Search NASA⌕ Search

SEARCH · Search NASA

Results for “Operator learning”

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 1,315 records · Page 73
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Hardware-accelerated inference for real-time gravitational-wave astronomy

The field of transient astronomy has seen a revolution with the first gravitational-wave detections and the arrival of multi-messenger observations they enabled. Transformed by the first detection of binary black hole and binary neutron star mergers, computational demands in gravitational-wave astronomy are expected to grow by at least a factor of two over the next five years as the global network of kilometer-scale interferometers are brought to design sensitivity. With the increase in detector sensitivity, real-time delivery of gravitational-wave alerts will become increasingly important as an enabler of multi-messenger followup. In this work, we report a novel implementation and deployment of deep learning inference for real-time gravitational-wave data denoising and astrophysical source identification. This is accomplished using a generic Inference-as-a-Service model that is capable of adapting to the future needs of gravitational-wave data analysis. Overall, our implementation allows seamless incorporation of hardware accelerators and also enables the use of commercial or private (dedicated) as-a-service computing. Based on our results, we propose a paradigm shift in low-latency and offline computing in gravitational-wave astronomy. Such a shift can address key challenges in peak-usage, scalability and reliability, and provide a data analysis platform particularly optimized for deep learning applications. The achieved sub-millisecond scale latency will also be relevant for any machine learning-based real-time control systems that may be invoked in the operation of near-future and next generation ground-based laser interferometers, as well as the front-end collection, distribution and processing of data from such instruments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Accurate and confident prediction of electron beam longitudinal properties using spectral virtual diagnostics

Abstract Longitudinal phase space (LPS) provides a critical information about electron beam dynamics for various scientific applications. For example, it can give insight into the high-brightness X-ray radiation from a free electron laser. Existing diagnostics are invasive, and often times cannot operate at the required resolution. In this work we present a machine learning-based Virtual Diagnostic (VD) tool to accurately predict the LPS for every shot using spectral information collected non-destructively from the radiation of relativistic electron beam. We demonstrate the tool’s accuracy for three different case studies with experimental or simulated data. For each case, we introduce a method to increase the confidence in the VD tool. We anticipate that spectral VD would improve the setup and understanding of experimental configurations at DOE’s user facilities as well as data sorting and analysis. The spectral VD can provide confident knowledge of the longitudinal bunch properties at the next generation of high-repetition rate linear accelerators while reducing the load on data storage, readout and streaming requirements.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

PRODeepSyn: predicting anticancer synergistic drug combinations by embedding cell lines with protein–protein interaction network

Abstract Although drug combinations in cancer treatment appear to be a promising therapeutic strategy with respect to monotherapy, it is arduous to discover new synergistic drug combinations due to the combinatorial explosion. Deep learning technology holds immense promise for better prediction of in vitro synergistic drug combinations for certain cell lines. In methods applying such technology, omics data are widely adopted to construct cell line features. However, biological network data are rarely considered yet, which is worthy of in-depth study. In this study, we propose a novel deep learning method, termed PRODeepSyn, for predicting anticancer synergistic drug combinations. By leveraging the Graph Convolutional Network, PRODeepSyn integrates the protein–protein interaction (PPI) network with omics data to construct low-dimensional dense embeddings for cell lines. PRODeepSyn then builds a deep neural network with the Batch Normalization mechanism to predict synergy scores using the cell line embeddings and drug features. PRODeepSyn achieves the lowest root mean square error of 15.08 and the highest Pearson correlation coefficient of 0.75, outperforming two deep learning methods and four machine learning methods. On the classification task, PRODeepSyn achieves an area under the receiver operator characteristics curve of 0.90, an area under the precision–recall curve of 0.63 and a Cohen’s Kappa of 0.53. In the ablation study, we find that using the multi-omics data and the integrated PPI network’s information both can improve the prediction results. Additionally, the case study demonstrates the consistency between PRODeepSyn and previous studies.

Wang, Xiaowen↗
DOE OSTI2025

Evolution at the Edge: Real-Time Evolution for Neuromorphic Engine Control

Neuromorphic computing systems are attractive for real-time control at the edge because of their low power operation, real-time processing capabilities and their potential ability to do online learning. In this work, we describe an approach for performing real-time evolution of spiking neural networks for neuromorphic systems at the edge called Neuromorphic Optimization using Dynamic Evolutionary Systems or NODES. We apply this approach to real-time combustion engine control and develop an engine-specific hardware platform for NODES called FireBox. We demonstrate how the real-time evolution approach works in simulation and the performance of networks trained in simulation on the physical engine.

