Detecting ditches using supervised learning on high-resolution digital elevation models
作者：
Highlights：
• A decision support system for forest management is presented.
• A large-scale experimental validation of ditch detection in forest wetlands.
• The system combines multiple digital terrain indices using supervised learning.
• The system often detects ditches despite LiDAR scan interference by forest canopy.
• Ditch retrieval rate outperforms the state-of-the-art for forest ditches.
摘要
•A decision support system for forest management is presented.•A large-scale experimental validation of ditch detection in forest wetlands.•The system combines multiple digital terrain indices using supervised learning.•The system often detects ditches despite LiDAR scan interference by forest canopy.•Ditch retrieval rate outperforms the state-of-the-art for forest ditches.
论文关键词：Machine learning,Geographic information systems,Classification and regression trees,Supervised learning by classification
论文评审过程：Received 29 January 2021, Revised 18 October 2021, Accepted 19 March 2022, Available online 26 March 2022, Version of Record 14 April 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116961
