Scholarlink

Assessment and mapping of coastal habitat vulnerabilityCoastal habitat vulnerability is essential for planning sustainable coastal conservation and management strategies. This study aims to develop the Coastal Habitat Vulnerability IndexHabitat vulnerability index (HVI) using GIS-based machine learningMachine learning techniques. Multiple geo-environmental parameters were analyzed, including shoreline erosion, beach subsidence, seawater inundation, sediment overwashing, changes in wetlands (such as salt marshes, swamps, and mud flats), human impacts (like settlement encroachment and population density), environmental hazardsHazards (including groundwater contamination and salinity intrusion), and the effects of storm surges and extreme events (such as cyclones and tsunamisTsunamis). Artificial neural networks (ANNs) were employed to develop the HVI model that integrates the data layers. The HVI values, ranging from 8 to 52 with an average of 30, are grouped into five categories to distinguish between high and low vulnerability zones. Approximately 9% of the area is highly vulnerable, affecting habitats such as estuaries, salt marshes, dunes, and eroded cliffs. Human settlements in low-lying areas (mean sea level < 10 m), including Inayamputhenthurai, Mandaikadu, Pallam, and Puthenthurai, are particularly susceptible to erosion and submergence due to high-energy waves and tidal actions. Changes in environmental conditions directly impact the productivity of wetlands, lagoons, estuaries, and coral reefs, while human activities exacerbate ecosystem degradation over time. The GIS machine learningMachine learning-based HVI model identifies hot spots of vulnerability and provides critical insights for sustainable coastal habitat management, ensuring long-term resilienceResilience against climate changeClimate change and anthropogenic pressures.

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

Development of Habitat Vulnerability Index (HVI) for Southern Indian Coastal Stretch: A Machine Learning-Based Spatial Modeling Approach

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • S. Kaliraj,
  • P. S. Fathimathu Sahala

摘要

Assessment and mapping of coastal habitat vulnerabilityCoastal habitat vulnerability is essential for planning sustainable coastal conservation and management strategies. This study aims to develop the Coastal Habitat Vulnerability IndexHabitat vulnerability index (HVI) using GIS-based machine learningMachine learning techniques. Multiple geo-environmental parameters were analyzed, including shoreline erosion, beach subsidence, seawater inundation, sediment overwashing, changes in wetlands (such as salt marshes, swamps, and mud flats), human impacts (like settlement encroachment and population density), environmental hazardsHazards (including groundwater contamination and salinity intrusion), and the effects of storm surges and extreme events (such as cyclones and tsunamisTsunamis). Artificial neural networks (ANNs) were employed to develop the HVI model that integrates the data layers. The HVI values, ranging from 8 to 52 with an average of 30, are grouped into five categories to distinguish between high and low vulnerability zones. Approximately 9% of the area is highly vulnerable, affecting habitats such as estuaries, salt marshes, dunes, and eroded cliffs. Human settlements in low-lying areas (mean sea level < 10 m), including Inayamputhenthurai, Mandaikadu, Pallam, and Puthenthurai, are particularly susceptible to erosion and submergence due to high-energy waves and tidal actions. Changes in environmental conditions directly impact the productivity of wetlands, lagoons, estuaries, and coral reefs, while human activities exacerbate ecosystem degradation over time. The GIS machine learningMachine learning-based HVI model identifies hot spots of vulnerability and provides critical insights for sustainable coastal habitat management, ensuring long-term resilienceResilience against climate changeClimate change and anthropogenic pressures.