Advances in Forest Fire Behaviour Modelling Using Remote Sensing

A special issue of Fire (ISSN 2571-6255).

Deadline for manuscript submissions: closed (19 July 2023) | Viewed by 37374

Special Issue Editors

GeoEnvironmental Cartography and Remote Sensing Group (CGAT), Universitat Politècnica de València, Camino de Vera s/n, 46022 Valencia, Spain
Interests: lidar for forest structure analysis; 3D fire behaviour models; object-based feature extraction and classification; land use/land cover change analysis
Special Issues, Collections and Topics in MDPI journals
U.S. Department of Agriculture, Forest Service Rocky Mountain Research Station, Moscow, ID 83843, USA
Interests: landscape, vegetation, and fire ecology; remote sensing of vegetation patterns and processes; forest and rangeland ecology and management; empirical modeling of spatially explicit ecological data
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Accurate information about three-dimensional canopy structure and heterogeneous wildland fuel across the landscape is necessary for fire behaviour modelling system predictions. Recently, physically-based fire behaviour models have been developed to represent fuels and fire behaviour processes, showing promise for examination of fuel/fire/atmosphere interactions. However, these models require very high spatial detail, such as locations and dimensions of individual trees, species composition, spatial distributions of understory fuels, 3D distribution of fuel mass and bulk density at voxel level, fuel surface area and moisture content. Remote sensing tools and methods are starting to play an important role in the acquisition of a variety of data and in the estimation of such parameters at finer spatial scales, so they can be used as input in fire behavior models, where bulk density of canopy, understory and surface fuels must be estimated and quantified at voxel level, and fuel moisture content, from leaves, pine needles and fine roundwood at tree or patch level. This multiscale concept can only be achieved by using different types of acquisition devices and techniques capable to produce models at distinct levels of detail. The wide range of platforms (satellites, aerial, UAS and field-based) and sensors (multi and hyper-spectral, RADAR, LiDAR) nowadays available for data acquisition offer excellent prospects for addressing this multiscale problem.

In this special issue, submissions describing new advances in data acquisition and methods for fire behaviour modelling, including integration of platforms and sensors, estimation of fuel parameters, analyses of factors affecting fire behaviour, and other topics involving the use of remote sensing data, are encouraged and welcome.

You may choose our Joint Special Issue in Remote Sensing.

Prof. Dr. Luis A. Ruiz
Dr. Andrew T. Hudak
Guest Editors

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. Fire is an international peer-reviewed open access monthly 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 2400 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 behavior models
  • Fire ecology
  • Forest structure
  • Canopy fuels
  • Canopy bulk density
  • Fuel moisture content
  • Understory vegetation
  • Surface fuels
  • Point clouds
  • ALS, TLS, UAV

Published Papers (13 papers)

