Comparative analysis of deep learning approaches for forest stand type classification: insights from the new VHRTreeSpecies benchmark dataset

Remotely sensed data are widely used for forest stand type classification; however, traditional classification methods are time consuming and mostly implemented for spatially limited areas and species, restricting the transferability of these models to other locations and diverse species. With the i...

Full description

Saved in:
Bibliographic Details
Main Authors: Elif Sertel, Sule Nur Topgul
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2522394
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224386953871360
author Elif Sertel
Sule Nur Topgul
author_facet Elif Sertel
Sule Nur Topgul
author_sort Elif Sertel
collection DOAJ
description Remotely sensed data are widely used for forest stand type classification; however, traditional classification methods are time consuming and mostly implemented for spatially limited areas and species, restricting the transferability of these models to other locations and diverse species. With the increasing availability of high-resolution satellite imagery, deep learning techniques have become widely used in forest management and species classification research. In this study, we generated a new benchmark dataset, VHRTreeSpecies, designed for forest stand type classification. We used Very High Resolution satellite images and corresponding labels derived from forest stand maps provided by the General Directorate of Forestry, covering 15 dominant tree species from Türkiye’s diverse forest ecosystems. Various deep learning models including CNN-based architectures (ResNet50, ResNet101, VGG16, ResNeXt, InceptionV3, ConvNeXt, EfficientNet), transformer models (DeepViT, Swin Transformer, CaiT, SegFormer-b0-b1-b2), and YOLO models (YOLOv8-l and YOLOv11-l) were utilized to assess the performance of these models for the forest tree species classification. Our results demonstrate the effectiveness of SegFormer, which achieved the highest classification accuracy of 96.25%, outperforming traditional CNN models. Additionally, YOLOv8-l proved to be a highly efficient model for both precision and real-time classification tasks, demonstrating its robustness across different tree species.
format Article
id doaj-art-a60036ddb3b74ffaa14cff61968eaacc
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-a60036ddb3b74ffaa14cff61968eaacc2025-08-25T11:24:57ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2522394Comparative analysis of deep learning approaches for forest stand type classification: insights from the new VHRTreeSpecies benchmark datasetElif Sertel0Sule Nur Topgul1Department of Geomatics Engineering, Faculty of Civil Engineering, Istanbul Technical University, Maslak, TürkiyeSatellite Communications and Remote Sensing program, Graduate School, Istanbul Technical University, Maslak, TürkiyeRemotely sensed data are widely used for forest stand type classification; however, traditional classification methods are time consuming and mostly implemented for spatially limited areas and species, restricting the transferability of these models to other locations and diverse species. With the increasing availability of high-resolution satellite imagery, deep learning techniques have become widely used in forest management and species classification research. In this study, we generated a new benchmark dataset, VHRTreeSpecies, designed for forest stand type classification. We used Very High Resolution satellite images and corresponding labels derived from forest stand maps provided by the General Directorate of Forestry, covering 15 dominant tree species from Türkiye’s diverse forest ecosystems. Various deep learning models including CNN-based architectures (ResNet50, ResNet101, VGG16, ResNeXt, InceptionV3, ConvNeXt, EfficientNet), transformer models (DeepViT, Swin Transformer, CaiT, SegFormer-b0-b1-b2), and YOLO models (YOLOv8-l and YOLOv11-l) were utilized to assess the performance of these models for the forest tree species classification. Our results demonstrate the effectiveness of SegFormer, which achieved the highest classification accuracy of 96.25%, outperforming traditional CNN models. Additionally, YOLOv8-l proved to be a highly efficient model for both precision and real-time classification tasks, demonstrating its robustness across different tree species.https://www.tandfonline.com/doi/10.1080/17538947.2025.2522394Forest stand typedeep learningclassificationremote sensingtree species
spellingShingle Elif Sertel
Sule Nur Topgul
Comparative analysis of deep learning approaches for forest stand type classification: insights from the new VHRTreeSpecies benchmark dataset
International Journal of Digital Earth
Forest stand type
deep learning
classification
remote sensing
tree species
title Comparative analysis of deep learning approaches for forest stand type classification: insights from the new VHRTreeSpecies benchmark dataset
title_full Comparative analysis of deep learning approaches for forest stand type classification: insights from the new VHRTreeSpecies benchmark dataset
title_fullStr Comparative analysis of deep learning approaches for forest stand type classification: insights from the new VHRTreeSpecies benchmark dataset
title_full_unstemmed Comparative analysis of deep learning approaches for forest stand type classification: insights from the new VHRTreeSpecies benchmark dataset
title_short Comparative analysis of deep learning approaches for forest stand type classification: insights from the new VHRTreeSpecies benchmark dataset
title_sort comparative analysis of deep learning approaches for forest stand type classification insights from the new vhrtreespecies benchmark dataset
topic Forest stand type
deep learning
classification
remote sensing
tree species
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2522394
work_keys_str_mv AT elifsertel comparativeanalysisofdeeplearningapproachesforforeststandtypeclassificationinsightsfromthenewvhrtreespeciesbenchmarkdataset
AT sulenurtopgul comparativeanalysisofdeeplearningapproachesforforeststandtypeclassificationinsightsfromthenewvhrtreespeciesbenchmarkdataset