Qing Wang
Research Areas
Authored Publications
Sort By
Uncertainty quantification in coupled wildfire-atmosphere simulations at scale
Paul Schwerdtner
Frederick Law
Cenk Gazen
Yi-fan Chen
Matthias Ihme
Benjamin Peherstorfer
PNAS Nexus (2024)
Preview abstract
Uncertainties in wildfire simulations pose a major challenge for making decisions about fire management, mitigation, and evacuations. However, ensemble calculations to quantify uncertainties are prohibitively expensive with high-fidelity models that are needed to capture today’s ever more intense and severe wildfires. This work shows that surrogate models trained on related data enable scaling multi-fidelity uncertainty quantification to high-fidelity wildfire simulations of unprecedented scale with billions of degrees of freedom. The key insight is that correlation is all that matters while bias is irrelevant for speeding up uncertainty quantification when surrogate models are combined with high-fidelity models in multi-fidelity approaches. This allows the surrogate models to be trained on abundantly available or cheaply generated related data samples that can be strongly biased as long as they are correlated to predictions of high-fidelity simulations. Numerical results with scenarios of the Tubbs 2017 wildfire demonstrate that surrogate models trained on related data make multi-fidelity uncertainty quantification in large-scale wildfire simulations practical by reducing the training time by several orders of magnitude from three months to under three hours and predicting the burned area at least twice as accurately compared to using high-fidelity simulations alone for a fixed computational budget. More generally, the results suggest that leveraging related data can greatly extend the scope of surrogate modeling, potentially benefiting other fields that require uncertainty quantification in computationally expensive high-fidelity simulations.
View details
Preview abstract
Background. Wildfire research uses ensemble methods to analyze fire behaviors and assess
uncertainties. Nonetheless, current research methods are either confined to simple models
or complex simulations with limits. Modern computing tools could allow for efficient, high-
fidelity ensemble simulations. Aims. This study proposes a high-fidelity ensemble wildfire
simulation framework for studying wildfire behavior, ML tasks, fire-risk assessment, and
uncertainty analysis. Methods. In this research, we present a simulation framework that
integrates the Swirl-Fire large-eddy simulation tool for wildfire predictions with the Vizier
optimization platform for automated run-time management of ensemble simulations and
large-scale batch processing. All simulations are executed on tensor-processing units to
enhance computational efficiency. Key results. A dataset of 117 simulations is created,
each with 1.35 billion mesh points. The simulations are compared to existing experimental
data and show good agreement in terms of fire rate of spread. Computations are done for
fire acceleration, mean rate of spread, and fireline intensity. Conclusions. Strong coupling
between these 2 parameters are observed for the fire spread and intermittency. A critical
Froude number that delineates fires from plume-driven to convection-driven is identified and
confirmed with literature observations. Implications. The ensemble simulation framework
is efficient in facilitating parametric wildfire studies.
View details
Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations
Anudhyan Boral
James Lottes
Yi-fan Chen
John Anderson
Advances in Neural Information Processing Systems (NeurIPS) 36 (2023)
Preview abstract
We introduce a data-driven learning framework that assimilates two powerful ideas: ideal large-eddy-simulation (LES) from turbulence closure modeling and neural stochastic differential equations (SDE) for modeling stochastic dynamical systems. ideal LES identifies the optimal reduced-order flow fields of the large-scale features by marginalizing out the effect of small-scales in stochastic turbulent trajectories. However, ideal LES is analytically intractable. In our work, we use a latent neural SDE to model the evolution of the stochastic process and a pair of encoder and decoder for transforming between the latent space and the desired optimal flow field. This stands in sharp contrast to other types of neural parameterization of the closure models where each trajectory is treated as a deterministic realization of the dynamics. We show the effectiveness of our approach (niLES – neural ideal LES) on a challenging chaotic dynamical systems: Kolmogorov flow at a Reynolds number of 20,000. Compared to prior works, our method is also able to handle non-uniform geometries and unstructured meshes. In particular, niLES leads to more accurate long term statistics, and is stable even when rolling out to long horizons.
