@ARTICLE
Coulon, V., Gaucherand, J., Xing, V., Laera, D., Lapeyre, C. and Poinsot, T. (2023) Direct numerical simulations of methane, ammonia-hydrogen and hydrogen turbulent premixed flames, Combustion and Flame, 256, pp. Article number 112933, doi: 10.1016/j.combustflame.2023.112933
[bibtex]
@ARTICLE{AR-CFD-23-89,
author = {Coulon, V. and Gaucherand, J. and Xing, V. and Laera, D. and Lapeyre, C. and Poinsot, T. },
title = {Direct numerical simulations of methane, ammonia-hydrogen and hydrogen turbulent premixed flames},
year = {2023},
volume = {256},
pages = {Article number 112933},
doi = {10.1016/j.combustflame.2023.112933},
journal = {Combustion and Flame}}
Lazzara, M., Chevalier, M., Colombo, M., Garay Garcia, J., Lapeyre, C. and Teste, O. (2022) Surrogate modelling for an aircraft dynamic landing loads simulation using an LSTM AutoEncoder-based dimensionality reduction approach, Aerospace Science and Technology, 126, pp. Article number 107629, doi: 10.1016/j.ast.2022.107629
[bibtex]
@ARTICLE{AR-PA-22-78,
author = {Lazzara, M. and Chevalier, M. and Colombo, M. and Garay Garcia, J. and Lapeyre, C. and Teste, O. },
title = {Surrogate modelling for an aircraft dynamic landing loads simulation using an LSTM AutoEncoder-based dimensionality reduction approach},
year = {2022},
volume = {126},
pages = {Article number 107629},
doi = {10.1016/j.ast.2022.107629},
journal = {Aerospace Science and Technology},
abstract = {Surrogate modelling can alleviate the computational burden of design activities as they rely on multiple evaluations of high-fidelity models. However, the learning task can be adversely affected by the high-dimensionality of the system, complex non-linearities and temporal dependencies, leading to an inaccurate surrogate model. In this paper we present an innovative dual-phase Long-Short Term Memory (LSTM) Autoencoder-based surrogate model applied in an industrial context for the prediction of aircraft dynamic landing response over time, conditioned by an exogenous set of design parameters. The LSTM-Autoencoder is adopted as a dimensionality-reduction tool that extracts the temporal features and the nonlinearities of the high-dimensional dynamical system response, and learns a low-dimensional representation of it. Then, a Fully Connected Neural Network is trained to learn the simplified relationship between the input parameters and the reduced representation of the output. For our application, the results demonstrate that our LSTM-AE based model outperforms both Principal Component Analysis and Convolutional-Autoencoder based surrogate models, in predicting the parameters-dependent high-dimensional temporal system response. }}
Yewgat, A., Busby, D., Chevalier, M., Lapeyre, C. and Teste, O. (2022) Physics-constrained deep learning forecasting: an application with capacitance resistive model, Computational Geosciences, 26 (4) , pp. 1065-1100, doi: 10.1007/s10596-022-10146-6
[bibtex]
@ARTICLE{AR-PA-22-208,
author = {Yewgat, A. and Busby, D. and Chevalier, M. and Lapeyre, C. and Teste, O. },
title = {Physics-constrained deep learning forecasting: an application with capacitance resistive model},
year = {2022},
number = {4},
volume = {26},
pages = {1065-1100},
doi = {10.1007/s10596-022-10146-6},
journal = {Computational Geosciences},
abstract = {It is well known that the construction of traditional reservoir simulation models can be very time and resources consuming. Particularly in the case of mature fields with long history and large number of wells where such models can be extremely difficult and long to history match. In this case data driven models can represent a cost-effective alternative, or they can provide complementary analysis to classical reservoir modelling. Due to data scarcity full machine learning approaches are also usually doomed to fail. In this work we develop a new Physics-Constrained Deep Learning approach that combined neural networks with a reduced physics approach: Capacitance Resistive Model (CRM). CRM are data-driven methods that are based