Remote Sensing

Research

29 pages, 3343 KiB

Open AccessArticle

Estimating Next Day’s Forest Fire Risk via a Complete Machine Learning Methodology

by Alexis Apostolakis, Stella Girtsou, Giorgos Giannopoulos, Nikolaos S. Bartsotas and Charalampos Kontoes

Remote Sens. 2022, 14(5), 1222; https://doi.org/10.3390/rs14051222 - 2 Mar 2022

Cited by 9 | Viewed by 4571

Abstract

Next day wildfire prediction is an open research problem with significant environmental, social, and economic impact since it can produce methods and tools directly exploitable by fire services, assisting, thus, in the prevention of fire occurrences or the mitigation of their effects. It [...] Read more.

Next day wildfire prediction is an open research problem with significant environmental, social, and economic impact since it can produce methods and tools directly exploitable by fire services, assisting, thus, in the prevention of fire occurrences or the mitigation of their effects. It consists in accurately predicting which areas of a territory are at higher risk of fire occurrence each next day, exploiting solely information obtained up until the previous day. The task’s requirements in spatial granularity and scale of predictions, as well as the extreme imbalance of the data distribution render it a rather demanding and difficult to accurately solve the problem. This is reflected in the current literature, where most existing works handle a simplified or limited version of the problem. Taking into account the above problem specificities, in this paper, we present a machine learning methodology that effectively (sensitivity > 90%, specificity > 65%) and efficiently performs next day fire prediction, in rather high spatial granularity and in the scale of a country. The key points of the proposed approach are summarized in: (a) the utilization of an extended set of fire driving factors (features), including topography-related, meteorology-related and Earth Observation (EO)-related features, as well as historical information of areas’ proneness to fire occurrence; (b) the deployment of a set of state-of-the-art classification algorithms that are properly tuned/optimized on the setting; (c) two alternative cross-validation schemes along with custom validation measures that allow the optimal and sound training of classification models, as well as the selection of different models, in relation to the desired trade-off between sensitivity (ratio of correctly identified fire areas) and specificity (ratio of correctly identified non-fire areas). In parallel, we discuss pitfalls, intuitions, best practices, and directions for further investigation derived from our analysis and experimental evaluation. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Figure 1

15 pages, 1222 KiB

Open AccessArticle

FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection

by Anshuman Dewangan, Yash Pande, Hans-Werner Braun, Frank Vernon, Ismael Perez, Ilkay Altintas, Garrison W. Cottrell and Mai H. Nguyen

Remote Sens. 2022, 14(4), 1007; https://doi.org/10.3390/rs14041007 - 18 Feb 2022

Cited by 33 | Viewed by 6745

Abstract

The size and frequency of wildland fires in the western United States have dramatically increased in recent years. On high-fire-risk days, a small fire ignition can rapidly grow and become out of control. Early detection of fire ignitions from initial smoke can assist [...] Read more.

The size and frequency of wildland fires in the western United States have dramatically increased in recent years. On high-fire-risk days, a small fire ignition can rapidly grow and become out of control. Early detection of fire ignitions from initial smoke can assist the response to such fires before they become difficult to manage. Past deep learning approaches for wildfire smoke detection have suffered from small or unreliable datasets that make it difficult to extrapolate performance to real-world scenarios. In this work, we present the Fire Ignition Library (FIgLib), a publicly available dataset of nearly 25,000 labeled wildfire smoke images as seen from fixed-view cameras deployed in Southern California. We also introduce SmokeyNet, a novel deep learning architecture using spatiotemporal information from camera imagery for real-time wildfire smoke detection. When trained on the FIgLib dataset, SmokeyNet outperforms comparable baselines and rivals human performance. We hope that the availability of the FIgLib dataset and the SmokeyNet architecture will inspire further research into deep learning methods for wildfire smoke detection, leading to automated notification systems that reduce the time to wildfire response. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Graphical abstract

32 pages, 29641 KiB

Open AccessArticle

Supervised Machine Learning Approaches on Multispectral Remote Sensing Data for a Combined Detection of Fire and Burned Area

by Janine Florath and Sina Keller

Remote Sens. 2022, 14(3), 657; https://doi.org/10.3390/rs14030657 - 29 Jan 2022

Cited by 22 | Viewed by 4857

Abstract

Bushfires pose a severe risk, among others, to humans, wildlife, and infrastructures. Rapid detection of fires is crucial for fire-extinguishing activities and rescue missions. Besides, mapping burned areas also supports evacuation and accessibility to emergency facilities. In this study, we propose a generic [...] Read more.