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

Research

Jump to: Review

22 pages, 15145 KiB  
Article
Surface Radiative Forcing as a Climate-Change Indicator in North India due to the Combined Effects of Dust and Biomass Burning
by Umesh Chandra Dumka, Panagiotis G. Kosmopoulos, Effrosyni Baxevanaki, Dimitris G. Kaskaoutis, Muhammad Nurul Huda, Md Firoz Khan, Muhammad Bilal, Balram Ambade, Sujan Khanal and Pavel Munshi
Fire 2023, 6(9), 365; https://doi.org/10.3390/fire6090365 - 19 Sep 2023
Viewed by 1899
Abstract
This study estimates the radiative forcing by biomass burning and dust aerosols over the Indian subcontinent, with emphasis on the Indo-Gangetic Plains (IGP) during the period from January 2021 to April 2021, based on multiple satellite and reanalysis datasets. In this respect, we [...] Read more.
This study estimates the radiative forcing by biomass burning and dust aerosols over the Indian subcontinent, with emphasis on the Indo-Gangetic Plains (IGP) during the period from January 2021 to April 2021, based on multiple satellite and reanalysis datasets. In this respect, we used retrievals from the Moderate Resolution Spectroradiometer (MODIS) and the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) system, as well as reanalysis data from the Goddard Earth Observing System, version 5 (GEOS-5), the Modern-Era Retrospective analysis for Research and Applications, version 2 (MERRA-2), the Copernicus Atmosphere Monitoring Service (CAMS), and ERA-Interim. According to the MERRA-2 and the CAMS, the highest black carbon (BC) concentrations in January 2021 were 7–8 µg m−3, which were significantly lower than measurements performed in main cities along the IGP, such as Patiala, Delhi, and Kanpur. The meteorological data analysis accompanied by the CALIPSO lidar measurements showed that the vertical distribution of total attenuated backscatter (TAB) could reach altitudes of up to ~4–5 km and could be transported over the central Himalayan region. The spatial-averaged daily aerosol radiative forcing (ARF) values over the Indian subcontinent from January 2021 to April 2021 were found to range from −51.40 to −6.08 W m−2 (mean of −22.02 ± 9.19 W m−2), while on a monthly basis, the ARF values varied widely, from −146.24 to −1.63 W m−2 (mean of −45.56 ± 22.85 W m−2) over different parts of the study region. Furthermore, the spatial-averaged daily BC radiative forcing ranged from −2.23 to −0.35 (−1.01 ± 0.40 W m−2), while it varied from −15.29 to −0.31 W m−2 (−2.46 ± 2.32 W m−2) over different regions of southern Asia, indicating a rather small contribution to the total aerosol radiative effect and a large presence of highly scattering aerosols. Our findings highlight the importance of growing biomass burning, in light of recent climate change and the rapid decline in air quality over North India and the Indian Ocean. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

20 pages, 46427 KiB  
Article
Predicting the Continuous Spatiotemporal State of Ground Fire Based on the Expended LSTM Model with Self-Attention Mechanisms
by Xinyu Wang, Xinquan Wang, Mingxian Zhang, Chun Tang, Xingdong Li, Shufa Sun, Yangwei Wang, Dandan Li and Sanping Li
Fire 2023, 6(6), 237; https://doi.org/10.3390/fire6060237 - 15 Jun 2023
Viewed by 1281
Abstract
Fire spread prediction is a crucial technology for fighting forest fires. Most existing fire spread models focus on making predictions after a specific time, and their predicted performance decreases rapidly in continuous prediction due to error accumulation when using the recursive method. Given [...] Read more.
Fire spread prediction is a crucial technology for fighting forest fires. Most existing fire spread models focus on making predictions after a specific time, and their predicted performance decreases rapidly in continuous prediction due to error accumulation when using the recursive method. Given that fire spread is a dynamic spatiotemporal process, this study proposes an expanded neural network of long short-term memory based on self-attention (SA-EX-LSTM) to address this issue. The proposed model predicted the combustion image sequence based on wind characteristics. It had two detailed feature transfer paths, temporal memory flow and spatiotemporal memory flow, which assisted the model in learning complete historical fire features as well as possible. Furthermore, self-attention mechanisms were integrated into the model’s forgetting gates, enabling the model to select the important features associated with the increase in fire spread from massive historical fire features. Datasets for model training and testing were derived from nine experimental ground fires. Compared with the state-of-the-art spatiotemporal prediction models, SA-EX-LSTM consistently exhibited the highest predicted performance and stability throughout the continuous prediction process. The experimental results in this paper have the potential to positively impact the application of spatiotemporal prediction models and UAV-based methods in the field of fire spread prediction. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

