Wildfire assessment using machine learning algorithms in different regions

被引:0
|
作者
Moghim, Sanaz [1 ]
Mehrabi, Majid [1 ]
机构
[1] Sharif Univ Technol, Dept Civil Engn, Azadi Ave, Tehran, Iran
来源
FIRE ECOLOGY | 2024年 / 20卷 / 01期
基金
美国海洋和大气管理局;
关键词
Wildfire; Fire regime; Machine learning; Random forest; Logistic regression; Fire Susceptibility map; Conservation ecology; SUPPORT VECTOR MACHINE; FOREST-FIRE DANGER; LOGISTIC-REGRESSION; SPATIAL-PATTERN; CLIMATE-CHANGE; BOREAL FOREST; SUSCEPTIBILITY; CANADA; PREDICTION; PROVINCE;
D O I
10.1186/s42408-024-00335-2
中图分类号
Q14 [生态学(生物生态学)];
学科分类号
071012 ; 0713 ;
摘要
BackgroundClimate change and human activities are two main forces that affect the intensity, duration, and frequency of wildfires, which can lead to risks and hazards to the ecosystems. This study uses machine learning (ML) as an effective tool for predicting wildfires using historical data and influential variables. The performance of two machine learning algorithms, including logistic regression (LR) and random forest (RF), to construct wildfire susceptibility maps is evaluated in regions with different physical features (Okanogan region in the US and Jam & eacute;sie region in Canada). The models' inputs are eleven physically related variables to output wildfire probabilities.ResultsResults indicate that the most important variables in both areas are land cover, temperature, wind, elevation, precipitation, and normalized vegetation difference index. In addition, results reveal that both models have temporal and spatial generalization capability to predict annual wildfire probability at different times and locations. Generally, the RF outperforms the LR model in almost all cases. The outputs of the models provide wildfire susceptibility maps with different levels of severity (from very high to very low). Results highlight the areas that are more vulnerable to fire. The developed models and analysis are valuable for emergency planners and decision-makers in identifying critical regions and implementing preventive action for ecological conservation. AntecedentesEl cambio clim & aacute;tico y las actividades humanas son dos de las fuerzas principales que afectan la intensidad, duraci & oacute;n, y frecuencia de los incendios, lo que puede conducir a riesgos e incertidumbres en los ecosistemas. Este estudio us & oacute; la t & eacute;cnica de aprendizaje autom & aacute;tico (machine learning) como una herramienta efectiva para predecir incendios de vegetaci & oacute;n usando datos hist & oacute;ricos y variables influyentes. La performance de dos algoritmos del aprendizaje autom & aacute;tico, incluyendo regresiones log & iacute;sticas (LR) y bosques al azar (Random Forest, RF), para construir mapas de susceptibilidad a los incendios, fue evaluado en regiones con diferentes caracter & iacute;sticas f & iacute;sicas (la regi & oacute;n de Okanogan en los EEUU y la de Jam & eacute;sie en Canad & aacute;). Los inputs del modelo fueron once variables f & iacute;sicamente relacionadas y cuyos resultados fueron las probabilidades de incendios.ResultadosLos resultados indican que las variables m & aacute;s importantes en esas dos & aacute;reas son la cobertura vegetal, la temperatura, el viento, la elevaci & oacute;n, la precipitaci & oacute;n, y el NDVI (Indice Normalizado de Vegetaci & oacute;n). Adicionalmente, los resultados revelan que ambos modelos tienen la capacidad de generar espacial y temporalmente la predicci & oacute;n de la probabilidad anual de la ocurrencia de incendios en tiempos y ubicaciones diferentes. Generalmente, el RF excede al modelo LR casi todos los casos. Como resultado, el modelo provee de mapas de susceptibilidad con diferentes niveles de severidad (desde muy altos a muy bajos). Los resultados tambi & eacute;n resaltan las & aacute;reas que son m & aacute;s vulnerables al fuego. Los modelos desarrollados y el an & aacute;lisis son muy valiosos para los que planifican las emergencias y, para los decisores, para identificar regiones cr & iacute;ticas e implementar acciones preventivas para la conservaci & oacute;n ecol & oacute;gica.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Effects of different sampling strategies for unburned label selection in machine learning modelling of wildfire occurrence probability
    Quan, Xingwen
    Jiao, Miao
    He, Zhili
    Jaafari, Abolfazl
    Xie, Qian
    Lai, Xiaoying
    INTERNATIONAL JOURNAL OF WILDLAND FIRE, 2023, 32 (04) : 561 - 575
  • [2] Landslide and Wildfire Susceptibility Assessment in Southeast Asia Using Ensemble Machine Learning Methods
    He, Qian
    Jiang, Ziyu
    Wang, Ming
    Liu, Kai
    REMOTE SENSING, 2021, 13 (08)
  • [3] Wildfire susceptibility mapping using two empowered machine learning algorithms
    Moayedi, Hossein
    Khasmakhi, Mohammad Ali Salehi Amin
    STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT, 2023, 37 (01) : 49 - 72
  • [4] Landslide Susceptibility Mapping in a Mountainous Area Using Machine Learning Algorithms
    Shahabi, Himan
    Ahmadi, Reza
    Alizadeh, Mohsen
    Hashim, Mazlan
    Al-Ansari, Nadhir
    Shirzadi, Ataollah
    Wolf, Isabelle D.
    Ariffin, Effi Helmy
    REMOTE SENSING, 2023, 15 (12)
  • [5] Early Delirium Detection Using Machine Learning Algorithms
    Figueiredo, Celia
    Braga, Ana Cristina
    Mariz, Jose
    COMPUTATIONAL SCIENCE AND ITS APPLICATIONS, ICCSA 2022 WORKSHOPS, PT I, 2022, 13377 : 555 - 570
  • [6] Credit Risk Assessment Using Machine Learning Algorithms
    Attigeri, Girija V.
    Pai, M. M. Manohara
    Pai, Radhika M.
    ADVANCED SCIENCE LETTERS, 2017, 23 (04) : 3649 - 3653
  • [7] Gully erosion susceptibility assessment and management of hazard-prone areas in India using different machine learning algorithms
    Gayen, Amiya
    Pourghasemi, Hamid Reza
    Saha, Sunil
    Keesstra, Saskia
    Bai, Shibiao
    SCIENCE OF THE TOTAL ENVIRONMENT, 2019, 668 : 124 - 138
  • [8] An insight into machine-learning algorithms to model human-caused wildfire occurrence
    Rodrigues, Marcos
    de la Riva, Juan
    ENVIRONMENTAL MODELLING & SOFTWARE, 2014, 57 : 192 - 201
  • [9] Assessment of Different Machine Learning Methods for Reservoir Outflow Forecasting
    Soria-Lopez, Anton
    Sobrido-Pouso, Carlos
    Mejuto, Juan C.
    Astray, Gonzalo
    WATER, 2023, 15 (19)
  • [10] A comparative study for landslide susceptibility assessment using machine learning algorithms based on grid unit and slope unit
    Deng, Niandong
    Li, Yuxin
    Ma, Jianquan
    Shahabi, Himan
    Hashim, Mazlan
    de Oliveira, Gabriel
    Chaeikar, Saman Shojae
    FRONTIERS IN ENVIRONMENTAL SCIENCE, 2022, 10