SEARCH · Engineering Papers

Results for “deep learning (DL)”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 145 records · Page 8

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Uncertainty Aware Deep Learning for Fault Prediction Using Multivariate Time Series Signals

The superconducting radio-frequency cavities are a crucial component of the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. When a cavity faults, beam delivery to experimental end users is disrupted. Prediction of cavity faults prior to onset is essential to reduce operation and maintenance costs. In this work, a parallel long short-term memory (LSTM)-convolution neural network (CNN)-based deep learning (DL) model is proposed to predict impending faults using pre-fault signals. Further, we introduce an uncertainty quantification approach using Monte Carlo dropout with the LSTM-CNN model to ascertain confidence in the prediction. The model was tested using multivariate time series signals from stable cavity operations and before faults. Initial results show that on the test dataset, the model can identify impending faults before their onset with an average 10-fold cross validation accuracy of 97.39% and a standard deviation of 0.12% using a 100-ms time window. It is also observed that the model performs better as the prediction time moves closer to the fault onset. For additional context, we compare the performance of the model with three machine-learning-based (ML) fault prediction models. Our proposed parallel LSTM-CNN-based DL method shows better performance than the ML-based methods.

Rahman, Md Monibor↗

DOE OSTI2024

Accelerating Lossy and Lossless Compression on Emerging BlueField DPU Architectures

Data compression has become a crucial technique in addressing performance bottlenecks caused by increasing data volumes in High-Performance Computing (HPC), Big Data, and Deep Learning (DL). Despite its potential to boost system performance, recent studies have identified significant challenges with existing compression methods, mainly due to their high computational demands amidst continuously growing data sizes. Concurrently, the advent of Data Processing Units (DPUs), equipped with programmable System-on-Chip (SoC) and specialized compression accelerators, offers a promising opportunity to alter the landscape of data compression. This paper explores the complexities and potential of leveraging NVIDIA BlueField DPUs to accelerate lossy and lossless compression. Towards this, we introduce PEDAL, an innovative library that leverages the hardware capabilities of DPUs to unify and optimize data compression designs. Moreover, we seamlessly co-design PEDAL with the popular MPICH MPI library, demonstrating up to 101x speedup in compression time and 88x decrease in communication latency. Drawing on these achievements, we share our experience with various research communities about accelerating data compression on DPUs in communication-oriented HPC scenarios.

Li, Yuke↗

DOE OSTI2026

FitCache: A Transparent Drop-In Framework for Multi-Tier Caching to Accelerate Distributed Deep Learning Workloads

Training in Deep learning (DL) remains highly compute- and data-intensive, with I/O becoming a critical bottleneck as models and datasets scale. Recent studies report that data loading can dominate training time, especially on large-scale HPC systems with shared parallel file systems (PFS). Existing caching approaches either rely on single-tier designs or require intrusive modifications to training pipelines, limiting their portability and effectiveness. In this work, we present FitCache, a transparent drop-in framework for multi-tier caching to accelerate distributed DL training by coordinating fast local memory (e.g., DRAM, Persistent Memory (PMem)) and NVMe as hierarchical caches atop PFS. Our design adapts to hardware diversity, i.e., if NVMe is missing, memory transparently acts as a caching tier, ensuring stable performance. FitCache transparently intercepts I/O requests and issues concurrent fetches across all tiers, returning data from the fastest responder without centralized metadata or static redirection paths. FitCache adapts to dynamic workloads and heterogeneous clusters while maintaining POSIX compatibility. Experiments on Frontier (2048 GPUs) and smaller research clusters show that FitCache reduces training time by up to 40% and per-batch I/O latency by up to 71.6% compared to Lustre Orion PFS, offering a drop-in solution for scalable DL training.

