Search NASA⌕ Search

SEARCH · Search NASA

Results for “Machine Learning Hardware”

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.

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

At least 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Elucidating and predicting the dynamic evolution of water and land systems due to natural and energy-related forcings

Focal Area(s): 3. Insight gleaned from complex data (both observed and simulated) using AI, big data analytics, and other advanced methods, including explainable AI and physics- or knowledge-guided AI; & 1. Data acquisition and assimilation enabled by machine learning, AI, and advanced methods including experimental/network design/optimization, unsupervised learning (including deep learning), and hardware-related efforts involving AI (e.g., edge computing). Science Challenge: Interactions between water, land, and energy systems are complex and occur on a variety of scales, ranging from local to basinal to regional. Accurately predicting the behavior of ground water and surface water systems for 5-10 years and beyond requires an understanding of the current system and the ability to model both the natural system at scale and human-induced forcings related to energy and other activities. Artificial intelligence and machine learning (AI/ML) combined with modern compilation and integration efforts for U.S. groundwater and surface water systems present potential solutions to bolstering detailed physics-based models of these systems. Big data tied with ML and physics-based modeling can drive breakthroughs in understanding the earth system, but research is often impeded by data access (e.g., privacy issues), quality, formats, gaps, multi-source, multi-scale, integration, and spatiotemporal challenges. Effective integration of real data and simulated (synthetic) data that fill gaps is critical. Overcoming these complex data and model integration challenges will enable a transformational approach to acquiring enhanced understanding of environmental systems.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

miniGAN: A Generative Adversarial Network proxy application WBS 2.2.6.08 ECP-2.1.3 (Q3 FY2020 Milestone Report) (V.1.0)

In order to support the machine learning co-design needs of ECP applications in current and future DOE HPC hardware, we have developed a generative adversarial network (GAN) proxy application, miniGAN, that has been released through the ECP proxy application suite. The proxy application is representative of the needs of ExaLearn's target applications, specifically the Cosmoflow and ExaGAN cosmology applications and the ExaWind energy application. The proxy application also demonstrates the first use of performance portable kernels within widely-used machine learning frameworks: PyTorch (Facebook) and Horovod (Uber). We provide performance scaling results for similar workloads to ExaGAN and a profile of individual GAN training components.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Framework for an adaptive integrated observation system using a hierarchy of machine learning approaches

Focal Area(s): 1. Data acquisition enabled by machine learning, AI, and advanced methods including experimental/network design/optimization, and hardware-related efforts involving AI. 2. Insight gleaned from complex measurements using AI, big data analytics, and other advanced methods, including explainable AI and physics- or knowledge-guided AI Science Challenge and Rationale: Atmospheric processes are stochastic, occur at scales from the micrometer to many kilometers, and are constantly changing over time. Characterizing these interactions and associated environmental conditions using traditional measurement techniques is difficult and can take years to build statistics on atmospheric phenomena that occurs episodically. Developing new innovative approaches to modify sampling strategies in real-time would enable the routine collection of targeted measurements focused on a specific set of science questions.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRSDate not supplied

Machine-learning Solution for Automatic Spacesuit Motion Recognition and Measurement from Conventional Video

Extravehicular Activity (EVA) spacesuits exhibit unique movement patterns due to their design characteristics. Mobility assessments using traditional motion capture systems are cost prohibitive and not feasible for some training conditions (e.g., simulated lunar outdoor terrain). This paper aims to present the ongoing development of machine learning solutions to quantify suit motions from conventional videos without special sensors or hardware. Preliminary work into this field was promising but given the fast growth in deep/machine learning technologies, external expertise was sought from open-source communities. Partnerships were formed with the NASA JSC Center of Excellence for Collaborative Innovation (CoCEI) and an execution crowdsourcing platform partner to solicit machine learning framework developments from external contenders. NASA provided contenders with images and video clips of spacesuits with simultaneously measured motion capture data during EVA simulation tasks. The contenders used this data to train and develop generalized algorithms to predict motions. At the end of the crowdsourcing event, the top five solutions were selected from 250 submissions. Each submission was tested and scored using video clips not previously disclosed to the contenders. The weighted scoring metrics measured how well the algorithm detected the suit shape, the 2D suit joint detection accuracy, and 3D joint detection accuracy. The winning solution was able to achieve roughly 85% prediction accuracy. Overall, the algorithms could efficiently detect various types of spacesuits and motions across different EVA environments such as the NASA Active Response Gravity Offload System (ARGOS). After continued improvements and validation, the fully developed system will enable EVA stakeholders to quantify suit kinematic patterns, which can help optimize suit, hardware, and task designs.