Maldonado Puente, Bryan [ORNL] (ORCID:000000033880↗
DOE OSTI2024

Multi-Edge Graph Convolutional Networks for Power Systems

The exponential electrification of transportation has contributed to highly intermittent load variations in the distribution grid. This uncertainty has raised challenges for distribution system operation and control. Accurate nodal voltage estimation is highly essential for the safe and reliable operation of the grid. Graph convolutional networks have been used in machine-learning-based models for power grid applications like voltage estimation for their ability to capture the network topology of the grid. This paper presents a novel multi-edge graph convolutional layer that considers resistance and reactance as edge attributes. This layer is created by modifying the message-passing function within the graph convolutional network. The novel layer is then used to create a multi-edge graph convolutional network-based surrogate model for estimating voltage in the distribution network with highly uncertain electric vehicle loads. Results indicate improved performance of the multi-edge graph convolutional network model when compared to a standard graph convolutional network model.

Ravi, Abhijith↗
DOE OSTI2022

Quantum Manifold Learning

SAND2022-12600 O Quantum Manifold Learning is a Python code to perform manifold learning from point clouds. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Sarovar, Mohan↗
DOE OSTI2015

Scaling to Nanotechnology Limits with the PIMS Computer Architecture and a new Scaling Rule

We describe a new approach to computing that moves towards the limits of nanotechnology using a newly formulated sc aling rule. This is in contrast to the current computer industry scali ng away from von Neumann's original computer at the rate of Moore's Law. We extend Moore's Law to 3D, which l eads generally to architectures that integrate logic and memory. To keep pow er dissipation cons tant through a 2D surface of the 3D structure requires using adiabatic principles. We call our newly proposed architecture Processor In Memory and Storage (PIMS). We propose a new computational model that integrates processing and memory into "tiles" that comprise logic, memory/storage, and communications functions. Since the programming model will be relatively stable as a system scales, programs repr esented by tiles could be executed in a PIMS system built with today's technology or could become the "schematic diagram" for implementation in an ultimate 3D nanotechnology of the future. We build a systems software approach that offers advantages over and above the technological and arch itectural advantages. Firs t, the algorithms may be more efficient in the conventional sens e of having fewer steps. Second, the algorithms may run with higher power efficiency per operation by being a better match for the adiabatic scaling ru le. The performance analysis based on demonstrated ideas in physical science suggests 80,000 x improvement in cost per operation for the (arguably) gene ral purpose function of emulating neurons in Deep Learning.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Final Report for CSP Tower Public Opinion and Education Project

As part of the CSP Plant Optimization Study for the California Power Market (DE-EE0009809) the project wanted to understand the public’s opinion of the technology and and explore the types of community engagement that is needed to support such development. The initial objectives for the public perception activities were twofold. The primary objective was to gather public opinion and feedback from the communities living near the two operating solar power tower plants, Ivanpah and Crescent Dunes, and to distill lessons learned from the community engagement conducted before, during, and after the plants were developed to inform future development. This included outreach to nearby airports. The other objective was to gauge public opinion about large-scale solar, specifically CSP towers, to start educating the public on the benefits and to begin building relationships with communities of interest, initially targeting the Kingman, Arizona area. The objectives shifted after the first exploratory trip to Ivanpah and Kingman, however, as it became apparent that it would be challenging to gather public opinion from the community surrounding Ivanpah that could be useful for other community profiles, and the company wasn’t ready to address the concerns in Kingman. Another area was chosen, therefore, to represent those where future development is possible. The recently published Lawrence Berkeley National Lab Perceptions of Large-Scale Solar Project Neighbors Study exemplified public perception polling based on social science and served as the foundation for the survey questions taken to the field. The intent was to ensure that people knew their input was valued and that the time they spent was valuable for the participant as well. It has been noted in the literature that in-person interaction has greater benefits than activities online or via mail, as well as limits the expense.

