A high-resolution large-eddy simulation framework for wildland fire predictions using TensorFlow

Wang, Qing; Ihme, Matthias; Linn, Rod Ray; Chen, Yi-Fan; Yang, Vivian; Sha, Fei; Clements, Craig; McDanold, Jenna Sjunneson; Anderson, John

doi:10.1071/wf22225

A high-resolution large-eddy simulation framework for wildland fire predictions using TensorFlow

Journal Article · Wed Oct 18 00:00:00 EDT 2023 · International Journal of Wildland Fire

DOI:https://doi.org/10.1071/wf22225· OSTI ID:2511288

^[1]; Ihme, Matthias ^[2]; ^[3]; Chen, Yi-Fan ^[1]; Yang, Vivian ^[1]; Sha, Fei ^[1]; Clements, Craig ^[4]; ^[3]; Anderson, John ^[1]

Research Google, Mountain View, CA (United States)
Research Google, Mountain View, CA (United States); Stanford Univ., CA (United States)
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
San Jose State Univ., CA (United States)

Background: Wildfires are becoming more severe, so we need improved tools to predict them over a wide range of conditions and scales. One approach towards this goal entails the use of coupled fire/atmosphere modelling tools. Although significant progress has been made in advancing their physical fidelity, existing tools have not taken full advantage of emerging programming paradigms and computing architectures to enable high-resolution wildfire simulations. Aims: The aim of this study was to present a new framework that enables landscape-scale wildfire simulations with physical representation of combustion at an affordable cost. Methods: We developed a coupled fire/atmosphere simulation framework using TensorFlow, which enables efficient and scalable computations on Tensor Processing Units. Key Results: Simulation results for a prescribed fire were compared with experimental data. Predicted fire behavior and statistical analysis for fire spread rate, scar area, and intermittency showed overall reasonable agreement. Scalability analysis was performed, showing close to linear scaling. Conclusions: While mesh refinement was shown to have less impact on global quantities, such as fire scar area and spread rate, it benefits predictions of intermittent fire behavior, buoyancy-driven dynamics, and small-scale turbulent motion. Implications: This new simulation framework is efficient in capturing both global quantities and unsteady dynamics of wildfires at high spatial resolutions.

View Accepted Manuscript (DOE)

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE Laboratory Directed Research and Development (LDRD) Program

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 2511288

Report Number(s):: LA-UR--22-32587

Journal Information:: International Journal of Wildland Fire, Journal Name: International Journal of Wildland Fire Journal Issue: 12 Vol. 32; ISSN 1049-8001

Publisher:: International Association of Wildland FireCopyright Statement

Country of Publication:: United States

Language:: English

References (38)

