Parameter Flexible Wildfire Prediction Using Machine Learning Techniques: Forward and Inverse Modelling

被引:1
|
作者
Cheng, Sibo [1 ,2 ]
Jin, Yufang [3 ]
Harrison, Sandy P. [2 ,4 ]
Quilodran-Casas, Cesar [1 ]
Prentice, Iain Colin [2 ,5 ]
Guo, Yi-Ke [1 ]
Arcucci, Rossella [1 ,6 ]
机构
[1] Imperial Coll London, Data Sci Inst, Dept Comp, London SW7 2BX, England
[2] Leverhulme Ctr Wildfires Environm & Soc, London SW7 2AZ, England
[3] Univ Calif Davis, Dept Land Air & Water Resources, Davis, CA 95616 USA
[4] Imperial Coll London, Georgina Mace Ctr Living Planet, Dept Life Sci, London SW7 2BX, England
[5] Univ Reading, Geog & Environm Sci, Reading RG6 6EU, Berks, England
[6] Imperial Coll London, Dept Earth Sci & Engn, London SW7 2BX, England
关键词
wildfire prediction; machine learning; reduced-order modelling; convolutional autoencoder; data assimilation; latent assimilation; parameter identification; UNCERTAINTY QUANTIFICATION; CELLULAR-AUTOMATA; FIRE PROPAGATION; NEURAL-NETWORKS; SPREAD; ALGORITHM;
D O I
10.3390/rs14133228
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Parameter identification for wildfire forecasting models often relies on case-by-case tuning or posterior diagnosis/analysis, which can be computationally expensive due to the complexity of the forward prediction model. In this paper, we introduce an efficient parameter flexible fire prediction algorithm based on machine learning and reduced order modelling techniques. Using a training dataset generated by physics-based fire simulations, the method forecasts burned area at different time steps with a low computational cost. We then address the bottleneck of efficient parameter estimation by developing a novel inverse approach relying on data assimilation techniques (latent assimilation) in the reduced order space. The forward and the inverse modellings are tested on two recent large wildfire events in California. Satellite observations are used to validate the forward prediction approach and identify the model parameters. By combining these forward and inverse approaches, the system manages to integrate real-time observations for parameter adjustment, leading to more accurate future predictions.
引用
收藏
页数:24
相关论文
共 50 条
  • [1] California Wildfire Prediction using Machine Learning
    Pham, Kaylee
    Ward, David
    Rubio, Saulo
    Shin, David
    Zlotikman, Lior
    Ramirez, Sergio
    Poplawski, Tyler
    Jiang, Xunfei
    [J]. 2022 21ST IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA, 2022, : 525 - 530
  • [2] International Roughness Index prediction for flexible pavements using novel machine learning techniques
    Kaloop, Mosbeh R.
    El-Badawy, Sherif M.
    Hu, Jong Wan
    El-Hakim, Ragaa T. Abd
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 122
  • [3] Enhanced Cardiovascular Disease Prediction Modelling using Machine Learning Techniques: A Focus on CardioVitalnet
    Ejiyi, Chukwuebuka Joseph
    Qin, Zhen
    Nneji, Grace Ugochi
    Monday, Happy Nkanta
    Agbesi, Victor K.
    Ejiyi, Makuachukwu Bennedith
    Ejiyi, Thomas Ugochukwu
    Bamisile, Olusola O.
    [J]. NETWORK-COMPUTATION IN NEURAL SYSTEMS, 2024,
  • [4] Prediction of hypercholesterolemia using machine learning techniques
    Pooyan Moradifar
    Mohammad Meskarpour Amiri
    [J]. Journal of Diabetes & Metabolic Disorders, 2023, 22 : 255 - 265
  • [5] Bankruptcy Prediction Using Machine Learning Techniques
    Shetty, Shekar
    Musa, Mohamed
    Bredart, Xavier
    [J]. JOURNAL OF RISK AND FINANCIAL MANAGEMENT, 2022, 15 (01)
  • [6] Emotion Prediction using Machine Learning Techniques
    Shamsi, Areeba
    Nasir, Sabika
    Hajiani, Mishaal Amin
    Ejaz, Afshan
    Ali, Syed Asim
    [J]. INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2019, 19 (06): : 166 - 172
  • [7] Diabetes Prediction using Machine Learning Techniques
    Obulesu, O.
    Suresh, K.
    Ramudu, B. Venkata
    [J]. HELIX, 2020, 10 (02): : 136 - 142
  • [8] Prediction of hypercholesterolemia using machine learning techniques
    Moradifar, Pooyan
    Amiri, Mohammad Meskarpour
    [J]. JOURNAL OF DIABETES AND METABOLIC DISORDERS, 2023, 22 (01) : 255 - 265
  • [9] Prediction of wildfire rate of spread in grasslands using machine learning methods
    Khanmohammadi, Sadegh
    Arashpour, Mehrdad
    Golafshani, Emadaldin Mohammadi
    Cruz, Miguel G.
    Rajabifard, Abbas
    Bai, Yu
    [J]. ENVIRONMENTAL MODELLING & SOFTWARE, 2022, 156
  • [10] APPLICATION OF MACHINE LEARNING TECHNIQUES FOR INVERSE PREDICTION IN MANUFACTURING PROCESS CHAINS
    Shah, Sapan
    Reddy, Sreedhar
    Sardeshmukh, Avadhut
    Gautham, B. P.
    Shroff, Gautam
    Srinivasan, Ashwin
    [J]. PROCEEDINGS OF THE 3RD WORLD CONGRESS ON INTEGRATED COMPUTATIONAL MATERIALS ENGINEERING (ICME), 2015, : 261 - 268