on a simple material balance approximation, that can provide very useful reservoir insight. CRM can be used to analyze the underlying connections between producer wells and injector wells that can then be used to better allocate water injection. Such analysis can usually require very long tracer tests or very expensive 4D seismic acquisition and interpretation. CRM can provide directly these wells connection information using only available production and pressure data. The problem with CRM approaches, based on classical optimizers, is that they often detect spurious correlations and can be not very robust and reliable. Our physics-constrained deep learning approach called Deep-CRM performs production data regularization via the neural network approximation that helps to provide a better CRM parameter identification also with the use of robust gradient descent optimization methods developed and widely used by the large deep learning community. We show first on a synthetic and then in real reservoir case that Deep-CRM was able to identify most of the injector-producer connections with higher accuracy with respect to traditional CRM. Deep-CRM produced also better liquid production forecasts on the performed blind tests.}}
Cellier, A., Lapeyre, C., Oztarlik, G., Poinsot, T., Schuller, T. and Selle, L. (2021) Detection of precursors of combustion instability using convolutional recurrent neural networks, Combustion and Flame, 233 (November) , pp. 111558
[bibtex]
[url]
@ARTICLE{AR-CFD-21-97,
author = {Cellier, A. and Lapeyre, C. and Oztarlik, G. and Poinsot, T. and Schuller, T. and Selle, L. },
title = {Detection of precursors of combustion instability using convolutional recurrent neural networks},
year = {2021},
number = {November},
volume = {233},
pages = { 111558},
journal = {Combustion and Flame},
abstract = {Many combustors are prone to Thermoacoustic Instabilities (TAI). Being able to avoid TAI is mandatory to efficiently operate a system without sacrificing neither performance nor safety. Based on Deep Learning techniques, and more specifically Convolutional Recurrent Neural Networks (CRNN)1, this study presents a tool able to detect and translate precursors of TAI in a swirled combustor for different fuel injection strategies. The tool is trained to use only time-series recorded by a few sensors in stable conditions to predict the proximity of unstable operating points on a mass flow rate / equivalence ratio operating map, offering a real-time information on the margin of the system versus TAI. This allows to change operating conditions, and detect the directions to avoid in order to remain in the stable domain.},
keywords = {Thermoacoustic instability, Instability precursors, Deep learning, Convolutional recurrent neural networks},
url = {https://www.sciencedirect.com/science/article/abs/pii/S0010218021003011?via%3Dihub}}
Besombes, C., Pannekoucke, O., Lapeyre, C., Sanderson, B.M. and Thual, O. (2021) Producing realistic climate data with generative adversarial networks, Nonlinear Processes in Geophysics, 28 (3) , pp. 347-370, doi: 10.5194/npg-28-347-2021
[bibtex]
[url] [pdf]
@ARTICLE{AR-CMGC-21-100,
author = {Besombes, C. and Pannekoucke, O. and Lapeyre, C. and Sanderson, B.M. and Thual, O. },
title = {Producing realistic climate data with generative adversarial networks},
year = {2021},
number = {3},
volume = {28},
pages = {347-370},
doi = {10.5194/npg-28-347-2021},
journal = {Nonlinear Processes in Geophysics},
pdf = {https://cerfacs.fr/wp-content/uploads/2021/07/Globc-AR-Besombes-npg-21-100.pdf},
url = {https://npg.copernicus.org/articles/28/347/2021/npg-28-347-2021.html}}
Xing, V., Lapeyre, C., Jaravel, T. and Poinsot, T. (2021) Generalization Capability of Convolutional Neural Networks for Progress Variable Variance and Reaction Rate Subgrid-Scale Modeling, Energies, 14 (16) , pp. 5096, doi: 10.3390/en14165096
[bibtex] [pdf]
@ARTICLE{AR-PA-21-107,
author = {Xing, V. and Lapeyre, C. and Jaravel, T. and Poinsot, T. },