Wildfire and climate change adaptation of western North American forests: a case for intentional management Hessburg, Paul F.; Prichard, Susan J.; Hagmann, R. Keala Ecological Applications, Vol. 31, Issue 8 https://doi.org/10.1002/eap.2432	journal	August 2021
Logarithmic-Linear Law of the Streamwise Velocity Variance in Stably Stratified Boundary Layers Yang, Xiang I. A.; Chen, Peng E. S.; Hu, Ruifeng Boundary-Layer Meteorology, Vol. 183, Issue 2 https://doi.org/10.1007/s10546-021-00683-5	journal	January 2022
Modeling wind fields and fire propagation following bark beetle outbreaks in spatially-heterogeneous pinyon-juniper woodland fuel complexes Linn, Rodman R.; Sieg, Carolyn H.; Hoffman, Chad M. Agricultural and Forest Meteorology, Vol. 173 https://doi.org/10.1016/j.agrformet.2012.11.007	journal	May 2013
A physical model for wildland fires Balbi, J. H.; Morandini, F.; Silvani, X. Combustion and Flame, Vol. 156, Issue 12 https://doi.org/10.1016/j.combustflame.2009.07.010	journal	December 2009
A TensorFlow simulation framework for scientific computing of fluid flows on tensor processing units Wang, Qing; Ihme, Matthias; Chen, Yi-Fan Computer Physics Communications, Vol. 274 https://doi.org/10.1016/j.cpc.2022.108292	journal	May 2022
A 3D physical model to study the behavior of vegetation fires at laboratory scale Morvan, Dominique; Accary, Gilbert; Meradji, Sofiane Fire Safety Journal, Vol. 101 https://doi.org/10.1016/j.firesaf.2018.08.011	journal	October 2018
Computational modeling of extreme wildland fire events: A synthesis of scientific understanding with applications to forecasting, land management, and firefighter safety Coen, Janice L.; Schroeder, W.; Conway, S. Journal of Computational Science, Vol. 45 https://doi.org/10.1016/j.jocs.2020.101152	journal	September 2020
Large eddy simulation of fire plumes Wang, Yi; Chatterjee, Prateep; de Ris, John L. Proceedings of the Combustion Institute, Vol. 33, Issue 2 https://doi.org/10.1016/j.proci.2010.07.031	journal	January 2011
Numerical simulations of grass fires using a coupled atmosphere–fire model: Basic fire behavior and dependence on wind speed Linn, Rodman R. Journal of Geophysical Research, Vol. 110, Issue D13 https://doi.org/10.1029/2004JD005597	journal	January 2005
Dynamic subgrid-scale models for momentum and scalar fluxes in large-eddy simulations of neutrally stratified atmospheric boundary layers over heterogeneous terrain: LARGE-EDDY SIMULATION Stoll, Rob; Porté-Agel, Fernando Water Resources Research, Vol. 42, Issue 1 https://doi.org/10.1029/2005WR003989	journal	January 2006
Warmer and Drier Fire Seasons Contribute to Increases in Area Burned at High Severity in Western US Forests From 1985 to 2017 Parks, S. A.; Abatzoglou, J. T. Geophysical Research Letters, Vol. 47, Issue 22 https://doi.org/10.1029/2020GL089858	journal	November 2020
Climate-induced variations in global wildfire danger from 1979 to 2013 Jolly, W. Matt; Cochrane, Mark A.; Freeborn, Patrick H. Nature Communications, Vol. 6, Issue 1 https://doi.org/10.1038/ncomms8537	journal	July 2015
A general classification of three‐dimensional flow fields Chong, M. S.; Perry, A. E.; Cantwell, B. J. Physics of Fluids A: Fluid Dynamics, Vol. 2, Issue 5 https://doi.org/10.1063/1.857730	journal	May 1990
Firespread through fuel beds: Modeling of wind-aided fires and induced hydrodynamics Porterie, B.; Morvan, D.; Loraud, J. C. Physics of Fluids, Vol. 12, Issue 7 https://doi.org/10.1063/1.870426	journal	July 2000
Wildland Fire Behaviour: Dynamics, Principles and Processes Finney, Mark A.; McAllister, Sara S.; Grumstrup, Torben P. https://doi.org/10.1071/9781486309092	book	January 2021
Studying wildfire behavior using FIRETEC Linn, Rodman; Reisner, Jon; Colman, Jonah J. International Journal of Wildland Fire, Vol. 11, Issue 4 https://doi.org/10.1071/WF02007	journal	January 2002
Wildland surface fire spread modelling, 1990 - 2007. 2: Empirical and quasi-empirical models Sullivan, Andrew L. International Journal of Wildland Fire, Vol. 18, Issue 4 https://doi.org/10.1071/WF06142	journal	January 2009
Wildland surface fire spread modelling, 1990 - 2007. 1: Physical and quasi-physical models Sullivan, Andrew L. International Journal of Wildland Fire, Vol. 18, Issue 4 https://doi.org/10.1071/WF06143	journal	January 2009
Wildland surface fire spread modelling, 1990 - 2007. 3: Simulation and mathematical analogue models Sullivan, Andrew L. International Journal of Wildland Fire, Vol. 18, Issue 4 https://doi.org/10.1071/WF06144	journal	January 2009
Simulation study of grass fire using a physics-based model: striving towards numerical rigour and the effect of grass height on the rate of spread Moinuddin, K. A. M.; Sutherland, D.; Mell, W. International Journal of Wildland Fire, Vol. 27, Issue 12 https://doi.org/10.1071/WF17126	journal	January 2018
The FireFlux II experiment: a model-guided field experiment to improve understanding of fire–atmosphere interactions and fire spread Clements, Craig B.; Kochanski, Adam K.; Seto, Daisuke International Journal of Wildland Fire, Vol. 28, Issue 4 https://doi.org/10.1071/WF18089	journal	January 2019