Hu, Guangxing [ORNL] (ORCID:0009000283203614)↗

DOE OSTI2021

Characterizing Machine Learning I/O Workloads on Leadership Scale HPC Systems

High performance computing (HPC) is no longer solely limited to traditional workloads such as simulation and modeling. With the increase in the popularity of machine learning (ML) and deep learning (DL) technologies, we are observing that an increasing number of HPC users are incorporating ML methods into their workflow and scientific discovery processes, across a wide spectrum of science domains such as biology, earth science, and physics. This gives rise to a diverse set of I/O patterns than the traditional checkpoint/restart-based HPC I/O behavior. The details of the I/O characteristics of such ML I/O workloads have not been studied extensively for large-scale leadership HPC systems. This paper aims to fill that gap by providing an in-depth analysis to gain an understanding of the I/O behavior of ML I/O workloads using darshan - an I/O characterization tool designed for lightweight tracing and profiling. We study the darshan logs of more than 23, 000 HPC ML I/O jobs over a time period of one year running on Summit - the second-fastest supercomputer in the world. This paper provides a systematic I/O characterization of ML I/O jobs running on a leadership scale supercomputer to understand how the I/O behavior differs across science domains and the scale of workloads, and analyze the usage of parallel file system and burst buffer by ML I/O workloads.

Paul, Arnab↗

DOE OSTI2021

HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization

We present a new software, HYPPO, that enables the automatic tuning of hyperparameters of various deep learning (DL) models. Unlike other hyperparameter optimization (HPO) methods, HYPPO uses adaptive surrogate models and directly accounts for uncertainty in model predictions to find accurate and reliable models that make robust predictions. Using asynchronous nested parallelism, we are able to significantly alleviate the computational burden of training complex architectures and quantifying the uncertainty. HYPPO is implemented in Python and can be used with both TensorFlow and PyTorch libraries. We demonstrate various software features on time-series prediction and image classification problems as well as a scientific application in computed tomography image reconstruction. Finally, we show that (1) we can reduce by an order of magnitude the number of evaluations necessary to find the most optimal region in the hyperparameter space and (2) we can reduce by two orders of magnitude the throughput for such HPO process to complete.

adaptation models↗

DOE OSTI2023

Machine Learning Based Resilience Testing of an Address Randomization Cyber Defense

Moving target defenses (MTDs) are widely used as an active defense strategy for thwarting cyberattacks on cyber-physical systems by increasing diversity of software and network paths. Recently, machine Learning (ML) and deep Learning (DL) models have been demonstrated to defeat some of the cyber defenses by learning attack detection patterns and defense strategies. It raises concerns about the susceptibility of MTD to ML and DL methods. Here, in this article, we analyze the effectiveness of ML and DL models when it comes to deciphering MTD methods and ultimately evade MTD-based protections in real-time systems. Specifically, we consider a MTD algorithm that periodically randomizes address assignments within the MIL-STD-1553 protocol—a military standard serial data bus. Two ML and DL-based tasks are performed on MIL-STD-1553 protocol to measure the effectiveness of the learning models in deciphering the MTD algorithm: 1) determining whether there is an address assignments change i.e., whether the given system employs a MTD protocol and if it does 2) predicting the future address assignments. The supervised learning models (random forest and k-nearest neighbors) effectively detected the address assignment changes and classified whether the given system is equipped with a specified MTD protocol. On the other hand, the unsupervised learning model (K-means) was significantly less effective. The DL model (long short-term memory) was able to predict the future addresses with varied effectiveness based on MTD algorithm's settings.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

DOE OSTI2023

Solving Seismic Wave Equations on Variable Velocity Models With Fourier Neural Operator

Here, in the study of subsurface seismic imaging, solving the acoustic wave equation is a pivotal component in existing models. The advancement of deep learning (DL) enables solving partial differential equations (PDEs), including wave equations, by applying neural networks to identify the mapping between the inputs and the solution. This approach can be faster than traditional numerical methods when numerous instances are to be solved. Previous works that concentrate on solving the wave equation by neural networks consider either a single velocity model or multiple simple velocity models, which is restricted in practice. Instead, inspired by the idea of operator learning, this work leverages the Fourier neural operator (FNO) to effectively learn the frequency domain seismic wavefields under the context of variable velocity models. We also propose a new framework paralleled FNO (PFNO) for efficiently training the FNO-based solver given multiple source locations and frequencies. Numerical experiments demonstrate the high accuracy of both FNO and PFNO with complicated velocity models in the OpenFWI datasets. Furthermore, the cross-dataset generalization test verifies that PFNO adapts to out-of-distribution velocity models. Finally, PFNO admits higher computational efficiency on large-scale testing datasets than the traditional finite-difference method. The aforementioned advantages endow the FNO-based solver with the potential to build powerful models for research on seismic waves.