title = {Generalization Capability of Convolutional Neural Networks for Progress Variable Variance and Reaction Rate Subgrid-Scale Modeling},
year = {2021},
number = {16},
volume = {14},
pages = {5096},
doi = {10.3390/en14165096},
journal = {Energies},
abstract = {Deep learning has recently emerged as a successful approach to produce accurate subgrid-scale (SGS) models for Large Eddy Simulations (LES) in combustion. However, the ability of these models to generalize to configurations far from their training distribution is still mainly unexplored, thus impeding their application to practical configurations. In this work, a convolutional neural network (CNN) model for the progress-variable SGS variance field is trained on a canonical premixed turbulent flame and evaluated a priori on a significantly more complex slot burner jet flame. Despite the extensive differences between the two configurations, the CNN generalizes well and outperforms existing algebraic models. Conditions for this successful generalization are discussed, including the effect of the filter size and flame–turbulence interaction parameters. The CNN is then integrated into an analytical reaction rate closure relying on a single-step chemical source term formulation
and a presumed beta PDF (probability density function) approach. The proposed closure is able to accurately recover filtered reaction rate values on both training and generalization flames.},
keywords = {large eddy simulation; turbulent combustion; deep learning; convolutional neural network; progress variable variance; generalization},
pdf = {https://cerfacs.fr/wp-content/uploads/2021/08/energies-14-05096-v2.pdf}}
Lapeyre, C., Misdariis, A., Cazard, N., Veynante, D. and Poinsot, T. (2019) Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates, Combustion and Flame, 203, pp. 255-264, doi: 10.1016/j.combustflame.2019.02.019
[bibtex]
[url] [pdf]
@ARTICLE{AR-PA-19-235,
author = {Lapeyre, C. and Misdariis, A. and Cazard, N. and Veynante, D. and Poinsot, T. },
title = {Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates},
year = {2019},
volume = {203},
pages = {255-264},
doi = {10.1016/j.combustflame.2019.02.019},
journal = {Combustion and Flame},
keywords = {Turbulent combustion, Deep learning, Flame surface density, Direct numerical simulation},
pdf = {https://doi.org/10.1016/j.combustflame.2019.02.019},
url = {https://www.sciencedirect.com/science/article/abs/pii/S0010218019300835}}
Lapeyre, C., Mazur, M, Scouflaire, P., Richecoeur, F., Ducruix, S. and Poinsot, T. (2017) Acoustically Induced Flashback in a Staged Swirl-Stabilized Combustor, Flow Turbulence and Combustion, 98 (1) , pp. 265–282, doi: 10.1007/s10494-016-9745-2
[bibtex]
@ARTICLE{AR-CFD-17-216,
author = {Lapeyre, C. and Mazur, M and Scouflaire, P. and Richecoeur, F. and Ducruix, S. and Poinsot, T. },
title = {Acoustically Induced Flashback in a Staged Swirl-Stabilized Combustor},
year = {2017},
number = {1},
volume = {98},
pages = {265–282},
doi = {10.1007/s10494-016-9745-2},
journal = {Flow Turbulence and Combustion},
abstract = {This paper describes a joint experimental and numerical investigation of the interaction between thermoacoustics and flashback mechanisms in a swirled turbulent burner. An academic air/propane combustor terminated by a choked nozzle is operated up to 2.5 bars. Experiments show that the flame can stabilize either within the combustion chamber or flashback inside the injection duct, intermittently or permanently. The present study focuses on the mechanisms leading to flashback: this phenomenon can occur naturally, depending on the swirl level which can be adjusted in the experiment by introducing axial flow through the upstream inlet. It can also be triggered by acoustic waves, either through acoustic forcing or self-excited thermoacoustic instability. Flashback is difficult to study experimentally, but it can be investigated numerically using LES: in a first configuration, the outlet of the chamber is treated as a non-reflecting surface through which harmonic waves can be introduced. In this case, a 20 kPa acoustic forcing is sufficient to trigger permanent flashback after a few cycles. When the LES computational domain includes the choked nozzle used experimentally, no forcing is needed for flashback to occur. Self-excited oscillations reach high levels rapidly, leading to flame flashback, as observed experimentally. These results also suggest a simple method to avoid flashback by using fuel staging, which is then tested successfully in both LES and experiments.},
