Wildfire Susceptibility Mapping Using Deep Learning Algorithms in Two Satellite Imagery Dataset

被引:6
|
作者
Bahadori, Nazanin [1 ]
Razavi-Termeh, Seyed Vahid [2 ]
Sadeghi-Niaraki, Abolghasem [2 ]
Al-Kindi, Khalifa M. [3 ]
Abuhmed, Tamer [4 ]
Nazeri, Behrokh [5 ]
Choi, Soo-Mi [2 ]
机构
[1] KN Toosi Univ Technol, Fac Geodesy & Geomat Engn, Geoinformat Technol Ctr Excellence, Tehran 163171419, Iran
[2] Sejong Univ, XR Res Ctr, Dept Comp Sci & Engn & Convergence Engn Intelligen, Seoul 05006, South Korea
[3] Univ Nizwa, UNESCO Aflaj Studies, Archaeohydrol, Nizwa 616, Oman
[4] Sungkyunkwan Univ, Coll Comp & Informat, Suwon 16419, South Korea
[5] Purdue Univ, Lyles Sch Civil Engn, W Lafayette, IN 47907 USA
来源
FORESTS | 2023年 / 14卷 / 07期
关键词
wildfire; satellite imagery; spatial modeling; deep learning algorithms; FOREST-FIRE RISK; PREDICTING SPATIAL-PATTERNS; NEURAL-NETWORK; LOGISTIC-REGRESSION; DRIVING FACTORS; CLIMATE-CHANGE; MODEL; SYSTEM; SEVERITY; PROBABILITY;
D O I
10.3390/f14071325
中图分类号
S7 [林业];
学科分类号
0829 ; 0907 ;
摘要
Recurring wildfires pose a critical global issue as they undermine social and economic stability and jeopardize human lives. To effectively manage disasters and bolster community resilience, the development of wildfire susceptibility maps (WFSMs) has emerged as a crucial undertaking in recent years. In this research endeavor, two deep learning algorithms were leveraged to generate WFSMs using two distinct remote sensing datasets. Specifically, the Moderate-Resolution Imaging Spectroradiometer (MODIS) and Landsat-8 images were utilized to monitor wildfires that transpired during the year 2021. To develop an effective WFSM, two datasets were created by incorporating 599 wildfire locations with Landsat-8 images and 232 sites with MODIS images, as well as twelve factors influencing wildfires. Deep learning algorithms, namely the long short-term memory (LSTM) and recurrent neural network (RNN), were utilized to model wildfire susceptibility using the two datasets. Subsequently, four WFSMs were generated using the LSTM (MODIS), LSTM (Landsat-8), RNN (MODIS), and RNN (Landsat-8) algorithms. The evaluation of the WFSMs was performed using the area under the receiver operating characteristic (ROC) curve (AUC) index. The results revealed that the RNN (MODIS) (AUC = 0.971), RNN (Landsat-8) (AUC = 0.966), LSTM (MODIS) (AUC = 0.964), and LSTM (Landsat-8) (AUC = 0.941) algorithms demonstrated the highest modeling accuracy, respectively. Moreover, the Gini index was employed to assess the impact of the twelve factors on wildfires in the study area. The results of the random forest (RF) algorithm indicated that temperature, wind speed, slope, and topographic wetness index (TWI) parameters had a significant effect on wildfires in the study region. These findings are instrumental in facilitating efficient wildfire management and enhancing community resilience against the detrimental effects of wildfires.
引用
收藏
页数:27
相关论文
共 50 条
  • [1] Wildfire susceptibility mapping using two empowered machine learning algorithms
    Hossein Moayedi
    Mohammad Ali Salehi Amin Khasmakhi
    Stochastic Environmental Research and Risk Assessment, 2023, 37 : 49 - 72
  • [2] 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
  • [3] MAPPING SLUMS FROM SATELLITE IMAGERY USING DEEP LEARNING
    Raj, Anjali
    Agrawal, Shubham
    Mitra, Adway
    Sinha, Manjira
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 6584 - 6587
  • [4] A deep learning ensemble model for wildfire susceptibility mapping
    Bjanes, Alexandra
    de la Fuente, Rodrigo
    Mena, Pablo
    ECOLOGICAL INFORMATICS, 2021, 65
  • [5] Satellite Imagery Super Resolution Using Classical and Deep Learning Algorithms
    Kuchkorov, T. A.
    Djumanov, J. X.
    Ochilov, T. D.
    Sabitova, N. Q.
    INTELLIGENT HUMAN COMPUTER INTERACTION, IHCI 2023, PT II, 2024, 14532 : 70 - 80
  • [6] Landslide Susceptibility Mapping with Deep Learning Algorithms
    Habumugisha, Jules Maurice
    Chen, Ningsheng
    Rahman, Mahfuzur
    Islam, Md Monirul
    Ahmad, Hilal
    Elbeltagi, Ahmed
    Sharma, Gitika
    Liza, Sharmina Naznin
    Dewan, Ashraf
    SUSTAINABILITY, 2022, 14 (03)
  • [7] Glacial Lakes Mapping Using Multi Satellite PlanetScope Imagery and Deep Learning
    Qayyum, Nida
    Ghuffar, Sajid
    Ahmad, Hafiz Mughees
    Yousaf, Adeel
    Shahid, Imran
    ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2020, 9 (10)
  • [8] SaRNet: A Dataset for Deep Learning Assisted Search and Rescue with Satellite Imagery
    Thoreau, Michael
    Wilson, Frazer
    PROCEEDINGS OF THE 12TH INTERNATIONAL SYMPOSIUM ON IMAGE AND SIGNAL PROCESSING AND ANALYSIS (ISPA 2021), 2021, : 204 - 208
  • [9] Advanced Deep Learning Framework for Improved Wildfire Detection and Aerosol Identification Using Active Satellite Imagery
    Kothapalli, Srija Venkata Sai Ravali
    Muntean, Cristina Hava
    Yagoob, Abid
    20TH INTERNATIONAL WIRELESS COMMUNICATIONS & MOBILE COMPUTING CONFERENCE, IWCMC 2024, 2024, : 955 - 960
  • [10] Residential Wildfire Structural Damage Detection Using Deep Learning to Analyze Uncrewed Aerial System (UAS) Imagery, Aerial Imagery, and Satellite Imagery
    Kang, Dae Kun
    Olsen, Michael J.
    Fischer, Erica
    Jung, Jaehoon
    FIRE AND MATERIALS, 2025,