Home About Browse Search
Svenska


Detecting ditches using supervised learning on high-resolution digital elevation models

Flyckt, Jonatan and Andersson, Filip and Lavesson, Niklas and Nilsson, Liselott and Ågren, Anneli (2022). Detecting ditches using supervised learning on high-resolution digital elevation models. Expert Systems with Applications. 201 , 116961
[Research article]

[img] PDF
6MB

Abstract

Drained wetlands can constitute a large source of greenhouse gas emissions, but the drainage networks in these wetlands are largely unmapped, and better maps are needed to aid in forest production and to better understand the climate consequences. We develop a method for detecting ditches in high resolution digital elevation models derived from LiDAR scans. Thresholding methods using digital terrain indices can be used to detect ditches. However, a single threshold generally does not capture the variability in the landscape, and generates many false positives and negatives. We hypothesise that, by combining the digital terrain indices using supervised learning, we can improve ditch detection at a landscape-scale. In addition to digital terrain indices, additional features are generated by transforming the data to include neighbouring cells for better ditch predictions. A Random Forests classifier is used to locate the ditches, and its probability output is processed to remove noise, and binarised to produce the final ditch prediction. The confidence interval for the Cohen’s Kappa index ranges [0.655 , 0.781] between the evaluation plots with a confidence level of 95%. The study demonstrates that combining information from a suite of digital terrain indices using machine learning provides an effective technique for automatic ditch detection at a landscape-scale, aiding in both practical forest management and in combatting climate change.

Authors/Creators:Flyckt, Jonatan and Andersson, Filip and Lavesson, Niklas and Nilsson, Liselott and Ågren, Anneli
Title:Detecting ditches using supervised learning on high-resolution digital elevation models
Series Name/Journal:Expert Systems with Applications
Year of publishing :2022
Volume:201
Article number:116961
Number of Pages:13
ISSN:0957-4174
Language:English
Publication Type:Research article
Article category:Scientific peer reviewed
Version:Published version
Copyright:Creative Commons: Attribution 4.0
Full Text Status:Public
Subjects:(A) Swedish standard research categories 2011 > 4 Agricultural Sciences > 401 Agricultural, Forestry and Fisheries > Forest Science
(A) Swedish standard research categories 2011 > 2 Engineering and Technology > 207 Environmental Engineering > Remote Sensing
Keywords:Machine learning, Geographic information systems, Classification and regression trees, Supervised learning by classification
URN:NBN:urn:nbn:se:slu:epsilon-p-116818
Permanent URL:
http://urn.kb.se/resolve?urn=urn:nbn:se:slu:epsilon-p-116818
Additional ID:
Type of IDID
DOI10.1016/j.eswa.2022.116961
ID Code:27648
Faculty:S - Faculty of Forest Sciences
Department:(S) > Dept. of Forest Ecology and Management
Deposited By: SLUpub Connector
Deposited On:29 Apr 2022 07:41
Metadata Last Modified:29 Apr 2022 07:51

Repository Staff Only: item control page

Downloads

Downloads per year (since September 2012)

View more statistics

Downloads
Hits