Linh Vu↗
DOE OSTI2020

An Intelligent Adaptable Monitoring Package. Final Report

The “Intelligent Adaptable Monitoring Package” project was a four-year effort that demonstrated the feasibility of integrated sensing packages at tidal and wave energy sites. Such integration is generally required by the breadth of sensors required to understand environmental effects at marine energy sites and the operational difficulty of deploying, maintaining, and recovering such sensors. Over the course of the project, the Adaptable Monitoring Package (AMP) was deployed in multiple settings, each corresponding to a project budget period: - Budget Period 1: Demonstration of cabled deployment at Pacific Northwest National Laboratory’s Marine Science Laboratory. The deployment highlighted AMP hardware endurance over a 4-month deployment in a tidally-dominated environment and laid the groundwork for machine learning algorithms to detect and classify targets present in active sonar data. - Budget Period 2: Demonstration of an autonomous deployment at PacWave South off the coast of Newport, Oregon. The deployment highlighted the stability of AMP hardware and software, with the autonomous package collecting data on a duty cycle over a 1.5-month deployment. - Budget Period 3: Demonstration of an autonomous deployment powered by a wave energy converter at the U.S. Navy’s Wave Energy Test Site. The deployment highlighted the potential of wave energy to power ocean observatories and led to the development of machine learning algorithms to detect and classify targets in optical camera data. In aggregate, this project’s greatest success was demonstrating the AMP’s flexibility in a range of deployment scenarios. Each budget period represented a “first of a kind” demonstration of integrated instrumentation – cabled AMP, autonomous AMP, wave-energy powered AMP – and each deployment helped to identify and set goals for the next. Further, despite the exploratory nature of these deployments, each one achieved high system up-time and proved that flexible integration of multiple sensors in a single package represents a viable strategy for marine energy environmental monitoring. The key lessons learned from the project are: - Without continuous power, either from a shore cable or in situ source, many of the benefits of integration are lost (If continuous power is not available, the ability to detect rare events is lost, as is the ability to minimize the risk of behavioral changes through adaptive sensing. However, even on a duty cycle, there is still value in being able to acquire synchronous data from multiple sensors.); and - Observations from a moving platform present substantially greater data processing challenges than those from stationary platforms. Finally, these deployments also demonstrate an important truth: successful integration alone does not guarantee that relevant data are collected. To grow the knowledge base about environmental interactions with marine energy converters, integrated systems, like the AMP, need to include the right sensor mix and connect the data pipelines to effective processing algorithms. These deployments establish a strong foundation for future collaborations with the environmental research community: not only to understand the environmental effects of marine energy, but also to improve our general ability to study life in the sea.

16 TIDAL AND WAVE POWER↗
DOE OSTI2023

Ultrafast radiographic imaging and tracking: An overview of instruments, methods, data, and applications

Ultrafast radiographic imaging and tracking (U-RadIT) use state-of-the-art ionizing particle and light sources to experimentally study sub-nanosecond transients or dynamic processes in physics, chemistry, biology, geology, materials science and other fields. These processes are fundamental to modern technologies and applications, such as nuclear fusion energy, advanced manufacturing, communication, and green transportation, which often involve one mole or more atoms and elementary particles, and thus are challenging to compute by using the first principles of quantum physics or other forward models. One of the central problems in U-RadIT is to optimize information yield through, e.g. high-luminosity X-ray and particle sources, efficient imaging and tracking detectors, novel methods to collect data, and large-bandwidth online and offline data processing, regulated by the underlying physics, statistics, and computing power. We review and highlight recent progress in: (a.) Detectors such as high-speed complementary metal-oxide semiconductor (CMOS) cameras, hybrid pixelated array detectors integrated with Timepix4 and other application-specific integrated circuits (ASICs), and digital photon detectors; (b.) U-RadIT modalities such as dynamic phase contrast imaging, dynamic diffractive imaging, and four-dimensional (4D) particle tracking; (c.) U-RadIT data and algorithms such as neural networks and machine learning, and (d.) Applications in ultrafast dynamic material science using XFELs, synchrotrons and laser-driven sources. Hardware-centric approaches to U-RadIT optimization are constrained by detector material properties, low signal-to-noise ratio, high cost and long development cycles of critical hardware components such as ASICs. Interpretation of experimental data, including comparisons with forward models, is frequently hindered by sparse measurements, model and measurement uncertainties, and noise. Alternatively, U-RadIT make increasing use of data science and machine learning algorithms, including experimental implementations of compressed sensing. Machine learning and artificial intelligence approaches, refined by physics and materials information, may also contribute significantly to data interpretation, uncertainty quantification and U-RadIT optimization.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

