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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Data readiness pipeline patterns for scientific AI at scale: Insights from climate, fusion, life sciences, and materials

This article examines how data readiness for AI principles apply to large scientific datasets used to train foundation models. We analyze archetypal workflows across four representative domains—climate, nuclear fusion, life sciences, and materials—to identify common preprocessing patterns and domain‐specific constraints. We introduce a two‐dimensional readiness model that combines canonical preprocessing patterns with a five‐level operational readiness scale, both tailored to high‐performance computing (HPC) environments. This construct helps outline key challenges in transforming large‐scale scientific data into formats suitable for scalable AI training. Together, these dimensions form a conceptual maturity matrix that characterizes scientific data readiness and guides infrastructure development toward standardized, cross‐domain support for scalable and reproducible AI for science. Finally, we evaluate this maturity matrix in the context of case studies including ClimaX (climate), AFLOW (materials), OpenFold (proteomics), and DIII‐D fusion disruption‐prediction workflows, from which we distill lessons learned and provide recommendations to guide practitioners in developing robust AI‐readiness pipelines. Finally, we discuss remaining cross‐cutting challenges that persist across scientific domains.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Data Readiness for Scientific AI at Scale

This paper examines how Data Readiness for AI (DRAI) principles apply to leadership-scale scientific datasets used to train foundation models. We analyze archetypal workflows across four representative domains—climate, nuclear fusion, bio/health, and materials—to identify common preprocessing patterns and domain-specific constraints. We introduce a two-dimensional readiness framework that combines canonical preprocessing patterns with a five-level operational readiness scale, both tailored to high-performance computing (HPC) environments. This framework helps outline key challenges in transforming large-scale scientific data into formats suitable for scalable AI training. Together, these dimensions form a conceptual maturity matrix that characterizes scientific data readiness and guides infrastructure development toward standardized, cross-domain support for scalable and reproducible AI for science.

Brewer, Wes [ORNL] (ORCID:0000000236393956)↗
NASA NTRS2001

On-Board Training for US Payloads

The International Space Station (ISS) crew follows a training rotation schedule that puts them in the United States about every three months for a three-month training window. While in the US, the crew receives training on both ISS systems and payloads. Crew time is limited, and system training takes priority over payload training. For most flights, there is sufficient time to train all systems and payloads. As more payloads are flown, training time becomes a more precious resource. Less training time requires payload developers (PDs) to develop alternatives to traditional ground training. To ensure their payloads have sufficient training to achieve their scientific goals, some PDs have developed on-board trainers (OBTs). These OBTs are used to train the crew when no or limited ground time is available. These lessons are also available on-orbit to refresh the crew about their ground training, if it was available. There are many types of OBT media, such as on-board computer based training (OCBT), video/photo lessons, or hardware simulators. The On-Board Training Working Group (OBTWG) and Courseware Development Working Group (CDWG) are responsible for developing the requirements for the different types of media.

Murphy, Benjamin↗
DOE OSTI2020

Threat Reduction Research Networks: Fostering Sustainable Collaborations Through Trainings for Genomics for Biosurveillance

Scientific research communities can be represented as heterogeneous or multidimensional networks encompassing multiple types of entities and relationships. These networks might include researchers, institutions, meetings, and publications, connected by relationships like authorship, employment, and attendance. We describe a method for efficiently and flexibly capturing, storing, and extracting information from multidimensional scientific networks using a graph database. The database structure is based on an ontology that captures allowable types of entities and relationships. This allows us to construct a variety of projections of the underlying multidimensional graph through database queries to answer specific research questions. We demonstrate this process through a study of the U.S. Biological Threat Reduction Program (BTRP), which seeks to develop Threat Reduction Networks to build and strengthen a sustainable international community of biosecurity, biosafety, and biosurveillance experts to address shared biological threat reduction challenges. Networks like these create connectional intelligence among researchers and institutions around the world, and are central to the concept of cooperative threat reduction. Our analysis focuses on a series of seven BTRP genome sequencing training workshops, showing how they created a growing network of participants and countries over time, which is also reflected in coauthorship relationships among attendees. By capturing concept and relationship hierarchies, our ontology-based approach allows us to pose general or specific questions about networks within the same framework. This approach can be applied to other research communities or multidimensional social networks to capture, analyze, and visualize different types of interactions and how they change over time.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRSDate not supplied