14 SOLAR ENERGY↗
DOE OSTI2025

Advanced Modeling of Beam Physics and Performance Optimization for Nuclear Physics Colliders

High energy colliders provide a critical tool in nuclear physics study by probing the fundamental structure and dynamics of matter. To maximize the potential of scientific discovery in nuclear physics study, it is important to optimize the parameters of these colliders to attain the best performance. The performance of a collider is typically measured by its integrated luminosity of colliding beams since the probability of a new event is proportional to the integrated luminosity. However, the achievable luminosity is limited by the electromagnetic interactions (beam-beam effects) of two colliding beams at higher energy, and the interplay between the space-charge effects and the beam-beam effects at lower energy. To achieve the best performance of a collider means to attain the highest luminosity of the collider with optimized collider parameters. Optimizing the collider’s machine parameters is both computationally and experimentally expensive. A fast and robust computational framework including beam-beam and space-charge effects will be critical to attaining the best performance of the collider. In this project, we will study the beam dynamics challenges, specifically the interplay of the space-charge and the beam-beam effects, and the machine tuning models for maximizing the performance of RHIC experiments. We will develop an advanced modeling framework based on first-principles physical simulations, lattice models and the state-of-the-art machine learning methods and apply this framework to performance improvement of the RHIC in operation. We will build data manipulation packages to connect the simulation data and the experimental data with the framework, develop a self-consistent hybrid model of space-charge and beam-beam effects, study underlying physics mechanisms, build surrogate models using the labeled data, integrate the models into the advanced modeling framework, and apply the framework to RHIC luminosity (STAR and sPHENIX) optimization. The success of this project would substantially improve the performance of existing and future colliders and increase the opportunity for scientific discovery.

43 PARTICLE ACCELERATORS↗
DOE OSTI2020

FLEET: Flexible Efficient Ensemble Training for Heterogeneous Deep Neural Networks

Parallel training of an ensemble of Deep Neural Networks (DNN) on a cluster of nodes is an effective approach to shorten the process of neural network architecture search and hyper-parameter tuning for a given learning task. Prior efforts have shown that data sharing, where the common preprocessing operation is shared across the DNN training pipelines, saves computational resources and improves pipeline efficiency. Data sharing strategy, however, performs poorly for a heterogeneous set of DNNs where each DNN has varying computational needs and thus different training rate and convergence speed. This paper proposes FLEET, a flexible ensemble DNN training framework for efficiently training a heterogeneous set of DNNs. We build FLEET via several technical innovations. We theoretically prove that an optimal resource allocation is NP-hard and propose a greedy algorithm to efficiently allocate resources for training each DNN with data sharing. We integrate data-parallel DNN training into ensemble training to mitigate the differences in training rates and introduce checkpointing into this context to address the issue of different convergence speeds. Experiments show that FLEET significantly improves the training efficiency of DNN ensembles without compromising the quality of the result.

Guan, Hui↗
DOE OSTI2016

Protecting the Columbia River through Removal and Packaging of Radioactive Sludge in Hanford's K Area - 16572

The Columbia River once provided power and cooling water to operations on the Hanford Site; today, more than a million people downstream from Hanford rely on the river for agriculture, fishing and recreation. The Department of Energy and contractor CH2M HILL Plateau Remediation Company (CH2M) is making significant progress in protecting that vital resource. Eight of nine reactors along the river have been cocooned and soil and groundwater remediation is successfully reducing the concentration of contaminants in groundwater. The 100-K area is the last area where significant work remains to protect the river. CH2M has accomplished much in the past ten years, including demolishing the K East reactor fuel storage basin in 2009. Prior to demolition of the basin, highly radioactive sludge from that basin was transferred into containers located in the nearby K West reactor fuel storage basin. Today, the K East reactor is in interim surveillance mode, and work is underway in the K West basin to remove the sludge, which is a mixture of tiny fuel corrosion particles, fuel rod and metal fragments and soil and sand less than 1/4-inch in diameter. CH2M has designed a sludge removal system that will safely and efficiently remove the sludge from the K West basin and deposit it into specially designed containers which will be relocated to a storage facility on Hanford's Central Plateau. Procurement, fabrication and delivery of the sludge removal system is underway, with extensive testing and training planned for 2016 and 2017 ahead of the goal of removing sludge from the river by September 30, 2018. This project must account for many technical and safety considerations that render the project very challenging. Several safety measures have been incorporated as a result of safety evaluations. This paper will describe the issues facing the project team in developing the safety basis requirements and incorporating them into the design of the process equipment and construction of the facility to house the repackaging operations. This paper will allow CH2M and DOE-RL to share lessons learned and progress to date with other complex and hazardous projects across the DOE complex. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Criticality Safety Evaluation Project Development for University of California Berkely Nuclear Criticality Safety Pipeline Course