keywords = {Flashback, Flame stabilization, Thermoacoustic instabilities, Experimental combustion, LES}}
Thiesset, F., Halter, F., Bariki, C., Lapeyre, C., Chauveau, C., Gökalp, I., Selle, L. and Poinsot, T. (2017) Isolating strain and curvature effects in premixed flame/vortex interactions, Journal of Fluid Mechanics, 831 (November) , pp. 618-654, doi: 10.1017/jfm.2017.641 618 Isolating
[bibtex]
@ARTICLE{AR-CFD-17-272,
author = {Thiesset, F. and Halter, F. and Bariki, C. and Lapeyre, C. and Chauveau, C. and Gökalp, I. and Selle, L. and Poinsot, T. },
title = {Isolating strain and curvature effects in premixed flame/vortex interactions},
year = {2017},
number = {November},
volume = {831},
pages = {618-654},
doi = {10.1017/jfm.2017.641 618 Isolating},
journal = {Journal of Fluid Mechanics},
abstract = {This study focuses on the response of premixed flames to a transient hydrodynamic
perturbation in an intermediate situation between laminar stretched flames and
turbulent flames: an axisymmetric vortex interacting with a flame. The reasons
motivating this choice are discussed in the framework of turbulent combustion
models and flame response to the stretch rate. We experimentally quantify the
dependence of the flame kinematic properties (displacement and consumption speeds)
to geometrical scalars (stretch rate and curvature) in flames characterized by different
effective Lewis numbers. Whilst the displacement speed can be readily measured
using particle image velocimetry and tomographic diagnostics, providing a reliable
estimate of the consumption speed from experiments remains particularly challenging.
In the present work, a method based on a budget of fuel on a well chosen domain is
proposed and validated both experimentally and numerically using two-dimensional
direct numerical simulations of flame/vortex interactions. It is demonstrated that
the Lewis number impact neither the geometrical nor the kinematic features of the
flames, these quantities being much more influenced by the vortex intensity. While
interacting with the vortex, the flame displacement (at an isotherm close to the
leading edge) and consumption speeds are found to increase almost independently of
the type of fuel. We show that the total stretch rate is not the only scalar quantity
impacting the flame displacement and consumption speeds and that curvature has
a significant influence. Experimental data are interpreted in the light of asymptotic
theories revealing the existence of two distinct Markstein numbers, one characterizing
the dependence of flame speed to curvature, the other to the total stretch rate. This
theory appears to be well suited for representing the evolution of the displacement
speed with respect to either the total stretch rate, curvature or strain rate. It also
explains the limited dependence of the flame displacement speed to Lewis number
and the strong correlation with curvature observed in the experiments. An explicit
relationship between displacement and consumption speeds is also given, indicating
that the fuel consumption rate is likely to be altered by both the total stretch rate
and curvature},
keywords = {combustion, reacting flows}}
@CONFERENCE
Serhani, A., Xing, V., Dupuy, D., Lapeyre, C. and Staffelbach, G. (2022) High-performance hybrid coupling of a CFD solver to deep neural networks, 33rd Parallel CFD International Conference, Alba, Italy ., 5 2022
[bibtex]
@CONFERENCE{PR-PA-22-55,
author = {Serhani, A. and Xing, V. and Dupuy, D. and Lapeyre, C. and Staffelbach, G. },