A Reconfigurable Neural Network ASIC for Detector Front-End Data Compression at the HL-LHC

Despite advances in the programmable logic capabilities of modern trigger systems, a significant bottleneck remains in the amount of data to be transported from the detector to off-detector logic where trigger decisions are made. We demonstrate that a neural network (NN) autoencoder model can be implemented in a radiation-tolerant application-specific integrated circuit (ASIC) to perform lossy data compression alleviating the data transmission problem while preserving critical information of the detector energy profile. For our application, we consider the high-granularity calorimeter from the Compact Muon Solenoid (CMS) experiment at the CERN Large Hadron Collider. The advantage of the machine learning approach is in the flexibility and configurability of the algorithm. By changing the NN weights, a unique data compression algorithm can be deployed for each sensor in different detector regions and changing detector or collider conditions. To meet area, performance, and power constraints, we perform quantization-aware training to create an optimized NN hardware implementation. The design is achieved through the use of high-level synthesis tools and the hls4ml framework and was processed through synthesis and physical layout flows based on a low-power (LP)-CMOS 65-nm technology node. The flow anticipates 200 Mrad of ionizing radiation to select gates and reports a total area of 3.6 mm 2 and consumes 95 mW of power. The simulated energy consumption per inference is 2.4 nJ. Furthermore, this is the first radiation-tolerant on-detector ASIC implementation of an NN that has been designed for particle physics applications.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

Machine learning for seismic low-frequency extrapolation

The cycle-skipping problem that plagues full waveform inversion (FWI) can be at least partially mitigated if low frequencies (which encode the kinematics of wave propagation in seismic data) are recorded. However, seismic sources and receivers are band-limited, so seismic data does not generally include signals down to 0 Hz. To improve our ability to solve the seismic inverse problem, one can synthesize this missing low-frequency (LF) content from the recorded high-frequency (HF) data using machine learning (ML) models. Deep learning models such as convolutional neural networks (CNNs) demonstrate impressive ability to perform low frequency extrapolation. However, such models require powerful hardware (GPU machines) and careful training. We assess the extrapolation capabilities of three different ML models that do not require GPU machines, namely, random forest, Gaussian process regression and gradient boosting, on both synthetic and real data. Experimental results on two synthetic data sets (generated from a low velocity lens embedded in a homogeneous medium, and the Marmousi model) demonstrate that FWI applied to the extrapolated data consistently improves inversion accuracy relative to FWI applied to the original data sets that do not contain low frequencies. Application of low-frequency extrapolation to real data from the Northwest Shelf of Australia demonstrates that tree-based ML models such as gradient boosting can outperform CNNs in terms of both accuracy and computational cost on non-GPU architectures.

58 GEOSCIENCES↗
DOE OSTI2021

Quantum Divide and Compute: Exploring the Effect of Different Noise Sources

Abstract Our recent work (Ayral et al. in Proceedings of IEEE computer society annual symposium on VLSI, ISVLSI, pp 138–140, 2020. 10.1109/ISVLSI49217.2020.00034 ) showed the first implementation of the Quantum Divide and Compute (QDC) method, which allows to break quantum circuits into smaller fragments with fewer qubits and shallower depth. This accommodates the limited number of qubits and short coherence times of quantum processors. This article investigates the impact of different noise sources—readout error, gate error and decoherence—on the success probability of the QDC procedure. We perform detailed noise modeling on the Atos Quantum Learning Machine, allowing us to understand tradeoffs and formulate recommendations about which hardware noise sources should be preferentially optimized. We also describe in detail the noise models we used to reproduce experimental runs on IBM’s Johannesburg processor. This article also includes a detailed derivation of the equations used in the QDC procedure to compute the output distribution of the original quantum circuit from the output distribution of its fragments. Finally, we analyze the computational complexity of the QDC method for the circuit under study via tensor-network considerations, and elaborate on the relation the QDC method with tensor-network simulation methods.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2014

