Naturalness indicators of forests in Southern Sweden derived from the canopy height model

Forest canopies embody a dynamic set of ecological factors, acting as a pivotal interface between the Earth and its atmosphere. They are not only the result of an ecosystem’s ability to maintain its inherent ecological processes, structures, and functions but also a reflection of human disturbance....

Full description

Saved in:
Bibliographic Details
Main Authors: Marco L. Della Vedova, Mattias Wahde
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:European Journal of Remote Sensing
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/22797254.2024.2441834
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850102238933942272
author Marco L. Della Vedova
Mattias Wahde
author_facet Marco L. Della Vedova
Mattias Wahde
author_sort Marco L. Della Vedova
collection DOAJ
description Forest canopies embody a dynamic set of ecological factors, acting as a pivotal interface between the Earth and its atmosphere. They are not only the result of an ecosystem’s ability to maintain its inherent ecological processes, structures, and functions but also a reflection of human disturbance. This study introduces a methodology for extracting a comprehensive and human-interpretable set of features from the Canopy Height Model (CHM) with a resolution of 1 meter. These features are then analyzed to identify reliable indicators of the degree of naturalness of forests in Southern Sweden. Using these features, machine learning models – specifically, the perceptron, logistic regression, and decision trees – are trained with examples of forests exhibiting known high and low degrees of naturalness. These models achieve prediction accuracies ranging from 89% to 95% on unseen data, depending on the area of the region of interest. The predictions of the proposed method are easy to interpret, making them particularly valuable to various stakeholders involved in forest management and conservation.
format Article
id doaj-art-d54f5e745214433baa8024d6cbe3bcf4
institution DOAJ
issn 2279-7254
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series European Journal of Remote Sensing
spelling doaj-art-d54f5e745214433baa8024d6cbe3bcf42025-08-20T02:39:48ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542025-12-0158110.1080/22797254.2024.2441834Naturalness indicators of forests in Southern Sweden derived from the canopy height modelMarco L. Della Vedova0Mattias Wahde1Dept. of Mechanics and Maritime Sciences, Chalmers University of Technology, Gothenburg, SwedenDept. of Mechanics and Maritime Sciences, Chalmers University of Technology, Gothenburg, SwedenForest canopies embody a dynamic set of ecological factors, acting as a pivotal interface between the Earth and its atmosphere. They are not only the result of an ecosystem’s ability to maintain its inherent ecological processes, structures, and functions but also a reflection of human disturbance. This study introduces a methodology for extracting a comprehensive and human-interpretable set of features from the Canopy Height Model (CHM) with a resolution of 1 meter. These features are then analyzed to identify reliable indicators of the degree of naturalness of forests in Southern Sweden. Using these features, machine learning models – specifically, the perceptron, logistic regression, and decision trees – are trained with examples of forests exhibiting known high and low degrees of naturalness. These models achieve prediction accuracies ranging from 89% to 95% on unseen data, depending on the area of the region of interest. The predictions of the proposed method are easy to interpret, making them particularly valuable to various stakeholders involved in forest management and conservation.https://www.tandfonline.com/doi/10.1080/22797254.2024.2441834Machine learninginterpretabilityforestscanopy height modelremote sensing
spellingShingle Marco L. Della Vedova
Mattias Wahde
Naturalness indicators of forests in Southern Sweden derived from the canopy height model
European Journal of Remote Sensing
Machine learning
interpretability
forests
canopy height model
remote sensing
title Naturalness indicators of forests in Southern Sweden derived from the canopy height model
title_full Naturalness indicators of forests in Southern Sweden derived from the canopy height model
title_fullStr Naturalness indicators of forests in Southern Sweden derived from the canopy height model
title_full_unstemmed Naturalness indicators of forests in Southern Sweden derived from the canopy height model
title_short Naturalness indicators of forests in Southern Sweden derived from the canopy height model
title_sort naturalness indicators of forests in southern sweden derived from the canopy height model
topic Machine learning
interpretability
forests
canopy height model
remote sensing
url https://www.tandfonline.com/doi/10.1080/22797254.2024.2441834
work_keys_str_mv AT marcoldellavedova naturalnessindicatorsofforestsinsouthernswedenderivedfromthecanopyheightmodel
AT mattiaswahde naturalnessindicatorsofforestsinsouthernswedenderivedfromthecanopyheightmodel