Scholarlink

<p>LULC change analysis is crucial for understanding the impact of human activities on the environment in the Anthropocene and guiding sustainable development practices. The present study investigates LULC dynamics and urban sprawl in Nagaon Circle, Assam, utilizing GIS-based Cellular Automata-Artificial Neural Networks (CA-ANN) and Shannon’s Entropy. By employing the Support Vector Machine (SVM) algorithm for LULC classification for the years 2004, 2014, and 2024, high classification accuracy was achieved, including the overall accuracy of 81.42%, 87.14%, and 84.28%, and Kappa coefficient values of 0.78, 0.85, and 0.82, respectively. Out of seven LULC classes, built-up areas experienced the highest increase in the geographical area during the study period. The CA-ANN-based MOLUSCE tool was used to predict future LULC scenarios for 2034 and 2044, validated with higher Kappa values, i.e., &gt; 80, revealed gradual urban expansion at the expense of natural land covers and agricultural lands. Shannon’s Entropy analysis with values above the threshold values of 1.5 and near the log2(n), which is 3 for the four decades from 2004 to 2044, indicated a trend toward more dispersed and accelerating urban growth. The findings revealed the significant impact of population growth and urbanization on LULC changes in the study area, highlighting the urgent need for sustainable urban planning and resource management. The research provides valuable insights for policymakers and urban planners, emphasizing the role of advanced geospatial and machine-learning techniques in environmental monitoring and sustainable development planning.</p>

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

Integrating GIS-based Cellular Automata-Artificial Neural Networks and Shannon’s Entropy for Monitoring Land Use Land Cover Change and Urban Growth in Nagaon Circle, Assam

  • 期刊论文

  • 发表日期：

    2026年5月27日

查看全文
  • Praduyt Dey,
  • Arpana Handique,
  • Santanu Kumar Patnaik,
  • Varsha Patnaik

摘要

LULC change analysis is crucial for understanding the impact of human activities on the environment in the Anthropocene and guiding sustainable development practices. The present study investigates LULC dynamics and urban sprawl in Nagaon Circle, Assam, utilizing GIS-based Cellular Automata-Artificial Neural Networks (CA-ANN) and Shannon’s Entropy. By employing the Support Vector Machine (SVM) algorithm for LULC classification for the years 2004, 2014, and 2024, high classification accuracy was achieved, including the overall accuracy of 81.42%, 87.14%, and 84.28%, and Kappa coefficient values of 0.78, 0.85, and 0.82, respectively. Out of seven LULC classes, built-up areas experienced the highest increase in the geographical area during the study period. The CA-ANN-based MOLUSCE tool was used to predict future LULC scenarios for 2034 and 2044, validated with higher Kappa values, i.e., > 80, revealed gradual urban expansion at the expense of natural land covers and agricultural lands. Shannon’s Entropy analysis with values above the threshold values of 1.5 and near the log2(n), which is 3 for the four decades from 2004 to 2044, indicated a trend toward more dispersed and accelerating urban growth. The findings revealed the significant impact of population growth and urbanization on LULC changes in the study area, highlighting the urgent need for sustainable urban planning and resource management. The research provides valuable insights for policymakers and urban planners, emphasizing the role of advanced geospatial and machine-learning techniques in environmental monitoring and sustainable development planning.