Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDeploying deep learning in OpenFOAM with TensorFlow
89
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
We outline the development of a data science module within OpenFOAM which allows for the in-situ deployment of trained deep learning architectures for general-purpose predictive tasks. This module is constructed with the TensorFlow C API and is integrated into OpenFOAM as an application that may be linked at run time. Notably, our formulation precludes any restrictions related to the type of neural network architecture (i.e., convolutional, fully-connected, etc.). This allows for potential studies of complicated neural architectures for practical CFD problems. In addition, the proposed module outlines a path towards an open-source, unified and transparent framework for computational fluid dynamics and machine learning.
rate research
Read More
We outline the development of a general-purpose Python-based data analysis tool for OpenFOAM. Our implementation relies on the construction of OpenFOAM applications that have bindings to data analysis libraries in Python. Double precision data in OpenFOAM is cast to a NumPy array using the NumPy C-API and Python modules may then be used for arbitrary data analysis and manipulation on flow-field information. We highlight how the proposed wrapper may be used for an in-situ online singular value decomposition (SVD) implemented in Python and accessed from the OpenFOAM solver PimpleFOAM. Here, `in-situ refers to a programming paradigm that allows for a concurrent computation of the data analysis on the same computational resources utilized for the partial differential equation solver. In addition, to demonstrate data-parallel analyses, we deploy a distributed SVD, which collects snapshot data across the ranks of a distributed simulation to compute the global left singular vectors. Crucially, both OpenFOAM and Python share the same message passing interface (MPI) communicator for this deployment which allows Python objects and functions to exchange NumPy arrays across ranks. Subsequently, we provide scaling assessments of this distributed SVD on multiple nodes of Intel Broadwell and KNL architectures for canonical test cases such as the large eddy simulations of a backward facing step and a channel flow at friction Reynolds number of 395. Finally, we demonstrate the deployment of a deep neural network for compressing the flow-field information using an autoencoder to demonstrate an ability to use state-of-the-art machine learning tools in the Python ecosystem.
Batch-splitting (data-parallelism) is the dominant distributed Deep Neural Network (DNN) training strategy, due to its universal applicability and its amenability to Single-Program-Multiple-Data (SPMD) programming. However, batch-splitting suffers from problems including the inability to train very large models (due to memory constraints), high latency, and inefficiency at small batch sizes. All of these can be solved by more general distribution strategies (model-parallelism). Unfortunately, efficient model-parallel algorithms tend to be complicated to discover, describe, and to implement, particularly on large clusters. We introduce Mesh-TensorFlow, a language for specifying a general class of distributed tensor computations. Where data-parallelism can be viewed as splitting tensors and operations along the batch dimension, in Mesh-TensorFlow, the user can specify any tensor-dimensions to be split across any dimensions of a multi-dimensional mesh of processors. A Mesh-TensorFlow graph compiles into a SPMD program consisting of parallel operations coupled with collective communication primitives such as Allreduce. We use Mesh-TensorFlow to implement an efficient data-parallel, model-parallel version of the Transformer sequence-to-sequence model. Using TPU meshes of up to 512 cores, we train Transformer models with up to 5 billion parameters, surpassing state of the art results on WMT14 English-to-French translation task and the one-billion-word language modeling benchmark. Mesh-Tensorflow is available at https://github.com/tensorflow/mesh .
Solving physical problems by deep learning is accurate and efficient mainly accounting for the use of an elaborate neural network. We propose a novel hybrid network which integrates two different kinds of neural networks: LSTM and ResNet, in order to overcome the difficulty met in solving strongly-oscillating dynamics of the systems time evolution. By taking the double-well model as an example we show that our new method can benefit from a pre-learning and verification of the periodicity of frequency by using the LSTM network, simultaneously making a high-fidelity prediction about the whole dynamics of system with ResNet, which is impossibly achieved in the case of single network. Such a hybrid network can be applied for solving cooperative dynamics in a system with fast spatial or temporal modulations, promising for realistic oscillation calculations under experimental conditions.
Measurements in Liquid Argon Time Projection Chamber (LArTPC) neutrino detectors, such as the MicroBooNE detector at Fermilab, feature large, high fidelity event images. Deep learning techniques have been extremely successful in classification tasks of photographs, but their application to LArTPC event images is challenging, due to the large size of the events. Events in these detectors are typically two orders of magnitude larger than images found in classical challenges, like recognition of handwritten digits contained in the MNIST database or object recognition in the ImageNet database. Ideally, training would occur on many instances of the entire event data, instead of many instances of cropped regions of interest from the event data. However, such efforts lead to extremely long training cycles, which slow down the exploration of new network architectures and hyperparameter scans to improve the classification performance. We present studies of scaling a LArTPC classification problem on multiple architectures, spanning multiple nodes. The studies are carried out on simulated events in the MicroBooNE detector. We emphasize that it is beyond the scope of this study to optimize networks or extract the physics from any results here. Institutional computing at Pacific Northwest National Laboratory and the SummitDev machine at Oak Ridge National Laboratorys Leadership Computing Facility have been used. To our knowledge, this is the first use of state-of-the-art Convolutional Neural Networks for particle physics and their attendant compute techniques onto the DOE Leadership Class Facilities. We expect benefits to accrue particularly to the Deep Underground Neutrino Experiment (DUNE) LArTPC program, the flagship US High Energy Physics (HEP) program for the coming decades.
Basal motion is the primary mechanism for ice flux outside Antarctica, yet a widely applicable model for predicting it in the absence of retrospective observations remains elusive. This is due to the difficulty in both observing small-scale bed properties and predicting a time-varying water pressure on which basal motion putatively depends. We take a Bayesian approach to these problems by coupling models of ice dynamics and subglacial hydrology and conditioning on observations of surface velocity in southwestern Greenland to infer the posterior probability distributions for eight spatially and temporally constant parameters governing the behavior of both the sliding law and hydrologic model. Because the model is computationally expensive, classical MCMC sampling is intractable. We skirt this issue by training a neural network as a surrogate that approximates the model at a sliver of the computational cost. We find that surface velocity observations establish strong constraints on model parameters relative to a prior distribution and also elucidate correlations, while the model explains 60% of observed variance. However, we also find that several distinct configurations of the hydrologic system and stress regime are consistent with observations, underscoring the need for continued data collection and model development.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