16 pages, 2402 KiB  
Article
A Comparison of Four Spatial Interpolation Methods for Modeling Fine-Scale Surface Fuel Load in a Mixed Conifer Forest with Complex Terrain
by Chad M. Hoffman, Justin P. Ziegler, Wade T. Tinkham, John Kevin Hiers and Andrew T. Hudak
Fire 2023, 6(6), 216; https://doi.org/10.3390/fire6060216 - 25 May 2023
Cited by 1 | Viewed by 1214
Abstract
Patterns of spatial heterogeneity in forests and other fire-prone ecosystems are increasingly recognized as critical for predicting fire behavior and subsequent fire effects. Given the difficulty in sampling continuous spatial patterns across scales, statistical approaches are common to scale from plot to landscapes. [...] Read more.
Patterns of spatial heterogeneity in forests and other fire-prone ecosystems are increasingly recognized as critical for predicting fire behavior and subsequent fire effects. Given the difficulty in sampling continuous spatial patterns across scales, statistical approaches are common to scale from plot to landscapes. This study compared the performance of four spatial interpolation methods (SIM) for mapping fine-scale fuel loads: classification (CL), multiple linear regression (LR), ordinary kriging (OK), and regression kriging (RK). These methods represent commonly used SIMs and demonstrate a diversity of non-geostatistical, geostatistical, and hybrid approaches. Models were developed for a 17.6-hectare site using a combination of metrics derived from spatially mapped trees, surface fuels sampled with an intensive network of photoload plots, and topographic variables. The results of this comparison indicate that all estimates produced unbiased spatial predictions. Regression kriging outperformed the other approaches that either relied solely on interpolation from point observations or regression-based approaches using auxiliary information for developing fine-scale surface fuel maps. While our analysis found that surface fuel loading was correlated with species composition, forest structure, and topography, the relationships were relatively weak, indicating that other variables and spatial interactions could significantly improve surface fuel mapping. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

16 pages, 2950 KiB  
Article
Evaluating Traffic Operation Conditions during Wildfire Evacuation Using Connected Vehicles Data
by Salman Ahmad, Asad Ali, Hafiz Usman Ahmed, Ying Huang and Pan Lu
Fire 2023, 6(5), 184; https://doi.org/10.3390/fire6050184 - 01 May 2023
Cited by 3 | Viewed by 1963
Abstract
With climate change and the resulting rise in temperatures, wildfire risk is increasing all over the world, particularly in the Western United States. Communities in wildland–urban interface (WUI) areas are at the greatest risk of fire. Such fires cause mass evacuations and can [...] Read more.
With climate change and the resulting rise in temperatures, wildfire risk is increasing all over the world, particularly in the Western United States. Communities in wildland–urban interface (WUI) areas are at the greatest risk of fire. Such fires cause mass evacuations and can result in traffic congestion, endangering the lives of both citizens and first responders. While existing wildfire evacuation research focuses on social science surveys and fire spread modeling, they lack data on traffic operations during such incidents. Additionally, traditional traffic data collection methods are unable to gather large sets of data on historical wildfire events. However, the recent availability of connected vehicle (CV) data containing lane-level precision historical vehicle movement data has enabled researchers to assess traffic operational performance at the region and timeframe of interest. To address this gap, this study utilized a CV dataset to analyze traffic operations during a short-notice evacuation event caused by a wildfire, demonstrating that the CV dataset is an effective tool for accurately assessing traffic delays and overall traffic operation conditions during the selected fire incident. The findings also showed that the selected CV dataset provides high temporal coverage and similar travel time estimates as compared to an alternate method of travel time estimation. The study thus emphasized the importance of utilizing advanced technologies, such as CV data, to develop effective evacuation strategies and improve emergency management. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

14 pages, 1882 KiB  
Article
Cyclic Trends of Wildfires over Sub-Saharan Africa
by Reason L. Machete and Kebonyethata Dintwe
Fire 2023, 6(2), 71; https://doi.org/10.3390/fire6020071 - 16 Feb 2023
Viewed by 2993
Abstract
In this paper, the patterns of the occurrences of fire incidents over sub-Saharan Africa are studied on the basis of satellite data. Patterns for the whole sub-Saharan Africa are contrasted with those for northern sub-Saharan Africa and southern-hemisphere Africa. This paper attempts to [...] Read more.
In this paper, the patterns of the occurrences of fire incidents over sub-Saharan Africa are studied on the basis of satellite data. Patterns for the whole sub-Saharan Africa are contrasted with those for northern sub-Saharan Africa and southern-hemisphere Africa. This paper attempts to unravel linear trends and overriding oscillations using regression and spectral techniques. It compares fire patterns for aggregated vegetation with those for specific types, which are savannahs, grasslands, shrublands, croplands, and forests, to identify key trend drivers. The underlying cyclic trends are interpreted in light of climate change and model projections. Considering sub-Saharan Africa, northern sub-Saharan Africa, and southern-hemisphere Africa, we found declining linear trends of wildfires with overriding cyclic patterns that have a period of ∼5 years, seemingly largely driven by savannahs, grasslands, and croplands. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

