Scholarlink

<p>Morphodiversity assessments in mountainous landscapes represent an important tool for geoconservation. Particularly useful are the Raster Continuous Morphodiversity (<i>RCM</i>) models, which are based on continuous variables and measures of pixel variability within statistical zones. Traditional <i>RCM</i> models of the Aggregating Ratings (<i>AR</i>) type define morphodiversity as the sum of standardized partial criteria; however, their drawback lies in the redundant aggregation of variability, which leads to evaluation errors. To mitigate this issue, a new <i>RCM</i> model was developed, based on Supervised Classification (SC) and Artificial Neural Networks (ANN), which accounts for interdependencies between variables and eliminates low-informative ones. This study presents the results of <i>RCM</i> modeling for the Pieniny Mountains (southern Poland) using the <i>RCM</i><sub><i>SC−ANN</i></sub> and the improved <i>RCM</i><sub><i>SC−ANN−M</i></sub> models. Variable reduction was performed using the Global Sensitivity Analysis (GSA) method in its Backward Analysis (BA) and Backward Stepwise Analysis (BSA) variants, resulting in simplified models. Comparisons with the <i>SC-ANN</i><sub><i>VSR−9−BS</i></sub> and <i>RCM</i><sub><i>SDcm</i></sub> models showed that <i>RCM</i><sub><i>SC−ANN−M</i></sub> produces more reliable evaluations and can be recommended for testing in other mountainous areas. The high correlation coefficients (0.96–0.98) between full and reduced sets of criteria confirm the effectiveness and efficiency of the BA and BSA procedures.</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

Development and optimization of a morphodiversity model for mountainous areas using supervised classification and artificial neural networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月22日

查看全文
  • Tomasz Bartuś

摘要

Morphodiversity assessments in mountainous landscapes represent an important tool for geoconservation. Particularly useful are the Raster Continuous Morphodiversity (RCM) models, which are based on continuous variables and measures of pixel variability within statistical zones. Traditional RCM models of the Aggregating Ratings (AR) type define morphodiversity as the sum of standardized partial criteria; however, their drawback lies in the redundant aggregation of variability, which leads to evaluation errors. To mitigate this issue, a new RCM model was developed, based on Supervised Classification (SC) and Artificial Neural Networks (ANN), which accounts for interdependencies between variables and eliminates low-informative ones. This study presents the results of RCM modeling for the Pieniny Mountains (southern Poland) using the RCMSC−ANN and the improved RCMSC−ANN−M models. Variable reduction was performed using the Global Sensitivity Analysis (GSA) method in its Backward Analysis (BA) and Backward Stepwise Analysis (BSA) variants, resulting in simplified models. Comparisons with the SC-ANNVSR−9−BS and RCMSDcm models showed that RCMSC−ANN−M produces more reliable evaluations and can be recommended for testing in other mountainous areas. The high correlation coefficients (0.96–0.98) between full and reduced sets of criteria confirm the effectiveness and efficiency of the BA and BSA procedures.