Expert versus Machine: A Comparison of Two Suitability Models for Emergency Helicopter Landing Areas in Yosemite National Park

A comparison of two geographic information system (GIS) models for identifying suitable emergency helicopter landing areas in Yosemite National Park reveals that both expert-derived and machine learning approaches effectively classify potential zones, with the latter offering greater efficiency and reduced risk of human bias. The study employed a weighted overlay algorithm based on predefined constraints alongside a maximum entropy model trained on presence-only data to predict flat, treeless areas away from hazards. While both models performed similarly in classifying test coordinates, the machine learning approach eliminated the need for subjective weighting, making it more objective. This research underscores the complementary nature of these methods and provides a robust tool for search-and-rescue operations in wilderness environments. It marks the first GIS study focused specifically on estimating helicopter landing zones for emergency response.

Doherty, P., Guo, Q., & Alvarez, O. (2013). Expert versus Machine: A Comparison of Two Suitability Models for Emergency Helicopter Landing Areas in Yosemite National Park. The Professional Geographer, 65(3), 466–481. https://doi.org/10.1080/00330124.2012.697857