Burned Area Detection and Mapping: Intercomparison of Sentinel-1 and Sentinel-2 Based Algorithms over Tropical Africa

Tanase, Mihai A.; Belenguer-Plomer, Miguel A.; Roteta, Ekhi; Bastarrika, Aitor; Wheeler, James; Fernández-Carrillo, Ángel; Tansey, Kevin; Wiedemann, Werner; Navratil, Peter; Lohberger, Sandra; Siegert, Florian; Chuvieco, Emilio

doi:10.3390/rs12020334

Cited by 45 publications

(23 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The presence of cloud cover is one of the main limitations when using Landsat data for change detection as it is a common occurrence that impacts both the creation of a ground truth mask and the training of the models. Radar data can be used instead but at the cost of a significant loss of spectral information and possibly accuracy [71]. Studies have been carried using CNNs and Synthetic Aperture Radar (SAR) data to detect burnt areas with results similar to those found in this study [46,72] although to much smaller extents.…”

Section: Discussionsupporting

confidence: 64%

Performance Analysis of Deep Convolutional Autoencoders with Different Patch Sizes for Change Detection from Burnt Areas

Júnior

Carvalho

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Fire is one of the primary sources of damages to natural environments globally. Estimates show that approximately 4 million km2 of land burns yearly. Studies have shown that such estimates often underestimate the real extent of burnt land, which highlights the need to find better, state-of-the-art methods to detect and classify these areas. This study aimed to analyze the use of deep convolutional Autoencoders in the classification of burnt areas, considering different sample patch sizes. A simple Autoencoder and the U-Net and ResUnet architectures were evaluated. We collected Landsat 8 OLI+ data from three scenes in four consecutive dates to detect the changes specifically in the form of burnt land. The data were sampled according to four different sampling strategies to evaluate possible performance changes related to sampling window sizes. The training stage used two scenes, while the validation stage used the remaining scene. The ground truth change mask was created using the Normalized Burn Ratio (NBR) spectral index through a thresholding approach. The classifications were evaluated according to the F1 index, Kappa index, and mean Intersection over Union (mIoU) value. Results have shown that the U-Net and ResUnet architectures offered the best classifications with average F1, Kappa, and mIoU values of approximately 0.96, representing excellent classification results. We have also verified that a sampling window size of 256 by 256 pixels offered the best results.

show abstract

Section: Discussionsupporting

confidence: 64%

Performance Analysis of Deep Convolutional Autoencoders with Different Patch Sizes for Change Detection from Burnt Areas

Júnior

Carvalho

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…A qualidade de mapas originados por sensoriamento remoto é geralmente avaliada com base numa comparação sistemática com outros mapas também derivados por sensoriamento remoto (Libonati et al, 2015). A precisão dos resultados é geralmente caracterizada através da tabulação cruzada em relação aos conjuntos de dados de referência, contabilizando as coincidências e desacordos espaçotemporais: a abordagem é amplamente usada em projetos de mapeamento de área queimada (Tanase et al, 2020).…”

Section: Avaliação Da Classificaçãounclassified

Análise Espaço-Temporal de Áreas de Queimadas no Estado do Maranhão a partir de Imagens MODIS e Classificação Random Forest

Pacheco

Silva

2021

Anu. Inst. Geoc.

