Data-driven surrogate model with latent data assimilation: application to wildfire forecasting

DOI10.1016/J.JCP.2022.111302MaRDI QIDQ2672756zbMATH OpenOpenAlexWikidataFDO

Authors Sibo Cheng, I. Colin Prentice, Yuhan Huang, Yufang Jin, Rossella Arcucci, Yi Ke Guo

Publication date 13 June 2022

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.jcp.2022.111302

zbMATH Keywords

deep learningdata assimilationreduced-order modellingfire spreadLSTMwildfire forecasting

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Thermodynamics and heat transfer (80Axx) Probabilistic methods, stochastic differential equations (65Cxx)

Recommendations

• A wildland fire model with data assimilation
• Data assimilation for wildland fires
• Joint modeling and prediction of massive spatio-temporal wildfire count and burnt area data with the INLA-SPDE approach
• Reconstruction of incomplete wildfire data using deep generative models
• A combined statistical and machine learning approach for spatial prediction of extreme wildfire frequencies and sizes

Cites work

• 10.1162/15324430260185646
• A cellular automata model for forest fire spread prediction: The case of the wildfire that swept through Spetses Island in 1990
• A wildland fire model with data assimilation
• An artificial neural network framework for reduced order modeling of transient flows
• Data assimilation: methods, algorithms, and applications
• Deep convolutional neural networks for image classification: a comprehensive review
• Eigenvalues, invariant factors, highest weights, and Schubert calculus
• Low-rank approximations for computing observation impact in 4D-Var data assimilation
• Radiant heat flux modelling for wildfires
• Turbulence and the dynamics of coherent structures. I. Coherent structures

Cited in

(7)

• Data assimilation for wildland fires
• A wildland fire model with data assimilation
• Generalised latent assimilation in heterogeneous reduced spaces with machine learning surrogate models
• Multi-domain encoder-decoder neural networks for latent data assimilation in dynamical systems
• Efficient deep data assimilation with sparse observations and time-varying sensors
• Hardware-friendly compression and hardware acceleration for transformer: a survey
• Gradient boosting with extreme-value theory for wildfire prediction

Describes a project that uses

Uses Software

• FARSITE
• FlamMap

This page was built for publication: Data-driven surrogate model with latent data assimilation: application to wildfire forecasting

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2672756)