Search NASA⌕ Search

SEARCH · Search NASA

Results for “collaborative 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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity

Recent advancements have highlighted the limitations of current quantum systems, particularly the restricted number of qubits available on near-term quantum devices. This constraint greatly inhibits the range of applications that can leverage quantum computers. Moreover, as the available qubits increase, the computational complexity grows exponentially, posing additional challenges. Consequently, there is an urgent need to use qubits efficiently and mitigate both present limitations and future complexities. To address this, existing quantum applications attempt to integrate classical and quantum systems in a hybrid framework. In this study, we concentrate on quantum deep learning and introduce a collaborative classical-quantum architecture called co-TenQu. The classical component employs a tensor network for compression and feature extraction, enabling higher-dimensional data to be encoded onto logical quantum circuits with limited qubits. On the quantum side, we propose a quantum-state-fidelity-based evaluation function to iteratively train the network through a feedback loop between the two sides. co-TenQu has been implemented and evaluated with both simulators and the IBM-Q platform. Compared to state-of-the-art approaches, co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. Additionally, it outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.

42 ENGINEERING↗
NASA NTRS2002

CIP Training Manual: Collaborative Information Portal Advance Training Information for Field Test Participants

The Collaborative Information Portal (CIP) is a web-based information management and retrieval system. Its purpose is to provide users at MER (Mars Exploration Rover) mission operations with easy access to a broad range of mission data and products and contextual information such as the current operations schedule. The CIP web-server provides this content in a user customizable web-portal environment. Since CIP is still under development, only a subset of the full feature set will be available for the EDO field test. The CIP web-portal will be accessed through a standard web browser. CIP is intended to be intuitive and simple to use, however, at the training session, users will receive a one to two page reference guide, which should aid them in using CIP. Users must provide their own computers for accessing CIP during the field test. These computers should be configured with Java 1.3 and a Java 2 enabled browser. Macintosh computers should be running OS 10.1.3 or later. Classic Mac OS (OS 9) is not supported. For more information please read section 7.3 in the FIASCO Rover Science Operations Test Mission Plan. Several screen shots of the Beta Release of CIP are shown on the following pages.

Schreiner, John↗
NASA NTRSDate not supplied

Immersive Technologies for Human-in-the-Loop Lunar Surface Simulations

NASA, the National Aeronautics and Space Administration, continually seeks innovative solutions to enhance its operations, particularly in the realms of testing, evaluation, and training for future missions. Immersive technologies, such as virtual, augmented, and mixed reality have proven to be powerful tools for realistic, interactive, and engaging environments. This paper explores how the Simulation and Graphics Branch at NASA’s Johnson Space Center (JSC) leverages immersive technology, modern commercial rendering engines, and physics-based systems simulations to develop human-in-the-loop systems for humanity’s return to the Moon through the Artemis program. When NASA returns to the Moon, astronauts will travel to the Moon’s South Pole where lighting conditions will cause a more complex operational environment. Human-in-the-loop testing plays a crucial role in NASA's mission planning, spacecraft and space systems development, and evaluation of operational scenarios. The development of immersive environments such as a lunar rover mockup at a video wall enables engineers and astronauts to simulate and experience mission scenarios, integrated spacecraft systems, and operational procedures in a relevant environment before deployment. By integrating realistic virtual environments, immersive technology allows for the visualization and interaction with virtual spacecraft models, mission landscapes, and complex operational tasks. This approach helps identify potential design flaws, operational challenges, and safety considerations. It also provides valuable insights for risk reduction and helps improve mission efficiency and effectiveness. With advanced motion tracking systems and custom virtual environments data can be gathered and evaluated to help NASA refine training protocols, develop specialized training procedures and optimize human-robotic interactions for future space missions. Furthermore, immersive technology offers opportunities for future training initiatives at NASA. The Virtual Reality Laboratory at JSC has pioneered training with Virtual Reality (VR) since the Hubble Space Telescope repair missions in the early 1990’s. Extended Reality (XR) simulations enable astronauts to rehearse complex spacewalks, spacecraft maneuvers, and extravehicular activities in a safe and controlled environment. By replicating the physical and cognitive challenges of space missions, immersive training experiences enhance astronauts' situational awareness, decision-making abilities, and adaptability to unexpected scenarios. Additionally, immersive technology facilitates collaborative training, allowing geographically dispersed crew and mission control personnel to engage in synchronized simulations, fostering teamwork and effective communication. The adoption of immersive technology in NASA's testing, evaluation, and future training programs has yielded significant benefits. By incorporating human-in-the-loop testing for studies involving Extra Vehicular Activities (EVA), surface mobility and landing systems, NASA can identify and mitigate risks, optimize operational procedures, and enhance mission success. Ultimately, immersive training experiences can empower astronauts to better navigate the complexities of space missions, ensuring their safety, productivity, and success in the dynamic and challenging environments they will experience at the Lunar South Pole.