Bushfires pose a severe risk, among others, to humans, wildlife, and infrastructures. Rapid detection of fires is crucial for fire-extinguishing activities and rescue missions. Besides, mapping burned areas also supports evacuation and accessibility to emergency facilities. In this study, we propose a generic approach for detecting fires and burned areas based on machine learning (ML) approaches and remote sensing data. While most studies investigated either the detection of fires or mapping burned areas, we addressed and evaluated, in particular, the combined detection on three selected case study regions. Multispectral Sentinel-2 images represent the input data for the supervised ML models. First, we generated the reference data for the three target classes, burned, unburned, and fire, since no reference data were available. Second, the three regional fire datasets were preprocessed and divided into training, validation, and test subsets according to a defined schema. Furthermore, an undersampling approach ensured the balancing of the datasets. Third, seven selected supervised classification approaches were used and evaluated, including tree-based models, a self-organizing map, an artificial neural network, and a one-dimensional convolutional neural network (1D-CNN). All selected ML approaches achieved satisfying classification results. Moreover, they performed a highly accurate fire detection, while separating burned and unburned areas was slightly more challenging. The 1D-CNN and extremely randomized tree were the best-performing models with an overall accuracy score of 98% on the test subsets. Even on an unknown test dataset, the 1D-CNN achieved high classification accuracies. This generalization is even more valuable for any use-case scenario, including the organization of fire-fighting activities or civil protection. The proposed combined detection could be extended and enhanced with crowdsourced data in further studies. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Figure 1

26 pages, 15049 KiB

Open AccessArticle

Spatial Prioritization for Wildfire Mitigation by Integrating Heterogeneous Spatial Data: A New Multi-Dimensional Approach for Tropical Rainforests

by Anjar Dimara Sakti, Adam Irwansyah Fauzi, Wataru Takeuchi, Biswajeet Pradhan, Masaru Yarime, Cristina Vega-Garcia, Elprida Agustina, Dionisius Wibisono, Tania Septi Anggraini, Megawati Oktaviani Theodora, Desi Ramadhanti, Miqdad Fadhil Muhammad, Muhammad Aufaristama, Agung Mahadi Putra Perdana and Ketut Wikantika

Remote Sens. 2022, 14(3), 543; https://doi.org/10.3390/rs14030543 - 24 Jan 2022

Cited by 19 | Viewed by 6604

Abstract

Wildfires drive deforestation that causes various losses. Although many studies have used spatial approaches, a multi-dimensional analysis is required to determine priority areas for mitigation. This study identified priority areas for wildfire mitigation in Indonesia using a multi-dimensional approach including disaster, environmental, historical, [...] Read more.

Wildfires drive deforestation that causes various losses. Although many studies have used spatial approaches, a multi-dimensional analysis is required to determine priority areas for mitigation. This study identified priority areas for wildfire mitigation in Indonesia using a multi-dimensional approach including disaster, environmental, historical, and administrative parameters by integrating 20 types of multi-source spatial data. Spatial data were combined to produce susceptibility, carbon stock, and carbon emission models that form the basis for prioritization modelling. The developed priority model was compared with historical deforestation data. Legal aspects were evaluated for oil-palm plantations and mining with respect to their impact on wildfire mitigation. Results showed that 379,516 km² of forests in Indonesia belong to the high-priority category and most of these are located in Sumatra, Kalimantan, and North Maluku. Historical data suggest that 19.50% of priority areas for wildfire mitigation have experienced deforestation caused by wildfires over the last ten years. Based on legal aspects of land use, 5.2% and 3.9% of high-priority areas for wildfire mitigation are in oil palm and mining areas, respectively. These results can be used to support the determination of high-priority areas for the REDD+ program and the evaluation of land use policies. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Figure 1

21 pages, 3885 KiB

Open AccessArticle

GIS-Based Forest Fire Risk Model: A Case Study in Laoshan National Forest Park, Nanjing

by Pengcheng Zhao, Fuquan Zhang, Haifeng Lin and Shuwen Xu

Remote Sens. 2021, 13(18), 3704; https://doi.org/10.3390/rs13183704 - 16 Sep 2021

Cited by 35 | Viewed by 6756

Abstract

Fire risk prediction is significant for fire prevention and fire resource allocation. Fire risk maps are effective methods for quantifying regional fire risk. Laoshan National Forest Park has many precious natural resources and tourist attractions, but there is no fire risk assessment model. [...] Read more.

