Abstract
Accurate burned area information is needed to assess the impacts of wildfires on people, communities, and natural ecosystems. Various burned area detection methods have been developed using satellite remote sensing measurements with wide coverage and frequent revisits. Our study aims to expound on the capability of deep learning (DL) models for automatically mapping burned areas from uni-temporal multispectral imagery. Specifically, several semantic segmentation network architectures, i.e., U-Net, HRNet, Fast-SCNN, and DeepLabv3+, and machine learning (ML) algorithms were applied to Sentinel-2 imagery and Landsat-8 imagery in three wildfire sites in two different local climate zones. The validation results show that the DL algorithms outperform the ML methods in two of the three cases with the compact burned scars, while ML methods seem to be more suitable for mapping dispersed burn in boreal forests. Using Sentinel-2 images, U-Net and HRNet exhibit comparatively identical performance with higher kappa (around 0.9) in one heterogeneous Mediterranean fire site in Greece; Fast-SCNN performs better than others with kappa over 0.79 in one compact boreal forest fire with various burn severity in Sweden. Furthermore, directly transferring the trained models to corresponding Landsat-8 data, HRNet dominates in the three test sites among DL models and can preserve the high accuracy. The results demonstrated that DL models can make full use of contextual information and capture spatial details in multiple scales from fire-sensitive spectral bands to map burned areas. Using only a post-fire image, the DL methods not only provide automatic, accurate, and bias-free large-scale mapping option with cross-sensor applicability, but also have potential to be used for onboard processing in the next Earth observation satellites.
Highlights
Wildfires are widely recognized as one of the most critical ecosystem disturbances, as they result in the significant loss of human lives and properties, and affect biodiversity and the carbon cycle [1]
The loss is a summation of the errors produced by each batch in training or validation sets, which indicates how properly or badly a trained model performs after each iteration of optimization
It can be observed that the deep learning (DL) network model tends to increase the mapping accuracy and thematic consistency of the final burned area delineation due to the fusion of multi-scale features rather than a pixel-based classification
Summary
Wildfires are widely recognized as one of the most critical ecosystem disturbances, as they result in the significant loss of human lives and properties, and affect biodiversity and the carbon cycle [1]. Accurate and timely mapping of burned areas is, needed for the assessment of economic losses caused by the wildfires, managing post-fire hazards such as landslides or mudflows, and planning of remediation and revegetation efforts. Ground-based estimates were used to collect burned area information [2]. With the launch of Earth observation satellites, remote sensing has become a more efficient alternative to monitor wildfire extent due to its timely coverage of fire occurrences regionally and globally [3,4]. Coarse-resolution satellite sensors such as the Moderate Resolution Imaging Spectroradiometer (MODIS) have been used to identify the burned areas globally based on the thermal emission of burned vegetation [4].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