Simulation Modeling Virtual Reality Immersive Tech↗
NASA NTRSDate not supplied

Immersive Technologies for Human-in-the-Loop Lunar Surface Simulations

NASA, the National Aeronautics and Space Administration, continually seeks innovative solutions to enhance its operations, particularly in the realms of testing, evaluation, and training for future missions. Immersive technologies, such as virtual, augmented, and mixed reality have proven to be powerful tools for immersing users in realistic, interactive, and engaging environments. This paper explores how the Simulation and Graphics Branch at NASA’s Johnson Space Center (JSC) leverages immersive technology, modern commercial rendering engines, and physics-based systems simulations to develop human-in-the-loop systems for humanity’s return to the Moon through the Artemis program. When NASA returns to the Moon, astronauts will travel to the Moon’s South Pole where lighting conditions will cause a more complex operational environment. Human-in-the-loop simulations play a crucial role in NASA’s mission planning, spacecraft and space systems development, and evaluation of operational scenarios. The development of immersive environments such as a lunar rover mockup at a video wall enables engineers and astronauts to simulate and experience mission scenarios, integrated spacecraft systems, and operational procedures in a relevant environment before deployment. By integrating realistic virtual environments, immersive technology allows for the visualization and interaction with virtual spacecraft models, mission landscapes, and complex operational tasks. This approach helps identify potential design flaws, operational challenges, and safety considerations. It also provides valuable insights for risk reduction and helps improve mission efficiency and effectiveness. With advanced motion tracking systems and custom virtual environments, data can be gathered and evaluated to help NASA refine training protocols, develop specialized training procedures, and optimize human-robotic interactions for future space missions. Furthermore, immersive technology offers opportunities for future training initiatives at NASA. The Virtual Reality Laboratory at JSC has pioneered training with Virtual Reality (VR) since the Hubble Space Telescope repair missions in the early 1990’s. Extended Reality (XR) simulations enable astronauts to rehearse complex spacewalks, spacecraft maneuvers, and extravehicular activities in a safe and controlled environment. By replicating the physical and cognitive challenges of space missions, immersive training experiences enhance astronauts’ situational awareness, decision-making abilities, and adaptability to unexpected scenarios. Additionally, immersive technology facilitates collaborative training, allowing geographically dispersed crew and mission control personnel to engage in synchronized simulations, fostering teamwork and effective communication. The adoption of immersive technology in NASA’s testing, evaluation, and future training programs has yielded significant benefits. By incorporating human-in-the-loop simulations for studies involving Extra Vehicular Activities (EVA), surface mobility and landing systems, NASA can identify and mitigate risks, optimize operational procedures, and enhance mission success. Ultimately, immersive simulation experiences can empower astronauts to better navigate the complexities of space missions, ensuring their safety, productivity, and success in the dynamic and challenging environments they will experience at the Lunar South Pole.

HITL↗
DOE OSTI2025

Construction Methodology Transformation for the Benefit of Workforce Development

Construction is a key economic engine driving both national and global economies. While manual, onsite construction methods dominate the U.S. construction industry, a major shift towards offsite methods has been underway due to its efficiency, speed, and potential cost savings. The workforce necessary for offsite construction growth does not exist in its current form because of the focus on onsite methodologies and the lack of exposure to offsite building methods at all levels of a student’s learning journey. The growth of the U.S. construction industry and competitiveness in an increasingly global construction market over the coming decades can only be supported by a dramatic increase in the use of offsite methods, which requires ramping up workforce training for certain skillsets. The goal of Construction Methodology Transformation for the Benefit of Workforce Development was to understand the opportunities and barriers in both education and industry and to identify best practices for offering curriculum and training to educators, industry, and students that would support skills needed for careers in offsite construction. Our team proposed combining three offsite construction workforce development needs: content development, exposure and training, and job placement - under a single Platform model that would increase experience and career opportunities for students and help match them with potential industry members. Through our proposed solution we expected to see: developed offsite curriculum being utilized by educators and students; an increase in the identification of construction technology and offsite construction methods; an average increase in knowledge gain of at least 25% after participation in pilots; better equipped candidates who are prepared for jobs in offsite construction; and a beta workforce development platform that helps build more pathways for students looking for careers in offsite construction. The two pilots included almost 250 students and resulted in an average knowledge gain of 37 percent. Our research has identified areas of opportunity, for both education and industry to make collaborative training programs more efficient and successful. The chosen techniques for this program are extremely effective when both the school and factory have solid processes and cultures in place to accept students into training programs. This project serves as an important stepping stone to industrywide collaboration to move workforce development for offsite construction forward across the country. With continued collaboration programs like this can provide much needed early exposure and training in offsite construction and we can begin to fill important positions for the future of construction.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Report of the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science