Fire risk prediction is significant for fire prevention and fire resource allocation. Fire risk maps are effective methods for quantifying regional fire risk. Laoshan National Forest Park has many precious natural resources and tourist attractions, but there is no fire risk assessment model. This paper aims to construct the forest fire risk map for Nanjing Laoshan National Forest Park. The forest fire risk model is constructed by factors (altitude, aspect, topographic wetness index, slope, distance to roads and populated areas, normalized difference vegetation index, and temperature) which have a great influence on the probability of inducing fire in Laoshan. Since the importance of factors in different study areas is inconsistent, it is necessary to calculate the significance of each factor of Laoshan. After the significance calculation is completed, the fire risk model of Laoshan can be obtained. Then, the fire risk map can be plotted based on the model. This fire risk map can clarify the fire risk level of each part of the study area, with 16.97% extremely low risk, 48.32% low risk, 17.35% moderate risk, 12.74% high risk and 4.62% extremely high risk, and it is compared with the data of MODIS fire anomaly point. The result shows that the accuracy of the risk map is 76.65%. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Graphical abstract

29 pages, 49907 KiB

Open AccessArticle

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

by Xikun Hu, Yifang Ban and Andrea Nascetti

Remote Sens. 2021, 13(8), 1509; https://doi.org/10.3390/rs13081509 - 14 Apr 2021

Cited by 52 | Viewed by 5794

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 [...] Read more.

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. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Graphical abstract

24 pages, 13923 KiB

Open AccessArticle

Forest Fire Susceptibility Prediction Based on Machine Learning Models with Resampling Algorithms on Remote Sensing Data

by Bahareh Kalantar, Naonori Ueda, Mohammed O. Idrees, Saeid Janizadeh, Kourosh Ahmadi and Farzin Shabani

Remote Sens. 2020, 12(22), 3682; https://doi.org/10.3390/rs12223682 - 10 Nov 2020

Cited by 91 | Viewed by 9079

Abstract

This study predicts forest fire susceptibility in Chaloos Rood watershed in Iran using three machine learning (ML) models—multivariate adaptive regression splines (MARS), support vector machine (SVM), and boosted regression tree (BRT). The study utilizes 14 set of fire predictors derived from vegetation indices, [...] Read more.

This study predicts forest fire susceptibility in Chaloos Rood watershed in Iran using three machine learning (ML) models—multivariate adaptive regression splines (MARS), support vector machine (SVM), and boosted regression tree (BRT). The study utilizes 14 set of fire predictors derived from vegetation indices, climatic variables, environmental factors, and topographical features. To assess the suitability of the models and estimating the variance and bias of estimation, the training dataset obtained from the Natural Resources Directorate of Mazandaran province was subjected to resampling using cross validation (CV), bootstrap, and optimism bootstrap techniques. Using variance inflation factor (VIF), weight indicating the strength of the spatial relationship of the predictors to fire occurrence was assigned to each contributing variable. Subsequently, the models were trained and validated using the receiver operating characteristics (ROC) area under the curve (AUC) curve. Results of the model validation based on the resampling techniques (non, 5- and 10-fold CV, bootstrap and optimism bootstrap) produced AUC values of 0.78, 0.88, 0.90, 0.86 and 0.83 for the MARS model; 0.82, 0.82, 0.89, 0.87, 0.84 for the SVM and 0.87, 0.90, 0.90, 0.90, 0.91 for the BRT model. Across the individual model, the 10-fold CV performed best in MARS and SVM with AUC values of 0.90 and 0.89. Overall, the BRT outperformed the other models in all ramification with highest AUC value of 0.91 using optimism bootstrap resampling algorithm. Generally, the resampling process enhanced the prediction performance of all the models. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Graphical abstract

20 pages, 7192 KiB

Open AccessArticle

Fire Detection and Fire Radiative Power in Forests and Low-Biomass Lands in Northeast Asia: MODIS versus VIIRS Fire Products

by Yuyun Fu, Rui Li, Xuewen Wang, Yves Bergeron, Osvaldo Valeria, Raphaël D. Chavardès, Yipu Wang and Jiheng Hu

Remote Sens. 2020, 12(18), 2870; https://doi.org/10.3390/rs12182870 - 4 Sep 2020

Cited by 40 | Viewed by 8958

Abstract

Fire omission and commission errors, and the accuracy of fire radiative power (FRP) from satellite moderate-resolution impede the studies on fire regimes and FRP-based fire emissions estimation. In this study, we compared the accuracy between the extensively used 1-km fire product of MYD14 [...] Read more.