On the intermittent nature of forest fire spread – Part 2 Viegas, Domingos Xavier Filomeno Carlos; Raposo, Jorge Rafael Nogueira; Ribeiro, Carlos Fernando Morgado International Journal of Wildland Fire, Vol. 31, Issue 10 https://doi.org/10.1071/WF21098	journal	September 2022
Fire behaviour and smoke modelling: model improvement and measurement needs for next-generation smoke research and forecasting systems Liu, Yongqiang; Kochanski, Adam; Baker, Kirk R. International Journal of Wildland Fire, Vol. 28, Issue 8 https://doi.org/10.1071/wf18204	journal	January 2019
Role of buoyant flame dynamics in wildfire spread Finney, Mark A.; Cohen, Jack D.; Forthofer, Jason M. Proceedings of the National Academy of Sciences, Vol. 112, Issue 32 https://doi.org/10.1073/pnas.1504498112	journal	July 2015
Impact of anthropogenic climate change on wildfire across western US forests Abatzoglou, John T.; Williams, A. Park Proceedings of the National Academy of Sciences, Vol. 113, Issue 42 https://doi.org/10.1073/pnas.1607171113	journal	October 2016
The changing risk and burden of wildfire in the United States Burke, Marshall; Driscoll, Anne; Heft-Neal, Sam Proceedings of the National Academy of Sciences, Vol. 118, Issue 2 https://doi.org/10.1073/pnas.2011048118	journal	January 2021
On the product of semi-groups of operators Trotter, H. F. Proceedings of the American Mathematical Society, Vol. 10, Issue 4 https://doi.org/10.1090/S0002-9939-1959-0108732-6	journal	April 1959
Increasing western US forest wildfire activity: sensitivity to changes in the timing of spring Westerling, Anthony LeRoy Philosophical Transactions of the Royal Society B: Biological Sciences, Vol. 371, Issue 1696 https://doi.org/10.1098/rstb.2015.0178	journal	June 2016
Ten Lessons From Three Generations Shaped Google’s TPUv4i : Industrial Product Jouppi, Norman P.; Hyun Yoon, Doe; Ashcraft, Matthew 2021 ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA) https://doi.org/10.1109/ISCA52012.2021.00010	conference	June 2021
Warming and Earlier Spring Increase Western U.S. Forest Wildfire Activity Westerling, A. L. Science, Vol. 313, Issue 5789 https://doi.org/10.1126/science.1128834	journal	August 2006
A review of a new generation of wildfire–atmosphere modeling Bakhshaii, A.; Johnson, E. A. Canadian Journal of Forest Research, Vol. 49, Issue 6 https://doi.org/10.1139/cjfr-2018-0138	journal	June 2019
Simulation of Coupled Fire/Atmosphere Interaction with the MesoNH-ForeFire Models Filippi, Jean-Baptiste; Bosseur, Frédéric; Pialat, Xavier Journal of Combustion, Vol. 2011 https://doi.org/10.1155/2011/540390	journal	January 2011
Numerical Simulation of Hydrostatic Mountain Waves Klemp, J. B.; Lilly, D. K. Journal of the Atmospheric Sciences, Vol. 35, Issue 1 https://doi.org/10.1175/1520-0469(1978)035<0078:NSOHMW>2.0.CO;2	journal	January 1978
A Large-Eddy-Simulation Model for the Study of Planetary Boundary-Layer Turbulence Moeng, Chin-Hoh Journal of the Atmospheric Sciences, Vol. 41, Issue 13 https://doi.org/10.1175/1520-0469(1984)041<2052:ALESMF>2.0.CO;2	journal	July 1984
A Large Eddy Simulation Intercomparison Study of Shallow Cumulus Convection Siebesma, A. Pier; Bretherton, Christopher S.; Brown, Andrew Journal of the Atmospheric Sciences, Vol. 60, Issue 10 https://doi.org/10.1175/1520-0469(2003)60<1201:ALESIS>2.0.CO;2	journal	May 2003
WRF-Fire: Coupled Weather–Wildland Fire Modeling with the Weather Research and Forecasting Model Coen, Janice L.; Cameron, Marques; Michalakes, John Journal of Applied Meteorology and Climatology, Vol. 52, Issue 1 https://doi.org/10.1175/JAMC-D-12-023.1	journal	January 2013
On the numerical simulation of buoyant convection Lilly, D. K. Tellus, Vol. 14, Issue 2 https://doi.org/10.3402/tellusa.v14i2.9537	journal	January 1962
Coupled atmosphere-wildland fire modeling with WRF 3.3 and SFIRE 2011 Mandel, J.; Beezley, J. D.; Kochanski, A. K. Geoscientific Model Development, Vol. 4, Issue 3 https://doi.org/10.5194/gmd-4-591-2011	journal	January 2011

Similar Records

Validation of coupled atmosphere-fire behavior models

Technical Report · Wed Dec 30 23:00:00 EST 1998 · OSTI ID:314171

Hybridizing Machine Learning and Physically-based Earth System Models to Improve Prediction of Multivariate Extreme Events (AI Exploration of Wildland Fire Prediction)

Technical Report · Thu Apr 15 00:00:00 EDT 2021 · OSTI ID:1769718

Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior

Journal Article · Sun Aug 06 20:00:00 EDT 2023 · Fire Technology · OSTI ID:1998774

Related Subjects

54 ENVIRONMENTAL SCIENCES
TensorFlow
fire management
fire propagation
fire/atmospheric coupling
large-eddy simulation
tensor processing units
wildfire modelling
wildland fire prediction

A high-resolution large-eddy simulation framework for wildland fire predictions using TensorFlow

Citation Formats

References (38)

Similar Records

Related Subjects