25 pages, 13960 KiB  
Article
Remote Sensing Applications for Mapping Large Wildfires Based on Machine Learning and Time Series in Northwestern Portugal
by Sarah Moura Batista dos Santos, Soltan Galano Duverger, António Bento-Gonçalves, Washington Franca-Rocha, António Vieira and Georgia Teixeira
Fire 2023, 6(2), 43; https://doi.org/10.3390/fire6020043 - 24 Jan 2023
Cited by 2 | Viewed by 2142
Abstract
Mapping large wildfires (LW) is essential for environmental applications and enhances the understanding of the dynamics of affected areas. Remote sensing techniques supported by machine learning and time series have been increasingly used in studies addressing this issue and have shown potential for [...] Read more.
Mapping large wildfires (LW) is essential for environmental applications and enhances the understanding of the dynamics of affected areas. Remote sensing techniques supported by machine learning and time series have been increasingly used in studies addressing this issue and have shown potential for this type of analysis. The main aim of this article is to develop a methodology for mapping LW in northwestern Portugal using a machine learning algorithm and time series from Landsat images. For the burnt area classification, we initially used the Fourier harmonic model to define outliers in the time series that represented pixels of possible burnt areas and, then, we applied the random forest classifier for the LW classification. The results indicate that the harmonic analysis provided estimates with the actual observed values of the NBR index; thus, the pixels classified by random forest were only those that were masked, collaborated in the processing, and reduced possible spectral confusion between targets with similar behaviour. The burnt area maps revealed that ~23.5% of the territory was burnt at least once from 2001 to 2020. The temporal variability of the burnt area indicated that, on average, 6.504 hectares were affected by LW within the 20 years. The annual burnt area varied over the years, with the minimum annual area detected in 2014 (679.5 hectares) and the maximum mapped area detected in 2005 (73,025.1 hectares). We concluded that the process of defining the mask with the outliers considerably reduced the universe of pixels to be classified within each image, which leaves the training of the classifier focused on separating the set of pixels into two groups with very similar spectral characteristics, thus contributing so that the separation of groups with similar spectral behaviour was performed automatically and without great sampling effort. The method showed satisfactory accuracy results with little omission for burnt areas. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

22 pages, 11921 KiB  
Article
The Spatiotemporal Characteristics of Wildfires across Australia and Their Connections to Extreme Climate Based on a Combined Hydrological Drought Index
by Lilu Cui, Chengkang Zhu, Zhengbo Zou, Chaolong Yao, Cheng Zhang and Yu Li
Fire 2023, 6(2), 42; https://doi.org/10.3390/fire6020042 - 22 Jan 2023
Cited by 3 | Viewed by 2027
Abstract
With the frequent occurrence of extreme climates around the world, the frequency of regional wildfires is also on the rise, which poses a serious threat to the safety of human life, property, and regional ecosystems. To investigate the role of extreme climates in [...] Read more.
With the frequent occurrence of extreme climates around the world, the frequency of regional wildfires is also on the rise, which poses a serious threat to the safety of human life, property, and regional ecosystems. To investigate the role of extreme climates in the occurrence and spread of wildfires, we combined precipitation, evapotranspiration, soil moisture (SM), maximum temperature (MT), relative humidity, plant canopy water, vapor pressure deficit, and a combined hydrological drought index based on six Gravity Recovery and Climate Experiment (GRACE) and its follow-on (GRACE-FO) products to study the relationship between climate change and wildfires across Australia between 2003 and 2020. The results show that Australia’s wildfires are mainly concentrated in the northern region, with a small number being distributed along the southeastern coast. The high burned months are September (2.5941 × 106 ha), October (4.9939 × 106 ha), and November (3.8781 × 106 ha), while the years with a larger burned area are 2011 (79.95 × 106 ha) and 2012 (78.33 × 106 ha) during the study period. On a seasonal scale, the terrestrial water storage change and the hydrometeorological factors have the strong correlations with burned area, while for only the drought index, SM and MT are strongly related to burned area on an interannual scale. By comparing the data between the high burned and normal years, the impact of droughts on wildfires is achieved through two aspects: (1) the creation of a dry atmospheric environment, and (2) the accumulation of natural combustibles. Extreme climates affect wildfires through the occurrence of droughts. Among them, the El Niño–Southern Oscillation has the greatest impact on drought in Australia, followed by the Pacific Decadal Oscillation and the Indian Ocean Dipole (correlation coefficients are −0.33, −0.31, and −0.23, respectively), but there is little difference among the three. The proposed hydrological drought index in our study has the potential to provide an early warning of regional wildfires. Our results have a certain reference significance for comprehensively understanding the impact mechanism of extreme climates on regional wildfires and for establishing an early warning system for regional wildfires. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

