Sign in Subscribe
Artificial intelligence

Artificial Intelligence Framework for Sustainable Ecotourism in India

Strategic Insights

— 1 min read

A new study published in the Discover Artificial Intelligence journal proposes an integrated framework using deep learning, machine learning, and multi-criteria decision analysis to assess ecotourism potential in India's Sundarban Biosphere Reserve. The researchers from the University of Delhi highlight the importance of sustainable ecotourism planning to balance development and conservation in fragile ecosystems. The study demonstrates the advantages of using artificial intelligence techniques to capture complex spatial patterns and overcome the limitations of traditional expert-based models.

Key Takeaways:

  • The study introduces an integrated framework combining deep learning, machine learning, and multi-criteria decision analysis to assess ecotourism potential in India's Sundarban Biosphere Reserve.
  • The framework incorporates 16 influencing factors, including Sentinel-2, SRTM, IMD rainfall data, OpenStreetMap, and Survey of India topographic maps, to develop potential maps using the Analytical Hierarchy Process (AHP), eXtreme Gradient Boosting (XGBoost), and Deep Learning Neural Network (DLNN).
  • The analysis shows that the DLNN model outperformed others with an AUC of 0.91, followed by XGBoost (0.86) and AHP (0.79), and classified only 4.63% and 6.22%, respectively.
  • SHapley Additive exPlanations (SHAP) analysis revealed that proximity to tourist spots, mangrove forests, and rivers strongly influenced ecotourism suitability.
  • Ground-truth validation confirmed the robustness of DLNN predictions.
  • The proposed framework offers an advanced tool for ecotourism planning and resource management, balancing development and conservation.
  • The study contributes methodologically and practically to the growing body of spatial decision-support systems in sustainable tourism.

Statistics:

  • 16 influencing factors were used to develop potential maps.
  • 43.85% of the area was identified as high or very high potential.
  • The DLNN model outperformed others with an AUC of 0.91.
  • XGBoost and DLNN classified only 4.63% and 6.22%, respectively.
  • 10 m resolution was used for AHP, XGBoost, and DLNN analysis.
  • 30 m resolution was used for SRTM analysis.

Sources:

  • NewsRx. University of Delhi Researchers Report Recent Findings in Machine Learning (Application of deep learning, machine learning and multi-criteria decision analysis for ecotourism potentiality assessment: a case study of the Sundarban Biosphere ...). Leisure & Travel Week. November 1, 2025; p 103.
  • Discover Artificial Intelligence. Application of deep learning, machine learning and multi-criteria decision analysis for ecotourism potentiality assessment: a case study of the Sundarban Biosphere Reserve, India. 2025,5(1):1-38.

Read more