Scholarlink

<p>This study aims to identify optimal mountaineering sites in the Eastern High Atlas of Morocco, accounting for terrain factors. Specifically, the study examines the Ziz region in SE Morocco and assesses the efficiency of two popular machine learning classifiers (MLCs) for locating prospective climbing areas. Identifying and delineating these areas is vital for promoting and enhancing geotourism in the region. The study commences with a thorough inventory of 120 mountain climbing sites and 120 non-mountain climbing sites, systematically collecting precise measurements of three topographical parameters. Data analysis is conducted utilizing ArcGIS, Weka, and SPSS. The dataset was randomly split into training (70%) and test (30%) sets. Logistic Regression (LR) and Support Vector Machine (SVM) algorithms are then employed to develop predictive spatial adequacy models. Both models successfully identify highly suitable areas, covering approximately 15.18% and 19.21% of the research area, respectively. These promising regions are largely concentrated in the western part of the study area, characterized by rugged terrain with short slopes and high altitudes. The research findings provide crucial insights for decision-makers, delivering essential information that supports effective tourism management and conservation initiatives in the Eastern High Atlas region.</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

Geospatial modeling of potential climbing sites in the semi-arid mountains of Morocco using machine learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月5日

查看全文
  • Mohamed Manaouch,
  • Nadia Rhoujjati,
  • Quoc Bao Pham,
  • Ali Rhoujjati

摘要

This study aims to identify optimal mountaineering sites in the Eastern High Atlas of Morocco, accounting for terrain factors. Specifically, the study examines the Ziz region in SE Morocco and assesses the efficiency of two popular machine learning classifiers (MLCs) for locating prospective climbing areas. Identifying and delineating these areas is vital for promoting and enhancing geotourism in the region. The study commences with a thorough inventory of 120 mountain climbing sites and 120 non-mountain climbing sites, systematically collecting precise measurements of three topographical parameters. Data analysis is conducted utilizing ArcGIS, Weka, and SPSS. The dataset was randomly split into training (70%) and test (30%) sets. Logistic Regression (LR) and Support Vector Machine (SVM) algorithms are then employed to develop predictive spatial adequacy models. Both models successfully identify highly suitable areas, covering approximately 15.18% and 19.21% of the research area, respectively. These promising regions are largely concentrated in the western part of the study area, characterized by rugged terrain with short slopes and high altitudes. The research findings provide crucial insights for decision-makers, delivering essential information that supports effective tourism management and conservation initiatives in the Eastern High Atlas region.