23 pages, 3020 KiB  
Article
Deep Learning Based Burnt Area Mapping Using Sentinel 1 for the Santa Cruz Mountains Lightning Complex (CZU) and Creek Fires 2020
by Harrison Luft, Calogero Schillaci, Guido Ceccherini, Diana Vieira and Aldo Lipani
Fire 2022, 5(5), 163; https://doi.org/10.3390/fire5050163 - 10 Oct 2022
Cited by 1 | Viewed by 1872
Abstract
The study presented here builds on previous synthetic aperture radar (SAR) burnt area estimation models and presents the first U-Net (a convolutional network architecture for fast and precise segmentation of images) combined with ResNet50 (Residual Networks used as a backbone for many computer [...] Read more.
The study presented here builds on previous synthetic aperture radar (SAR) burnt area estimation models and presents the first U-Net (a convolutional network architecture for fast and precise segmentation of images) combined with ResNet50 (Residual Networks used as a backbone for many computer vision tasks) encoder architecture used with SAR, Digital Elevation Model, and land cover data for burnt area mapping in near-real time. The Santa Cruz Mountains Lightning Complex (CZU) was one of the most destructive fires in state history. The results showed a maximum burnt area segmentation F1-Score of 0.671 in the CZU, which outperforms current models estimating burnt area with SAR data for the specific event studied models in the literature, with an F1-Score of 0.667. The framework presented here has the potential to be applied on a near real-time basis, which could allow land monitoring as the frequency of data capture improves. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

17 pages, 2927 KiB  
Article
Transferability of Airborne LiDAR Data for Canopy Fuel Mapping: Effect of Pulse Density and Model Formulation
by Eva Marino, José Luis Tomé, Carmen Hernando, Mercedes Guijarro and Javier Madrigal
Fire 2022, 5(5), 126; https://doi.org/10.3390/fire5050126 - 26 Aug 2022
Cited by 8 | Viewed by 1988
Abstract
Canopy fuel characterization is critical to assess fire hazard and potential severity in forest stands. Simulation tools provide useful information for fire prevention planning to reduce wildfire impacts, provided that reliable fuel maps exist at adequate spatial resolution. Free airborne LiDAR data are [...] Read more.
Canopy fuel characterization is critical to assess fire hazard and potential severity in forest stands. Simulation tools provide useful information for fire prevention planning to reduce wildfire impacts, provided that reliable fuel maps exist at adequate spatial resolution. Free airborne LiDAR data are becoming available in many countries providing an opportunity to improve fuel monitoring at large scales. In this study, models were fitted to estimate canopy base height (CBH), fuel load (CFL) and bulk density (CBD) from airborne LiDAR in a pine stand area where four point-cloud datasets were acquired at different pulse densities. Best models for CBH, CFL and CBD fitted with LiDAR metrics from the 1 p/m2 dataset resulted in an adjusted R2 of 0.88, 0.68 and 0.58, respectively, with RMSE (MAPE) of 1.85 m (18%), 0.16 kg/m2 (14%) and 0.03 kg/m3 (20%). Transferability assessment of fitted models indicated different level of accuracy depending on LiDAR pulse density (both higher and lower than the calibration dataset) and model formulation (linear, power and exponential). Best results were found for exponential models and similar pulse density (1.7 p/m2) compared to lower (0.5 p/m2) or higher return density (4 p/m2). Differences were also observed regarding the canopy fuel attributes. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

