Burned Area Mapping Using SAR and Multispectral Data Integration via Generative Adversarial Networks

Multispectral data have been successfully exploited in the literature for burned area detection. However, the occurrence of suitable weather and illumination conditions limits their availability, especially at high latitudes and tropical environments. The usage of synthetic aperture radar (SAR) data, due to their all-weather and all-time characteristics, can potentially be a breakthrough, but it is still underexploited due to the ambiguity of the radar reflectivity of burned vegetation. The recent availability of generative networks is providing a new tool for combining such complementary information. This paper introduces a new framework for burned area mapping based on image domain translation. The main novelties against the related literature are the i) exploitation of SAR phase information as an input for the translation and the pointing to multispectral indices as a translation target. In particular, a bi-temporal coherent change detection-oriented SAR product is used as input for generative networks targeting the post-event normalized burned ratio index. Then, generated data are combined with native optical pre-event ones to produce the difference image typically used for thresholding segmentation. Experimental results obtained using a dataset extracted from the Copernicus Emergency Management Service database show that the proposed methodology outperforms the literature reaching a burned area mapping accuracy of above 90% with negligible false alarm, thus introducing a new robust solution for the integration of SAR and multispectral data.

• Publication year

  2025

• Venue

  IEEE Access

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/ACCESS.2025.3593878
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Burned Areas Mapping Using Sentinel-2 Data and a Rao’s Q Index-Based Change Detection Approach: A Case Study in Three Mediterranean Islands’ Wildfires (2019–2022)

  2025cited by this paper
• Burned-Area Mapping Using Post-Fire PlanetScope Images and a Convolutional Neural Network

  2024cited by this paper
• Multitemporal SAR-to-Optical Image Translation Using Pix2Pix With Application to Vegetation Monitoring

  2024cited by this paper
• Stripe Error Correction for Landsat-7 Using Deep Learning

  2024cited by this paper
• GAN-based SAR and optical image translation for wildfire impact assessment using multi-source remote sensing data

  2023influential reference
• CYCLE-GAN BASED FEATURE TRANSLATION FOR OPTICAL-SAR DATA IN BURNED AREA MAPPING

  2023cited by this paper
• CFRWD-GAN for SAR-to-Optical Image Translation

  2023cited by this paper
• Forest fire area detection using Sentinel-2 data: Case of the Beni Salah national forest ‒ Algeria

  2023cited by this paper
• Urban Area Mapping Using Multitemporal SAR Images in Combination with Self-Organizing Map Clustering and Object-Based Image Analysis

  2022influential reference
• A Review of Image Super-Resolution Approaches Based on Deep Learning and Applications in Remote Sensing

  2022cited by this paper
• Benchmarking Framework for Multitemporal SAR Despeckling

  2022cited by this paper
• Assessing the Utility of Sentinel-1 Coherence Time Series for Temperate and Tropical Forest Mapping

  2021cited by this paper
• A SAR-to-Optical Image Translation Method Based on PIX2PIX

  2021cited by this paper
• SAR Imaging Distortions Induced by Topography: A Compact Analytical Formulation for Radiometric Calibration

  2021cited by this paper
• Learning U-Net without forgetting for near real-time wildfire monitoring by the fusion of SAR and optical time series

  2021cited by this paper
• Semantic Unsupervised Change Detection of Natural Land Cover With Multitemporal Object-Based Analysis on SAR Images

  2021cited by this paper
• CNN-based burned area mapping using radar and optical data

  2021cited by this paper
• Attention Consistent Network for Remote Sensing Scene Classification

  2021cited by this paper
• Earth Environmental Monitoring Using Multi-Temporal Synthetic Aperture Radar: A Critical Review of Selected Applications

  2021cited by this paper
• Satellite Remote Sensing Contributions to Wildland Fire Science and Management

  2020cited by this paper
• Improving Co-Registration for Sentinel-1 SAR and Sentinel-2 Optical Images

  2020cited by this paper
• Quality Assessment of SAR-to-Optical Image Translation

  2020cited by this paper
• Near Real-Time Wildfire Progression Monitoring with Sentinel-1 SAR Time Series and Deep Learning

  2020cited by this paper
• Historical background and current developments for mapping burned area from satellite Earth observation

  2019cited by this paper
• SAR-to-Optical Image Translation Using Supervised Cycle-Consistent Adversarial Networks

  2019cited by this paper
• Applicability of the MultiTemporal Coherence Approach to Sentinel-1 for the Detection and Delineation of Burnt Areas in the Context of the Copernicus Emergency Management Service

  2019cited by this paper
• GENERATIVE ADVERSARIAL NETS

  2018influential reference
• Which Training Methods for GANs do actually Converge?

  2018cited by this paper
• Relationships of S-Band Radar Backscatter and Forest Aboveground Biomass in Different Forest Types

  2017cited by this paper
• Effect of the Vegetation Fire on Backscattering: An Investigation Based on Sentinel-1 Observations

  2017cited by this paper
• Unsupervised Image-to-Image Translation Networks

  2017cited by this paper
• Generative Adversarial Networks: An Overview

  2017influential reference
• An end-user-oriented framework for the classification of multitemporal SAR images

  2016cited by this paper
• Image-to-Image Translation with Conditional Adversarial Networks

  2016influential reference
• C-Band SAR Backscatter Evaluation of 2008 Gallipoli Forest Fire

  2015cited by this paper
• U-Net: Convolutional Networks for Biomedical Image Segmentation

  2015cited by this paper
• Integration of Optical and SAR Data for Burned Area Mapping in Mediterranean Regions

  2015cited by this paper
• Climate-induced variations in global wildfire danger from 1979 to 2013

  2015cited by this paper
• Benchmarking Framework for SAR Despeckling

  2014cited by this paper
• On the SAR Backscatter of Burned Forests: A Model-Based Study in C-Band, Over Burned Pine Canopies

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014influential reference
• Conditional Generative Adversarial Nets

  2014cited by this paper
• Detecting post-fire burn severity and vegetation recovery using multitemporal remote sensing spectral indices and field-collected composite burn index data in a ponderosa pine forest

  2011cited by this paper
• The temporal dimension of differenced Normalized Burn Ratio (dNBR) fire/burn severity studies: the case of the large 2007 Peloponnese wildfires in Greece.

  2010cited by this paper
• Sensitivity of X-, C-, and L-Band SAR Backscatter to Burn Severity in Mediterranean Pine Forests

  2010cited by this paper
• Object based image analysis for remote sensing

  2010cited by this paper
• Fire intensity, fire severity and burn severity: a brief review and suggested usage

  2009influential reference
• Remote sensing information for fire management and fire effects assessment

  2007cited by this paper
• Regionally adaptable dNBR-based algorithm for burned area mapping from MODIS data

  2007cited by this paper
• What's under the ROC? An Introduction to Receiver Operating Characteristics Curves

  2007influential reference
• Global cloud cover trends inferred from two decades of HIRS observations

  2005cited by this paper
• Image quality assessment: from error visibility to structural similarity

  2004cited by this paper
• Radar Interferometry: Data Interpretation and Error Analysis

  2001cited by this paper
• SIGMA: A Knowledge-Based Aerial Image Understanding System

  1990cited by this paper
• L-Band Radar Backscatter Modeling of Forest Stands

  1987cited by this paper
• SAR-to-optical image translation based on improved CGAN

  year unknowncited by this paper

• No citing papers are available for this paper.