The Nuclear Criticality Safety Division at Lawrence Livermore National Laboratory (LLNL) has taken a unique approach to developing criticality safety evaluation topics in support of the University of California Berkeley criticality safety pipeline course. The evaluation topics are designed to go beyond the typical evaluation examples used for many training courses including vault storage and variations on storage arrays. These types of evaluations provide in-depth analysis into the fundamentals of criticality safety and are complex but may be far off from what a new criticality safety engineer may actually be evaluating. To provide more practical examples of criticality safety evaluation topics that are better fit for the knowledge level of a criticality safety engineer in-training, variations of current and future operations and research operations performed at LLNL are used as evaluation topics. Additionally, an emphasis on research is included in all evaluation topics as it allows students to take advantage of the concepts learned in class to apply them for process improvement, engineering equipment that is favorable for criticality safety, and negotiation tactics to work with operations personnel. The process used by LLNL to develop project topics for the pipeline course is provided in this paper. The intent is to provide an alternative technique for training students and potentially younger staff members in criticality safety on developing criticality safety evaluations.

42 ENGINEERING↗
DOE OSTI2024

teemi: An open-source literate programming approach for iterative design-build-test-learn cycles in bioengineering

Synthetic biology dictates the data-driven engineering of biocatalysis, cellular functions, and organism behavior. Integral to synthetic biology is the aspiration to efficiently find, access, interoperate, and reuse high-quality data on genotype-phenotype relationships of native and engineered biosystems under FAIR principles, and from this facilitate forward-engineering strategies. However, biology is complex at the regulatory level, and noisy at the operational level, thus necessitating systematic and diligent data handling at all levels of the design, build, and test phases in order to maximize learning in the iterative design-build-test-learn engineering cycle. To enable user-friendly simulation, organization, and guidance for the engineering of biosystems, we have developed an open-source python-based computer-aided design and analysis platform operating under a literate programming user-interface hosted on Github. The platform is called teemi and is fully compliant with FAIR principles. In this study we apply teemi for i) designing and simulating bioengineering, ii) integrating and analyzing multivariate datasets, and iii) machine-learning for predictive engineering of metabolic pathway designs for production of a key precursor to medicinal alkaloids in yeast. The teemi platform is publicly available at PyPi and GitHub.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Deep reinforcement learning for predicting kinetic pathways to surface reconstruction in a ternary alloy

Abstract The majority of computational catalyst design focuses on the screening of material components and alloy composition to optimize selectivity and activity for a given reaction. However, predicting the metastability of the alloy catalyst surface at realistic operating conditions requires an extensive sampling of possible surface reconstructions and their associated kinetic pathways. We present CatGym, a deep reinforcement learning (DRL) environment for predicting the thermal surface reconstruction pathways and their associated kinetic barriers in crystalline solids under reaction conditions. The DRL agent iteratively changes the positions of atoms in the near-surface region to generate kinetic pathways to accessible local minima involving changes in the surface compositions. We showcase our agent by predicting the surface reconstruction pathways of a ternary Ni 3 Pd 3 Au 2 (111) alloy catalyst. Our results show that the DRL agent can not only explore more diverse surface compositions than the conventional minima hopping method, but also generate the kinetic surface reconstruction pathways. We further demonstrate that the kinetic pathway to a global minimum energy surface composition and its associated transition state predicted by our agent is in good agreement with the minimum energy path predicted by nudged elastic band calculations.

36 MATERIALS SCIENCE↗
DOE OSTI2022

High-Throughput Microfluidics Platform for Intracellular Delivery and Sampling of Biomolecules from Live Cells

