Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern Portugal
Mapping large wildfires (LW) is essential for environmental applications and enhances the understanding of the dynamics of affected areas. Remote sensing techniques supported by machine learning and time series have been increasingly used in studies addressing this issue and have shown potential for...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Fire |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-6255/6/2/43 |
| _version_ | 1797621098212229120 |
|---|---|
| author | Sarah Moura Batista dos Santos Soltan Galano Duverger António Bento-Gonçalves Washington Franca-Rocha António Vieira Georgia Teixeira |
| author_facet | Sarah Moura Batista dos Santos Soltan Galano Duverger António Bento-Gonçalves Washington Franca-Rocha António Vieira Georgia Teixeira |
| author_sort | Sarah Moura Batista dos Santos |
| collection | DOAJ |
| description | Mapping large wildfires (LW) is essential for environmental applications and enhances the understanding of the dynamics of affected areas. Remote sensing techniques supported by machine learning and time series have been increasingly used in studies addressing this issue and have shown potential for this type of analysis. The main aim of this article is to develop a methodology for mapping LW in northwestern Portugal using a machine learning algorithm and time series from Landsat images. For the burnt area classification, we initially used the Fourier harmonic model to define outliers in the time series that represented pixels of possible burnt areas and, then, we applied the random forest classifier for the LW classification. The results indicate that the harmonic analysis provided estimates with the actual observed values of the NBR index; thus, the pixels classified by random forest were only those that were masked, collaborated in the processing, and reduced possible spectral confusion between targets with similar behaviour. The burnt area maps revealed that ~23.5% of the territory was burnt at least once from 2001 to 2020. The temporal variability of the burnt area indicated that, on average, 6.504 hectares were affected by LW within the 20 years. The annual burnt area varied over the years, with the minimum annual area detected in 2014 (679.5 hectares) and the maximum mapped area detected in 2005 (73,025.1 hectares). We concluded that the process of defining the mask with the outliers considerably reduced the universe of pixels to be classified within each image, which leaves the training of the classifier focused on separating the set of pixels into two groups with very similar spectral characteristics, thus contributing so that the separation of groups with similar spectral behaviour was performed automatically and without great sampling effort. The method showed satisfactory accuracy results with little omission for burnt areas. |
| first_indexed | 2024-03-11T08:50:56Z |
| format | Article |
| id | doaj.art-7f47bdc6892a41f5b5636aa9fe4a2f1d |
| institution | Directory Open Access Journal |
| issn | 2571-6255 |
| language | English |
| last_indexed | 2024-03-11T08:50:56Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fire |
| spelling | doaj.art-7f47bdc6892a41f5b5636aa9fe4a2f1d2023-11-16T20:27:06ZengMDPI AGFire2571-62552023-01-01624310.3390/fire6020043Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern PortugalSarah Moura Batista dos Santos0Soltan Galano Duverger1António Bento-Gonçalves2Washington Franca-Rocha3António Vieira4Georgia Teixeira5Centro de Estudos em Comunicação e Sociedade (CECS), Departamento de Geografia, Universidade do Minho (UMinho), 4800-058 Guimarães, PortugalDoutorado Multi-Institucional Multidisciplinar em Difusão do Conhecimento (DMMDC), Universidade Federal da Bahia (UFBA), Salvador 40110-909, BrazilCentro de Estudos em Comunicação e Sociedade (CECS), Departamento de Geografia, Universidade do Minho (UMinho), 4800-058 Guimarães, PortugalPrograma de Pós-Graduação em Ciências da Terra e do Ambiente (PPGM), Departamento de Ciências Exatas, Universidade Estadual de Feira de Santana (UEFS), Feira de Santana 44036-900, BrazilCentro de Estudos em Comunicação e Sociedade (CECS), Departamento de Geografia, Universidade do Minho (UMinho), 4800-058 Guimarães, PortugalInstituto de Geografia (IG), Universidade Federal de Uberlândia (UFU), Uberlândia 38408-100, BrazilMapping large wildfires (LW) is essential for environmental applications and enhances the understanding of the dynamics of affected areas. Remote sensing techniques supported by machine learning and time series have been increasingly used in studies addressing this issue and have shown potential for this type of analysis. The main aim of this article is to develop a methodology for mapping LW in northwestern Portugal using a machine learning algorithm and time series from Landsat images. For the burnt area classification, we initially used the Fourier harmonic model to define outliers in the time series that represented pixels of possible burnt areas and, then, we applied the random forest classifier for the LW classification. The results indicate that the harmonic analysis provided estimates with the actual observed values of the NBR index; thus, the pixels classified by random forest were only those that were masked, collaborated in the processing, and reduced possible spectral confusion between targets with similar behaviour. The burnt area maps revealed that ~23.5% of the territory was burnt at least once from 2001 to 2020. The temporal variability of the burnt area indicated that, on average, 6.504 hectares were affected by LW within the 20 years. The annual burnt area varied over the years, with the minimum annual area detected in 2014 (679.5 hectares) and the maximum mapped area detected in 2005 (73,025.1 hectares). We concluded that the process of defining the mask with the outliers considerably reduced the universe of pixels to be classified within each image, which leaves the training of the classifier focused on separating the set of pixels into two groups with very similar spectral characteristics, thus contributing so that the separation of groups with similar spectral behaviour was performed automatically and without great sampling effort. The method showed satisfactory accuracy results with little omission for burnt areas.https://www.mdpi.com/2571-6255/6/2/43burnt areaspectral indexGoogle Earth Enginelandsat time seriesrandom forest |
| spellingShingle | Sarah Moura Batista dos Santos Soltan Galano Duverger António Bento-Gonçalves Washington Franca-Rocha António Vieira Georgia Teixeira Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern Portugal Fire burnt area spectral index Google Earth Engine landsat time series random forest |
| title | Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern Portugal |
| title_full | Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern Portugal |
| title_fullStr | Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern Portugal |
| title_full_unstemmed | Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern Portugal |
| title_short | Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern Portugal |
| title_sort | remote sensing applications for mapping large wildfires based on machine learning and time series in northwestern portugal |
| topic | burnt area spectral index Google Earth Engine landsat time series random forest |
| url | https://www.mdpi.com/2571-6255/6/2/43 |
| work_keys_str_mv | AT sarahmourabatistadossantos remotesensingapplicationsformappinglargewildfiresbasedonmachinelearningandtimeseriesinnorthwesternportugal AT soltangalanoduverger remotesensingapplicationsformappinglargewildfiresbasedonmachinelearningandtimeseriesinnorthwesternportugal AT antoniobentogoncalves remotesensingapplicationsformappinglargewildfiresbasedonmachinelearningandtimeseriesinnorthwesternportugal AT washingtonfrancarocha remotesensingapplicationsformappinglargewildfiresbasedonmachinelearningandtimeseriesinnorthwesternportugal AT antoniovieira remotesensingapplicationsformappinglargewildfiresbasedonmachinelearningandtimeseriesinnorthwesternportugal AT georgiateixeira remotesensingapplicationsformappinglargewildfiresbasedonmachinelearningandtimeseriesinnorthwesternportugal |