58 GEOSCIENCES↗

DOE OSTI2022

Learning Global Proliferation Expertise Evolution Using AI-Driven Analytics and Public Information

Detecting and anticipating global proliferation expertise and capability evolution from unstructured, noisy, and incomplete public data streams is a highly desired, but extremely challenging task. Here, in this article, we present our pioneering data-driven approach to support the non-proliferation mission to detect and explain the evolution of proliferation expertise and capability development globally from terabytes of publicly available information (PAI), focusing on our knowledge extraction pipeline and descriptive analytics. We first discuss how we fuse nine open-source data streams, including multilingual data, to convert 4 TB of unstructured data to structured knowledge and encode dynamically evolving proliferation expertise representations—content and context graphs. For this, we rely on natural language processing (NLP) and deep learning (DL) models to perform information extraction, topic modeling, and distributed text representation (aka embedding) learning. We then present interactive, usable, and explainable descriptive analytics to refine domain knowledge and present it in a human-understandable form. Finally, we introduce future work avenues that will leverage our dynamic knowledge representations and descriptive analytics to enable predictive and prescriptive inferences to achieve real-time domain understanding and contextual reasoning about global proliferation expertise and capability evolution.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

DOE OSTI2026

3D Deep Learning Joint Inversion of Active Seismic Full Waveform and Passive Seismic Traveltime Data for Reservoir Imaging and Uncertainty Quantification

Here, we present deep learning (DL) networks for three-dimensional (3D) joint inversion of active seismic full waveform and passive seismic traveltime data to image reservoirs and their properties and quantify imaging uncertainties. Active seismic full-waveform data can provide high-resolution monitoring images but are collected only intermittently because of their high acquisition cost. In contrast, passive seismic data can be gathered at relatively low cost between regular active surveys, although their imaging quality can be compromised by factors such as low signal-to-noise ratios and limited ray coverage of the target. Although these datasets are routinely acquired together at CO 2 storage sites, their combined inversion within a 3D DL framework has not been previously demonstrated. To our knowledge, this is the first study to address this gap, combining the strength of both data types. For efficient data storage and DL training with large 3D seismic datasets, we use a 3D data matrix in which a random number of passive seismic traveltime data are stored as parabolic envelopes using one-hot encoding and a 3D full-waveform data matrix in which multiple shot gathers are summed. Two network architectures are evaluated: a single-encoder U-Net for single-data type inversion and a dual-encoder U-Net for joint inversion of active and passive seismic data. We also evaluate the single-encoder U-Net for joint inversion by concatenating full-waveform data and traveltime data. We propose a systematic approach for selecting an optimal dropout rate that balances regularization during training and Monte Carlo dropout-based uncertainty quantification during prediction by examining the correlation coefficient between standard deviation and prediction error, along with the training misfit, across a range of dropout rates. 3D DL inversion experiments include five different network configurations, with evaluations under ideal, noisy and dropout-enabled conditions. Both model and data uncertainties are assessed, as well as their combined effects. Across all conditions, the networks consistently predict accurate CO 2 saturation models with low prediction errors, such as a structural similarity index of 0.993 and CO 2 difference of 1.1%. Uncertainty estimates show strong spatial correlation with prediction errors, confirming the effectiveness of the proposed dropout selection approach. The results demonstrate that our DL approach, utilizing compact data representations and appropriate uncertainty quantification, yields accurate subsurface images under various inversion conditions and provides valuable insights into the reliability of predictions.

Um, Evan Schankee [Lawrence Berkeley National Labo↗

DOE OSTI2021

Predicting Nugget Size of Resistance Spot Welds Using Infrared Thermal Videos With Image Segmentation and Convolutional Neural Network

Resistance spot welding (RSW) is a widely adopted joining technique in automotive industry. Recent advancement in sensing technology makes it possible to collect thermal videos of the weld nugget during RSW using an infrared (IR) camera. The effective and timely analysis of such thermal videos has the potential of enabling in situ nondestructive evaluation (NDE) of the weld nugget by predicting nugget thickness and diameter. Deep learning (DL) has demonstrated to be effective in analyzing imaging data in many applications. However, the thermal videos in RSW present unique data-level challenges that compromise the effectiveness of most pre-trained DL models. We propose a novel image segmentation method for handling the RSW thermal videos to improve the prediction performance of DL models in RSW. The proposed method transforms raw thermal videos into spatial-temporal instances in four steps: video-wise normalization, removal of uninformative images, watershed segmentation, and spatial-temporal instance construction. The extracted spatial-temporal instances serve as the input data for training a DL-based NDE model. The proposed method is able to extract high-quality data with spatial-temporal correlations in the thermal videos, while being robust to the impact of unknown surface emissivity. Overall, our case studies demonstrate that the proposed method achieves better prediction of nugget thickness and diameter than predicting without the transformation.

