Uni-Temporal Multispectral Imagery for Burned Area Mapping with Deep Learning

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.

Deep Learning Based Burnt Area Mapping Using Sentinel 1 for the Santa Cruz Mountains Lightning Complex (CZU) and Creek Fires 2020

“…Several studies have combined SAR and MSI with success in BA assessment [10][11][12][13][14][15][16][17][18][19]. Verhegghen et al, 2016 [19] show that the combined use of Sentinel-2 MSI and Sentinel-1 SAR can be utilized to detect and monitor fire outbreaks.…”

“…These advances have enabled researchers to apply CNNs with success in land cover, water and built environment classification tasks [12]. Many of these studies are carried out with fine or medium resolution optical data, often achieving >90% accuracies [13][14][15]. With the launch of the ESA Sentinel-1 satellites, a surge of SAR related research is being published in the context of land cover classification, environmental disturbance monitoring and change detection [16][17][18].…”

DSMNN-Net: A Deep Siamese Morphological Neural Network Model for Burned Area Mapping Using Multispectral Sentinel-2 and Hyperspectral PRISMA Images

“…The diversity of RS Earth observation imagery and its free availability has meant that monitoring of changes following disasters has turned into a hot topic for research [21][22][23][24][25][26][27][28]. Indeed, we are witnessing many BAM products on a global scale that differ in terms of spatial resolution and reliability of the burned areas mapped.…”

“…Their results showed that Res-U-Net had high efficiency, with a patch-size of 256 × 266. Hu, Ban and Nascetti [26] evaluated the potential of deep learning methods for BAM based on the unitemporal multispectral Sentinel-2 and Landsat-8 datasets. Their study showed that deep-learning methods have a high potential for BAM in comparison to machine-learning methods.…”

Detection of burned areas with extreme gradient boosting algorithm in a multi-temporal setting (MBAGB)

“…Commonly, a burned vegetation index is created for allowing the identification of burned and unburned areas defined on different thresholds after filtering low-quality pixels, and then combining this information with active fires. The use of different auxiliary information as input attribute is also frequent [13]. Very well known methods as random forest [14,15], support vector machines [16,17], artificial neural networks [18], convolutional neural networks with long short term memory (LSTM) [19], BA-Net deep learning method [20], U-net convolutional neural networks [21], geometric semantic genetic programming [22] and XGBoost [23,24] are now popular methods for segmentation of burned regions.…”