Harnessing Large Language Models for Scientific Endeavors

The rapid proliferation of Large Language Models (LLMs) such as GPT, Bard, and Llama has revolutionized various sectors, including the scientific community. These models, with their potential to automate and augment tasks, are increasingly being recognized as both a valuable asset and a potential challenge in the realm of scientific research and data management. However, the current LLMs, primarily trained on general corpora, exhibit a limited understanding of scientific concepts and terminologies due to the lack of scientific corpus in their training data. Recognizing this gap, several groups are now advocating for the development of LLMs specifically tailored for scientific applications. A notable initiative in this direction is the Large Language Model effort initiated by NASA's CSDO. This endeavor aims to align LLM efforts across NASA’s Science Mission Directorate, develop a science-specific corpus and validation test set for model training, and create an encoder-only model for various downstream tasks. Moreover, the initiative also plans to develop a decoder-only model to explore the potential benefits and risks associated with a generative LLM for science. Lastly, the project aims to create a science evaluation suite, encompassing various categories of downstream scientific tasks, to serve as a benchmark for assessing the value of any LLM for future use. This presentation will provide an overview and current status of this ongoing initiative, highlighting its potential to reshape the use of LLMs in the scientific domain.

Rahul Ramachandran↗
DOE OSTI2022

Applications and Techniques for Fast Machine Learning in Science

In this community review report, we discuss applications and techniques for fast machine learning (ML) in science—the concept of integrating powerful ML methods into the real-time experimental data processing loop to accelerate scientific discovery. The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML across a number of scientific domains; techniques for training and implementing performant and resource-efficient ML algorithms; and computing architectures, platforms, and technologies for deploying these algorithms. We also present overlapping challenges across the multiple scientific domains where common solutions can be found. This community report is intended to give plenty of examples and inspiration for scientific discovery through integrated and accelerated ML solutions. This is followed by a high-level overview and organization of technical advances, including an abundance of pointers to source material, which can enable these breakthroughs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS2004

DASL-Data and Activities for Solar Learning

DASL-Data and Activities for Solar Learning Data and Activities for Solar Learning (DASL) provides a classroom learning environment based on a twenty-five year record of solar magnetograms from the National Solar Observatory (NSO) at Kitt Peak, AZ. The data, together with image processing software for Macs or PCs, can be used to learn basic facts about the Sun and astronomy at the middle school level. At the high school level, students can study properties of the Sun's magnetic cycle with classroom exercises emphasizing data and error analysis and can participate in a new scientific study, Research in Active Solar Longitudes (RASL), in collaboration with classrooms throughout the country and scientists at NSO and NASA. We present a half-day course to train teachers in the scientific content of the project and its classroom use. We will provide a compact disc with the data and software and will demonstrate software installation and use, classroom exercises, and participation in RASL with computer projection.

Jones, Harrison P.↗
NASA NTRS2024

The NASA Facility for Astromaterials Research at the Johnson Space Center – A National Laboratory for Planetary Research

The Astromaterials Research and Exploration Science (ARES) Division at the NASA Johnson Space Center houses a unique combination of laboratories, instruments, infrastructure, technical expertise, and other assets for conducting broad-based world-class planetary research. These facilities have been accessed for decades by hundreds of external scientists, including faculty, post-docs, students, and interns, most at no-cost and on a collaborative basis. With funding through NASA’s Planetary Science Enabling Facilities (PSEF) program, we have established the NASA Facility for Astromaterials Research (NFAR) to expand access to and enhance these laboratories for a diverse and inclusive external user base, focusing on training of the next generation of scientists and, thus, maximizing the science return from research funded by R&A programs in NASA’s Planetary Science Division (PSD). NFAR enables new planetary sample analyses, making new scientific discoveries possible, including training the next generation of planetary scientists. NFAR laboratories are co-located with JSC Curation that houses the NASA-controlled astromaterials collections, thus enabling direct access to both research and curation expertise, to facilitate specialized sample handling and analysis of allocated samples to sample PIs, particularly those affiliated with institutions that historically have limited access to or lack in-house analytical or experimental facilities.

J. I. Simon↗
DOE OSTI2020

The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid Parallelism

Here, we present scalable hybrid-parallel algorithms for training large-scale 3D convolutional neural networks. Deep learning-based emerging scientific workflows often require model training with large, high-dimensional samples, which can make training much more costly and even infeasible due to excessive memory usage. We solve these challenges by extensively applying hybrid parallelism throughout the end-to-end training pipeline, including both computations and I/O. Our hybrid-parallel algorithm extends the standard data parallelism with spatial parallelism, which partitions a single sample in the spatial domain, realizing strong scaling beyond the mini-batch dimension with a larger aggregated memory capacity. We evaluate our proposed training algorithms with two challenging 3D CNNs, CosmoFlow and 3D U-Net. Our comprehensive performance studies show that good weak and strong scaling can be achieved for both networks using up to 2K GPUs. More importantly, we enable training of CosmoFlow with much larger samples than previously possible, realizing an order-of-magnitude improvement in prediction accuracy.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2018

