Integrating Machine Learning and a Spatial Contextual Algorithm to Detect Wildfire from Himawari-8 Data in Southwest China
Timely wildfire detection is helpful for fire monitoring and fighting. However, the available wildfire products with high temporal resolutions face problems, such as high omission error and commission error (false alarm) rates. This study proposed a wildfire detection algorithm combined with an impr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/14/5/919 |
| _version_ | 1797600095205588992 |
|---|---|
| author | Chuanfeng Liu Rui Chen Binbin He |
| author_facet | Chuanfeng Liu Rui Chen Binbin He |
| author_sort | Chuanfeng Liu |
| collection | DOAJ |
| description | Timely wildfire detection is helpful for fire monitoring and fighting. However, the available wildfire products with high temporal resolutions face problems, such as high omission error and commission error (false alarm) rates. This study proposed a wildfire detection algorithm combined with an improved spatial contextual algorithm and machine learning method in southwest China. First, a dataset consisting of a formation of high-confidence fire pixels combining the WLF (Himawari Wild Fire product) and VIIRS wildfire products was constructed. Then, a model to extract potential fire pixels was built using the random forest method. Additionally, an improved spatial contextual algorithm was used to identify actual fire pixels from potential fire pixels. Finally, strategies such as sun glint rejection were used to remove false alarms. As a result, the proposed algorithm performed better, with both a lower omission error rate and a lower commission error rate than the WLF product. It had a higher F1 score (0.47) than WLF (0.43) with VIIRS for reference, which means it is more suitable for wildfire detection. |
| first_indexed | 2024-03-11T03:43:41Z |
| format | Article |
| id | doaj.art-7780aa1b60d1485fa4548bc35f12f808 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-11T03:43:41Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-7780aa1b60d1485fa4548bc35f12f8082023-11-18T01:23:40ZengMDPI AGForests1999-49072023-04-0114591910.3390/f14050919Integrating Machine Learning and a Spatial Contextual Algorithm to Detect Wildfire from Himawari-8 Data in Southwest ChinaChuanfeng Liu0Rui Chen1Binbin He2School of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Resources and Environment, University of Electronic Science and Technology of China, Chengdu 611731, ChinaTimely wildfire detection is helpful for fire monitoring and fighting. However, the available wildfire products with high temporal resolutions face problems, such as high omission error and commission error (false alarm) rates. This study proposed a wildfire detection algorithm combined with an improved spatial contextual algorithm and machine learning method in southwest China. First, a dataset consisting of a formation of high-confidence fire pixels combining the WLF (Himawari Wild Fire product) and VIIRS wildfire products was constructed. Then, a model to extract potential fire pixels was built using the random forest method. Additionally, an improved spatial contextual algorithm was used to identify actual fire pixels from potential fire pixels. Finally, strategies such as sun glint rejection were used to remove false alarms. As a result, the proposed algorithm performed better, with both a lower omission error rate and a lower commission error rate than the WLF product. It had a higher F1 score (0.47) than WLF (0.43) with VIIRS for reference, which means it is more suitable for wildfire detection.https://www.mdpi.com/1999-4907/14/5/919wildfirerandom forest modelspatial contextual algorithmHimawari-8 satellite |
| spellingShingle | Chuanfeng Liu Rui Chen Binbin He Integrating Machine Learning and a Spatial Contextual Algorithm to Detect Wildfire from Himawari-8 Data in Southwest China Forests wildfire random forest model spatial contextual algorithm Himawari-8 satellite |
| title | Integrating Machine Learning and a Spatial Contextual Algorithm to Detect Wildfire from Himawari-8 Data in Southwest China |
| title_full | Integrating Machine Learning and a Spatial Contextual Algorithm to Detect Wildfire from Himawari-8 Data in Southwest China |
| title_fullStr | Integrating Machine Learning and a Spatial Contextual Algorithm to Detect Wildfire from Himawari-8 Data in Southwest China |
| title_full_unstemmed | Integrating Machine Learning and a Spatial Contextual Algorithm to Detect Wildfire from Himawari-8 Data in Southwest China |
| title_short | Integrating Machine Learning and a Spatial Contextual Algorithm to Detect Wildfire from Himawari-8 Data in Southwest China |
| title_sort | integrating machine learning and a spatial contextual algorithm to detect wildfire from himawari 8 data in southwest china |
| topic | wildfire random forest model spatial contextual algorithm Himawari-8 satellite |
| url | https://www.mdpi.com/1999-4907/14/5/919 |
| work_keys_str_mv | AT chuanfengliu integratingmachinelearningandaspatialcontextualalgorithmtodetectwildfirefromhimawari8datainsouthwestchina AT ruichen integratingmachinelearningandaspatialcontextualalgorithmtodetectwildfirefromhimawari8datainsouthwestchina AT binbinhe integratingmachinelearningandaspatialcontextualalgorithmtodetectwildfirefromhimawari8datainsouthwestchina |