Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A Imagery
Fire in Brazilian Pantanal represents a serious threat to biodiversity. The Brazilian National Institute of Spatial Research (INPE) has a program named Queimadas, which estimated from January 2020 to October 2020, a burned area in Pantanal of approximately 40,606 km<inline-formula><math xml...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/3/688 |
| _version_ | 1797485009758584832 |
|---|---|
| author | Leandro Higa José Marcato Junior Thiago Rodrigues Pedro Zamboni Rodrigo Silva Laisa Almeida Veraldo Liesenberg Fábio Roque Renata Libonati Wesley Nunes Gonçalves Jonathan Silva |
| author_facet | Leandro Higa José Marcato Junior Thiago Rodrigues Pedro Zamboni Rodrigo Silva Laisa Almeida Veraldo Liesenberg Fábio Roque Renata Libonati Wesley Nunes Gonçalves Jonathan Silva |
| author_sort | Leandro Higa |
| collection | DOAJ |
| description | Fire in Brazilian Pantanal represents a serious threat to biodiversity. The Brazilian National Institute of Spatial Research (INPE) has a program named Queimadas, which estimated from January 2020 to October 2020, a burned area in Pantanal of approximately 40,606 km<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mn>2</mn></msup></semantics></math></inline-formula>. This program also provides daily data of active fire (fires spots) from a methodology that uses MODIS (Aqua and Terra) sensor data as reference satellites, which presents limitations mainly when dealing with small active fires. Remote sensing researches on active fire dynamics have contributed to wildfire comprehension, despite generally applying low spatial resolution data. Convolutional Neural Networks (CNN) associated with high- and medium-resolution remote sensing data may provide a complementary strategy to small active fire detection. We propose an approach based on object detection methods to map active fire in the Pantanal. In this approach, a post-processing strategy is adopted based on Non-Max Suppression (NMS) to reduce the number of highly overlapped detections. Extensive experiments were conducted, generating 150 models, as five-folds were considered. We generate a public dataset with 775-RGB image patches from the Wide Field Imager (WFI) sensor onboard the China Brazil Earth Resources Satellite (CBERS) 4A. The patches resulted from 49 images acquired from May to August 2020 and present a spatial and temporal resolutions of 55 m and five days, respectively. The proposed approach uses a point (active fire) to generate squared bounding boxes. Our findings indicate that accurate results were achieved, even considering recent images from 2021, showing the generalization capability of our models to complement other researches and wildfire databases such as the current program Queimadas in detecting active fire in this complex environment. The approach may be extended and evaluated in other environmental conditions worldwide where active fire detection is still a required information in fire fighting and rescue initiatives. |
| first_indexed | 2024-03-09T23:12:39Z |
| format | Article |
| id | doaj.art-64b1c6d4de094a9e9a7fbb398c865a14 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T23:12:39Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-64b1c6d4de094a9e9a7fbb398c865a142023-11-23T17:41:53ZengMDPI AGRemote Sensing2072-42922022-01-0114368810.3390/rs14030688Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A ImageryLeandro Higa0José Marcato Junior1Thiago Rodrigues2Pedro Zamboni3Rodrigo Silva4Laisa Almeida5Veraldo Liesenberg6Fábio Roque7Renata Libonati8Wesley Nunes Gonçalves9Jonathan Silva10Faculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, BrazilFaculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, BrazilLaboratory of Atmospheric Sciences, Institute of Physics, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, BrazilFaculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, BrazilFaculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, BrazilFaculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, BrazilDepartment of Forest Engineering, Santa Catarina State University, Lages 88520-000, BrazilFaculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, BrazilDepartamento de Meteorologia, Universidade Federal do Rio de Janeiro, Rio de Janeiro 21941-916, BrazilFaculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, BrazilFaculty of Engineering, Architecture and Urbanism and Geography, Federal University of Mato Grosso do Sul, Campo Grande 79070-900, BrazilFire in Brazilian Pantanal represents a serious threat to biodiversity. The Brazilian National Institute of Spatial Research (INPE) has a program named Queimadas, which estimated from January 2020 to October 2020, a burned area in Pantanal of approximately 40,606 km<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mn>2</mn></msup></semantics></math></inline-formula>. This program also provides daily data of active fire (fires spots) from a methodology that uses MODIS (Aqua and Terra) sensor data as reference satellites, which presents limitations mainly when dealing with small active fires. Remote sensing researches on active fire dynamics have contributed to wildfire comprehension, despite generally applying low spatial resolution data. Convolutional Neural Networks (CNN) associated with high- and medium-resolution remote sensing data may provide a complementary strategy to small active fire detection. We propose an approach based on object detection methods to map active fire in the Pantanal. In this approach, a post-processing strategy is adopted based on Non-Max Suppression (NMS) to reduce the number of highly overlapped detections. Extensive experiments were conducted, generating 150 models, as five-folds were considered. We generate a public dataset with 775-RGB image patches from the Wide Field Imager (WFI) sensor onboard the China Brazil Earth Resources Satellite (CBERS) 4A. The patches resulted from 49 images acquired from May to August 2020 and present a spatial and temporal resolutions of 55 m and five days, respectively. The proposed approach uses a point (active fire) to generate squared bounding boxes. Our findings indicate that accurate results were achieved, even considering recent images from 2021, showing the generalization capability of our models to complement other researches and wildfire databases such as the current program Queimadas in detecting active fire in this complex environment. The approach may be extended and evaluated in other environmental conditions worldwide where active fire detection is still a required information in fire fighting and rescue initiatives.https://www.mdpi.com/2072-4292/14/3/688remote sensingwildfireobject detectionconvolutional neural network |
| spellingShingle | Leandro Higa José Marcato Junior Thiago Rodrigues Pedro Zamboni Rodrigo Silva Laisa Almeida Veraldo Liesenberg Fábio Roque Renata Libonati Wesley Nunes Gonçalves Jonathan Silva Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A Imagery Remote Sensing remote sensing wildfire object detection convolutional neural network |
| title | Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A Imagery |
| title_full | Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A Imagery |
| title_fullStr | Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A Imagery |
| title_full_unstemmed | Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A Imagery |
| title_short | Active Fire Mapping on Brazilian Pantanal Based on Deep Learning and CBERS 04A Imagery |
| title_sort | active fire mapping on brazilian pantanal based on deep learning and cbers 04a imagery |
| topic | remote sensing wildfire object detection convolutional neural network |
| url | https://www.mdpi.com/2072-4292/14/3/688 |
| work_keys_str_mv | AT leandrohiga activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT josemarcatojunior activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT thiagorodrigues activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT pedrozamboni activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT rodrigosilva activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT laisaalmeida activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT veraldoliesenberg activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT fabioroque activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT renatalibonati activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT wesleynunesgoncalves activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery AT jonathansilva activefiremappingonbrazilianpantanalbasedondeeplearningandcbers04aimagery |