Reflectance-Based Imaging Spectrometer Error Budget Field Practicum at the Railroad Valley Test Site, Nevada

Calibration and validation determine the quality and integrity of the data provided by sensors and have enormous downstream impacts on the accuracy and reliabilityof the products generated by these sensors. With the imminent launch of the next generation of space borne imaging spectroscopy sensors, the IEEE Geoscience and Remote Sensing Society's (GRSS's) Geoscience Spaceborne Imaging Spectroscopy Technical Committee (GSIS TC) initiated a calibration and validation initiative.This article reports on a recent reflectance-based imaging spectrometer error budget field practicum focused on radiometric calibration of spaceborne imaging spectroscopy sensors. The field exercise, conducted at Railroad Valley in Nevada, provided valuable training for personnel in a variety of Earth observation (EO) areas, from engineers developing future sensors to calibration scientists actively working in the field. Future work in this area will focus on analyzing the data acquired as part of the training to answer numerous scientific questions, e.g., understanding the spatial and spectral homogeneity of the site being measured, identifying the optimal sampling to characterize the site, and optimizating the sampling techniques, including looking into the automation of some measurement protocol aspects. The training exercise was recorded to ensure that the knowledge can be disseminated across the GRSS and wider imaging spectroscopy community.

Ong, Cindy↗
NASA NTRS2019

Tactical Scientific Decision-Making during Crewed Astrobiology Mars Missions

The limitations placed upon human explorers on the surface of Mars will necessitate a methodology for scientific exploration that is different from standard approaches to terrestrial fieldwork and prior crewed exploration of the Moon. In particular, the data transmission limitations and communication latency between Earth and Mars create a unique situation for surface crew in contact with a terrestrial science team. The BASALT research program simulated a series of extravehicular activities (EVAs) in Mars analog terrains under various Mars-relevant bandwidth and latency conditions to investigate how best to approach this problem. Here we discuss tactical decision-making under these conditions, that is, how the crew on Mars interacts with a team of scientists and support personnel on Earth to collect samples of maximum scientific interest. We describe the strategies, protocols, and tools tested in BASALT EVAs and give recommendations on how best to conduct human exploration of Mars with support from Earth-based scientists. We find that even with scientists supporting them, the crew performing the exploration must be trained in the appropriate scientific disciplines in order to provide the terrestrial scientists with enough information to make decisions, but that with appropriate planning and structure, and tools such as a ‘‘dynamic leaderboard,’’ terrestrial scientists can add scientific value to an EVA, even under Mars communication latency

Decision-making↗
DOE OSTI2020

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗
DOE OSTI2025

Training and onboarding initiatives in high energy physics experiments

In this article we document the current analysis software training and onboarding activities in several High Energy Physics (HEP) experiments: ATLAS, CMS, LHCb, Belle II and DUNE. Fast and efficient onboarding of new collaboration members is increasingly important for HEP experiments. With rapidly increasing data volumes and larger collaborations the analyses and consequently, the related software, become ever more complex. This necessitates structured onboarding and training. Recognizing this, a meeting series was held by the HEP Software Foundation (HSF) in 2022 for experiments to showcase their initiatives. Here we document and analyze these in an attempt to determine a set of key considerations for future HEP experiments.

analysis software↗
DOE OSTI2024

Performance of chatbots in queries concerning fundamental concepts in photochemistry

Abstract The advent of chatbots raises the possibility of a paradigm shift across society including the most technical of fields with regard to access to information, generation of knowledge, and dissemination of education and training. Photochemistry is a scientific endeavor with roots in chemistry and physics and branches that encompass diverse disciplines ranging from astronomy to zoology. Here, five chatbots have each been challenged with 13 photochemically relevant queries. The chatbots included ChatGPT 3.5, ChatGPT 4.0, Copilot, Gemini Advanced, and Meta AI. The queries encompassed fundamental concepts (e.g., “Why is the fluorescence spectrum typically the mirror image of the absorption spectrum?”), practical matters (e.g., “What is the inner filter effect and how to avoid it?”), philosophical matters (“Please create the most important photochemistry questions.”), and specific molecular features (e.g., “Why are azo dyes non‐fluorescent?”). The chatbots were moderately effective in answering queries concerning fundamental concepts in photochemistry but were glaringly deficient in specialized queries for dyes and fluorophores. In some instances, a correct response was embedded in verbose scientific nonsense whereas in others the entire response, while grammatically correct, was utterly meaningless. The unreliable accuracy makes present chatbots poorly suited for unaided educational purposes and highlights the importance of domain experts.