title = {High-performance hybrid coupling of a CFD solver to deep neural networks},
year = {2022},
month = {5},
booktitle = {33rd Parallel CFD International Conference, Alba, Italy }}
Defontaine, T., Ricci, S., Lapeyre, C., Le Pape, E. and Marchandise, A. (2022) Flood Forecasting with Machine Learning in a scarce data layout, HydroInformatics Conference, Bucarest, Roumanie., 7 2022
[bibtex]
@CONFERENCE{PR-CMGC-22-136,
author = {Defontaine, T. and Ricci, S. and Lapeyre, C. and Le Pape, E. and Marchandise, A. },
title = {Flood Forecasting with Machine Learning in a scarce data layout},
year = {2022},
month = {7},
booktitle = {HydroInformatics Conference, Bucarest, Roumanie},
keywords = {EGU Paper}}
Defontaine, T., Ricci, S., Lapeyre, C., Marchandise, A. and Le Pape, E. (2022) Discharge forecasting with Machine Learning in a scarce data layout, HydroInformatics Conference, Bucarest, Roumanie., 7 2022
[bibtex]
@CONFERENCE{PR-CMGC-22-174,
author = {Defontaine, T. and Ricci, S. and Lapeyre, C. and Marchandise, A. and Le Pape, E. },
title = {Discharge forecasting with Machine Learning in a scarce data layout},
year = {2022},
month = {7},
booktitle = {HydroInformatics Conference, Bucarest, Roumanie},
keywords = {EGU Paper}}
Badhe, A., Laurent, C., Lapeyre, C. and Nicoud, F. (2021) Low-Order Thermoacoustic Analysis of Real Engines, Colloque INCA 2021 (Initiative en Combustion Avancée) – Visioconférence. 2021
[bibtex]
@CONFERENCE{PR-CFD-21-47,
author = {Badhe, A. and Laurent, C. and Lapeyre, C. and Nicoud, F. },
title = {Low-Order Thermoacoustic Analysis of Real Engines},
year = {2021},
booktitle = {Colloque INCA 2021 (Initiative en Combustion Avancée) – Visioconférence},
keywords = {combustion}}
Cellier, A., Lapeyre, C., Oztarlik, G., Poinsot, T., Schuller, T. and Selle, L. (2021) Detection of precursors of Thermoacoustic Instability using Deep Learning Techniques, Colloque INCA 2021 (Initiative en Combustion Avancée) – Visioconférence. 2021
[bibtex]
@CONFERENCE{PR-CFD-21-48,
author = {Cellier, A. and Lapeyre, C. and Oztarlik, G. and Poinsot, T. and Schuller, T. and Selle, L. },
title = {Detection of precursors of Thermoacoustic Instability using Deep Learning Techniques },
year = {2021},
booktitle = {Colloque INCA 2021 (Initiative en Combustion Avancée) – Visioconférence},
keywords = {combustion}}
Badhe, A., Laurent, C., Lapeyre, C. and Nicoud, F. (2021) Low-Order Thermoacoustic Analysis of Real Engines - Paper No 8496 - Virtual Conference, Symposium on Thermoacoustics in Combustion (SoTiC): Industry meets Academia, 6-10 Sept - Munich. 2021
[bibtex]
@CONFERENCE{PR-CFD-21-117,
author = {Badhe, A. and Laurent, C. and Lapeyre, C. and Nicoud, F. },
title = {Low-Order Thermoacoustic Analysis of Real Engines - Paper No 8496 - Virtual Conference},
year = {2021},
booktitle = {Symposium on Thermoacoustics in Combustion (SoTiC): Industry meets Academia, 6-10 Sept - Munich},
abstract = {This article illustrates the capability of the recently introduced low-order acoustic-network modeling (LOM) approach
(Laurent et al., Combust. Flame, vol. 206, 2019) based on the ’generalized modal-expansions’ and the ’state-space’
framework to study thermoacoustic combustion instabilities in complex realistic configurations under the assumption
of zero-Mach mean flow conditions. The acoustics modeling is essentially an improved and generalized version of
the classical modal expansions (Galerkin series) technique. Here, one can use as the basis functions either an overcomplete set of acoustic eigenmodes (called an Over-Complete (OC) Frame) or a simple orthogonal (OB) basis as has
been the norm so far. The former, where deemed necessary, offers enhanced convergence, correct representation of
acoustic variables at the interfaces of the subdomains in the network fixing issues such as Gibbs oscillations, and at
the same time, presents the opportunity for interconnecting subdomains with 1D/2D/3D acoustics and even modeling
advanced features such as complex boundary impedances and multi-perforated liners (Laurent et al., J Comp. Phy., vol.