View details
A TensorFlow Simulation Framework for Scientific Computing of Fluid Flows on Tensor Processing Units
Preview abstract
A computational fluid dynamics (CFD) simulation framework for predicting complex flows is developed on the Tensor Processing Unit (TPU) platform. The TPU architecture is featured with accelerated performance of dense matrix multiplication, large high bandwidth memory, and a fast inter-chip interconnect, which makes it appealing for scientific high performance computing (HPC). This CFD framework is implemented with the finite difference method on a collocated structured mesh, and it uses the graph-based TensorFlow as the programming library. The accuracy and speed of this framework is studied both numerically and analytically. In particular, the impact of machine precision on the mesh convergence is discussed in detail, which provides a guideline for the simulation framework to achieve the desired rate of convergence. Additionally, a linear weak scaling and a super-linear strong scaling is observed up to a full TPU v3 pod with 2048 cores. The algorithm and implementation are validated with canonical 2D and 3D Taylor Green vortex simulations. To demonstrate the capability for simulating turbulent flows, verification simulations are conducted for two configurations, namely the decaying homogeneous isotropic turbulence and a turbulent planar jet. Both simulations show good statistical agreement with reference solutions.
View details
Preview abstract
This work presents a high-fidelity simulation framework for modeling large-scale wildfire scenarios that take into consideration realistic topographies, atmospheric conditions, turbulence/fire interaction, and flow dynamics. With the overall goal of enabling large-scale ensemble simulations and the integration of the simulation results into machine-learning applications, this modeling framework has been implemented into the TensorFlow programming environment. To demonstrate the capability of this simulation framework in predicting large-scale fires, we performed high-resolution simulations of a realistic wildfire scenario that is representative of the 2017 Tubbs fire.
View details
Distributed Data Processing for Large-Scale Simulations on Cloud
Lily Hu
TJ Lu
Yi-fan Chen
2021 IEEE INTERNATIONAL SYMPOSIUM ON ELECTROMAGNETIC COMPATIBILITY, SIGNAL & POWER INTEGRITY (2021) (to appear)
Preview abstract
In this work, we proposed a distributed data pipeline for large-scale simulations by using libraries and frameworks available on Cloud services. The data pipeline is designed with careful considerations for the characteristics of the simulation data. The implementation of the data pipeline is with Apache Beam and Zarr. Beam is a unified, open-source programming model for building both batch- and streaming-data parallel-processing pipelines. By using Beam, one can simply focus on the logical composition of the data processing task and bypass the low-level details of distributed computing. The orchestration of distributed processing is fully managed by the runner, in this work, Dataflow on Google Cloud. Beam separates the programming layer from the runtime layer such that the proposed pipeline can be executed across various runners. The storage format of the output tensor of the data pipeline is Zarr.
Zarr allows concurrent reading and writing, storage on a file system, and data compression before the storage. The performance of the data pipeline is analyzed with an example, of which the simulation data is obtained with an in-house developed computational fluid dynamic solver running in parallel on Tensor Processing Unit (TPU) clusters. The performance analysis demonstrates good storage and computational efficiency of the proposed data pipeline.
View details
Machine learning accelerated computational fluid dynamics
Ayya Alieva
Dmitrii Kochkov
Jamie Alexander Smith
Proceedings of the National Academy of Sciences USA (2021)
Preview abstract
Numerical simulation of fluids plays an essential role in modeling many physical phenomena, such as in weather, climate, aerodynamics and plasma physics. Fluids are well described by the Navier-Stokes equations, but solving these equations at scale remains daunting, limited by the computational cost of resolving the smallest spatiotemporal features. This leads to unfavorable trade-offs between accuracy and tractability. Here we use end-to-end deep learning to improve approximations inside computational fluid dynamics for modeling two dimensional turbulent flows. For both direct numerical simulation of turbulence and large eddy simulation, our results are as accurate as baseline solvers with 8-16x finer resolution in each spatial dimension, resulting in a 40-400x fold computational speedups. Our method remains stable during long simulations, and generalizes to forcing functions and Reynolds numbers outside of the flows where it is trained, in contrast to black box machine learning approaches. Our approach exemplifies how scientific computing can leverage machine learning and hardware accelerators to improve simulations without sacrificing accuracy or generalization.
View details
Deep Learning Models for Predicting Wildfires from Historical Remote-Sensing Data
Fantine Huot
R. Lily Hu
Matthias Ihme
John Burge
TJ Lu
Jason J. Hickey
Yi-fan Chen
John Roberts Anderson
NeurIPS Artificial Intelligence for Humanitarian Assistance and Disaster Response Workshop (2020)
Preview abstract
Identifying regions that have high likelihood for wildfires is a key component of land and forestry management and disaster preparedness. We create a data set by aggregating nearly a decade of remote-sensing data and historical fire records to predict wildfires. This prediction problem is framed as three machine learning tasks. Results are compared and analyzed for four different deep learning models to estimate wildfire likelihood. The results demonstrate that deep learning models can successfully identify areas of high fire likelihood using aggregated data about vegetation, weather, and topography with an AUC of 83%.
View details