18 pages, 5611 KiB  
Article
Point Cloud Based Mapping of Understory Shrub Fuel Distribution, Estimation of Fuel Consumption and Relationship to Pyrolysis Gas Emissions on Experimental Prescribed Burns
by Molly M. Herzog, Andrew T. Hudak, David R. Weise, Ashley M. Bradley, Russell G. Tonkyn, Catherine A. Banach, Tanya L. Myers, Benjamin C. Bright, Jonathan L. Batchelor, Akira Kato, John S. Maitland and Timothy J. Johnson
Fire 2022, 5(4), 118; https://doi.org/10.3390/fire5040118 - 16 Aug 2022
Cited by 3 | Viewed by 1836
Abstract
Forest fires spread via production and combustion of pyrolysis gases in the understory. The goal of the present paper is to understand the spatial location, distribution, and fraction (relative to the overstory) of understory plants, in this case, sparkleberry shrub, namely its degree [...] Read more.
Forest fires spread via production and combustion of pyrolysis gases in the understory. The goal of the present paper is to understand the spatial location, distribution, and fraction (relative to the overstory) of understory plants, in this case, sparkleberry shrub, namely its degree of understory consumption upon burn, and to search for correlations between the degree of shrub consumption to the composition of emitted pyrolysis gases. Data were collected in situ at seven small experimental prescribed burns at Ft. Jackson, an army base in South Carolina, USA. Using airborne laser scanning (ALS) to map overstory tree crowns and terrestrial laser scanning (TLS) to characterize understory shrub fuel density, both pre- and postburn estimates of sparkleberry coverage were obtained. Sparkleberry clump polygons were manually digitized from a UAV-derived orthoimage of the understory and intersected with the TLS point cloud-derived rasters of pre- and postburn shrub fuel bulk density; these were compared in relation to overstory crown cover as well as to ground truth. Shrub fuel consumption was estimated from the digitized images; sparkleberry clump distributions were generally found to not correlate well to the overstory tree crowns, suggesting it is shade-tolerant. Moreover, no relationship was found between the magnitude of the fuel consumption and the chemical composition of pyrolysis gases, even though mixing ratios of 25 individual gases were measured. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

17 pages, 7463 KiB  
Article
Phenology Patterns and Postfire Vegetation Regeneration in the Chiquitania Region of Bolivia Using Sentinel-2
by Oswaldo Maillard, Marcio Flores-Valencia, Gilka Michme, Roger Coronado, Mercedes Bachfischer, Huascar Azurduy, Roberto Vides-Almonacid, Reinaldo Flores, Sixto Angulo and Nicolas Mielich
Fire 2022, 5(3), 70; https://doi.org/10.3390/fire5030070 - 28 May 2022
Cited by 6 | Viewed by 3168
Abstract
The natural regeneration of ecosystems impacted by fires is a high priority in Bolivia, and represents one of the country’s greatest environmental challenges. With the abundance of spatial data and access to improved technologies, it is critical to provide an effective method of [...] Read more.
The natural regeneration of ecosystems impacted by fires is a high priority in Bolivia, and represents one of the country’s greatest environmental challenges. With the abundance of spatial data and access to improved technologies, it is critical to provide an effective method of analysis to evaluate changes in land use in the face of the global need to understand the dynamics of vegetation in regeneration processes. In this context, we evaluated the dynamics of natural regeneration through phenological patterns by measuring the maximal and minimal spectral thresholds at four fire-impacted sites in Chiquitania in 2019 and 2020, and compared them with unburned areas using harmonic fitted values of the Normalized Difference Vegetation Index (NDVI) and the Normalized Burn Ratio (NBR). We used two-way ANOVA test to evaluate the significant differences in the values of the profiles of NDVI and NBR indices. We quantified severity at the four study sites using the dNBR obtained from the difference between pre- and postfire NBR. Additionally, we selected 66 sampling sites to apply the Composite Burn Index (CBI) methodology. Our results indicate that NBR is the most reliable index for interannual comparisons and determining changes in the phenological pattern, which allow for the detection of postfire regeneration. Fire severity levels based on dNBR and CBI indices are reliable methodologies that allow for determining the severity and dynamics of changes in postfire regeneration levels in forested and nonforested areas. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