428, 2021). The potential of the tool is illustrated by performing a linear stability analysis of a real SAFRAN aeronautical
engine combustor with twenty 3D quasi-compact flames while keeping all the geometrical complexities intact. The
results are similar to those obtained by a 3D finite element based Helmholtz solver but with CPU-time significantly lower
(by 3 orders of magnitude). These observations suggest the feasibility of exploiting the tool for extensive parametric
studies directly on industrially relevant configurations},
keywords = {Combustion Instabilities, Thermoacoustics, Acoustic Network tool, Low-Order Modeling (LOM), Modal Expansions, Galerkin Series, State-Space, Linear Stability Analysis, Annular Engine, Azimuthal Instabilities}}
Drozda, L., Mohanamuraly, P., Realpe, Y., Lapeyre, C., Adler, A., Daviller, G. and Poinsot, T. (2021) Data-driven Taylor-Galerkin finite-element scheme for convection problems - The symbiosis of Deep Learning and differential equations, 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia - Virtual conference. 2021
[bibtex]
[url] [pdf]
@CONFERENCE{PR-PA-21-198,
author = {Drozda, L. and Mohanamuraly, P. and Realpe, Y. and Lapeyre, C. and Adler, A. and Daviller, G. and Poinsot, T. },
title = {Data-driven Taylor-Galerkin finite-element scheme for convection problems - The symbiosis of Deep Learning and differential equations},
year = {2021},
booktitle = {35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia - Virtual conference},
abstract = { High-fidelity large-eddy simulations (LES) of high Reynolds number flows are essential to design low-carbon footprint energy conversion devices. The two-level Taylor-Galerkin (TTGC) finite-element method (FEM) has remained the workhorse of modern industrial-scale combustion LES. In this work, we propose an improved FEM termed ML-TTGC that introduces locally tunable parameters in the TTGC scheme, whose values are provided by a graph neural network (GNN). We show that ML-TTGC outperforms TTGC in solving the convection problem in both irregular and regular meshes over a wide-range of initial conditions. We train the GNN using parameter values that (i) minimize a weighted loss function of the dispersion and dissipation error and (ii) enforce them to be numerically stable. As a result no additional ad-hoc dissipation is necessary for numerical stability or to damp spurious waves amortizing the additional cost of running the GNN.},
keywords = {Poster},
pdf = {https://cerfacs.fr/wp-content/uploads/2021/12/ALGO_PR_Drozda_PR-PA-21-198.pdf},
url = {https://openreview.net/forum?id=jm1rLJikNfH}}
Lapeyre, C., Cazard, N., Roy, P., Ricci, S. and Zaoui, F. (2020) Reconstruction of Hydraulic Data by Machine Learning, Advances in Hydroinformatics., 7 2020, Philippe Gourbesville, Guy Caignaert, doi: 10.1007/978-981-15-5436-0
[bibtex]
[url]
@CONFERENCE{PR-PA-20-206,
author = {Lapeyre, C. and Cazard, N. and Roy, P. and Ricci, S. and Zaoui, F. },
title = {Reconstruction of Hydraulic Data by Machine Learning},
year = {2020},
month = {7},
booktitle = {Advances in Hydroinformatics},
editor = {Philippe Gourbesville, Guy Caignaert},
publisher = {Springer Singapore},
number = {54},
pages = {701-715},
isbn = {978-981-15-5435-3},
doi = {10.1007/978-981-15-5436-0},