42 ENGINEERING↗

DOE OSTI2021

Reconfigurable Framework for Resilient Semantic Segmentation for Space Applications

Deep learning (DL) presents new opportunities for enabling spacecraft autonomy, onboard analysis, and intelligent applications for space missions. However, DL applications are computationally intensive and often infeasible to deploy on radiation-hardened (rad-hard) processors, which traditionally harness a fraction of the computational capability of their commercial-off-the-shelf counterparts. Commercial FPGAs and system-on-chips present numerous architectural advantages and provide the computation capabilities to enable onboard DL applications; however, these devices are highly susceptible to radiation-induced single-event effects (SEEs) that can degrade the dependability of DL applications. In this article, we propose Reconfigurable ConvNet (RECON), a reconfigurable acceleration framework for dependable, high-performance semantic segmentation for space applications. In RECON, we propose both selective and adaptive approaches to enable efficient SEE mitigation. In our selective approach, control-flow parts are selectively protected by triple-modular redundancy to minimize SEE-induced hangs, and in our adaptive approach, partial reconfiguration is used to adapt the mitigation of dataflow parts in response to a dynamic radiation environment. Combined, both approaches enable RECON to maximize system performability subject to mission availability constraints. We perform fault injection and neutron irradiation to observe the susceptibility of RECON and use dependability modeling to evaluate RECON in various orbital case studies to demonstrate a 1.5–3.0× performability improvement in both performance and energy efficiency compared to static approaches.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Topological Interpretability for Deep Learning

With the growing adoption of AI-based systems across everyday life, the need to understand their decision-making mechanisms is correspondingly increasing. The level at which we can trust the statistical inferences made from AI-based decision systems is an increasing concern, especially in high-risk systems such as criminal justice or medical diagnosis, where incorrect inferences may have tragic consequences. Despite their successes in providing solutions to problems involving real-world data, deep learning (DL) models cannot quantify the certainty of their predictions. These models are frequently quite confident, even when their solutions are incorrect. This work presents a method to infer prominent features in two DL classification models trained on clinical and non-clinical text by employing techniques from topological and geometric data analysis. We create a graph of a model's feature space and cluster the inputs into the graph's vertices by the similarity of features and prediction statistics. We then extract subgraphs demonstrating high-predictive accuracy for a given label. These subgraphs contain a wealth of information about features that the DL model has recognized as relevant to its decisions. We infer these features for a given label using a distance metric between probability measures, and demonstrate the stability of our method compared to the LIME and SHAP interpretability methods. This work establishes that we may gain insights into the decision mechanism of a DL model. This method allows us to ascertain if the model is making its decisions based on information germane to the problem or identifies extraneous patterns within the data.

Spannaus, Adam↗

DOE OSTI2024

The Case for Co-Designing Model Architectures with Hardware

While GPUs are responsible for training the vast majority of state-of-the-art deep learning models, the implications of their architecture are often overlooked when designing new deep learning (DL) models. As a consequence, modifying a DL model to be more amenable to the target hardware can significantly improve the runtime performance of DL training and inference. In this paper, we provide a set of guidelines for users to maximize the runtime performance of their transformer models. These guidelines have been created by carefully considering the impact of various model hyperparameters controlling model shape on the efficiency of the underlying computation kernels executed on the GPU. We find the throughput of models with “efficient” model shapes is up to 39% higher while preserving accuracy compared to models with a similar number of parameters but with unoptimized shapes.

Yin, Junqi↗

DOE OSTI2020

Wattile: Probabilistic Deep Learning-based Forecasting of Building Energy Consumption [SWR-20-94]

Accurate energy forecasting is becoming critical due to many reasons: i ) optimal distributed energy resources operations and dispatch, ii) fault detection and diagnostics, and iii) meeting operational energy efficiency targets. Wattile uses deep learning (DL) for the building's short-term load forecasting application. Two specific types of neural networks called, Long Short Term Memory (LSTM) and Sequence-to-Sequence (S2S) models are used to make predictions. Forecasting models are trained using online historical weather and occupancy indicator data streams from the Intelligent Campus Program's data acquisition systems at the National Renewable Energy Laboratory (NREL) for main meters and sub-meters of multiple building types. These models use probabilistic methods to provide quantile-based forecasts in addition to nominal conditional median predictions of electricity consumption.