This report summarizes insights from the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science, which convened more than 40 experts from national laboratories, academia, industry, and community organizations to chart a path toward more powerful, sustainable, and collaborative scientific software ecosystems. To address urgent challenges at the intersection of high-performance computing (HPC), AI, and scientific software, participants envisioned agile, robust ecosystems built through socio-technical co-design—the intentional integration of social and technical components as interdependent parts of a unified strategy. This approach combines advances in AI, HPC, and software with new models for cross-disciplinary collaboration, training, and workforce development. Key recommendations include building modular, trustworthy AI-enabled scientific software systems; enabling scientific teams to integrate AI systems into their workflows while preserving human creativity, trust, and scientific rigor; and creating innovative training pipelines that keep pace with rapid technological change. Pilot projects were identified as near-term catalysts, with initial priorities focused on hybrid AI/HPC infrastructure, cross-disciplinary collaboration and pedagogy, responsible AI guidelines, and prototyping of public-private partnerships. This report presents a vision of next-generation ecosystems for scientific computing where AI, software, hardware, and human expertise are interwoven to drive discovery, expand access, strengthen the workforce, and accelerate scientific progress.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Ongoing Cooperative Engagement Facilitates Agile Pandemic and Outbreak Response: Lessons Learned Through Cooperative Engagement Between Uganda and the United States

Pathogens threaten human lives and disrupt economies around the world. This has been clearly illustrated by the current COVID-19 pandemic and outbreaks in livestock and food crops. Here, to manage pathogen emergence and spread, cooperative engagement programs develop and strengthen biosafety, biosecurity, and biosurveillance capabilities among local researchers to detect pathogens. In this case study, we describe the efforts of a collaboration between the Los Alamos National Laboratory and the Uganda Virus Research Institute, the primary viral diagnostic laboratory in Uganda, to implement and ensure the sustainability of sequencing for biosurveillance. We describe the process of establishing this capability along with the lessons learned from both sides of the partnership to inform future cooperative engagement efforts in low- and middle-income countries. We found that by strengthening sequencing capabilities at the Uganda Virus Research Institute before the COVID-19 pandemic, the institute was able to successfully sequence SARS-CoV-2 samples and provide data to the scientific community. We highlight the need to strengthen and sustain capabilities through in-country training, collaborative research projects, and trust.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Electrical Load Forecasting Over Multihop Smart Metering Networks With Federated Learning

Electric load forecasting is essential for power management and stability in smart grids. This is mainly achieved via advanced metering infrastructure, where smart meters (SMs) record household energy data. Traditional machine learning (ML) methods are often employed for load forecasting, but require data sharing, which raises data privacy concerns. Federated learning (FL) can address this issue by running distributed ML models at local SMs without data exchange. However, current FL-based approaches struggle to achieve efficient load forecasting due to imbalanced data distribution across heterogeneous SMs. Here, this article presents a novel personalized FL (PFL) method for high-quality load forecasting in metering networks. A meta-learning-based strategy is developed to address data heterogeneity at local SMs in the collaborative training of local load forecasting models. Moreover, to minimize the load forecasting delays in our PFL model, we study a new latency optimization problem based on optimal resource allocation at SMs. A theoretical convergence analysis is also conducted to provide insights into FL design for federated load forecasting. Extensive simulations from real-world datasets show that our method outperforms existing approaches regarding better load forecasting and reduced operational latency costs.

