Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
8.3
4.2
Journals
Remote Sensing
Special Issues
Remote Sensing Applications for Wildland Urban Interfaces (WUI) Fire
remotesensing-logo
Submit to Remote Sensing Review for Remote Sensing Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Remote Sensing Applications for Wildland Urban Interfaces (WUI) Fire

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

Deadline for manuscript submissions: closed (31 December 2021) | Viewed by 16865

Special Issue Editors

Dr. Mario Elia

E-Mail Website
Guest Editor
Department of Agricultural and Environmental Science, University of Bari, Bari, Italy
Interests: forest ecology; fire and fuel management; geospatial modelling
Special Issues, Collections and Topics in MDPI journals
Dr. Vincenzo Giannico

E-Mail Website
Guest Editor
Department of Agricultural and Environmental Science, University of Bari, 70126 Bari, Italy
Interests: above-ground biomass; ecosystem services; urban forest; fire behavior; LiDAR; spatial modeling; predictive modeling; image processing; image analysis; machine learning; google earth engine

Special Issue Information

Dear Colleagues,

Wildfires are one of the most important ecological factors worldwide and are recognized as a key driver for many ecosystems. However, wildfires are also considered a serious threat due to their detrimental effects on natural resources and dangerous impact on human life, especially when occurring in wildland urban interfaces (WUIs) (Elia et al. 2019). The expansion of urban settlements into rural and forest areas has led to the creation of landscapes where fires can occur and recur, frequently encroaching on cities. For example, recent newspapers have reported that northern areas of Europe (e.g., Scandinavia and Siberia) are experiencing extraordinary WUI wildfires. In 2018, extreme wildfires occurred in the United Kingdom, Ireland and Latvia, landscapes in which fires have never represented a hazard for natural resources and/or risk to human lives. At the same time, southern Europe continues to record the annual burned area, which in many cases involves the urban and peri-urban areas of many cities.

In this regard, remote sensing represents a cost-effective tool for the study of a large number of fire-related processes. For example, multispectral satellite sensors have been largely applied to estimate the extension of burned areas or to understand how forests recover in relation to burn severity. More recently, active remote sensors such as LiDAR, have been used to understand post-fire modifications in forest stand structure and composition (Giannico et al., 2016). In addition, increasing computational power, has allowed for the development of wildfire event predictive models in terms of occurrence and frequency.

This Special Issue of Remote Sensing hosts studies focusing on the fire and post-fire dynamics in WUIs. The papers will attempt to integrate multi-sensor remote sensing technology and derived products in a streamlined spatial and temporal framework.

Contributions concerning the following topics are invited.

  1. Comparison and evaluation of different remote sensing (RS) techniques for monitoring wildfires in WUIs.
  2. Analysis of WUI areas and the assessment of wildfire risk using RS approaches.
  3. RS techniques for evaluating the post-fire recovery processes of WUI areas.
  4. Application of RS-derived tools for the planning of fire and fuel management.
  5. Wildfire sensitivity in the intermingling of global warming and the urban interfaces.
  6. RS techniques to model wildfire probability and susceptibility in WUIs.
  7. Modeling of wildfire causes in WUIs using RS data.
  8. Review articles covering one or more of the aforementioned topics.

References

Elia, M.; Giannico, V.; Lafortezza, R. and Sanesi, G. Modeling fire ignition patterns in Mediterranean urban interfaces. Stochastic Environmental Research and Risk Assessment. 2019, 33, 169-181.

Giannico, V.; Lafortezza, R.; John, R.; Sanesi, G.; Pesola, L. and Chen, J. Estimating stand volume and above-ground biomass of urban forests using LiDAR. Remote Sensing. 2016, 8, 339.