url = {https://doi.org/10.1007/978-981-15-5436-0_54}}
Yewgat, A., Busby, D., Chevalier, M., Lapeyre, C. and Teste, O. (2020) Deep-CRM: A New Deep Learning Approach for Capacitance Resistive Models, ECMOR XVII. ECMOR XVII, 9 2020, doi: 10.3997/2214-4609.202035123
[bibtex]
[url]
@CONFERENCE{PR-PA-20-207,
author = {Yewgat, A. and Busby, D. and Chevalier, M. and Lapeyre, C. and Teste, O. },
title = {Deep-CRM: A New Deep Learning Approach for Capacitance Resistive Models},
year = {2020},
month = {9},
booktitle = {ECMOR XVII},
publisher = {European Association of Geoscientists & Engineers},
volume = {2020},
number = {1},
pages = {1 - 19},
organization = {ECMOR XVII},
doi = {10.3997/2214-4609.202035123},
url = {https://doi.org/10.3997/2214-4609.202035123}}
Paugam, R., Rochoux, M., Cazard, N., Lapeyre, C., Mell, W., Johnston, J. and Wooster, M. (2019) Computing high resolution fire behavior metrics from prescribed burn using handheld airborne thermal camera observations, 6th International Fire Behavior and Fuels Conference, Marseille, 29 April-3 May, France. 2019
[bibtex]
@CONFERENCE{PR-CMGC-19-88,
author = {Paugam, R. and Rochoux, M. and Cazard, N. and Lapeyre, C. and Mell, W. and Johnston, J. and Wooster, M. },
title = {Computing high resolution fire behavior metrics from prescribed burn using handheld airborne thermal camera observations},
year = {2019},
booktitle = {6th International Fire Behavior and Fuels Conference, Marseille, 29 April-3 May, France}}
Paugam, R., Rochoux, M., Cazard, N., Lapeyre, C., Mell, W. and Wooster, M. (2019) Image segmentation – Fire front extraction for rate of spread estimation, European Geophysical Union (EGU), Vienna, 15-19 April, Austria,. 2019
[bibtex] [pdf]
@CONFERENCE{PR-CMGC-19-90,
author = {Paugam, R. and Rochoux, M. and Cazard, N. and Lapeyre, C. and Mell, W. and Wooster, M. },
title = {Image segmentation – Fire front extraction for rate of spread estimation},
year = {2019},
booktitle = {European Geophysical Union (EGU), Vienna, 15-19 April, Austria,},
keywords = {egu poster},
pdf = {https://www.egu2019.eu}}
Paugam, R., Rochoux, M., Cazard, N., Lapeyre, C., Mell, W. and Wooster, M. (2019) Image segmentation – Fire front extraction for rate of spread estimation, Journée thématique Intelligence Artificielle et Océan-Atmosphère-Climat (LEFE), 6 February, Rennes, France . 2019
[bibtex]
@CONFERENCE{PR-CMGC-19-91,
author = {Paugam, R. and Rochoux, M. and Cazard, N. and Lapeyre, C. and Mell, W. and Wooster, M. },
title = {Image segmentation – Fire front extraction for rate of spread estimation},
year = {2019},
booktitle = {Journée thématique Intelligence Artificielle et Océan-Atmosphère-Climat (LEFE), 6 February, Rennes, France }}
Lapeyre, C., Misdariis, A., Cazard, N., Xing, V., Veynante, D. and Poinsot, T. (2019) A convolutional neural network-based efficiency function for sub-grid flame-turbulence interaction in LES, 17th International Conference on Numerical Combustion., Aachen (Germany) 2019
[bibtex]
@CONFERENCE{PR-CFD-19-97,
author = {Lapeyre, C. and Misdariis, A. and Cazard, N. and Xing, V. and Veynante, D. and Poinsot, T. },
title = {A convolutional neural network-based efficiency function for sub-grid flame-turbulence interaction in LES},
year = {2019},
booktitle = {17th International Conference on Numerical Combustion},
