remotesensing-logo

Journal Browser

Journal Browser

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

A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Environmental Remote Sensing".

Deadline for manuscript submissions: closed (31 December 2021) | Viewed by 25299

Special Issue Editor

Special Issue Information

Dear Colleagues,

Remote sensing technologies have long been considered as a key tool for fire data, science, modelling, management, and monitoring. The most recent developments in computer technology, data processing, artificial intelligence (AI), deep learning approaches, and geospatial data mining techniques, enable advanced dynamic modelling, tools, data integration, and assimilation schemes, and are expected to significantly support and improve fire science and operational applications. Recently, the availability of new sensors from satellite, aerial, drone, and ground, along with the free access to large archives of data, has opened new perspectives for both fire science and applications. We invite you to submit articles on topics including, but not limited to, the following:

  • Earth observation (optical, SAR, UAV, and LiDAR) as a tool for data science and operational applications
  • Advanced geospatial data mining techniques
  • Integration of satellite, aerial/drone, and in situ observation in the Copernicus Era
  • Fire disturbance monitoring at multiple spatio-temporal scales
  • Deep learning approaches for fire science and applications
  • Advances in remote sensing of forest fire fuel mapping
  • Data integration for fire and post fire geo-hazards risk mitigation and management
  • Earth big data for monitoring and mapping fire and post-fire induced risk
  • Fusion and integration of data and information from multiple sources
  • Integration of RS with climate and meteorological data and forecasting
  • New tools and methods for fire monitoring and mitigation strategies

Dr. Rosa Lasaponara
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2500 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Fire 
  • Earth observation 
  • Copernicus
  • Data integration

Published Papers (12 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Estimating Next Day’s Forest Fire Risk via a Complete Machine Learning Methodology
Remote Sens. 2022, 14(5), 1222; https://doi.org/10.3390/rs14051222 - 02 Mar 2022
Viewed by 1000
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
Show Figures

Figure 1

Article
FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection
Remote Sens. 2022, 14(4), 1007; https://doi.org/10.3390/rs14041007 - 18 Feb 2022
Viewed by 1097
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
Show Figures

Graphical abstract

Article
Supervised Machine Learning Approaches on Multispectral Remote Sensing Data for a Combined Detection of Fire and Burned Area
Remote Sens. 2022, 14(3), 657; https://doi.org/10.3390/rs14030657 - 29 Jan 2022
Cited by 3 | Viewed by 1193
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
Show Figures

Figure 1

Article
Spatial Prioritization for Wildfire Mitigation by Integrating Heterogeneous Spatial Data: A New Multi-Dimensional Approach for Tropical Rainforests
Remote Sens. 2022, 14(3), 543; https://doi.org/10.3390/rs14030543 - 24 Jan 2022
Cited by 10 | Viewed by 1937
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
Show Figures

Figure 1

Article
GIS-Based Forest Fire Risk Model: A Case Study in Laoshan National Forest Park, Nanjing
Remote Sens. 2021, 13(18), 3704; https://doi.org/10.3390/rs13183704 - 16 Sep 2021
Cited by 7 | Viewed by 1226
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
Show Figures

Graphical abstract

Article
Uni-Temporal Multispectral Imagery for Burned Area Mapping with Deep Learning
Remote Sens. 2021, 13(8), 1509; https://doi.org/10.3390/rs13081509 - 14 Apr 2021
Cited by 7 | Viewed by 1433
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
Show Figures

Graphical abstract

Article
Forest Fire Susceptibility Prediction Based on Machine Learning Models with Resampling Algorithms on Remote Sensing Data
Remote Sens. 2020, 12(22), 3682; https://doi.org/10.3390/rs12223682 - 10 Nov 2020
Cited by 21 | Viewed by 2211
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
Show Figures

Graphical abstract

Article
Fire Detection and Fire Radiative Power in Forests and Low-Biomass Lands in Northeast Asia: MODIS versus VIIRS Fire Products
Remote Sens. 2020, 12(18), 2870; https://doi.org/10.3390/rs12182870 - 04 Sep 2020
Cited by 12 | Viewed by 3019
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
Show Figures

Graphical abstract

Article
An Automatic Processing Chain for Near Real-Time Mapping of Burned Forest Areas Using Sentinel-2 Data
Remote Sens. 2020, 12(4), 674; https://doi.org/10.3390/rs12040674 - 18 Feb 2020
Cited by 24 | Viewed by 2039
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
Show Figures

Graphical abstract

Article
Burned Area Detection and Mapping: Intercomparison of Sentinel-1 and Sentinel-2 Based Algorithms over Tropical Africa
Remote Sens. 2020, 12(2), 334; https://doi.org/10.3390/rs12020334 - 20 Jan 2020
Cited by 29 | Viewed by 3439
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
Show Figures

Graphical abstract

Article
Exploring the Potential of C-Band SAR in Contributing to Burn Severity Mapping in Tropical Savanna
Remote Sens. 2020, 12(1), 49; https://doi.org/10.3390/rs12010049 - 20 Dec 2019
Cited by 9 | Viewed by 3346
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
Show Figures

Graphical abstract

Article
Temporal Decorrelation of C-Band Backscatter Coefficient in Mediterranean Burned Areas
Remote Sens. 2019, 11(22), 2661; https://doi.org/10.3390/rs11222661 - 14 Nov 2019
Cited by 7 | Viewed by 1296
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
Show Figures

Figure 1

Back to TopTop