Dr. Mario Elia
Dr. Vincenzo Giannico
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. 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 2700 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

  • wildland urban interface
  • wildfire modeling
  • spatial and temporal modeling
  • global warming on urban forest fire dynamics
  • wildfire and fuel management and planning in WUI
  • WUI mapping and risk analysis
  • multi-sensor data applications

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

17 pages, 4453 KiB  
Article
Machine Learning Techniques for Fine Dead Fuel Load Estimation Using Multi-Source Remote Sensing Data
by Marina D’Este, Mario Elia, Vincenzo Giannico, Giuseppina Spano, Raffaele Lafortezza and Giovanni Sanesi
Remote Sens. 2021, 13(9), 1658; https://doi.org/10.3390/rs13091658 - 23 Apr 2021
Cited by 31 | Viewed by 4139
Abstract
Fine dead fuel load is one of the most significant components of wildfires without which ignition would fail. Several studies have previously investigated 1-h fuel load using standard fuel parameters or site-specific fuel parameters estimated ad hoc for the landscape. On the one [...] Read more.
Fine dead fuel load is one of the most significant components of wildfires without which ignition would fail. Several studies have previously investigated 1-h fuel load using standard fuel parameters or site-specific fuel parameters estimated ad hoc for the landscape. On the one hand, these methods have a large margin of error, while on the other their production times and costs are high. In response to this gap, a set of models was developed combining multi-source remote sensing data, field data and machine learning techniques to quantitatively estimate fine dead fuel load and understand its determining factors. Therefore, the objectives of the study were to: (1) estimate 1-h fuel loads using remote sensing predictors and machine learning techniques; (2) evaluate the performance of each machine learning technique compared to traditional linear regression models; (3) assess the importance of each remote sensing predictor; and (4) map the 1-h fuel load in a pilot area of the Apulia region (southern Italy). In pursuit of the above, fine dead fuel load estimation was performed by the integration of field inventory data (251 plots), Synthetic Aperture Radar (SAR, Sentinel-1), optical (Sentinel-2), and Light Detection and Ranging (LIDAR) data applying three different algorithms: Multiple Linear regression (MLR), Random Forest (RF), and Support Vector Machine (SVM). Model performances were evaluated using Root Mean Squared Error (RMSE), Mean Squared Error (MSE), the coefficient of determination (R2) and Pearson’s correlation coefficient (r). The results showed that RF (RMSE: 0.09; MSE: 0.01; r: 0.71; R2: 0.50) had more predictive power compared to the other models, while SVM (RMSE: 0.10; MSE: 0.01; r: 0.63; R2: 0.39) and MLR (RMSE: 0.11; MSE: 0.01; r: 0.63; R2: 0.40) showed similar performances. LIDAR variables (Canopy Height Model and Canopy cover) were more important in fuel estimation than optical and radar variables. In fact, the results highlighted a positive relationship between 1-h fuel load and the presence of the tree component. Conversely, the geomorphological variables appeared to have lower predictive power. Overall, the 1-h fuel load map developed by the RF model can be a valuable tool to support decision making and can be used in regional wildfire risk management. Full article
(This article belongs to the Special Issue Remote Sensing Applications for Wildland Urban Interfaces (WUI) Fire)
►▼ Show Figures

Graphical abstract

21 pages, 9242 KiB  
Article
Global Wildfire Outlook Forecast with Neural Networks
by Yongjia Song and Yuhang Wang
Remote Sens. 2020, 12(14), 2246; https://doi.org/10.3390/rs12142246 - 13 Jul 2020
Cited by 13 | Viewed by 4369
Abstract
Wildfire occurrence and spread are affected by atmospheric and land-cover conditions, and therefore meteorological and land-cover parameters can be used in area burned prediction. We apply three forecast methods, a generalized linear model, regression trees, and neural networks (Levenberg–Marquardt backpropagation) to produce monthly [...] Read more.
Wildfire occurrence and spread are affected by atmospheric and land-cover conditions, and therefore meteorological and land-cover parameters can be used in area burned prediction. We apply three forecast methods, a generalized linear model, regression trees, and neural networks (Levenberg–Marquardt backpropagation) to produce monthly wildfire predictions 1 year in advance. The models are trained using the Global Fire Emissions Database version 4 with small fires (GFEDv4s). Continuous 1-year monthly fire predictions from 2011 to 2015 are evaluated with GFEDs data for 10 major fire regions around the globe. The predictions by the neural network method are superior. The 1-year moving predictions have good prediction skills over these regions, especially over the tropics and the southern hemisphere. The temporal refined index of agreement (IOA) between predictions and GFEDv4s regional burned areas are 0.82, 0.82, 0.8, 0.75, and 0.56 for northern and southern Africa, South America, equatorial Asia and Australia, respectively. The spatial refined IOA for 5-year averaged monthly burned area range from 0.69 in low-fire months to 0.86 in high-fire months over South America, 0.3–0.93 over northern Africa, 0.69–0.93 over southern Africa, 0.47–0.85 over equatorial Asia, and 0.53–0.8 over Australia. For fire regions in the northern temperate and boreal regions, the temporal and spatial IOA between predictions and GFEDv4s data in fire seasons are 0.7–0.79 and 0.24–0.83, respectively. The predictions in high-fire months are better than low-fire months. This study illustrates the feasibility of global fire activity outlook forecasts using a neural network model and the method can be applied to quickly assess the potential effects of climate change on wildfires. Full article
(This article belongs to the Special Issue Remote Sensing Applications for Wildland Urban Interfaces (WUI) Fire)
►▼ Show Figures