Fire omission and commission errors, and the accuracy of fire radiative power (FRP) from satellite moderate-resolution impede the studies on fire regimes and FRP-based fire emissions estimation. In this study, we compared the accuracy between the extensively used 1-km fire product of MYD14 from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the 375-m fire product of VNP14IMG from the Visible Infrared Imaging Radiometer Suite (VIIRS) in Northeastern Asia using data from 2012–2017. We extracted almost simultaneous observation of fire detection and FRP from MODIS-VIIRS overlapping orbits from the two fire products, and identified and removed duplicate fire detections and corresponding FRP in each fire product. We then compared the performance of the two products between forests and low-biomass lands (croplands, grasslands, and herbaceous vegetation). Among fire pixels detected by VIIRS, 65% and 83% were missed by MODIS in forests and low-biomass lands, respectively; whereas associated omission rates by VIIRS for MODIS fire pixels were 35% and 53%, respectively. Commission errors of the two fire products, based on the annual mean measurements of burned area by Landsat, decreased with increasing FRP per fire pixel, and were higher in low-biomass lands than those in forests. Monthly total FRP from MODIS was considerably lower than that from VIIRS due to more fire omission by MODIS, particularly in low-biomass lands. However, for fires concurrently detected by both sensors, total FRP was lower with VIIRS than with MODIS. This study contributes to a better understanding of fire detection and FRP retrieval performance between MODIS and its successor VIIRS, providing valuable information for using those data in the study of fire regimes and FRP-based fire emission estimation. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Graphical abstract

27 pages, 10237 KiB

Open AccessArticle

An Automatic Processing Chain for Near Real-Time Mapping of Burned Forest Areas Using Sentinel-2 Data

by Luca Pulvirenti, Giuseppe Squicciarino, Elisabetta Fiori, Paolo Fiorucci, Luca Ferraris, Dario Negro, Andrea Gollini, Massimiliano Severino and Silvia Puca

Remote Sens. 2020, 12(4), 674; https://doi.org/10.3390/rs12040674 - 18 Feb 2020

Cited by 49 | Viewed by 5437

Abstract

A fully automated processing chain for near real-time mapping of burned forest areas using Sentinel-2 multispectral data is presented. The acronym AUTOBAM (AUTOmatic Burned Areas Mapper) is used to denote it. AUTOBAM is conceived to work daily at a national scale for the [...] Read more.

A fully automated processing chain for near real-time mapping of burned forest areas using Sentinel-2 multispectral data is presented. The acronym AUTOBAM (AUTOmatic Burned Areas Mapper) is used to denote it. AUTOBAM is conceived to work daily at a national scale for the Italian territory to support the Italian Civil Protection Department in the management of one of the major natural hazards, which affects the territory. The processing chain includes a Sentinel-2 data procurement component, an image processing algorithm, and the delivery of the map to the end-user. The data procurement component searches every day for the most updated products into different archives. The image processing part represents the core of AUTOBAM and implements an algorithm for burned forest areas mapping that uses, as fundamental parameters, the relativized form of the delta normalized burn ratio and the normalized difference vegetation index. The minimum mapping unit is 1 ha. The algorithm implemented in the image processing block is validated off-line using maps of burned areas produced by the Copernicus Emergency Management Service. The results of the validation shows an overall accuracy (considering the classes of burned and unburned areas) larger than 95% and a kappa coefficient larger than 80%. For what concerns the class of burned areas, the commission error is around 1%−3%, except for one case where it reaches 25%, while the omission error ranges between 6% and 25%. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Graphical abstract

15 pages, 3506 KiB

Open AccessArticle

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

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

Remote Sens. 2020, 12(2), 334; https://doi.org/10.3390/rs12020334 - 20 Jan 2020

Cited by 51 | Viewed by 8525

Abstract

This study provides a comparative analysis of two Sentinel-1 and one Sentinel-2 burned area (BA) detection and mapping algorithms over 10 test sites (100 × 100 km) in tropical and sub-tropical Africa. Depending on the site, the burned area was mapped at different [...] Read more.

This study provides a comparative analysis of two Sentinel-1 and one Sentinel-2 burned area (BA) detection and mapping algorithms over 10 test sites (100 × 100 km) in tropical and sub-tropical Africa. Depending on the site, the burned area was mapped at different time points during the 2015–2016 fire seasons. The algorithms relied on diverse burned area (BA) mapping strategies regarding the data used (i.e., surface reflectance, backscatter coefficient, interferometric coherence) and the detection method. Algorithm performance was compared by evaluating the detected BA agreement with reference fire perimeters independently derived from medium resolution optical imagery (i.e., Landsat 8, Sentinel-2). The commission (CE) and omission errors (OE), as well as the Dice coefficient (DC) for burned pixels, were compared. The mean OE and CE were 33% and 31% for the optical-based Sentinel-2 time-series algorithm and increased to 66% and 36%, respectively, for the radar backscatter coefficient-based algorithm. For the coherence based radar algorithm, OE and CE reached 72% and 57%, respectively. When considering all tiles, the optical-based algorithm provided a significant increase in agreement over the Synthetic Aperture Radar (SAR) based algorithms that might have been boosted by the use of optical datasets when generating the reference fire perimeters. The analysis suggested that optical-based algorithms provide for a significant increase in accuracy over the radar-based algorithms. However, in regions with persistent cloud cover, the radar sensors may provide a complementary data source for wall to wall BA detection. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Graphical abstract

