Fire-net: a deep learning framework for active forest fire detection
Forest conservation is crucial for the maintenance of a healthy and thriving ecosystem. The field of remote sensing (RS) has been integral with the wide adoption of computer vision and sensor technologies for forest land observation. One critical area of interest is the detection of active forest fi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Hindawi
2022
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/101527/ |
| _version_ | 1848863579745288192 |
|---|---|
| author | Seydi, Seyd Teymoor Saeidi, Vahideh Kalantar, Bahareh Ueda, Naonori Abdul Halin, Alfian |
| author_facet | Seydi, Seyd Teymoor Saeidi, Vahideh Kalantar, Bahareh Ueda, Naonori Abdul Halin, Alfian |
| author_sort | Seydi, Seyd Teymoor |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Forest conservation is crucial for the maintenance of a healthy and thriving ecosystem. The field of remote sensing (RS) has been integral with the wide adoption of computer vision and sensor technologies for forest land observation. One critical area of interest is the detection of active forest fires. A forest fire, which occurs naturally or manually induced, can quickly sweep through vast amounts of land, leaving behind unfathomable damage and loss of lives. Automatic detection of active forest fires (and burning biomass) is hence an important area to pursue to avoid unwanted catastrophes. Early fire detection can also be useful for decision makers to plan mitigation strategies as well as extinguishing efforts. In this paper, we present a deep learning framework called Fire-Net, that is trained on Landsat-8 imagery for the detection of active fires and burning biomass. Specifically, we fuse the optical (Red, Green, and Blue) and thermal modalities from the images for a more effective representation. In addition, our network leverages the residual convolution and separable convolution blocks, enabling deeper features from coarse datasets to be extracted. Experimental results show an overall accuracy of 97.35%, while also being able to robustly detect small active fires. The imagery for this study is taken from Australian and North American forests regions, the Amazon rainforest, Central Africa and Chernobyl (Ukraine), where forest fires are actively reported. |
| first_indexed | 2025-11-15T13:35:10Z |
| format | Article |
| id | upm-101527 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-15T13:35:10Z |
| publishDate | 2022 |
| publisher | Hindawi |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1015272023-10-04T06:50:41Z http://psasir.upm.edu.my/id/eprint/101527/ Fire-net: a deep learning framework for active forest fire detection Seydi, Seyd Teymoor Saeidi, Vahideh Kalantar, Bahareh Ueda, Naonori Abdul Halin, Alfian Forest conservation is crucial for the maintenance of a healthy and thriving ecosystem. The field of remote sensing (RS) has been integral with the wide adoption of computer vision and sensor technologies for forest land observation. One critical area of interest is the detection of active forest fires. A forest fire, which occurs naturally or manually induced, can quickly sweep through vast amounts of land, leaving behind unfathomable damage and loss of lives. Automatic detection of active forest fires (and burning biomass) is hence an important area to pursue to avoid unwanted catastrophes. Early fire detection can also be useful for decision makers to plan mitigation strategies as well as extinguishing efforts. In this paper, we present a deep learning framework called Fire-Net, that is trained on Landsat-8 imagery for the detection of active fires and burning biomass. Specifically, we fuse the optical (Red, Green, and Blue) and thermal modalities from the images for a more effective representation. In addition, our network leverages the residual convolution and separable convolution blocks, enabling deeper features from coarse datasets to be extracted. Experimental results show an overall accuracy of 97.35%, while also being able to robustly detect small active fires. The imagery for this study is taken from Australian and North American forests regions, the Amazon rainforest, Central Africa and Chernobyl (Ukraine), where forest fires are actively reported. Hindawi 2022-02-21 Article PeerReviewed Seydi, Seyd Teymoor and Saeidi, Vahideh and Kalantar, Bahareh and Ueda, Naonori and Abdul Halin, Alfian (2022) Fire-net: a deep learning framework for active forest fire detection. Journal of Sensors, 2022. art. no. 8044390. pp. 1-14. ISSN 1687-725X; ESSN: 1687-7268 https://www.hindawi.com/journals/js/2022/8044390/ 10.1155/2022/8044390 |
| spellingShingle | Seydi, Seyd Teymoor Saeidi, Vahideh Kalantar, Bahareh Ueda, Naonori Abdul Halin, Alfian Fire-net: a deep learning framework for active forest fire detection |
| title | Fire-net: a deep learning framework for active forest fire detection |
| title_full | Fire-net: a deep learning framework for active forest fire detection |
| title_fullStr | Fire-net: a deep learning framework for active forest fire detection |
| title_full_unstemmed | Fire-net: a deep learning framework for active forest fire detection |
| title_short | Fire-net: a deep learning framework for active forest fire detection |
| title_sort | fire-net: a deep learning framework for active forest fire detection |
| url | http://psasir.upm.edu.my/id/eprint/101527/ http://psasir.upm.edu.my/id/eprint/101527/ http://psasir.upm.edu.my/id/eprint/101527/ |