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
  • [21] GEOMEMBRANE BASINS DETECTION BASED ON SATELLITE HIGH-RESOLUTION IMAGERY USING DEEP LEARNING ALGORITHMS
    Benayad, Mohamed
    Houran, Nouriddine
    Aamir, Zakaria
    Maanan, Mehdi
    Rhinane, Hassan
    GEOINFORMATION WEEK 2022, VOL. 48-4, 2023, : 75 - 79
  • [22] Reliable, accurate and timely forest mapping for wildfire management using ASTER and Hyperion satellite imagery
    Keramitsoglou, I.
    Kontoes, C.
    Sykioti, O.
    Sifakis, N.
    Xofis, P.
    FOREST ECOLOGY AND MANAGEMENT, 2008, 255 (10) : 3556 - 3562
  • [23] Glacial lakes mapping using satellite images and deep learning algorithms in Northwestern Indian Himalayas
    Sharma, Anita
    Prakash, Chander
    MODELING EARTH SYSTEMS AND ENVIRONMENT, 2024, 10 (02) : 2063 - 2077
  • [24] Glacial lakes mapping using satellite images and deep learning algorithms in Northwestern Indian Himalayas
    Anita Sharma
    Chander Prakash
    Modeling Earth Systems and Environment, 2024, 10 : 2063 - 2077
  • [25] Ten-year wildfire mapping using satellite imagery: the case study of Western Greece
    Dimitriou, Eirini
    Kyriou, Aggeliki
    Nikolakopoulos, Konstantinos
    EARTH RESOURCES AND ENVIRONMENTAL REMOTE SENSING/GIS APPLICATIONS XIII, 2022, 12268
  • [26] Mapping tree species proportions from satellite imagery using spectral-spatial deep learning
    Bolyn, Corentin
    Lejeune, Philippe
    Michez, Adrien
    Latte, Nicolas
    REMOTE SENSING OF ENVIRONMENT, 2022, 280
  • [27] Mapping Antarctic crevasses and their evolution with deep learning applied to satellite radar imagery
    Surawy-Stepney, Trystan
    Hogg, Anna E.
    Cornford, Stephen L.
    Hogg, David C.
    CRYOSPHERE, 2023, 17 (10): : 4421 - 4445
  • [28] Mapping Missing Population in Rural India: A Deep Learning Approach with Satellite Imagery
    Hu, Wenjie
    Patel, Jay Harshadbhai
    Robert, Zoe-Alanah
    Novosad, Paul
    Asher, Samuel
    Tang, Zhongyi
    Burke, Marshall
    Lobell, David
    Ermon, Stefano
    AIES '19: PROCEEDINGS OF THE 2019 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY, 2019, : 353 - 359
  • [29] SAMPLE Dataset Objects Classification Using Deep Learning Algorithms
    Turcanik, Michal
    Perdoch, Jozef
    RADIOENGINEERING, 2023, 32 (01) : 63 - 73
  • [30] Flood susceptibility mapping using AutoML and a deep learning framework with evolutionary algorithms for hyperparameter optimization
    Vincent, Amala Mary
    Parthasarathy, K. S. S.
    Jidesh, P.
    APPLIED SOFT COMPUTING, 2023, 148