	
									
				1
				College of Art and Communication, China Jiliang University, Hangzhou, 310018, China
				 
			 
										
				
				
		
		 
			
			
			
			 
			Submission date: 2024-09-25
			 
		 		
		
			
			 
			Final revision date: 2024-11-28
			 
		 		
		
		
			
			 
			Acceptance date: 2024-12-16
			 
		 		
		
			
			 
			Online publication date: 2025-04-22
			 
		 		
		
		 
	
							
										    		
    			 
    			
    				    					Corresponding author
    					    				    				
    					Jingting  Meng   
    					College of Art and Communication, China Jiliang University, Hangzhou, 310018, China
    				
 
    			
				 
    			 
    		 		
			
							 
		
	 
		
 
 
		
 
 
KEYWORDS
TOPICS
ABSTRACT
This research investigates the evolving rural environment in Libo County, Guizhou Province,
in the context of climate fluctuations and human interventions. By applying landscape ecology principles
and land use information spanning from 1995 to 2020, a comprehensive quantitative assessment of land
use composition, evolution, and transformation was performed. A cellular automaton combined with
a Markov model was utilized to forecast land use configurations for the year 2030. The results reveal
substantial urban and agricultural land alterations, indicative of swift economic growth and urban
expansion. Although forest regions remained relatively constant, their spatial distribution became more
focused, and grasslands experienced a significant reduction post-2000. Forecasts for 2030 project that
agricultural land (45.66%) and forest land (40.25%) will be the predominant land uses, with urban land at
7.89%, grasslands at 6.01%, and water bodies at a minimal 0.19%. This study provides a scientific basis
for regional sustainable development, ecological protection, and restoration, especially for protecting
key ecosystems such as forests and grasslands. Predicting land use patterns in 2030 provides data
support for urban planning and land resource optimization. Help with agricultural policy development
and improve the efficiency of using arable land and forest land. Provide insights for environmental
policymakers and promote the optimization of ecological protection policies. Environmental protection
awareness is raised through education, public participation, and strategies to combat climate change are
developed.