Integrating geospatial, remote sensing, and machine learning for climate-induced forest fire susceptibility mapping in Similipal Tiger Reserve, India: English

Research output: Contribution to journalArticleResearchpeer review

Authors

  • Chiranjit Singha
  • Kishore Chandra Swain
  • Armin Moghimi
  • Fatemeh Foroughnia
  • Sanjay Kumar Swain

External Research Organisations

  • Visva-Bharati University
  • Delft University of Technology
View graph of relations

Details

Original languageEnglish
Article number121729
Number of pages21
JournalForest ecology and management
Volume555
Early online date31 Jan 2024
Publication statusPublished - 1 Mar 2024

Abstract

Accurately assessing forest fire susceptibility (FFS) in the Similipal Tiger Reserve (STR) is essential for biodiversity conservation, climate change mitigation, and community safety. Most existing studies have primarily focused on climatic and topographical factors, while this research expands the scope by employing a synergistic approach that integrates geographical information systems (GIS), remote sensing (RS), and machine learning (ML) methodologies for identifying and assessing forest fire-prone areas in the STR and their vulnerability to climate change. To achieve this, the study employed a comprehensive dataset of forty-four influencing factors, including topographic, climate-hydrologic, forest health, vegetation indices, radar features, and anthropogenic interference, into ten ML models: neural net (nnet), AdaBag, Extreme Gradient Boosting (XGBTree), Gradient Boosting Machine (GBM), Random Forest (RF), and its hybrid variants with differential evolution algorithm (RF-DEA), Gravitational Based Search (RF-GBS), Grey Wolf Optimization (RF-GWO), Particle Swarm Optimization (RF-PSO), and genetic algorithm (RF-GA). The study revealed high FFS in both the northern and southern portions of the study area, with the nnet and RF-PSO models demonstrating susceptibility percentages of 12.44% and 12.89%, respectively. Conversely, very low FFS zones consistently displayed susceptibility scores of approximately 23.41% and 18.57% for the nnet and RF-PSO models. The robust mapping methodology was validated by impressive AUROC (>0.88) and kappa coefficient (>0.62) scores across all ML validation metrics. Future climate models (ssp245 and ssp585, 2022–2100) indicated high FFS zones along the northern and southern edges of the STR, with the central zone categorized from low to very low susceptibility. Boruta analysis identified actual evapotranspiration (AET) and relative humidity as key factors influencing forest fire ignition. SHAP evaluation reinforced the influence of these factors on FFS, while also highlighting the significant role of distance to road, distance to settlement, dNBR, slope, and humidity in prediction accuracy. These results emphasize the critical importance of the proposed approach for forest fire mapping and provide invaluable insights for firefighting teams, forest management, planning, and qualification strategies to address future fire sustainability.

Keywords

    Boruta-SHAP, Forest fire, Machine learning, Risk map, Susceptibility map

ASJC Scopus subject areas

Sustainable Development Goals

Cite this

Integrating geospatial, remote sensing, and machine learning for climate-induced forest fire susceptibility mapping in Similipal Tiger Reserve, India: English. / Singha, Chiranjit; Swain, Kishore Chandra; Moghimi, Armin et al.
In: Forest ecology and management, Vol. 555, 121729, 01.03.2024.

Research output: Contribution to journalArticleResearchpeer review

Download
@article{12aaea8493cf4077a312fb20d3da3602,
title = "Integrating geospatial, remote sensing, and machine learning for climate-induced forest fire susceptibility mapping in Similipal Tiger Reserve, India: English",
abstract = "Accurately assessing forest fire susceptibility (FFS) in the Similipal Tiger Reserve (STR) is essential for biodiversity conservation, climate change mitigation, and community safety. Most existing studies have primarily focused on climatic and topographical factors, while this research expands the scope by employing a synergistic approach that integrates geographical information systems (GIS), remote sensing (RS), and machine learning (ML) methodologies for identifying and assessing forest fire-prone areas in the STR and their vulnerability to climate change. To achieve this, the study employed a comprehensive dataset of forty-four influencing factors, including topographic, climate-hydrologic, forest health, vegetation indices, radar features, and anthropogenic interference, into ten ML models: neural net (nnet), AdaBag, Extreme Gradient Boosting (XGBTree), Gradient Boosting Machine (GBM), Random Forest (RF), and its hybrid variants with differential evolution algorithm (RF-DEA), Gravitational Based Search (RF-GBS), Grey Wolf Optimization (RF-GWO), Particle Swarm Optimization (RF-PSO), and genetic algorithm (RF-GA). The study revealed high FFS in both the northern and southern portions of the study area, with the nnet and RF-PSO models demonstrating susceptibility percentages of 12.44% and 12.89%, respectively. Conversely, very low FFS zones consistently displayed susceptibility scores of approximately 23.41% and 18.57% for the nnet and RF-PSO models. The robust mapping methodology was validated by impressive AUROC (>0.88) and kappa coefficient (>0.62) scores across all ML validation metrics. Future climate models (ssp245 and ssp585, 2022–2100) indicated high FFS zones along the northern and southern edges of the STR, with the central zone categorized from low to very low susceptibility. Boruta analysis identified actual evapotranspiration (AET) and relative humidity as key factors influencing forest fire ignition. SHAP evaluation reinforced the influence of these factors on FFS, while also highlighting the significant role of distance to road, distance to settlement, dNBR, slope, and humidity in prediction accuracy. These results emphasize the critical importance of the proposed approach for forest fire mapping and provide invaluable insights for firefighting teams, forest management, planning, and qualification strategies to address future fire sustainability.",
keywords = "Boruta-SHAP, Forest fire, Machine learning, Risk map, Susceptibility map",
author = "Chiranjit Singha and Swain, {Kishore Chandra} and Armin Moghimi and Fatemeh Foroughnia and Swain, {Sanjay Kumar}",
year = "2024",
month = mar,
day = "1",
doi = "10.1016/j.foreco.2024.121729",
language = "English",
volume = "555",
journal = "Forest ecology and management",
issn = "0378-1127",
publisher = "Elsevier",

