Satellite-Based Forest Stand Detection Using Artificial Intelligence
The forest constitutes an essential and irreplaceable component of life for all organisms, with its primary significance lying in its role in creating a breathable atmosphere on Earth. Forests are vital for human health and well-being and hold significant ecological and economic value for humanity....
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10836691/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592927710248960 |
|---|---|
| author | Patrik Kovacovic Rastislav Pirnik Julia Kafkova Mario Michalik Alzbeta Kanalikova Pavol Kuchar |
| author_facet | Patrik Kovacovic Rastislav Pirnik Julia Kafkova Mario Michalik Alzbeta Kanalikova Pavol Kuchar |
| author_sort | Patrik Kovacovic |
| collection | DOAJ |
| description | The forest constitutes an essential and irreplaceable component of life for all organisms, with its primary significance lying in its role in creating a breathable atmosphere on Earth. Forests are vital for human health and well-being and hold significant ecological and economic value for humanity. This study aims to propose a method for identifying forest stands using artificial intelligence techniques. A custom dataset was developed, comprising high-quality satellite images that capture various structures such as forests, fields, roads, buildings, and lakes. This dataset was employed to train models from the category of convolutional neural networks that operate on the principle of instance segmentation. Several models, including YOLOv8, YOLOv5 and Mask R-CNN, were tested and compared. An optimal model was selected based on parameters such as detection accuracy, total training time, and the precision of labeling detected image elements. The selected model was then evaluated using images not included in the original training dataset to simulate real-world deployment scenarios. The final accuracy of best model achieved 91.67%. This model can detect the presence of forest stands in satellite images, as well as other features such as roads, buildings etc. The proposed method offers potential benefits for forest technicians, who can integrate it with other methods to monitor forest cover effectively. |
| format | Article |
| id | doaj-art-6386d38005ce4be0994f69f80aa3ebcf |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-6386d38005ce4be0994f69f80aa3ebcf2025-01-21T00:01:01ZengIEEEIEEE Access2169-35362025-01-0113108981091710.1109/ACCESS.2025.352821510836691Satellite-Based Forest Stand Detection Using Artificial IntelligencePatrik Kovacovic0https://orcid.org/0009-0007-8624-2842Rastislav Pirnik1https://orcid.org/0000-0003-1644-2180Julia Kafkova2https://orcid.org/0009-0009-5994-531XMario Michalik3https://orcid.org/0009-0008-2458-8570Alzbeta Kanalikova4https://orcid.org/0000-0003-4925-0919Pavol Kuchar5https://orcid.org/0000-0003-3295-1989Department of Control and Information Systems, Faculty of Electrical Engineering and Information Technology, University of Žilina, Žilina, SlovakiaDepartment of Control and Information Systems, Faculty of Electrical Engineering and Information Technology, University of Žilina, Žilina, SlovakiaDepartment of Control and Information Systems, Faculty of Electrical Engineering and Information Technology, University of Žilina, Žilina, SlovakiaDepartment of Control and Information Systems, Faculty of Electrical Engineering and Information Technology, University of Žilina, Žilina, SlovakiaDepartment of Control and Information Systems, Faculty of Electrical Engineering and Information Technology, University of Žilina, Žilina, SlovakiaDepartment of Control and Information Systems, Faculty of Electrical Engineering and Information Technology, University of Žilina, Žilina, SlovakiaThe forest constitutes an essential and irreplaceable component of life for all organisms, with its primary significance lying in its role in creating a breathable atmosphere on Earth. Forests are vital for human health and well-being and hold significant ecological and economic value for humanity. This study aims to propose a method for identifying forest stands using artificial intelligence techniques. A custom dataset was developed, comprising high-quality satellite images that capture various structures such as forests, fields, roads, buildings, and lakes. This dataset was employed to train models from the category of convolutional neural networks that operate on the principle of instance segmentation. Several models, including YOLOv8, YOLOv5 and Mask R-CNN, were tested and compared. An optimal model was selected based on parameters such as detection accuracy, total training time, and the precision of labeling detected image elements. The selected model was then evaluated using images not included in the original training dataset to simulate real-world deployment scenarios. The final accuracy of best model achieved 91.67%. This model can detect the presence of forest stands in satellite images, as well as other features such as roads, buildings etc. The proposed method offers potential benefits for forest technicians, who can integrate it with other methods to monitor forest cover effectively.https://ieeexplore.ieee.org/document/10836691/Artificial intelligenceneural networksforestdatasetmodel |
| spellingShingle | Patrik Kovacovic Rastislav Pirnik Julia Kafkova Mario Michalik Alzbeta Kanalikova Pavol Kuchar Satellite-Based Forest Stand Detection Using Artificial Intelligence IEEE Access Artificial intelligence neural networks forest dataset model |
| title | Satellite-Based Forest Stand Detection Using Artificial Intelligence |
| title_full | Satellite-Based Forest Stand Detection Using Artificial Intelligence |
| title_fullStr | Satellite-Based Forest Stand Detection Using Artificial Intelligence |
| title_full_unstemmed | Satellite-Based Forest Stand Detection Using Artificial Intelligence |
| title_short | Satellite-Based Forest Stand Detection Using Artificial Intelligence |
| title_sort | satellite based forest stand detection using artificial intelligence |
| topic | Artificial intelligence neural networks forest dataset model |
| url | https://ieeexplore.ieee.org/document/10836691/ |
| work_keys_str_mv | AT patrikkovacovic satellitebasedforeststanddetectionusingartificialintelligence AT rastislavpirnik satellitebasedforeststanddetectionusingartificialintelligence AT juliakafkova satellitebasedforeststanddetectionusingartificialintelligence AT mariomichalik satellitebasedforeststanddetectionusingartificialintelligence AT alzbetakanalikova satellitebasedforeststanddetectionusingartificialintelligence AT pavolkuchar satellitebasedforeststanddetectionusingartificialintelligence |