Vision Based Autonomous Robotic Control for Advanced Inspection and Repair

The advanced inspection system is an autonomous control and analysis system that improves the inspection and remediation operations for ground and surface systems. It uses optical imaging technology with intelligent computer vision algorithms to analyze physical features of the real-world environment to make decisions and learn from experience. The advanced inspection system plans to control a robotic manipulator arm, an unmanned ground vehicle and cameras remotely, automatically and autonomously. There are many computer vision, image processing and machine learning techniques available as open source for using vision as a sensory feedback in decision-making and autonomous robotic movement. My responsibilities for the advanced inspection system are to create a software architecture that integrates and provides a framework for all the different subsystem components; identify open-source algorithms and techniques; and integrate robot hardware.

sensory feedback↗
DOE OSTI2019

Restricted Boltzmann Machines for galaxy morphology classification with a quantum annealer

We present the application of Restricted Boltzmann Machines (RBMs) to the task of astronomical image classification using a quantum annealer built by D-Wave Systems. Morphological analysis of galaxies provides critical information for studying their formation and evolution across cosmic time scales. We compress the images using principal component analysis to fit a representation on the quantum hardware. Then, we train RBMs with discriminative and generative algorithms, including contrastive divergence and hybrid generative-discriminative approaches. We compare these methods to Quantum Annealing (QA), Markov Chain Monte Carlo (MCMC) Gibbs Sampling, Simulated Annealing (SA) as well as machine learning algorithms like gradient boosted decision trees. We find that RBMs implemented on D-wave hardware perform well, and that they show some classification performance advantages on small datasets, but they don't offer a broadly strategic advantage for this task. During this exploration, we analyzed the steps required for Boltzmann sampling with the D-Wave 2000Q, including a study of temperature estimation, and examined the impact of qubit noise by comparing and contrasting the original D-Wave 2000Q to the lower-noise version recently made available. While these analyses ultimately had minimal impact on the performance of the RBMs, we include them for reference.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Performance on HPC Platforms Is Possible Without C++

Computing at large scales has become extremely challenging due to increasing heterogeneity in both hardware and software. More and more scientific workflows must tackle a range of scales and use machine learning and AI intertwined with more traditional numerical modeling methods, placing more demands on computational platforms. These constraints indicate a need to fundamentally rethink the way computational science is done and the tools that are needed to enable these complex workflows. The current set of C++-based solutions may not suffice, and relying exclusively upon C++ may not be the best option, especially because several newer languages and boutique solutions offer more robust design features to tackle the challenges of heterogeneity. In June 2023, we held a mini symposium that explored the use of newer languages and heterogeneity solutions that are not tied to C++ and that offer options beyond template metaprogramming and Parallel. For for performance and portability. In conclusion, we describe some of the presentations and discussion from the mini symposium in this article.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Machine learning for collective variable discovery and enhanced sampling in biomolecular simulation

Classical molecular dynamics simulates the time evolution of molecular systems through the phase space spanned by the positions and velocities of the constituent atoms. Molecular-level thermodynamic, kinetic, and structural data extracted from the resulting trajectories provide valuable information for the understanding, engineering, and design of biological and molecular materials. The cost of simulating many-body atomic systems makes simulations of large molecules prohibitively expensive, and the high-dimensionality of the resulting trajectories presents a challenge for analysis. Driven by advances in algorithms, hardware, and data availability, there has been a flare of interest in recent years in the applications of machine learning – especially deep learning – to molecular simulation. Furthermore, these techniques have demonstrated great power and flexibility in both extracting mechanistic understanding of the important nonlinear collective variables governing the dynamics of a molecular system, and in furnishing good low-dimensional system representations with which to perform enhanced sampling or develop long-timescale dynamical models. It is the purpose of this article to introduce the key machine learning approaches, describe how they are married with statistical mechanical theory into domain-specific tools, and detail applications of these approaches in understanding and accelerating biomolecular simulation.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2025