Rahman, Ratun [Univ. of Alabama, Huntsville, AL (U↗
DOE OSTI2026

Optimal Client Sampling in Federated Learning with Client-level Heterogeneous Differential Privacy

Federated Learning with client-level differential privacy (DP) provides a promising framework for collaboratively training models while rigorously protecting clients’ privacy. However, classic approaches like DP-FedAvg struggle when clients have heterogeneous privacy requirements, as they must uniformly enforce the strictest privacy level across all clients, leading to excessive DP noise and significant degradation in model utility. Existing methods to improve the model utility in such heterogeneous privacy settings often assume a trusted server and are largely heuristic, resulting in suboptimal performance and lacking strong theoretical foundations. Here, in this work, we address these challenges under a practical attack model where both clients and the server are honest-but-curious. We propose GDPFed, which partitions clients into groups based on their privacy budgets and achieves client-level DP within each group to reduce the privacy budget waste and hence improve the model utility. Based on the privacy and convergence analysis of GDPFed, we find that the magnitude of DP noise depends on both model dimensionality and the per-group client sampling ratios. To further improve the performance of GDPFed, we introduce GDPFed+, which integrates model sparsification to eliminate unnecessary noise and optimizes per-group client sampling ratios to minimize convergence error. Extensive empirical evaluations on multiple benchmark datasets demonstrate the effectiveness of GDPFed+, showing substantial performance gains compared with state-of-the-art methods.

Xu, Jiahao [Univ. of Nevada, Reno, NV (United Stat↗
DOE OSTI2024

Secure Federated Learning Across Heterogeneous Cloud and High-Performance Computing Resources: A Case Study on Federated Fine-Tuning of LLaMA 2

Federated learning enables multiple data owners to collaboratively train robust machine learning models without transferring large or sensitive local datasets by only sharing the parameters of the locally trained models. Here, in this article, we elaborate on the design of our Advanced Privacy-Preserving Federated Learning (APPFL) framework, which streamlines end-to-end secure and reliable federated learning experiments across cloud computing facilities and high-performance computing resources by leveraging Globus Compute, a distributed function as a service platform, and Amazon Web Services. We further demonstrate the use case of APPFL in fine-tuning an LLaMA 2 7B model using several cloud resources and supercomputers.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Position-Enhanced Gradient Attack (PEGA) on Medical Language Models

Federated Learning (FL) enables collaborative training of language models on sensitive clinical notes without sharing the data. However, this paradigm is vulnerable to gradient inversion attacks that can reconstruct private data from shared gradients. We find that state-of-the-art attacks are less effective in the medical domain, failing to overcome the unique challenges posed by its specialized vocabulary and unstructured format. To address this, we introduce the Position-Enhanced Gradient Attack (PEGA), a novel attack that makes gradients position-aware by optimizing token and position embeddings simultaneously. PEGA employs two key innovations: a periodic sorting of positional embeddings to resolve token order ambiguity and a late-stage embedding replacement strategy to correct hard-to-recover critical tokens. To evaluate the leakage of sensitive data more directly, we also propose the Unified PHI-Recall (UPHI), a new metric measuring the recovery of Protected Health Information. Experiments on the MIMIC-III dataset show that PEGA significantly outperforms leading attacks like TAG and LAMP, particularly in its ability to reconstruct identifiable patient information, exposing a more severe and nuanced privacy risk in federated medical NLP.

Xu, Nuo [University of Minnesota]↗
DOE OSTI2025

FedOSAA: Improving Federated Learning with One-Step Anderson Acceleration

Federated learning (FL) is a distributed machine learning approach that enables multiple local clients and a central server to collaboratively train a model while keeping the data on their own devices. First-order methods, particularly those incorporating variance reduction techniques, are the most widely used FL algorithms due to their simple implementation and stable performance. However, these methods tend to be slow and require a large number of communication rounds to reach the global minimizer. We propose FedOSAA, a novel approach that preserves the simplicity of first-order methods while achieving the rapid convergence typically associated with second-order methods. Our approach applies one Anderson acceleration (AA) step following classical local updates based on first-order methods with variance reduction, such as FedSVRG and SCAFFOLD, during local training. This AA step is able to leverage curvature information from the history points and gives a new update that approximates the Newton-GMRES direction, thereby significantly improving the convergence. We establish a local linear convergence rate to the global minimizer of FedOSAA for smooth and strongly convex loss functions. Numerical comparisons show that FedOSAA substantially improves the communication and computation efficiency of the original first-order methods, achieving performance comparable to second-order methods like GIANT.

