Scholarlink

<p>Uncontrolled mass tourism has led to severe environmental degradation such as waste generation, air and water pollution, loss of Biodiversity, overcrowding, noise, etc., particularly in developing countries like India. To address this, identifying suitable zones for sustainable eco-tourism is crucial so that the negative effects of mass tourism can be minimized by implementing eco-friendly practices rather than conventional tourism models. For this, the current study employed Remote Sensing (RS) and GIS-based machine learning models—Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF)—to assess Eco-Tourism Potential Zones (ETPZ) in Jangal Mahal, West Bengal, India, using 14 conditioning parameters. The analysis identified 28 high-potential sites in Purulia, 14 in Jhargram, 11 in Bankura and 6 in Paschim Medinipur, emphasizing natural and cultural attractions. Key influencing factors included forest, geo-sites, waterbodies, elevation and rural areas. Model performance was validated using Receiver Operating Characteristic (ROC), Kappa coefficient and proximity test, with RF outperforming DT and SVM. A strategic framework is proposed following the United Nations World Tourism Organization’s (UNWTO) principles of sustainable tourism development to aid policymakers, tourism planners, and stakeholders in promoting sustainable tourism aligned with Sustainable Development Goals (SDGs) 8, 11, 12, 13, and 15.</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

Eco-tourism potential zonation for sustainable tourism development in Jangal Mahal, Eastern India using GIS and machine learning

  • 期刊论文

  • 发表日期：

    2026年7月21日

查看全文
  • Samu Lohar,
  • Somnath Rudra

摘要

Uncontrolled mass tourism has led to severe environmental degradation such as waste generation, air and water pollution, loss of Biodiversity, overcrowding, noise, etc., particularly in developing countries like India. To address this, identifying suitable zones for sustainable eco-tourism is crucial so that the negative effects of mass tourism can be minimized by implementing eco-friendly practices rather than conventional tourism models. For this, the current study employed Remote Sensing (RS) and GIS-based machine learning models—Decision Tree (DT), Support Vector Machine (SVM), and Random Forest (RF)—to assess Eco-Tourism Potential Zones (ETPZ) in Jangal Mahal, West Bengal, India, using 14 conditioning parameters. The analysis identified 28 high-potential sites in Purulia, 14 in Jhargram, 11 in Bankura and 6 in Paschim Medinipur, emphasizing natural and cultural attractions. Key influencing factors included forest, geo-sites, waterbodies, elevation and rural areas. Model performance was validated using Receiver Operating Characteristic (ROC), Kappa coefficient and proximity test, with RF outperforming DT and SVM. A strategic framework is proposed following the United Nations World Tourism Organization’s (UNWTO) principles of sustainable tourism development to aid policymakers, tourism planners, and stakeholders in promoting sustainable tourism aligned with Sustainable Development Goals (SDGs) 8, 11, 12, 13, and 15.