Modeling land cover changes using an enhanced Markov-future land use simulation model with spatial distribution considerations: a case study in the Yellow River Basin

The traditional Markov-future land use simulation (FLUS) model for land use prediction primarily emphasizes the quantity changes and spatial distribution of land use types, but it neglects the influence of their inherent spatial characteristics on the prediction precision. This study introduces an i...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianchen Zhang, Heying Li, Hanwen Zhang, Jiayao Wang, Guangxia Wang, JianWei Xu, Haohua Zheng, HuiLing Ma
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2528626
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The traditional Markov-future land use simulation (FLUS) model for land use prediction primarily emphasizes the quantity changes and spatial distribution of land use types, but it neglects the influence of their inherent spatial characteristics on the prediction precision. This study introduces an innovative approach by designing shape control parameters and developing an enhanced Markov-FLUS model. The model integrates artificial neural networks to capture the relationships between the land use type occurrence probability and driving factors. It incorporates common points, common edges, distance, and aggregation parameters alongside a cellular automata model. Taking the Yellow River Basin as an example for analysis, this study compares the model's simulation performance before and after enhancement, focusing on the land use types with the most and least improvement. The results indicate that the refined model achieves a superior fitness function value in simulating land use within the Yellow River Basin.HIGHLIGHTS The Enhanced Markov-FLUS model has been meticulously constructed through the strategic design of a comprehensive set of shape control parameters.The refined model demonstrates significantly elevated fitness values, particularly within a 3 × 3 Moore neighborhood framework.This model stands out in accurately forecasting land use types characterized by enhanced contiguity and more regularized shapes.The improved model significantly diminishes the miss rate, notably along the edges of land type boundaries.
ISSN:1753-8947
1753-8955