}

Download

TY - JOUR

T1 - Integrating geospatial, remote sensing, and machine learning for climate-induced forest fire susceptibility mapping in Similipal Tiger Reserve, India

T2 - English

AU - Singha, Chiranjit

AU - Swain, Kishore Chandra

AU - Moghimi, Armin

AU - Foroughnia, Fatemeh

AU - Swain, Sanjay Kumar

PY - 2024/3/1

Y1 - 2024/3/1

N2 - Accurately assessing forest fire susceptibility (FFS) in the Similipal Tiger Reserve (STR) is essential for biodiversity conservation, climate change mitigation, and community safety. Most existing studies have primarily focused on climatic and topographical factors, while this research expands the scope by employing a synergistic approach that integrates geographical information systems (GIS), remote sensing (RS), and machine learning (ML) methodologies for identifying and assessing forest fire-prone areas in the STR and their vulnerability to climate change. To achieve this, the study employed a comprehensive dataset of forty-four influencing factors, including topographic, climate-hydrologic, forest health, vegetation indices, radar features, and anthropogenic interference, into ten ML models: neural net (nnet), AdaBag, Extreme Gradient Boosting (XGBTree), Gradient Boosting Machine (GBM), Random Forest (RF), and its hybrid variants with differential evolution algorithm (RF-DEA), Gravitational Based Search (RF-GBS), Grey Wolf Optimization (RF-GWO), Particle Swarm Optimization (RF-PSO), and genetic algorithm (RF-GA). The study revealed high FFS in both the northern and southern portions of the study area, with the nnet and RF-PSO models demonstrating susceptibility percentages of 12.44% and 12.89%, respectively. Conversely, very low FFS zones consistently displayed susceptibility scores of approximately 23.41% and 18.57% for the nnet and RF-PSO models. The robust mapping methodology was validated by impressive AUROC (>0.88) and kappa coefficient (>0.62) scores across all ML validation metrics. Future climate models (ssp245 and ssp585, 2022–2100) indicated high FFS zones along the northern and southern edges of the STR, with the central zone categorized from low to very low susceptibility. Boruta analysis identified actual evapotranspiration (AET) and relative humidity as key factors influencing forest fire ignition. SHAP evaluation reinforced the influence of these factors on FFS, while also highlighting the significant role of distance to road, distance to settlement, dNBR, slope, and humidity in prediction accuracy. These results emphasize the critical importance of the proposed approach for forest fire mapping and provide invaluable insights for firefighting teams, forest management, planning, and qualification strategies to address future fire sustainability.

AB - Accurately assessing forest fire susceptibility (FFS) in the Similipal Tiger Reserve (STR) is essential for biodiversity conservation, climate change mitigation, and community safety. Most existing studies have primarily focused on climatic and topographical factors, while this research expands the scope by employing a synergistic approach that integrates geographical information systems (GIS), remote sensing (RS), and machine learning (ML) methodologies for identifying and assessing forest fire-prone areas in the STR and their vulnerability to climate change. To achieve this, the study employed a comprehensive dataset of forty-four influencing factors, including topographic, climate-hydrologic, forest health, vegetation indices, radar features, and anthropogenic interference, into ten ML models: neural net (nnet), AdaBag, Extreme Gradient Boosting (XGBTree), Gradient Boosting Machine (GBM), Random Forest (RF), and its hybrid variants with differential evolution algorithm (RF-DEA), Gravitational Based Search (RF-GBS), Grey Wolf Optimization (RF-GWO), Particle Swarm Optimization (RF-PSO), and genetic algorithm (RF-GA). The study revealed high FFS in both the northern and southern portions of the study area, with the nnet and RF-PSO models demonstrating susceptibility percentages of 12.44% and 12.89%, respectively. Conversely, very low FFS zones consistently displayed susceptibility scores of approximately 23.41% and 18.57% for the nnet and RF-PSO models. The robust mapping methodology was validated by impressive AUROC (>0.88) and kappa coefficient (>0.62) scores across all ML validation metrics. Future climate models (ssp245 and ssp585, 2022–2100) indicated high FFS zones along the northern and southern edges of the STR, with the central zone categorized from low to very low susceptibility. Boruta analysis identified actual evapotranspiration (AET) and relative humidity as key factors influencing forest fire ignition. SHAP evaluation reinforced the influence of these factors on FFS, while also highlighting the significant role of distance to road, distance to settlement, dNBR, slope, and humidity in prediction accuracy. These results emphasize the critical importance of the proposed approach for forest fire mapping and provide invaluable insights for firefighting teams, forest management, planning, and qualification strategies to address future fire sustainability.

KW - Boruta-SHAP

KW - Forest fire

KW - Machine learning

KW - Risk map

KW - Susceptibility map

UR - http://www.scopus.com/inward/record.url?scp=85183983684&partnerID=8YFLogxK

U2 - 10.1016/j.foreco.2024.121729

DO - 10.1016/j.foreco.2024.121729

M3 - Article

AN - SCOPUS:85183983684

VL - 555

JO - Forest ecology and management

JF - Forest ecology and management

SN - 0378-1127

M1 - 121729

ER -