address = {Aachen (Germany)},
abstract = {Speaker: V. Xing},
keywords = {Deep learning, Efficiency function, Wrinkling, LES}}
Lapeyre, C., Cazard, N., Roy, P., Ricci, S. and Zaoui, F. (2019) Prediction and reconstruction of hydraulic state with machine learning, SimHydro 2019, 12-14 June, Sophia-Antipolis, France.. 2019
[bibtex]
@CONFERENCE{PR-CMGC-19-148,
author = {Lapeyre, C. and Cazard, N. and Roy, P. and Ricci, S. and Zaoui, F. },
title = {Prediction and reconstruction of hydraulic state with machine learning},
year = {2019},
booktitle = {SimHydro 2019, 12-14 June, Sophia-Antipolis, France.}}
Cuenot, B., Poinsot, T., Gicquel, L.Y.M., Vermorel, O., Duchaine, F., Riber, E., Dauptain, A., Staffelbach, G., Dombard, J., Misdariis, A. and Lapeyre, C. (2019) Large Eddy Simulation of turbulent reacting flows : methods and applications - Invited plenary lecture, 17th International Conference on Numerical Combustion. German section of the Combustion Institute, Aachen (Germany, 5 2019
[bibtex] [pdf]
@CONFERENCE{PR-CFD-19-164,
author = {Cuenot, B. and Poinsot, T. and Gicquel, L.Y.M. and Vermorel, O. and Duchaine, F. and Riber, E. and Dauptain, A. and Staffelbach, G. and Dombard, J. and Misdariis, A. and Lapeyre, C. },
title = {Large Eddy Simulation of turbulent reacting flows : methods and applications - Invited plenary lecture},
year = {2019},
month = {5},
booktitle = {17th International Conference on Numerical Combustion},
organization = { German section of the Combustion Institute},
address = {Aachen (Germany},
keywords = {combustion},
pdf = {https://cerfacs.fr/wp-content/uploads/2021/01/ICNC2019-Cuenot.pdf}}
Lapeyre, C., Misdariis, A., Cazard, N. and Poinsot, T. (2018) A-posteriori evaluation of a deep convolutionalneural network approach to subgrid-scaleflame surface estimation, 2018 Proceedings of the Summer Program - Studying Turbulence Using Numerical Simulation Databases - XVI. Center for Turbulence Research, Stanford University, USA, 7 2018
[bibtex] [pdf]
@CONFERENCE{PR-CFD-18-218,
author = {Lapeyre, C. and Misdariis, A. and Cazard, N. and Poinsot, T. },
title = {A-posteriori evaluation of a deep convolutionalneural network approach to subgrid-scaleflame surface estimation},
year = {2018},
month = {7},
booktitle = {2018 Proceedings of the Summer Program - Studying Turbulence Using Numerical Simulation Databases - XVI},
pages = {349-358},
organization = {Center for Turbulence Research},
address = {Stanford University, USA},
abstract = {Deep learning (DL) and the field of artificial intelligence (AI) have been hot topicsin the software industry in 2018, notably in the field of convolutional neural networks(CNNs). In fluid dynamics, recent studies are starting to show promising results, includ-ing for large eddy simulation (LES) applications. In this work, a CNN previously trainedto replace a model for the unresolved flame surface in turbulent premixed combustionis implemented inside a parallel LES solver.A-posterioricomparisons are made with adirect numerical simulation (DNS) of a fully resolved flame, and show good agreement. Astate-of-the-art dynamic method is included for comparison, and the CNN outperformsit on the target configuration.},
keywords = {COMBUSTION},
pdf = {https://cerfacs.fr/wp-content/uploads/2019/01/CFD_CTR18_LAPEYREetal.pdf}}
