A forestry investigation: Exploring factors behind improved tree species classification using bark images
Novel ground-based remote sensing approaches have demonstrated high potential for accurate and detailed mapping and monitoring of forest ecosystems. These methods enable the measurement of various tree parameters important for forest inventory or ecological research, such as diameter at breast heigh...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Ecological Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1574954124004746 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595424572080128 |
|---|---|
| author | Gokul Kottilapurath Surendran Deekshitha Martin Lukac Martin Lukac Jozef Vybostok Martin Mokros |
| author_facet | Gokul Kottilapurath Surendran Deekshitha Martin Lukac Martin Lukac Jozef Vybostok Martin Mokros |
| author_sort | Gokul Kottilapurath Surendran |
| collection | DOAJ |
| description | Novel ground-based remote sensing approaches have demonstrated high potential for accurate and detailed mapping and monitoring of forest ecosystems. These methods enable the measurement of various tree parameters important for forest inventory or ecological research, such as diameter at breast height, tree height and volume, and crown parameters. One crucial piece of information is tree species, which is essential for various reasons and challenging to implement within ground-based technology workflows. This study investigates why researchers often focus on segment-specific bark images for tree species classification via deep neural networks rather than large or entire tree images. Additionally, the aim is to determine the most effective algorithmic approaches for efficient tree species classification from bark images and to make these methods more accessible to interdisciplinary researchers. The findings reveal that segment-specific datasets with more overlaps provide better accuracy across various algorithms. Additionally, pre-processing techniques such as scaling can enhance accuracy to a certain extent. Convolutional Neural Networks (CNNs) consistently deliver the highest accuracy, even with diverse datasets, but fine-tuning these algorithms poses significant challenges for interdisciplinary researchers. To address this, we developed Windows-based research software, CNN Parameter Tuner 1.0, which allows the import of various data formats (jpg and png) and efficiently conducts parameter tuning by selecting parameters and values from the menu options. |
| format | Article |
| id | doaj-art-cafabc721a144303a544a26b28224385 |
| institution | Kabale University |
| issn | 1574-9541 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Informatics |
| spelling | doaj-art-cafabc721a144303a544a26b282243852025-01-19T06:24:34ZengElsevierEcological Informatics1574-95412025-03-0185102932A forestry investigation: Exploring factors behind improved tree species classification using bark imagesGokul Kottilapurath Surendran0 Deekshitha1Martin Lukac2Martin Lukac3Jozef Vybostok4Martin Mokros5Faculty of Forestry and Wood Sciences, Czech University of Life Sciences Prague, Prague CZ 165 000, CzechiaNetherlands eScience Center, Science Park 402, Amsterdam, North Holland 1098 XH, the Netherlands; Leiden Institute for Advanced Computer Science, University of Leiden, Leiden 9500 2300 RA, the Netherlands; Information and Computing Sciences, Utrecht University, Utrecht 80125 3508 TC, the NetherlandsFaculty of Forestry and Wood Sciences, Czech University of Life Sciences Prague, Prague CZ 165 000, Czechia; School of Agriculture, Policy and Development, University of Reading, Reading RG6 6EU, UKDepartment of Computer Networks and Engineering, Hiroshima City University, JapanFaculty of Forestry, Technical University in Zvolen, SlovakiaFaculty of Forestry and Wood Sciences, Czech University of Life Sciences Prague, Prague CZ 165 000, Czechia; Department of Geography, University College London, Gower Street, London WC1E 6BT, UK; Corresponding author at: Department of Geography, University College London, Gower Street, London WC1E 6BT, UK.Novel ground-based remote sensing approaches have demonstrated high potential for accurate and detailed mapping and monitoring of forest ecosystems. These methods enable the measurement of various tree parameters important for forest inventory or ecological research, such as diameter at breast height, tree height and volume, and crown parameters. One crucial piece of information is tree species, which is essential for various reasons and challenging to implement within ground-based technology workflows. This study investigates why researchers often focus on segment-specific bark images for tree species classification via deep neural networks rather than large or entire tree images. Additionally, the aim is to determine the most effective algorithmic approaches for efficient tree species classification from bark images and to make these methods more accessible to interdisciplinary researchers. The findings reveal that segment-specific datasets with more overlaps provide better accuracy across various algorithms. Additionally, pre-processing techniques such as scaling can enhance accuracy to a certain extent. Convolutional Neural Networks (CNNs) consistently deliver the highest accuracy, even with diverse datasets, but fine-tuning these algorithms poses significant challenges for interdisciplinary researchers. To address this, we developed Windows-based research software, CNN Parameter Tuner 1.0, which allows the import of various data formats (jpg and png) and efficiently conducts parameter tuning by selecting parameters and values from the menu options.http://www.sciencedirect.com/science/article/pii/S1574954124004746Tree species classificationMachine learningClose-range remote sensingGrid searchCNN parameter tuning |
| spellingShingle | Gokul Kottilapurath Surendran Deekshitha Martin Lukac Martin Lukac Jozef Vybostok Martin Mokros A forestry investigation: Exploring factors behind improved tree species classification using bark images Ecological Informatics Tree species classification Machine learning Close-range remote sensing Grid search CNN parameter tuning |
| title | A forestry investigation: Exploring factors behind improved tree species classification using bark images |
| title_full | A forestry investigation: Exploring factors behind improved tree species classification using bark images |
| title_fullStr | A forestry investigation: Exploring factors behind improved tree species classification using bark images |
| title_full_unstemmed | A forestry investigation: Exploring factors behind improved tree species classification using bark images |
| title_short | A forestry investigation: Exploring factors behind improved tree species classification using bark images |
| title_sort | forestry investigation exploring factors behind improved tree species classification using bark images |
| topic | Tree species classification Machine learning Close-range remote sensing Grid search CNN parameter tuning |
| url | http://www.sciencedirect.com/science/article/pii/S1574954124004746 |
| work_keys_str_mv | AT gokulkottilapurathsurendran aforestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT deekshitha aforestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT martinlukac aforestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT martinlukac aforestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT jozefvybostok aforestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT martinmokros aforestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT gokulkottilapurathsurendran forestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT deekshitha forestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT martinlukac forestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT martinlukac forestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT jozefvybostok forestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages AT martinmokros forestryinvestigationexploringfactorsbehindimprovedtreespeciesclassificationusingbarkimages |