Figure 1

21 pages, 3182 KiB  
Article
Detecting Burn Severity across Mediterranean Forest Types by Coupling Medium-Spatial Resolution Satellite Imagery and Field Data
by Luigi Saulino, Angelo Rita, Antonello Migliozzi, Carmine Maffei, Emilia Allevato, Antonio Pietro Garonna and Antonio Saracino
Remote Sens. 2020, 12(4), 741; https://doi.org/10.3390/rs12040741 - 24 Feb 2020
Cited by 48 | Viewed by 7275
Abstract
In Mediterranean countries, in the year 2017, extensive surfaces of forests were damaged by wildfires. In the Vesuvius National Park, multiple summer wildfires burned 88% of the Mediterranean forest. This unprecedented event in an environmentally vulnerable area suggests conducting spatial assessment of the [...] Read more.
In Mediterranean countries, in the year 2017, extensive surfaces of forests were damaged by wildfires. In the Vesuvius National Park, multiple summer wildfires burned 88% of the Mediterranean forest. This unprecedented event in an environmentally vulnerable area suggests conducting spatial assessment of the mixed-severity fire effects for identifying priority areas and support decision-making in post-fire restoration. The main objective of this study was to compare the ability of the delta Normalized Burn Ratio (dNBR) spectral index obtained from Landsat-8 and Sentinel-2A satellites in retrieving burn severity levels. Burn severity levels experienced by the Mediterranean forest communities were defined by using two quali-quantitative field-based composite burn indices (FBIs), namely the Composite Burn Index (CBI), its geometrically modified version CBI (GeoCBI), and the dNBR derived from the two medium-resolution multispectral remote sensors. The accuracy of the burn severity map produced by using the dNBR thresholds developed by Key and Benson (2006) was first evaluated. We found very low agreement (0.15 < K < 0.21) between the burn severity class obtained from field-based indices (CBI and GeoCBI) and satellite-derived metrics (dNBR) from both Landsat-8 and Sentinel-2A. Therefore, the most appropriate dNBR thresholds were rebuilt by analyzing the relationships between two field-based (CBI and GeoCBI) and dNBR from Landsat-8 and Sentinel-2A. By regressing alternatively FBIs and dNBRs, a slightly stronger relationship between GeoCBI and dNBR metrics obtained from the Sentinel-2A remote sensor (R2 = 0.69) was found. The regressed dNBR thresholds showed moderately high classification accuracy (K = 0.77, OA = 83%) for Sentinel-2A, suggesting the appropriateness of dNBR-Sentinel 2A in assessing mixed-severity Mediterranean wildfires. Our results suggest that there is no single set of dNBR thresholds that are appropriate for all burnt biomes, especially for the low levels of burn severity, as biotic factors could affect satellite observations. Full article
(This article belongs to the Special Issue Remote Sensing Applications for Wildland Urban Interfaces (WUI) Fire)
►▼ Show Figures

Graphical abstract

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop