Double-Step U-Net: A Deep Learning-Based Approach for the Estimation of Wildfire Damage Severity through Sentinel-2 Satellite Data

Farasin, Alessandro; Colomba, Luca; Garza, Paolo

doi:10.3390/app10124332

Cited by 40 publications

(26 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model is validated across five European regions. It also showed a comparable result to the threshold of the delta Normalized Burn Ratio method [92].…”

Section: Post-fire Mapping Based Satellite Remote Sensing Imagerymentioning

confidence: 59%

“…It also proved its ability to overcome the limitations of traditional methodologies such as the filtering of lower quality and no shadows and clouds mask [90]. Farasin et al [92] also developed a novel deep learning model, Double-Step U-Net, to estimate the wildfire damage severity from the sentinel-2 satellite. Two subtasks, Binary Classification U-Net and Regression U-Net, are proposed.…”

Section: Post-fire Mapping Based Satellite Remote Sensing Imagerymentioning

confidence: 99%

See 1 more Smart Citation

Wildfire Segmentation Using Deep Vision Transformers

Ghali

Akhloufi

Jmal³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

In this paper, we address the problem of forest fires’ early detection and segmentation in order to predict their spread and help with fire fighting. Techniques based on Convolutional Networks are the most used and have proven to be efficient at solving such a problem. However, they remain limited in modeling the long-range relationship between objects in the image, due to the intrinsic locality of convolution operators. In order to overcome this drawback, Transformers, designed for sequence-to-sequence prediction, have emerged as alternative architectures. They have recently been used to determine the global dependencies between input and output sequences using the self-attention mechanism. In this context, we present in this work the very first study, which explores the potential of vision Transformers in the context of forest fire segmentation. Two vision-based Transformers are used, TransUNet and MedT. Thus, we design two frameworks based on the former image Transformers adapted to our complex, non-structured environment, which we evaluate using varying backbones and we optimize for forest fires’ segmentation. Extensive evaluations of both frameworks revealed a performance superior to current methods. The proposed approaches achieved a state-of-the-art performance with an F1-score of 97.7% for TransUNet architecture and 96.0% for MedT architecture. The analysis of the results showed that these models reduce fire pixels mis-classifications thanks to the extraction of both global and local features, which provide finer detection of the fire’s shape.

show abstract

“…This model is validated across five European regions. It also showed a comparable result to the threshold of the delta Normalized Burn Ratio method [92].…”

Section: Post-fire Mapping Based Satellite Remote Sensing Imagerymentioning

confidence: 59%

Section: Post-fire Mapping Based Satellite Remote Sensing Imagerymentioning

confidence: 99%

Wildfire Segmentation Using Deep Vision Transformers

Ghali

Akhloufi

Jmal³

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Therefore, comparison of the results of this work obtained with single-instrument models with the results of other works in the field is presented to merely put the results of this work in context. Table VII presents a comparison between the results achieved by single-instrument models in this work and results achieved in [38], [39], [40], [41], [42], [43]. Only three out of the four single-instrument models are compared because, to the best of the authors knowledge, only one comprehensive evaluation of performance of Sentinel-3 SLSTR data for detection of fire affected areas exists to date [35], which, unfortunately, does not report any accuracy or precision metrics.…”

Section: Comparison Of Results To Other Work In the Fieldmentioning

confidence: 96%

Wildfire Detection From Multisensor Satellite Imagery Using Deep Semantic Segmentation

Rashkovetsky

Mauracher

Langer

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Deriving the extent of areas affected by wildfires is critical to fire management, protection of the population, damage assessment, and better understanding of the consequences of fires. In the last two decades, several algorithms utilizing data from Earth observation satellites have been developed to detect fire-affected areas. However, most of these methods require the establishment of complex functional relationships between numerous remote sensing data parameters. In contrast, more recently, deep learning has found its way into the application, having the advantage of being able to detect patterns in complex data by learning from examples automatically. In this paper, a workflow for the detection of fire-affected areas from satellite imagery acquired in the visible, infrared and microwave domains is described. Using this workflow, the fire detection potentials of four sources of freely available satellite imagery were investigated: The C-SAR instrument on board Sentinel-1, the MSI instrument on board Sentinel-2, the SLSTR instrument on board Sentinel-3 and the MODIS instrument on board Terra and Aqua. For each of them, a single-input convolutional neural network based on the well-known U-Net architecture was trained on a newly created dataset. The performance of the resulting four single-instrument models was evaluated in presence of clouds and in clear conditions.In addition, the potential of combining predictions from pairs of single-instrument models was investigated. The results show that fusion of Sentinel-2 and Sentinel-3 data provides the best detection rate in clear conditions, whereas the fusion of Sentinel-1 and Sentinel-2 data shows a significant benefit in cloudy weather.

show abstract

“…Copernicus Emergency Management Service (EMS) provides us with delineation products and grading products (https://emergency.copernicus.eu/mapping/list-of-activationsrapid, accessed on 9 April 2021) as precise annotation masks for corresponding training and testing images. These products have been used as reference data in burned area detection or burn severity estimation in previous studies [16,18,23,33,57,65,66]. Most EMS delineation or grading maps are derived from VHR post-fire images using WorldView-2 and/or SPOT6/7 with 1.5-2.0 m resolution under approximately 0% cloud coverage.…”

Section: Reference Datamentioning

confidence: 99%

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

Ban

Nascetti

2021

Remote Sensing

View full text Add to dashboard Cite

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.

show abstract

Double-Step U-Net: A Deep Learning-Based Approach for the Estimation of Wildfire Damage Severity through Sentinel-2 Satellite Data

Cited by 40 publications

References 40 publications

Wildfire Segmentation Using Deep Vision Transformers

Wildfire Segmentation Using Deep Vision Transformers

Wildfire Detection From Multisensor Satellite Imagery Using Deep Semantic Segmentation

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

Contact Info

Product

Resources

About