23 pages, 7293 KiB  
Article
Simulating Forest Fire Spread with Cellular Automation Driven by a LSTM Based Speed Model
by Xingdong Li, Mingxian Zhang, Shiyu Zhang, Jiuqing Liu, Shufa Sun, Tongxin Hu and Long Sun
Fire 2022, 5(1), 13; https://doi.org/10.3390/fire5010013 - 20 Jan 2022
Cited by 14 | Viewed by 6738
Abstract
The simulation of forest fire spread is a key problem for the management of fire, and Cellular Automata (CA) has been used to simulate the complex mechanism of the fire spread for a long time. The simulation of CA is driven by the [...] Read more.
The simulation of forest fire spread is a key problem for the management of fire, and Cellular Automata (CA) has been used to simulate the complex mechanism of the fire spread for a long time. The simulation of CA is driven by the rate of fire spread (ROS), which is hard to estimate, because some input parameters of the current ROS model cannot be provided with a high precision, so the CA approach has not been well applied yet in the forest fire management system to date. The forest fire spread simulation model LSTM-CA using CA with LSTM is proposed in this paper. Based on the interaction between wind and fire, S-LSTM is proposed, which takes full advantage of the time dependency of the ROS. The ROS estimated by the S-LSTM is satisfactory, even though the input parameters are not perfect. Fifteen kinds of ROS models with the same structure are trained for different cases of slope direction and wind direction, and the model with the closest case is selected to drive the transmission between the adjacent cells. In order to simulate the actual spread of forest fire, the LSTM-based models are trained based on the data captured, and three correction rules are added to the CA model. Finally, the prediction accuracy of forest fire spread is verified though the KAPPA coefficient, Hausdorff distance, and horizontal comparison experiments based on remote sensing images of wildfires. The LSTM-CA model has good practicality in simulating the spread of forest fires. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

Review

Jump to: Research

35 pages, 1217 KiB  
Review
Deep Learning Approaches for Wildland Fires Using Satellite Remote Sensing Data: Detection, Mapping, and Prediction
by Rafik Ghali and Moulay A. Akhloufi
Fire 2023, 6(5), 192; https://doi.org/10.3390/fire6050192 - 07 May 2023
Cited by 9 | Viewed by 5853
Abstract
Wildland fires are one of the most dangerous natural risks, causing significant economic damage and loss of lives worldwide. Every year, millions of hectares are lost, and experts warn that the frequency and severity of wildfires will increase in the coming years due [...] Read more.
Wildland fires are one of the most dangerous natural risks, causing significant economic damage and loss of lives worldwide. Every year, millions of hectares are lost, and experts warn that the frequency and severity of wildfires will increase in the coming years due to climate change. To mitigate these hazards, numerous deep learning models were developed to detect and map wildland fires, estimate their severity, and predict their spread. In this paper, we provide a comprehensive review of recent deep learning techniques for detecting, mapping, and predicting wildland fires using satellite remote sensing data. We begin by introducing remote sensing satellite systems and their use in wildfire monitoring. Next, we review the deep learning methods employed for these tasks, including fire detection and mapping, severity estimation, and spread prediction. We further present the popular datasets used in these studies. Finally, we address the challenges faced by these models to accurately predict wildfire behaviors, and suggest future directions for developing reliable and robust wildland fire models. Full article
(This article belongs to the Special Issue Advances in Forest Fire Behaviour Modelling Using Remote Sensing)
Show Figures

Figure 1

Back to TopTop