Forest fire progress monitoring using dual-polarisation Synthetic Aperture Radar (SAR) images combined with multi-scale segmentation and unsupervised classification

Age Shama; Rui Zhang; Ting Wang; Anmengyun Liu; Xin Bao; Jichao Lv; Yuchun Zhang; Guoxiang Liu

doi:10.1071/WF23124

RESEARCH ARTICLE (Open Access)

Previous Next Contents Vol 33(1)

Forest fire progress monitoring using dual-polarisation Synthetic Aperture Radar (SAR) images combined with multi-scale segmentation and unsupervised classification

Age Shama ^A , Rui Zhang

^A ^* , Ting Wang ^A , Anmengyun Liu ^A , Xin Bao ^A , Jichao Lv ^A , Yuchun Zhang ^A and Guoxiang Liu ^A

+ Author Affiliations

- Author Affiliations

^A Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu, 611756, China.

^* Correspondence to: zhangrui@swjtu.edu.cn

International Journal of Wildland Fire 33, WF23124 https://doi.org/10.1071/WF23124

Submitted: 29 July 2023 Accepted: 23 November 2023 Published: 21 December 2023

© 2024 The Author(s) (or their employer(s)). Published by CSIRO Publishing on behalf of IAWF. This is an open access article distributed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND)

Abstract

Background

The cloud-penetrating and fog-penetrating capability of Synthetic Aperture Radar (SAR) give it the potential for application in forest fire progress monitoring; however, the low extraction accuracy and significant salt-and-pepper noise in SAR remote sensing mapping of the burned area are problems.

Aims

This paper provides a method for accurately extracting the burned area based on fully exploiting the changes in multiple different dimensional feature parameters of dual-polarised SAR images before and after a fire.

Methods

This paper describes forest fire progress monitoring using dual-polarisation SAR images combined with multi-scale segmentation and unsupervised classification. We first constructed polarisation feature and texture feature datasets using multi-scene Sentinel-1 images. A multi-scale segmentation algorithm was then used to generate objects to suppress the salt-and-pepper noise, followed by an unsupervised classification method to extract the burned area.

Key results

The accuracy of burned area extraction in this paper is 91.67%, an improvement of 33.70% compared to the pixel-based classification results.

Conclusions

Compared with the pixel-based method, our method effectively suppresses the salt-and-pepper noise and improves the SAR burned area extraction accuracy.

Implications

The fire monitoring method using SAR images provides a reference for extracting the burned area under continuous cloud or smoke cover.

Keywords: burned areas, forest fire progress monitoring, multi-scale segmentation, polarisation features, Sentinel-1 image, synthetic aperture radar, texture features, unsupervised classification.

References

Abid N, Malik MI, Shahzad M, Shafait F, Ali H, Ghaffar MM, Weis C, Wehn N, Liwicki M (2021) Burnt Forest Estimation from Sentinel-2 Imagery of Australia using Unsupervised Deep Learning. In ‘2021 Digit. Image Comput. Tech. Appl. DICTA’, Gold Coast, Australia. pp. 1–8. (IEEE: Gold Coast, Australia) 10.1109/DICTA52665.2021.9647174

Belenguer-Plomer MA, Tanase MA, Fernandez-Carrillo A, Chuvieco E (2019) Burned area detection and mapping using Sentinel-1 backscatter coefficient and thermal anomalies. Remote Sensing of Environment 233, 111345.
| Crossref | Google Scholar |

Belenguer-Plomer MA, Tanase MA, Chuvieco E, Bovolo F (2021) CNN-based burned area mapping using radar and optical data. Remote Sensing of Environment 260, 112468.
| Crossref | Google Scholar |

Chen Y, He X, Xu J, Zhang R, Lu Y (2020) Scattering Feature Set Optimization and Polarimetric SAR Classification Using Object-Oriented RF-SFS Algorithm in Coastal Wetlands. Remote Sensing 12, 407.
| Crossref | Google Scholar |

Dixon DJ, Callow JN, Duncan JMA, Setterfield SA, Pauli N (2022) Regional-scale fire severity mapping of Eucalyptus forests with the Landsat archive. Remote Sensing of Environment 270, 112863.
| Crossref | Google Scholar |

Dostálová A, Lang M, Ivanovs J, Waser LT, Wagner W (2021) European Wide Forest Classification Based on Sentinel-1 Data. Remote Sensing 13, 337.
| Crossref | Google Scholar |

Du S, Guo Z, Wang W, Guo L, Nie J (2016) A comparative study of the segmentation of weighted aggregation and multiresolution segmentation. GIScience & Remote Sensing 53, 651-670.
| Crossref | Google Scholar |

Dufera AG, Liu T, Xu J (2023) Regression models of Pearson correlation coefficient. Statistical Theory and Related Fields 7, 97-106.
| Crossref | Google Scholar |

Foroughnia F, Alfieri SM, Menenti M, Lindenbergh R (2022) Evaluation of SAR and Optical Data for Flood Delineation Using Supervised and Unsupervised Classification. Remote Sensing 14, 3718.
| Crossref | Google Scholar |

Fu B, He X, Yao H, Liang Y, Deng T, He H, Fan D, Lan G, He W (2022) Comparison of RFE-DL and stacking ensemble learning algorithms for classifying mangrove species on UAV multispectral images. International Journal of Applied Earth Observation and Geoinformation 112, 102890.
| Crossref | Google Scholar |