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗
DOE OSTI2018

A Heterogeneity-Aware Task Scheduler for Spark

Big data processing systems such as Spark are employed in an increasing number of diverse applications-such as machine learning, graph computation, and scientific computing-each with dynamic and different resource needs. These applications increasingly run on heterogeneous hardware, e.g., with out-of-core accelerators. However, big data platforms do not factor in the multi-dimensional heterogeneity of applications and hardware. This leads to a fundamental mismatch between the application and hardware characteristics, and the resource scheduling adopted in big data platforms. For example, Hadoop and Spark consider only data locality when assigning tasks to nodes, and typically disregard the hardware capabilities and suitability to specific application requirements. In this paper, we present RUPAM, a heterogeneity-aware task scheduling system for big data platforms, which considers both task-level resource characteristics and underlying hardware characteristics, as well as preserves data locality. RUPAM adopts a simple yet effective heuristic to decide the dominant scheduling factor (e.g., CPU, memory, or I/O), given a task in a particular stage. Our experiments show that RUPAM is able to improve the performance of representative applications by up to 62.3% compared to the standard Spark scheduler.

Computer Science↗
DOE OSTI2021

Implementing a neural network interatomic model with performance portability for emerging exascale architectures

The two main thrusts of computational science are increasingly accurate predictions and faster calculations; to this end, the zeitgeist in molecular dynamics (MD) simulations is pursuing machine learned and data driven interatomic models, e.g. neural network potentials, and novel hardware architectures, e.g. GPUs. Current implementations of neural network potentials are orders of magnitude slower than traditional interatomic models and while looming exascale computing offers the ability to run large, accurate simulations with these models, achieving portable performance for MD with new and varied exascale hardware requires rethinking traditional algorithms, using novel data structures, and library solutions. We re-implement a neural network interatomic model in CabanaMD, an MD proxy application, built on libraries developed for performance portability. Our implementation shows significantly improved thread scaling in this complex kernel as compared to a current LAMMPS implementation, across both strong and weak scaling. Our single-source solution enables simulations up to 20 million atoms on a single CPU node and 4 million atoms with improved performance on a single GPU. Furthermore, we also explore parallelism and data layout choices (using flexible data structures called AoSoAs) and their effect on performance, seeing up to ~50% and ~5% improvements in performance on a GPU by choosing the right level of parallelism and data layout respectively.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Mixed Precision: A Strategy for New Science Opportunities

Since the days of vector supercomputers, computational scientists have relied on high-precision arithmetic to accurately solve problems. But changes to hardware, spurred by the demand for more computing capability and growth in machine learning, have researchers considering lower precision alternatives.

Computer Science↗
DOE OSTI2023

VDiSC: An Open Source Framework for Distributed Smart City Vision and Biometric Surveillance Networks

Recent global growth in the interest of smart cities has led to trillions of dollars of investment toward research and development. These connected cities have the potential to create a symbiosis of technology and society and revolutionize the cost of living, safety, ecological sustainability, and quality of life of societies on a world-wide scale. Some key components of the smart city construct are connected smart grids, self-driving cars, federated learning systems, smart utilities, large-scale public transit, and proactive surveillance systems. While exciting in prospect, these technologies and their subsequent integration cannot be attempted without addressing the potential societal impacts of such a high degree of automation and data sharing. Additionally, the feasibility of coordinating so many disparate tasks will require a fast, extensible, unifying framework. To that end, we propose the Distributed Smart City framework for Vision, or VDiSC. VDiSC serves as a unified biometric API harness that allows for seamless evaluation, deployment, and simple pipeline creation for heterogeneous biometric software. VDiSC additionally provides a fully declarative capability for defining and coordinating custom machine learning and sensor pipelines, allowing the distribution of processes across otherwise incompatible hardware and networks. VDiSC ultimately provides a way to quickly configure, hot-swap, and expand large coordinated or federated systems online without interruptions for maintenance. Because much of the data collected in a smart city contains Personally Identifying Information (PII), VDiSC also provides built-in tools and layers to ensure secure and encrypted streaming, storage, and access of PII data across distributed systems.

Brogan, Joel↗