19 pages, 16658 KiB

Open AccessArticle

Exploring the Potential of C-Band SAR in Contributing to Burn Severity Mapping in Tropical Savanna

by Marius B. Philipp and Shaun R. Levick

Remote Sens. 2020, 12(1), 49; https://doi.org/10.3390/rs12010049 - 20 Dec 2019

Cited by 19 | Viewed by 6699

Abstract

The ability to map burn severity and to understand how it varies as a function of time of year and return frequency is an important tool for landscape management and carbon accounting in tropical savannas. Different indices based on optical satellite imagery are [...] Read more.

The ability to map burn severity and to understand how it varies as a function of time of year and return frequency is an important tool for landscape management and carbon accounting in tropical savannas. Different indices based on optical satellite imagery are typically used for mapping fire scars and for estimating burn severity. However, cloud cover is a major limitation for analyses using optical data over tropical landscapes. To address this pitfall, we explored the suitability of C-band Synthetic Aperture Radar (SAR) data for detecting vegetation response to fire, using experimental fires in northern Australia. Pre- and post-fire results from Sentinel-1 C-band backscatter intensity data were compared to those of optical satellite imagery and were corroborated against structural changes on the ground that we documented through terrestrial laser scanning (TLS). Sentinel-1 C-band backscatter (VH) proved sensitive to the structural changes imparted by fire and was correlated with the Normalised Burn Ratio (NBR) derived from Sentinel-2 optical data. Our results suggest that C-band SAR holds potential to inform the mapping of burn severity in savannas, but further research is required over larger spatial scales and across a broader spectrum of fire regime conditions before automated products can be developed. Combining both Sentinel-1 SAR and Sentinel-2 multi-spectral data will likely yield the best results for mapping burn severity under a range of weather conditions. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Graphical abstract

19 pages, 3040 KiB

Open AccessArticle

Temporal Decorrelation of C-Band Backscatter Coefficient in Mediterranean Burned Areas

by Miguel A. Belenguer-Plomer, Emilio Chuvieco and Mihai A. Tanase

Remote Sens. 2019, 11(22), 2661; https://doi.org/10.3390/rs11222661 - 14 Nov 2019

Cited by 8 | Viewed by 3288

Abstract

Burned area algorithms from radar images are often based on temporal differences between pre- and post-fire backscatter values. However, such differences may occur long past the fire event, an effect known as temporal decorrelation. Improvements in radar-based burned areas monitoring depend on a [...] Read more.

Burned area algorithms from radar images are often based on temporal differences between pre- and post-fire backscatter values. However, such differences may occur long past the fire event, an effect known as temporal decorrelation. Improvements in radar-based burned areas monitoring depend on a better understanding of the temporal decorrelation effects as well as its sources. This paper analyses the temporal decorrelation of the Sentinel-1 C-band backscatter coefficient over burned areas in Mediterranean ecosystems. Several environmental variables influenced the radar scattering such as fire severity, post-fire vegetation recovery, water content, soil moisture, and local slope and aspect were analyzed. The ensemble learning method random forests was employed to estimate the importance of these variables to the decorrelation process by land cover classes. Temporal decorrelation was observed for over 32% of the burned pixels located within the study area. Fire severity, vegetation water content, and soil moisture were the main drivers behind temporal decorrelation processes and are of the utmost importance for areas detected as burned immediately after fire events. When burned areas were detected long after fire (decorrelated areas), due to reduced backscatter coefficient variations between pre- to post-fire acquisitions, water content (soil and vegetation) was the main driver behind the backscatter coefficient changes. Therefore, for efficient synthetic aperture radar (SAR)-based monitoring of burned areas, detection, and mapping algorithms need to account for the interaction between fire impact and soil and vegetation water content. Full article

(This article belongs to the Special Issue Remote Sensing of Forest Fire: Data, Science and Operational Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Remote Sensing of Forest Fire: Data, Science and Operational Applications

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (12 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI