Search NASA⌕ Search

SEARCH · Search NASA

Results for “scientific training”

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 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Trustworthy Physics-Informed Deep Learning for Predictive Scientific Computing

This project has developed powerful trustworthy physics-informed deep learning (TPiDL) models and methods to fundamentally enhance the scale and power of computational modeling in the scientific and engineering domains. Deep learning (DL) has radically advanced the state-of-the-art in machine learning, computer vision, natural language processing, and also scientific computing. Nevertheless, progress has been driven almost entirely by empirical observations, hacks, and tricks. Under the support of this project, the graph operator learning tools and advanced trustworthy physical informed neural networks have been developed. In addition, stochastic gradient replica-exchange Markov Chain Monte Carlo (MCMC) sampling algorithms have been designed to quantify the uncertainties and speed up the training of large-scale neural networks.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A Survey on Sustainable Software Ecosystems to Support Experimental and Observational Science at Oak Ridge National Laboratory

In the search for a sustainable approach for software ecosystems that supports experimental and observational science (EOS) across Oak Ridge National Laboratory (ORNL), we conducted a survey to understand the current and future landscape of EOS software and data. This paper describes the survey design we used to identify significant areas of interest, gaps, and potential opportunities, followed by a discussion on the obtained responses. The survey formulates questions about project demographics, technical approach, and skills required for the present and the next five years. The study was conducted among 38 ORNL participants between June and July of 2021 and followed the required guidelines for human subjects training. We plan to use the collected information to help guide a vision for sustainable, community-based, and reusable scientific software ecosystems that need to adapt effectively to: i) the evolving landscape of heterogeneous hardware in the next generation of instruments and computing (e.g. edge, distributed, accelerators), and ii) data management requirements for data-driven science using artificial intelligence.

Bernholdt, David↗
DOE OSTI2026

Active operator learning with predictive uncertainty quantification for partial differential equations

With the increased prevalence of neural operators being used to provide rapid solutions to partial differential equations (PDEs), understanding the accuracy of model predictions and the associated error levels is necessary for deploying reliable surrogate models in scientific applications. Existing uncertainty quantification (UQ) frameworks employ ensembles or Bayesian methods, which can incur substantial computational costs during both training and inference. Here, we propose a lightweight predictive UQ method tailored for Deep operator networks (DeepONets) that also generalizes to other operator networks. Numerical experiments on linear and nonlinear PDEs demonstrate that the framework’s uncertainty estimates are unbiased and provide accurate out-of-distribution uncertainty predictions with a sufficiently large training dataset. Our framework provides fast inference and uncertainty estimates that can efficiently drive outer-loop analyses that would be prohibitively expensive with conventional solvers. We demonstrate how predictive uncertainties can be used in the context of Bayesian optimization and active learning problems to yield improvements in accuracy and data-efficiency for outer-loop optimization procedures. In the active learning setup, we extend the framework to Fourier Neural Operators (FNO) and describe a generalized method for other operator networks. To enable real-time deployment, we introduce an inference strategy based on precomputed trunk outputs and a sparse placement matrix, reducing evaluation time by more than a factor of five. Our method provides a practical route to uncertainty-aware operator learning in time-sensitive settings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Experiential findings for sustainable software ecosystems to support experimental and observational science

In the search for a sustainable approach for software ecosystems that supports experimental and observational science (EOS) across Oak Ridge National Laboratory (ORNL), we conducted a survey to understand the current and future landscape of EOS software and data. This paper describes the survey design we used to identify significant areas of interest, gaps, and potential opportunities, followed by a discussion on the obtained responses. The survey formulates questions about project demographics, technical approach, and skills required for the present and the next five years. Here, the study was conducted among 38 ORNL participants between June and July of 2021 and followed the required guidelines for human subjects training. We plan to use the collected information to help guide a vision for sustainable, community-based, and reusable scientific software ecosystems that need to adapt effectively to: (i) the evolving landscape of heterogeneous hardware in the next generation of instruments and computing (e.g. edge, distributed, accelerators), and (ii) data management requirements for data-driven science using artificial intelligence.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

DeepFreeze: Towards Scalable Asynchronous Checkpointing of Deep Learning Models

In the age of big data, deep learning has emerged as a powerful tool to extract insight and exploit its value, both in industry and scientific applications. One common pattern emerging in such applications is frequent checkpointing of the state of the learning model during training, needed in a variety of scenarios: analysis of intermediate states to explain features and correlations with training data, exploration strategies involving alternative models that share a common ancestor, knowledge transfer, resilience, etc. However, with increasing size of the learning models and popularity of distributed data-parallel training approaches, simple checkpointing techniques used so far face several limitations: low serialization performance, blocking I/O, stragglers due to the fact that only a single process is involved in checkpointing. This paper proposes a checkpointing technique specifically designed to address the aforementioned limitations, introducing efficient asynchronous techniques to hide the overhead of serialization and I/O, and distribute the load over all participating processes. Experiments with two deep learning applications (CANDLE and ResNet) on a pre-Exascale HPC platform (Theta) shows significant improvement over state-of-art, both in terms of checkpointing duration and runtime overhead.

checkpointing↗
DOE OSTI2022

Novel Proposals for FAIR, Automated, Recommendable, and Robust Workflows

Lightning talks of the Workflows in Support of Large-Scale Science (WORKS) workshop are a venue where the workflow community (researchers, developers, and users) can discuss work in progress, emerging technologies and frameworks, and training and education materials. This paper summarizes the WORKS 2022 lightning talks, which cover five broad topics: data integrity of scientific workflows; a machine learning-based recommendation system; a Python toolkit for running dynamic ensembles of simulations; a cross-platform, high-performance computing utility for processing shell commands; and a meta(data) framework for reproducing hybrid workflows.

Abhinit, Ishan↗
DOE OSTI2023

GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics

We seek to transform how new and emergent variants of pandemic-causing viruses, specifically SARS-CoV-2, are identified and classified. By adapting large language models (LLMs) for genomic data, we build genome-scale language models (GenSLMs) which can learn the evolutionary landscape of SARS-CoV-2 genomes. By pre-training on over 110 million prokaryotic gene sequences and fine-tuning a SARS-CoV-2-specific model on 1.5 million genomes, we show that GenSLMs can accurately and rapidly identify variants of concern. Thus, to our knowledge, GenSLMs represents one of the first whole-genome scale foundation models which can generalize to other prediction tasks. We demonstrate scaling of GenSLMs on GPU-based supercomputers and AI-hardware accelerators utilizing 1.63 Zettaflops in training runs with a sustained performance of 121 PFLOPS in mixed precision and peak of 850 PFLOPS. We present initial scientific insights from examining GenSLMs in tracking evolutionary dynamics of SARS-CoV-2, paving the path to realizing this on large biological data.

Zvyagin, Maxim↗
DOE OSTI2024

Final Report on the 2023 LaserNetUS Annual Meeting

LaserNetUS is a network of advanced laser facilities created by the Department of Energy Fusion Energy Sciences to provide greatly improved access to the most powerful lasers in North America. It is dedicated to the development of the high energy density physics workforce, especially the training and advancement of early career scientists. The network is helping to build a larger, better skilled and more diverse scientific community. The result of the work of LaserNetUS towards these goals was on display at the 2023 LaserNetUS Annual Meeting, held at the University of Maryland, College Park, Maryland on June 27-29, 2023 (Figure 1). The meeting had 216 participants, the largest sponsor/exhibitor participation of any LaserNetUS annual meeting, wide ranging plenary, invited, and contributed talks, a vigorous poster session, outreach to a diverse range of students, and two awards sessions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Final Technical Report for DoE award DE‐SC0023367 “Energetic Electron Transport in Magnetized Plasma with Magnetic Islands”

This project investigated how plasmas interact with energetic particles and solid materials under extreme conditions relevant to fusion energy, space plasmas, and planetary environments. Using experiments on the DIII-D National Fusion Facility, the research first examined how high-energy electrons move, become trapped, and are released in plasmas containing magnetic islands—structures commonly found in fusion reactors and Earth’s magnetosphere—providing new insight into particle transport and acceleration processes. The project also explored plasma-driven chemical reactions that can occur during meteoroid entry into planetary atmospheres, demonstrating that simple molecules such as ammonia can be produced and survive in high-temperature plasma conditions. Together, these results improve understanding of plasma behavior across laboratory, space, and planetary systems while informing fusion plasma control and plasma–material interaction studies. The project additionally contributed to workforce development by training graduate students, undergraduates, and early-career researchers and by disseminating results through peer-reviewed publications and international scientific conferences.

Orlov, Dmitri Mikhailovich [UC San Diego] (ORCID:0↗
DOE OSTI2026

Blueprint for DOE Quantum Supercomputing: Ensuring U.S. Leadership in the Quantum Decade

Quantum computing stands at the threshold of a transformative decade, where the field will evolve from small-scale demonstrations toward practical scientific computing at scale. This Blueprint identifies fault-tolerant quantum computers (FTQCs) as a viable, scalable, and broadly applicable path to achieving “quantum scientific utility,” defined as solving scientifically valuable problems beyond the reach of conventional, classical computers. This capability is expected to show scientific demonstrations in the late 2020s and to mature in the early-to-mid 2030s. This Blueprint outlines a strategy to prepare the U.S. Department of Energy (DOE) for FTQCs and their integration into the U.S. national scientific computing infrastructure. Its purpose is to identify the steps, milestones, and research directions necessary for DOE to enable initial deployment of FTQCs in 2028 as a scientific tool for the nation and mature this capability into the 2030s. DOE has a long history of supporting quantum information science and technology, contributing significantly to research advancements, training a quantum-ready workforce, and providing access to early small-scale quantum hardware. Given recent demonstrations of logical operations on error-corrected logical qubits and the advancement of commercial hardware roadmaps, DOE should begin preparations for large-scale, fault-tolerant quantum computing deployment for DOE science missions. This Blueprint proposes that DOE focus on (1) deploying first-generation scientifically relevant quantum computers with at least 100 logical qubits and performing at least 10,000 to 100,000 hard logical operations in scientifically relevant calculations; (2) developing essential FTQC programming competencies, system software, and facility readiness; and (3) investing in cutting edge focused R&D that fosters breakthroughs in scientific applications, algorithms, and logical architectures needed to accelerate the advent of scientific utility. This effort will position DOE to transition to larger systems: production-scale quantum computers that comprise 1,000 to 10,000 logical qubits, perform 1 to 10 billion hard logical operations, and execute scientifically useful computations at scale. Achieving these goals will require DOE facilities to evolve with urgency to support scientific campaigns that integrate quantum and classical computing resources into efficient workflows, novel software and firmware environments for compiling and routing quantum programs on FTQC machines, and suitable infrastructure for quantum hardware. It will also require further development and optimization of scientific applications from the fields of materials science, quantum chemistry, and high-energy and nuclear physics. The Blueprint calls for transformative R&D and collective action to accelerate the advent of scientific quantum utility and bring it within reach by 2028.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

DPM: A deep learning PDE augmentation method with application to large-eddy simulation

A framework is introduced that leverages known physics to reduce overfitting in machine learning for scientific applications. The partial differential equation (PDE) that expresses the physics is augmented with a neural network that uses available data to learn a description of the corresponding unknown or unrepresented physics. Training within this combined system corrects for missing, unknown, or erroneously represented physics, including discretization errors associated with the PDE's numerical solution. For optimization of the network within the PDE, an adjoint PDE is solved to provide high-dimensional gradients, and a stochastic adjoint method (SAM) further accelerates training. Additionally, the approach is demonstrated for large-eddy simulation (LES) of turbulence. High-fidelity direct numerical simulations (DNS) of decaying isotropic turbulence provide the training data used to learn sub-filter-scale closures for the filtered Navier–Stokes equations. Out-of-sample comparisons show that the deep learning PDE method outperforms widely-used models, even for filter sizes so large that they become qualitatively incorrect. It also significantly outperforms the same neural network when a priori trained based on simple data mismatch, not accounting for the full PDE. Measures of discretization errors, which are well-known to be consequential in LES, point to the importance of the unified training formulation's design, which without modification corrects for them. For comparable accuracy, simulation runtime is significantly reduced. A relaxation of the typical discrete enforcement of the divergence-free constraint in the solver is also successful, instead allowing the DPM to approximately enforce incompressibility physics. Since the training loss function is not restricted to correspond directly to the closure to be learned, training can incorporate diverse data, including experimental data.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Tribute to Kenneth Sauer (1931–2022): a mentor, a role-model, and an inspiration to all in the field of photosynthesis

Abstract Kenneth (Ken) Sauer was a mainstay of research in photosynthesis at the University of California, Berkeley and the Lawrence Berkeley National Laboratory (LBNL) for more than 50 years. Ken will be remembered by his colleagues, and other workers in the field of photosynthesis as well, for his pioneering work that introduced the physical techniques whose application have enriched our understanding of the basic reactions of oxygenic photosynthesis. His laboratory was a training ground for many students and postdocs who went on to success in the field of photosynthesis and many others. Trained as a physical chemist, he always brought that quantitative approach to research questions and used several spectroscopic methods in his research. His broad scientific interests concerned the role of manganese in oxygen evolution, electronic properties of chlorophylls, energy transport in antenna complexes, and electron transport reactions. He was also an enthusiastic teacher, an enormously successful mentor who leaves behind a legion of scientists as his abiding legacy, a lover of music and the outdoors with many interests beyond science, and a dedicated family man with a great sense of humility. In this tribute, we summarize some aspects of Ken Sauer’s life and career, illustrated with selected research achievements, and describe his approach to research and life as we perceived it, which is complemented by reminiscences of several current researchers in photosynthesis and other fields. The supporting material includes Ken Sauers’s CV and publication list, as well as a list of the graduate students and postdocs he trained and of researchers that spent a sabbatical in his lab.

Plant Sciences↗
DOE OSTI2023

Monsoon Extremes: Impacts, Metrics, and Synoptic-Scale Drivers

This project was led by UC Berkeley with a subcontract to UC Davis and collaborative funding at the Lawrence Berkeley National Lab (LBNL). It produced new understanding of transient atmospheric disturbances in monsoon regions, the precipitation extremes they produce, and the sensitivity of precipitation and monsoon winds to fine-scale orography (i.e., the narrow mountain ranges that are difficult to represent in conventional Earth system models). Fundamental research undertaken as part of this project led to discovery of new mechanisms that control the generation of extreme weather events and that govern the spatial patterns of intense precipitation in monsoon climates—including the North American monsoon. These research accomplishments are summarized below and documented in a series of 23 publications, 20 of which were led by project personnel (the others were collaborative work led by staff of other projects). One of the publications produced by this project was in Nature, where it was selected for the main cover image, and another was in PNAS. The project also produced two datasets and a tracking algorithm, both of which are publicly available and listed below. The project trained three Ph.D. students and four postdoctoral scientists, the vast majority of whom have progressed to more advanced positions in their scientific careers. Although the university funding for this project ended in 2022, the LBNL component of the project proceeded for almost one year longer; this report is being provided after completion of all components of the project.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Artificial-Intelligence Aided Design and Synthesis of Novel Layered 2D Multi-Principal Element Materials for Energy Storage (Final Report)

This DOE-EPSCoR project aimed to predict, synthesize, and characterize novel layered two-dimensional (2D) high-entropy materials (HEMs). These 2D-HEMs, composed of multiple principal elements in nearly equal concentrations, are distinct from traditional 2D materials (typically containing two or three elements) and conventional alloys (dominated by a single primary element with minor secondary additions). Their unique structural and compositional features enable significant lattice strain accommodation, resulting in enhanced electrode performance and potential applications in catalysis, hydrogen storage, sensing, quantum information technologies, and flexible electronics. The research focused on addressing four fundamental questions: (i) What combinations of elements can form stable and synthesizable 2D-HEMs? (ii) What mechanisms drive the stability and synthesizability of crystalline single-phase 2D-HEMs? (iii) How do local chemical disorder and defects influence the macroscopic electronic and mechanical properties? and (iv) What charge storage mechanisms are active in selectively synthesized 2D-HEMs for battery and supercapacitor electrode applications? To achieve these goals, the project employed an integrated theory-experiment approach, incorporating high-throughput first-principles calculations, theoretical modeling, data mining, experimental synthesis, and advanced characterization techniques. The advanced computing resources and state-of-the-art experimental characterization facilities at Oak Ridge National Laboratory (ORNL) were leveraged through collaboration. Beyond scientific advancements, the project contributed to workforce development. Two postdoctoral researchers and three graduate students at the University of Maine were trained through co-advising by ORNL scientists and collaborative interactions, strengthening their expertise in cutting-edge materials science.

36 MATERIALS SCIENCE↗
DOE OSTI2025

PDF Entity Annotation Tool (PEAT)

While different text mining approaches – including the use of Artificial Intelligence (AI) and other machine based methods - continue to expand at a rapid pace, the tools used by researchers to create the labeled datasets required for training, modeling, and evaluation remain rudimentary. Labeled datasets contain the target attributes the machine is going to learn; for example, training an algorithm to delineate between images of a car or truck would generally require a set of images with a quantitative description of the underlying features of each vehicle type. Development of labeled textual data that can be used to build natural language machine learning models for scientific literature is not currently integrated into existing manual workflows used by domain experts. Published literature is rich with important information, such as different types of embedded text, plots, and tables that can all be used as inputs to train ML/natural language processing (NLP) models, when extracted and prepared in machine readable formats. Currently, both normalized data extraction of use to domain experts and extraction to support development of ML/NLP models are labor intensive and cumbersome manual processes. Automatic extraction of data and information from formats such as PDFs that are optimized for layout and human readability, not machine readability. The PDF (Portable Document Format) Entity Annotation Tool (PEAT) was developed with the goal of allowing users to annotate publications within their current print format, while also allowing those annotations to be captured in a machine-readable format. One of the main issues with traditional annotation tools is that they require transforming the PDF into plain text to facilitate the annotation process. While doing so lessens the technical challenges of annotating data, the user loses all structure and provenance that was inherent in the underlying PDF. Also, textual data extraction from PDFs can be an error prone process. Challenges include identifying sequential blocks of text and a multitude of document formats (multiple columns, font encodings, etc.). As a result of these challenges, using existing tools for development of NLP/ML models directly from PDFs is difficult because the generated outputs are not interoperable. We created a system that allows annotations to be completed on the original PDF document structure, with no plain text extraction. The result is an application that allows for easier and more accurate annotations. In addition, by including a feature that grants the user the ability to easily create a schema, we have developed a system that can be used to annotate text for different domain-centric schemas of relevance to subject matter experts. Different knowledge domains require distinct schemas and annotation tags to support machine learning.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2021

Physics guided machine learning using simplified theories

Recent applications of machine learning, in particular deep learning, motivate the need to address the generalizability of the statistical inference approaches in physical sciences. In this Letter, we introduce a modular physics guided machine learning framework to improve the accuracy of such data-driven predictive engines. The chief idea in our approach is to augment the knowledge of the simplified theories with the underlying learning process. To emphasize their physical importance, our architecture consists of adding certain features at intermediate layers rather than in the input layer. To demonstrate our approach, we select a canonical airfoil aerodynamic problem with the enhancement of the potential flow theory. We include the features obtained by a panel method that can be computed efficiently for an unseen configuration in our training procedure. By addressing the generalizability concerns, our results suggest that the proposed feature enhancement approach can be effectively used in many scientific machine learning applications, especially for the systems where we can use a theoretical, empirical, or simplified model to guide the learning module.

42 ENGINEERING↗
DOE OSTI2024

PHASM: A Toolkit for Creating AI Surrogate Models within Legacy Codebases

PHASM (“Parallel Hardware viA Surrogate Models”) is a software toolkit for creating AI-based surrogate models of scientific code. AI-based surrogate models are widely used for creating fast and inverse simulations. PHASM anticipates an additional future use case: adapting legacy code to modern hardware. While data centers are investing in heterogeneous hardware such as GPUs and FPGAs, many established scientific codebases remain unable to take advantage of the hardware’s higher parallelism without undergoing a costly rewrite. An alternative is to train a AI-based surrogate model to mimic computationally intensive functions in the code, and run the surrogate instead. PHASM formalizes a development lifecycle for such surrogate models, including discovering functions amenable to replacement with a surrogate model, predicting the resulting performance, identifying the function’s space of inputs and outputs, binding the model to the code, and managing model versions. A suite of software tools for facilitating these steps was written and validated against a set of model problems.

97 MATHEMATICS AND COMPUTING↗