Frank, Stephen↗

DOE OSTI2022

LivermorE Al Projector for Computed Tomography Tasks

With recent computed tomography (CT) efforts using Artificial Intelligence (AI) and Deep Learning (DL)techniques, there is a strong need for differentiable forward projection models that can be integrated into existing DL frameworks. We developed a pytorch-based package library providing differentiable forward and back projection functions and classes to facilitate forward and back propagation of CT operations in the training procedure. This forward projectors support three CT projection geometries: cone, parallel and modular beams. This package can be used with both CPU and GPU with CUDA.

Kim, Hyojin↗

DOE OSTI2024

Multivariate Time Series Intermittent Fault Detectionin Controller Area Network CAN

Fault detection in Controller Area Network (CAN) systems is crucial for ensuring the reliability and safety of automotive and industrial applications. This study investigates and compares the effectiveness of time series classification models for supervised fault detection in CAN data. This repository contains the code and data for our benchmarking experiment aimed at detecting intermittent faults in automotive Controller Area Network (CAN) data. The goal of this project is to compare various machine learning (ML) and deep learning (DL) models using different Time Series Cross-Validation (TSCV) techniques to evaluate their effectiveness in a streaming environment for fault detection.

Hespeler, Steven [Oak Ridge National Laboratory (O↗

DOE OSTI2022

Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules

Abstract Graph Convolutional Neural Network (GCNN) is a popular class of deep learning (DL) models in material science to predict material properties from the graph representation of molecular structures. Training an accurate and comprehensive GCNN surrogate for molecular design requires large-scale graph datasets and is usually a time-consuming process. Recent advances in GPUs and distributed computing open a path to reduce the computational cost for GCNN training effectively. However, efficient utilization of high performance computing (HPC) resources for training requires simultaneously optimizing large-scale data management and scalable stochastic batched optimization techniques. In this work, we focus on building GCNN models on HPC systems to predict material properties of millions of molecules. We use HydraGNN, our in-house library for large-scale GCNN training, leveraging distributed data parallelism in PyTorch. We use ADIOS, a high-performance data management framework for efficient storage and reading of large molecular graph data. We perform parallel training on two open-source large-scale graph datasets to build a GCNN predictor for an important quantum property known as the HOMO-LUMO gap. We measure the scalability, accuracy, and convergence of our approach on two DOE supercomputers: the Summit supercomputer at the Oak Ridge Leadership Computing Facility (OLCF) and the Perlmutter system at the National Energy Research Scientific Computing Center (NERSC). We present our experimental results with HydraGNN showing (i) reduction of data loading time up to 4.2 times compared with a conventional method and (ii) linear scaling performance for training up to 1024 GPUs on both Summit and Perlmutter.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Three-dimensional cooperative inversion of airborne magnetic and gravity gradient data using deep-learning techniques

Using multiple geophysical methods has become a prevailing approach in numerous geophysical applications to investigate subsurface structures and parameters. These multimethod-based exploration strategies have the potential to greatly diminish uncertainties and ambiguities encountered during geophysical data analysis and interpretation. One of the applications is the cooperative inversion of airborne magnetic and gravity gradient data for the interpretation of data obtained in mineral, oil and gas, and geothermal explorations. In this paper, a unified cooperative inversion framework is designed by combining the standard separate inversions with a deep neural network (DNN), which serves as the link between different types of data. A well-trained DNN takes the separately inverted susceptibility and density models as the inputs and provides improved models that will be used as the initial models of deterministic inversions. A two-round iteration strategy is adopted to guarantee the reasonability of the recovered models and overall efficiency of the inversion. In addition, this deep-learning (DL)-based framework demonstrates excellent generalization abilities when tested on models that are entirely distinct from the training data sets. The framework can easily incorporate multiphysics without necessitating any structural changes to the network. Synthetic experiments validate that our DL-based method outperforms conventional separate inversions and cross-gradient-based joint inversion in view of the accuracy of the recovered models and inversion efficiency. Successful application to field data further verifies the effectiveness of our DL-based method.

Geochemistry & Geophysics↗