Nondestructive cell membrane permeabilization systems enable the intracellular delivery of exogenous biomolecules for cell engineering tasks as well as the temporal sampling of cytosolic contents from live cells for the analysis of dynamic processes. Here, in this paper, we report a microwell array format live-cell analysis device (LCAD) that can perform localized-electroporation induced membrane permeabilization, for cellular delivery or sampling, and directly interfaces with surface-based biosensors for analyzing the extracted contents. We demonstrate the capabilities of the LCAD via an automated high-throughput workflow for multimodal analysis of live-cell dynamics, consisting of quantitative measurements of enzyme activity using self-assembled monolayers for MALDI mass spectrometry (SAMDI) and deep-learning enhanced imaging and analysis. By combining a fabrication protocol that enables robust assembly and operation of multilayer devices with embedded gold electrodes and an automated imaging workflow, we successfully deliver functional molecules (plasmid and siRNA) into live cells at multiple time-points and track their effect on gene expression and cell morphology temporally. Furthermore, we report sampling performance enhancements, achieving saturation levels of protein tyrosine phosphatase activity measured from as few as 60 cells, and demonstrate control over the amount of sampled contents by optimization of electroporation parameters using a lumped model. Lastly, we investigate the implications of cell morphology on electroporation-induced sampling of fluorescent molecules using a deep-learning enhanced image analysis workflow.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Improved guided-wave acoustic defect detection and localization in pipes under varying temperature conditions using deep learning

Early defect detection in pipelines is critical across industries, particularly in the oil and gas sector, where failures result in significant maintenance costs and operational disruptions. Acoustic guided-wave techniques are widely used for nondestructive evaluation of pipeline defects due to their long-distance propagation capability. However, environmental variations, sensitivity limitations, and complex signal interpretation challenges limit the effectiveness of traditional signal processing approaches with guided-wave signals. Recent advances in deep learning methods have demonstrated remarkable success in solving complex real-world problems in many fields. In particular, deep-learning-based signal processing holds substantial promise to overcome limitations and challenges of conventional signal processing. This study presents a deep learning framework for pipeline inspection using acoustic guided-wave signals under temperature varying environments. The proposed framework employs a dual-path one-dimensional convolutional autoencoder that combines defect detection, localization, and temperature prediction functions. The proposed system utilizes multi-mode and broadband acoustic waves with an optimized number of sensors that provide high accuracy while retaining practical simplicity. Experimental validation is performed on a carbon steel pipe. The results indicate exceptional defect detection accuracy and precise defect localization with a mean absolute error of 66 mm. The proposed technique also predicts the effective average temperature of the pipe with a mean absolute error of 0.2°C. Comparative analysis shows superior performance of the proposed method over a traditional method previously developed by the authors' team. These results highlight the potential of integrating deep learning methods into guided-wave pipeline inspection systems to improve reliability under varying environmental conditions.

42 ENGINEERING↗
DOE OSTI2024

Reinforcement learning pulses for transmon qubit entangling gates

The utility of a quantum computer is highly dependent on the ability to reliably perform accurate quantum logic operations. For finding optimal control solutions, it is of particular interest to explore model-free approaches, since their quality is not constrained by the limited accuracy of theoretical models for the quantum processor—in contrast to many established gate implementation strategies. In this work, we utilize a continuous control reinforcement learning algorithm to design entangling two-qubit gates for superconducting qubits; specifically, our agent constructs cross-resonance and CNOT gates without any prior information about the physical system. Using a simulated environment of fixed-frequency fixed-coupling transmon qubits, we demonstrate the capability to generate novel pulse sequences that outperform the standard cross-resonance gates in both fidelity and gate duration, while maintaining a comparable susceptibility to stochastic unitary noise. We further showcase an augmentation in training and input information that allows our agent to adapt its pulse design abilities to drifting hardware characteristics, importantly, with little to no additional optimization. Our results exhibit clearly the advantages of unbiased adaptive-feedback learning-based optimization methods for transmon gate design.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

Report for 2.2.1 Task 5: Develop and Document a State-Based Alarm System for a Nuclear Power Plant Control Room Using Machine Learning

Idaho National Laboratory (INL) has contracted IFE to support human factors research and the development of leading-edge technology to support control room operators as the U.S. fleet undergoes modernization and digitalization in legacy plants and control rooms. As the nuclear industry starts to shift to more digital controls and systems, these upgrades provide more information to the main control room in the form of digital signals and values. Also, an increase in the number of alarms points is provided by the vendors. New digital control rooms shift from main control boards to soft controls, and alarm panels to a single display. This change to a single display has created a problem of alarm waterfall, a situation in which the addition of new alarm points causes an overload of information to the operator during either a plant disturbance or other than normal full power operations. IFE’s goal is to find a workable solution to assist operators in both handling and understanding incoming alarms during emergency situations under these waterfall conditions.

99 GENERAL AND MISCELLANEOUS↗