Feng, Xue [University of California, Davis]↗
NASA NTRS1996

Translating Research Into Airline Practice: Case Studies In Collaboration

Airline training departments are avid customers for research that will help them enhance the effectiveness of training and the safety of flight operations. However, various factors often make it difficult for training department managers to draw upon the large body of human factors research, e.g.: research may not address the specific questions facing the training departments, the research literature may not be in a form that training managers can readily interpret, researchers' recommendations may be too expensive or impractical to implement, etc. This panel will discuss ways in which researchers can work with training departments to design research and translate findings into products that airlines can use readily. This collaboration is most effective when it is an integral part of the study from its inception. To illustrate the process of collaboration we will use as a case study the recently completed LOFT (Line Oriented Flight Training) Debriefing research project. We will summarize the findings from that study and discuss how we translated those findings into two training tools: a manual on how to facilitate LOFT debriefings and a video that illustrates facilitation techniques in a realistically enacted debriefing. In some cases, instead of starting a new research project, training department needs can be addressed by reviewing the existing research literature and using expert opinion to develop products that specifically address those needs. To illustrate this approach we will discuss a recent informal working group of scientists and airline personnel that met to develop training material to enhance situation awareness. This group reviewed scientific literature and ASRS (Aviation Safety Reporting System) reports, analyzed contributing factors, and produced a model for managing situation awareness.

Dismukes, R. Key↗
DOE OSTI2024

Privacy-Preserving Federated Learning for Science: Challenges and Research Directions

This paper discusses the key challenges and future research directions for privacy-preserving federated learning (PPFL), with a focus on its application to large-scale scientific AI models, in particular, foundation models~(FMs). PPFL enables collaborative model training across distributed datasets while preserving privacy-- an important collaborative approach for science. We discuss the need for efficient and scalable algorithms to address the increasing complexity of FMs, particularly when dealing with heterogeneous clients. In addition, we underscore the need for developing advance privacy-preserving techniques, such as differential privacy, to balance privacy and utility in large FMs emphasizing fairness and incentive mechanisms to ensure equitable participation among heterogeneous clients. Finally, we emphasize the need for a robust software stack supporting scalable and secure PPFL deployments across multiple high-performance computing facilities. We envision that PPFL would play a crucial role to advance scientific discovery and enable large-scale, privacy-aware collaborations across science domains.

Kim, Kibaek [Argonne National Laboratory (ANL)]↗
NASA NTRS2015

How to Enter, Fly In, and Exit the A-Train Constellation

The collaborative science obtained from the satellites in the A-Train is an unparalleled success. The constellation framework that has evolved is well-formulated and documented by its international members. Communication between teams is enhanced by a web-based Constellation Coordination System. Safety and correlated observations are ensured by defining independent control boxes with buffers in between. Each mission stays within its control box by regular drag makeup maneuvers. Annual inclination adjustments are coordinated by all missions to maintain their absolute and relative Mean Local Time of Ascending Node (MLTAN). Since the satellites are in different orbit planes their separation involves a three-dimensional triad made up of the along track separations, reference groundtracks and MLTAN's. For further safety, a Constellation Envelope has been defined to determine safe entry and exit orbits.

MLTAN↗
DOE OSTI2026

Federated learning for 2D synchrotron x-ray diffractometry: a cross-institutional approach for phase quantification of Ti–6Al–4V alloy

High-energy Two dimensional (2D) synchrotron x-ray diffractometry provides important insights into the atomistic structure and phase evolution of materials, yet traditional analysis methods remain complex, knowledge-intensive, and computationally demanding. Deep-learning models offer a powerful alternative for automating their analysis. Institutions that hold these datasets may be unwilling to share their data due to privacy and security policies, as well as the challenges associated with large-scale data transfer. As a result, models trained on local datasets often perform well only on their own data but exhibit bias and poor generalization across different instruments or facilities. To overcome these limitations, we explore federated learning (FL) for 2D synchrotron diffractograms, enabling collaborative model training without exchanging raw data. In this study, 2D synchrotron diffractograms of Ti–6Al–4V alloy collected from two independent facilities are used to train convolutional neural networks for predicting the β-phase volume fraction. Experimental results show that federated global models significantly outperform locally trained models in terms of generalization and achieve accuracy comparable to centralized trained models. These findings demonstrate the potential of FL to enable secure, cross-institutional collaboration and enhance the scalability of deep-learning-based materials characterization.

36 MATERIALS SCIENCE↗