Scholarlink

This study employs an integrated geospatial approach using machine learning algorithms to analyze land use and land cover (LULC) and land surface temperature (LST) dynamics in Indore, India, from 1991 to 2041. High-accuracy LULC maps (Kappa coefficient >0.85) were generated using the Random Forest algorithm for 1991, 2001, 2011, and 2021, showing a 286.55% increase in built-up areas, alongside a 43.48% decrease in bare lands and a 13.55% reduction in vegetation. Corresponding LST maps revealed a 5.13 °C rise in maximum LST and a 2.63 °C increase in mean LST, with cooler zones declining by 70.96% and hot/extremely hot zones expanding significantly. The Multi-Layer Perceptron-Markov Chain Analysis (MLP-MCA) model forecasts a 57.6% increase in built-up areas by 2041, further reducing vegetation and bare lands. This evidence highlights rapid urbanization and its environmental impact, providing critical insights for sustainable urban planning and conservation efforts.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Geospatial LULC and LST Change Analysis with Future Growth Prediction Using Random-Forest and MLP-MCA Algorithms

  • 章节

  • 发表日期：

    2026年

查看全文
  • Jayket Sachapara,
  • Shobhit Chaturvedi,
  • Debasis Sarkar,
  • Naimish Bhatt

摘要

This study employs an integrated geospatial approach using machine learning algorithms to analyze land use and land cover (LULC) and land surface temperature (LST) dynamics in Indore, India, from 1991 to 2041. High-accuracy LULC maps (Kappa coefficient >0.85) were generated using the Random Forest algorithm for 1991, 2001, 2011, and 2021, showing a 286.55% increase in built-up areas, alongside a 43.48% decrease in bare lands and a 13.55% reduction in vegetation. Corresponding LST maps revealed a 5.13 °C rise in maximum LST and a 2.63 °C increase in mean LST, with cooler zones declining by 70.96% and hot/extremely hot zones expanding significantly. The Multi-Layer Perceptron-Markov Chain Analysis (MLP-MCA) model forecasts a 57.6% increase in built-up areas by 2041, further reducing vegetation and bare lands. This evidence highlights rapid urbanization and its environmental impact, providing critical insights for sustainable urban planning and conservation efforts.