View full text Add to dashboard Cite

O mapeamento de áreas queimadas através de imagens de sensoriamento remoto apresenta uma série de questões importantes no gerenciamento espacial de estudos de detecção de focos de calor, análise de risco de incêndio, avaliação de danos e gerenciamento de processos de regeneração florestal. Neste estudo foi apresentada uma abordagem metodológica para mapeamento de áreas de queimadas no estado do Maranhão de 2001 a 2019 a partir de dados do satélite Terra/MODIS e do Algoritmo de Classificação Binária Random Forest. A avaliação da qualidade dos mapas gerados foi realizada a partir do produto padrão NASA MCD64A1 de áreas queimadas do sensor MODIS, que resultou num Coeficiente de Determinação geral (R²) de 0,55 e Correlação de Spearman de 0,78. O modelo Random Forest com 400 árvores permitiu avaliar a banda espectral de maior contribuição na classificação, bem como os erros relacionados ao número de árvores empregado. Algumas feições de áreas queimadas foram superestimadas, apresentando elevados erros de comissão. Os resultados mostraram que esta abordagem é útil para determinar áreas queimadas derivadas de dados de satélite de órbita polar. O modelo Random Forest mostrou-se aplicável em áreas de transição entre biomas. Constatou-se uma relação não linear entre a variabilidade espaço-temporal de incêndio e o clima em ecossistemas temperados. A Metodologia estabelecida e validada neste estudo poderá ser aplicada em outras regiões de clima temperado.

show abstract

“…Previous studies have shown the capabilities of SAR systems for forest change monitoring at lower scales [16,[27][28][29][30][31][32][33]. Most of these studies were based on pairwise or single epoque image comparison for detecting the changes between two specific dates.…”

Section: Detecting Forest Changes With Pairwise Analysis Of Sar Datamentioning

confidence: 99%

Continuous Forest Monitoring Using Cumulative Sums of Sentinel-1 Timeseries

et al. 2020

View full text Add to dashboard Cite

Forest degradation is recognized as a major environmental threat on a global scale. The recent rise in natural and anthropogenic destruction of forested ecosystems highlights the need for developing new, rapid, and accurate remote sensing monitoring systems, which capture forested land transformations. In spite of the great technological advances made in airborne and spaceborne sensors over the past decades, current Earth observation (EO) change detection methods still need to overcome numerous limitations. Optical sensors have been commonly used for detecting land use and land cover changes (LULCC), however, the requirement of certain technical and environmental conditions (e.g., sunlight, not cloud-coverage) restrict their use. More recently, synthetic aperture radar (SAR)-based change detection approaches have been used to overcome these technical limitations, but they commonly rely on static detection approaches (e.g., pre and post disturbance scenario comparison) that are slow to monitor change. In this context, this paper presents a novel approach for mapping forest structural changes in a continuous and near-real-time manner using dense Sentinel-1 image time-series. Our cumulative sum–spatial mean corrected (CUSU-SMC) algorithm approach is based on cumulative sum statistical analysis, which allows the continuous monitoring of radar signal variations, derived from forest structural change. Taking advantage of the high data availability offered by the Sentinel-1 (S-1) C-band constellation, we used an S-1 ground range detected (GRD) dual (VV, VH) polarization timeseries, formed by a total of 84 images, to monitor clear-cutting operations carried out in a Scottish forest during 2019. The analysis showed a user’s accuracy of 82% for the (conservative) detection approach. The use of a post-processing neighbor filter increased the detection performance to a user’s accuracy of 86% with an overall accuracy of 77% for areas of a minimum extent of 0.4 ha. To further validate the detection performance of the method, the CUSU-SMC change detector was tested against commonly-used pairwise change detection approaches for the same period. These results emphasize the capabilities of dense SAR time-series for environmental monitoring and provide a useful tool for optimizing national forest inventories.

show abstract

Burned Area Detection and Mapping: Intercomparison of Sentinel-1 and Sentinel-2 Based Algorithms over Tropical Africa

Cited by 45 publications

References 49 publications

Performance Analysis of Deep Convolutional Autoencoders with Different Patch Sizes for Change Detection from Burnt Areas

Performance Analysis of Deep Convolutional Autoencoders with Different Patch Sizes for Change Detection from Burnt Areas

Análise Espaço-Temporal de Áreas de Queimadas no Estado do Maranhão a partir de Imagens MODIS e Classificação Random Forest

Continuous Forest Monitoring Using Cumulative Sums of Sentinel-1 Timeseries

Contact Info

Product

Resources

About