Mapping burnt areas using very high-resolution imagery and deep learning algorithms - a case study in Bandipur, India.
Burnt area (BA) mapping is crucial for assessing wildfire impact, guiding restoration efforts, and improving fire management strategies. Accurate BA data helps estimate carbon emissions, biodiversity loss, and land surface properties post-fire changes. In this study, we designed and evaluated two de...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0327125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849717780452999168 |
|---|---|
| author | Sai Balakavi Vineet Vadrevu Kristofer Lasko |
| author_facet | Sai Balakavi Vineet Vadrevu Kristofer Lasko |
| author_sort | Sai Balakavi |
| collection | DOAJ |
| description | Burnt area (BA) mapping is crucial for assessing wildfire impact, guiding restoration efforts, and improving fire management strategies. Accurate BA data helps estimate carbon emissions, biodiversity loss, and land surface properties post-fire changes. In this study, we designed and evaluated two deep learning-based architectures, a Custom UNET and a novel UNET-Gated Recurrent Unit (GRU), for burnt area classification using PlanetScope data over Bandipur, India. Both models demonstrated high accuracy in classifying burnt and unburnt areas. Performance metrics, including Precision, Recall, F1-Score, Accuracy, Mean Intersection over Union (IoU), and Dice Coefficient, revealed that the UNET-GRU hybrid consistently outperformed the Custom UNET, particularly in Recall and spatial overlap metrics. The Receiver Operating Characteristic (ROC) curve indicated excellent classification performance for both models, with the UNET-GRU achieving a higher AUC (0.98) compared to the Custom UNET (0.96). These findings highlight the UNET-GRU's enhanced capacity to handle finer distinctions and capture spatial and contextual features, making it a robust choice for burnt area classification in the study area. While both models avoided overfitting and maintained generalizability, integrating GRU into the UNET architecture proved particularly effective for precise classification and spatial accuracy. Our results highlight the potential of the novel UNET-GRU for burnt area mapping using very high-resolution data. |
| format | Article |
| id | doaj-art-85ec11f31e784d1ba633a574a0042dea |
| institution | DOAJ |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-85ec11f31e784d1ba633a574a0042dea2025-08-20T03:12:34ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032712510.1371/journal.pone.0327125Mapping burnt areas using very high-resolution imagery and deep learning algorithms - a case study in Bandipur, India.Sai BalakaviVineet VadrevuKristofer LaskoBurnt area (BA) mapping is crucial for assessing wildfire impact, guiding restoration efforts, and improving fire management strategies. Accurate BA data helps estimate carbon emissions, biodiversity loss, and land surface properties post-fire changes. In this study, we designed and evaluated two deep learning-based architectures, a Custom UNET and a novel UNET-Gated Recurrent Unit (GRU), for burnt area classification using PlanetScope data over Bandipur, India. Both models demonstrated high accuracy in classifying burnt and unburnt areas. Performance metrics, including Precision, Recall, F1-Score, Accuracy, Mean Intersection over Union (IoU), and Dice Coefficient, revealed that the UNET-GRU hybrid consistently outperformed the Custom UNET, particularly in Recall and spatial overlap metrics. The Receiver Operating Characteristic (ROC) curve indicated excellent classification performance for both models, with the UNET-GRU achieving a higher AUC (0.98) compared to the Custom UNET (0.96). These findings highlight the UNET-GRU's enhanced capacity to handle finer distinctions and capture spatial and contextual features, making it a robust choice for burnt area classification in the study area. While both models avoided overfitting and maintained generalizability, integrating GRU into the UNET architecture proved particularly effective for precise classification and spatial accuracy. Our results highlight the potential of the novel UNET-GRU for burnt area mapping using very high-resolution data.https://doi.org/10.1371/journal.pone.0327125 |
| spellingShingle | Sai Balakavi Vineet Vadrevu Kristofer Lasko Mapping burnt areas using very high-resolution imagery and deep learning algorithms - a case study in Bandipur, India. PLoS ONE |
| title | Mapping burnt areas using very high-resolution imagery and deep learning algorithms - a case study in Bandipur, India. |
| title_full | Mapping burnt areas using very high-resolution imagery and deep learning algorithms - a case study in Bandipur, India. |
| title_fullStr | Mapping burnt areas using very high-resolution imagery and deep learning algorithms - a case study in Bandipur, India. |
| title_full_unstemmed | Mapping burnt areas using very high-resolution imagery and deep learning algorithms - a case study in Bandipur, India. |
| title_short | Mapping burnt areas using very high-resolution imagery and deep learning algorithms - a case study in Bandipur, India. |
| title_sort | mapping burnt areas using very high resolution imagery and deep learning algorithms a case study in bandipur india |
| url | https://doi.org/10.1371/journal.pone.0327125 |
| work_keys_str_mv | AT saibalakavi mappingburntareasusingveryhighresolutionimageryanddeeplearningalgorithmsacasestudyinbandipurindia AT vineetvadrevu mappingburntareasusingveryhighresolutionimageryanddeeplearningalgorithmsacasestudyinbandipurindia AT kristoferlasko mappingburntareasusingveryhighresolutionimageryanddeeplearningalgorithmsacasestudyinbandipurindia |