Gibson R, Danaher T, Hehir W, Collins L (2020) A remote sensing approach to mapping fire severity in south-eastern Australia using sentinel 2 and random forest. Remote Sensing of Environment 240, 111702.
| Crossref | Google Scholar |

Homer C, Dewitz J, Yang L, Jin S, Danielson P, Coulston J, Herold N, Wickham J, Megown K (2015) Completion of the 2011 National Land Cover Database for the Conterminous United States – Representing a Decade of Land Cover Change Information. Photogrammetric Engineering & Remote Sensing 81, 345-354.
| Google Scholar |

Kalogirou V, Ferrazzoli P, Della Vecchia A, Foumelis M (2014) On the SAR Backscatter of Burned Forests: A Model-Based Study in C-Band, Over Burned Pine Canopies. IEEE Transactions on Geoscience and Remote Sensing 52, 6205-6215.
| Crossref | Google Scholar |

Lasaponara R, Proto AM, Aromando A, Cardettini G, Varela V, Danese M (2020) On the Mapping of Burned Areas and Burn Severity Using Self Organizing Map and Sentinel-2 Data. IEEE Geoscience and Remote Sensing Letters 17, 854-858.
| Crossref | Google Scholar |

Luo C, Qi B, Liu H, Guo D, Lu L, Fu Q, Shao Y (2021) Using Time Series Sentinel-1 Images for Object-Oriented Crop Classification in Google Earth Engine. Remote Sensing 13, 561.
| Crossref | Google Scholar |

Mishra D, Pathak G, Singh BP, Mohit , Sihag P, Rajeev , Singh S (2023) Crop classification by using dual-pol SAR vegetation indices derived from Sentinel-1 SAR-C data. Environmental Monitoring and Assessment 195, 115.
| Crossref | Google Scholar | PubMed |

Pinto MM, Trigo RM, Trigo IF, DaCamara CC (2021) A Practical Method for High-Resolution Burned Area Monitoring Using Sentinel-2 and VIIRS. Remote Sensing 13, 1608.
| Crossref | Google Scholar |

Qu J, Qiu X, Ding C, Lei B (2021) Unsupervised Classification of Polarimetric SAR Image Based on Geodesic Distance and Non-Gaussian Distribution Feature. Sensors 21, 1317.
| Crossref | Google Scholar | PubMed |

Roy DP, Huang H, Boschetti L, Giglio L, Yan L, Zhang HH, Li Z (2019) Landsat-8 and Sentinel-2 burned area mapping - A combined sensor multi-temporal change detection approach. Remote Sensing of Environment 231, 111254.
| Crossref | Google Scholar |

Shama A, Zhang R, Zhan R, Wang T, Xie L, Bao X, Lv J (2023) A Burned Area Extracting Method Using Polarization and Texture Feature of Sentinel-1A Images. IEEE Geoscience and Remote Sensing Letters 20, 1-5.
| Crossref | Google Scholar |

Shiraishi T, Hirata R, Hirano T (2021) New Inventories of Global Carbon Dioxide Emissions through Biomass Burning in 2001–2020. Remote Sensing 13, 1914.
| Crossref | Google Scholar |

Sinaga KP, Yang M-S (2020) Unsupervised K-Means Clustering Algorithm. IEEE Access 8, 80716-80727.
| Crossref | Google Scholar |

Sismanis M, Chadoulis R-T, Manakos I, Drosou A (2023) An Unsupervised Burned Area Mapping Approach Using Sentinel-2 Images. Land 12, 379.
| Crossref | Google Scholar |

Stroppiana D, Azar R, Calò F, Pepe A, Imperatore P, Boschetti M, Silva J, Brivio P, Lanari R (2015) Integration of Optical and SAR Data for Burned Area Mapping in Mediterranean Regions. Remote Sensing 7, 1320-1345.
| Crossref | Google Scholar |

Wei J, Zhang Y, Wu H, Cui B (2018) The Automatic Detection of Fire Scar in Alaska using Multi-Temporal PALSAR Polarimetric SAR Data. Canadian Journal of Remote Sensing 44, 447-461.
| Crossref | Google Scholar |

West RD, LaBruyere Iii TE, Skryzalin J, Simonson KM, Hansen RL, Van Benthem MH (2019) Polarimetric SAR Image Terrain Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 12, 4467-4485.
| Crossref | Google Scholar |

Zhang P, Nascetti A, Ban Y, Gong M (2019) An implicit radar convolutional burn index for burnt area mapping with Sentinel-1 C-band SAR data. ISPRS Journal of Photogrammetry and Remote Sensing 158, 50-62.
| Crossref | Google Scholar |

Zhang X, Xu J, Chen Y, Xu K, Wang D (2021) Coastal Wetland Classification with GF-3 Polarimetric SAR Imagery by Using Object-Oriented Random Forest Algorithm. Sensors 21, 3395.
| Crossref | Google Scholar | PubMed |

Zhang C, Gao G, Zhang L, Chen C, Gao S, Yao L, Bai Q, Gou S (2022) A novel full-polarization SAR image ship detector based on scattering mechanisms and wave polarization anisotropy. ISPRS Journal of Photogrammetry and Remote Sensing 190, 129-143.
| Crossref | Google Scholar |

Zhang D, Ying C, Wu L, Meng Z, Wang X, Ma Y (2023) Using Time Series Sentinel Images for Object-Oriented Crop Extraction of Planting Structure in the Google Earth Engine. Agronomy 13, 2350.
| Crossref | Google Scholar |