<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD Journal Publishing DTD v3.0 20080202//EN" "https://jats.nlm.nih.gov/nlm-dtd/publishing/3.0/journalpublishing3.dtd">
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article" dtd-version="3.0" xml:lang="en">
<front>
<journal-meta>
<journal-id journal-id-type="publisher">ICA-Adv</journal-id>
<journal-title-group>
<journal-title>Advances in Cartography and GIScience of the ICA</journal-title>
<abbrev-journal-title abbrev-type="publisher">ICA-Adv</abbrev-journal-title>
<abbrev-journal-title abbrev-type="nlm-ta">Adv. Cartogr. GIScience Int. Cartogr. Assoc.</abbrev-journal-title>
</journal-title-group>
<issn pub-type="epub">2570-2084</issn>
<publisher><publisher-name>Copernicus Publications</publisher-name>
<publisher-loc>Göttingen, Germany</publisher-loc>
</publisher>
</journal-meta>
<article-meta>
<article-id pub-id-type="doi">10.5194/ica-adv-5-20-2025</article-id>
<title-group>
<article-title>Spatial Susceptibility Mapping of Boreal Forest Fires: Insights from Quebec’s Historical and Future Trends (1980-2050)</article-title>
</title-group>
<contrib-group><contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Mahdizadeh Gharakhanlou</surname>
<given-names>Navid</given-names>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
</contrib>
<contrib contrib-type="author" xlink:type="simple"><name name-style="western"><surname>Perez</surname>
<given-names>Liliana</given-names>
<ext-link>https://orcid.org/0000-0002-6599-9893</ext-link>
</name>
<xref ref-type="aff" rid="aff1">
<sup>1</sup>
</xref>
</contrib>
</contrib-group><aff id="aff1">
<label>1</label>
<addr-line>Laboratoire de Géosimulation Environnementale (LEDGE), Département de Géographie, Université de Montréal, 1375 Avenue Thérèse-Lavoie-Roux, Montréal, QC, H2V 0B3, Canada</addr-line>
</aff>
<pub-date pub-type="epub">
<day>20</day>
<month>10</month>
<year>2025</year>
</pub-date>
<volume>5</volume>
<elocation-id>20</elocation-id>
<permissions>
<copyright-statement>Copyright: &#x000a9; 2025 Navid Mahdizadeh Gharakhanlou</copyright-statement>
<copyright-year>2025</copyright-year>
<license license-type="open-access">
<license-p>This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this licence, visit <ext-link ext-link-type="uri"  xlink:href="https://creativecommons.org/licenses/by/4.0/">https://creativecommons.org/licenses/by/4.0/</ext-link></license-p>
</license>
</permissions>
<self-uri xlink:href="https://ica-adv.copernicus.org/articles/5/20/2025/ica-adv-5-20-2025.html">This article is available from https://ica-adv.copernicus.org/articles/5/20/2025/ica-adv-5-20-2025.html</self-uri>
<self-uri xlink:href="https://ica-adv.copernicus.org/articles/5/20/2025/ica-adv-5-20-2025.pdf">The full text article is available as a PDF file from https://ica-adv.copernicus.org/articles/5/20/2025/ica-adv-5-20-2025.pdf</self-uri>
<abstract>
<p>Forest fires cause significant loss and damage each year, with climate change exacerbating their frequency and severity, highlighting the need for accurate susceptibility maps for effective mitigation and planning. This study integrating various environmental, ecological, and meteorological factors assesses the current and future forest fire susceptibility of Quebec&amp;rsquo;s boreal forests under two climate change scenarios over the next 30 years (2021-2050). The study involved identifying factors affecting forest fires and collecting 40 years of historical forest fire data (1980-2020). Climate variables were downloaded, and the Fire Weather Index (FWI) was calculated using BioSIM software and then interpolated into raster layers in ArcGIS Pro. The data was divided into training (70%) and testing (30%) sets, with a Random Forest (RF) model trained and validated using three accuracy metrics including receiver operating characteristics-area under the curve (ROC-AUC), the figure of merit (FoM), and F1 score, achieving results of 0.895, 0.808, and 0.894, respectively. Although forest fire susceptibility maps displayed some variation over the next 30 years (2021-2050), no distinct upward or downward trend was detected. Additionally, susceptibility remained largely unchanged under both the RCP 4.5 and RCP 8.5 scenarios. The study also highlighted the key factors affecting fire susceptibility, with the FWI, live biomass, and dead biomass being the most significant, contributing 21.8%, 14.28%, and 11.35%, respectively. This study predicting fire susceptibility and providing current and future susceptibility maps offers a proactive approach to climate change preparedness and improving resource allocation and forest fire risk management.</p>
</abstract>
<counts><page-count count="9"/></counts>
</article-meta>
</front>
<body/>
<back>
</back>
</article>