Taniguchi, Masahiko↗
DOE OSTI2026

REDI – Readiness Engine for Data Integration

The Readiness Engine for Data Integration (REDI) is an open-source framework for automating, standardizing, and assessing the process of preparing scientific data for AI training. REDI implements a five-stage pipeline (ingest, preprocess, transform, structure, output) with per-stage provenance instrumentation via Flowcept, domain-aware transformation logic (PII anonymization, regridding, graph encoding, and more), and built-in readiness assessment and validation modes. REDI has been evaluated across climate, proteomics, materials science, and nuclear fusion datasets, demonstrating near-ideal parallel scaling to 100 nodes on OLCF's Frontier system. REDI is deployable as an agent-callable skill in coding environments such as Claude Code and OpenAI Codex, and is complemented by SetGo for FAIR compliance and catalog publication.

Brewer, Wesley [Oak Ridge National Laboratory (ORN↗
DOE OSTI2025

Towards Exascale Astrophysics of Mergers and Supernovae (TEAMS)

The TEAMS project brought together cutting-edge simulations, theoretical insights, and collaborative efforts to deepen our understanding of some of the universe’s most extreme phenomena—supernovae, neutron star mergers, and the powerful signals they emit. Using one of the largest suites of 3D supernova simulations ever conducted, researchers uncovered new insights into how massive stars explode, how those explosions vary by stellar mass, and what conditions lead to the birth of neutron stars or black holes. They also studied the radiation and gravitational wave signals emitted during these events, revealing how future observations can be used to uncover what happens deep inside collapsing stars. The team developed improved tools for modeling how light and neutrinos behave in such explosive environments, enabling more accurate predictions of what astronomers might observe. Work also explored how the chemical composition and geometry of kilonovae—the visible explosions that follow neutron star mergers—influence their signals and can reveal the origins of heavy elements like gold. These efforts not only advanced scientific knowledge, but also trained a new generation of researchers at the intersection of astrophysics, computational science, and nuclear theory.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
NASA NTRS2011

Development of a Multivariable Parametric Cost Analysis for Space-Based Telescopes

Over the past 400 years, the telescope has proven to be a valuable tool in helping humankind understand the Universe around us. The images and data produced by telescopes have revolutionized planetary, solar, stellar, and galactic astronomy and have inspired a wide range of people, from the child who dreams about the images seen on NASA websites to the most highly trained scientist. Like all scientific endeavors, astronomical research must operate within the constraints imposed by budget limitations. Hence the importance of understanding cost: to find the balance between the dreams of scientists and the restrictions of the available budget. By logically analyzing the data we have collected for over thirty different telescopes from more than 200 different sources, statistical methods, such as plotting regressions and residuals, can be used to determine what drives the cost of telescopes to build and use a cost model for space-based telescopes. Previous cost models have focused their attention on ground-based telescopes due to limited data for space telescopes and the larger number and longer history of ground-based astronomy. Due to the increased availability of cost data from recent space-telescope construction, we have been able to produce and begin testing a comprehensive cost model for space telescopes, with guidance from the cost models for ground-based telescopes. By separating the variables that effect cost such as diameter, mass, wavelength, density, data rate, and number of instruments, we advance the goal to better understand the cost drivers of space telescopes.. The use of sophisticated mathematical techniques to improve the accuracy of cost models has the potential to help society make informed decisions about proposed scientific projects. An improved knowledge of cost will allow scientists to get the maximum value returned for the money given and create a harmony between the visions of scientists and the reality of a budget.

Dollinger, Courtnay↗
NASA NTRS2017

Comprehensive Oculomotor Behavioral Response Assessment (COBRA)

An eye movement-based methodology and assessment tool may be used to quantify many aspects of human dynamic visual processing using a relatively simple and short oculomotor task, noninvasive video-based eye tracking, and validated oculometric analysis techniques. By examining the eye movement responses to a task including a radially-organized appropriately randomized sequence of Rashbass-like step-ramp pursuit-tracking trials, distinct performance measurements may be generated that may be associated with, for example, pursuit initiation (e.g., latency and open-loop pursuit acceleration), steady-state tracking (e.g., gain, catch-up saccade amplitude, and the proportion of the steady-state response consisting of smooth movement), direction tuning (e.g., oblique effect amplitude, horizontal-vertical asymmetry, and direction noise), and speed tuning (e.g., speed responsiveness and noise). This quantitative approach may provide fast and results (e.g., a multi-dimensional set of oculometrics and a single scalar impairment index) that can be interpreted by one without a high degree of scientific sophistication or extensive training.

Stone, Leland S.↗