Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generative 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 595 records · Page 33
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

High-Throughput Screening of Li Solid-State Electrolytes With Bond Valence Methods and Graph Neural Networks

Li-based solid-state electrolyte (Li-SSE) materials enable safer, all-solid-state batteries but the computational search for candidates with favorable stability and Li-ion conductivity is challenging due to the size of the search space and the cost of evaluating transport properties with ab initio methods. We present a high-throughput screening approach for Li-SSE materials using a combination of bond-valence methods and graph neural networks. We demonstrate the screening approach with a dataset containing tens of thousands of Li-containing compounds. Furthermore, we combine the machine-learning screening procedure with an isovalent substitution scheme to generate and screen additional Li SSE candidates beyond existing databases. Finally, we discuss relative importances of geometric and bond-valence quantities in the training of graph neural networks, providing insight for future modeling of ionic conductivity in Li-SSE materials.

Materials discovery↗
NASA NTRSDate not supplied

Screening of Li-Based Solid Electrolytes Using Bond-Valence Methods and Graph Neural Networks

Li-based solid-state electrolyte (Li-SSE) materials enable safer, all-solid-state batteries but the computational search for candidates with favorable stability and Li-ion conductivity is challenging due to the size of the search space and the cost of evaluating transport properties with ab initio methods. We present a high-throughput screening approach for Li-SSE materials using a combination of bond-valence methods and graph neural networks. We demonstrate the screening approach with a dataset containing tens of thousands of Li-containing compounds. Furthermore, we combine the machine-learning screening procedure with an isovalent substitution scheme to generate and screen additional Li SSE candidates beyond existing databases. Finally, we discuss relative importances of geometric and bond-valence quantities in the training of graph neural networks, providing insight for future modeling of ionic conductivity in Li-SSE materials.

Materials discovery↗
NASA NTRS2024

Discrete Event Simulation-Based Timeline Validation Using R2U2

The Gateway Vehicle Systems Manager (VSM), the top-level software control system in a distributed, hierarchical Autonomous System Management Architecture is, like most modern spacecraft software control systems, heavily data-driven. For example, schedules (timelines) will be developed on the ground and, due to the high degree of autonomy, contain complex procedures involving conditional branching, variable timing, and resource contention resolution. In order to verify that an uploaded timeline will function correctly, it is necessary to explore the feasible set of possible executions. While it is possible to test a timeline using a mission simulation, the complexity of the system and duration of a timeline limits the number of trials and therefore the test coverage. To address this problem, the VSM team is using a discrete event system model that can rapidly generate from a timeline sets of event sequences using Monte Carlo techniques. To achieve rapid and trustworthy checking of the event sequences, we use an offline version of the runtime model checking tool R2U2. This presentation describes the approach the VSM team is using to implement the discrete event simulation and evaluate event sequences using R2U2. The presentation will discuss: 1. Description of the timelines by VSM in the context of VSM operations 2. Expansion of a timeline into a sequence of atomic events 3. Adjustment, in the Monte Carlo environment, of an event sequence to account for uncertainty, external events, and failures 4. Definition of R2U2 input and mission-time linear temporal logic files 5. Generation and use of R2U2 verdict sequences 6. Lessons learned and future work

Verification↗
NASA NTRS2009

Interface Generation and Compositional Verification in JavaPathfinder

We present a novel algorithm for interface generation of software components. Given a component, our algorithm uses learning techniques to compute a permissive interface representing legal usage of the component. Unlike our previous work, this algorithm does not require knowledge about the component s environment. Furthermore, in contrast to other related approaches, our algorithm computes permissive interfaces even in the presence of non-determinism in the component. Our algorithm is implemented in the JavaPathfinder model checking framework for UML statechart components. We have also added support for automated assume-guarantee style compositional verification in JavaPathfinder, using component interfaces. We report on the application of the presented approach to the generation of interfaces for flight software components.

Giannakopoulou, Dimitra↗
DOE OSTI2024

Updates and Lessons Learned from NuMI Beamline at Fermilab

The Neutrinos at the Main Injector (NuMI) beamline at Fermilab generates an intense muon neutrino beam for the NOvA (NuMI Off-axis $\nu_e$ Appearance) long-baseline neutrino experiment. Over the years, the NuMI beamline has been pivotal in advancing neutrino physics, providing invaluable data and insights. This proceeding paper discusses updates and the lessons learned from recent experiences during the beam operations, maintenance, and monitoring of the NuMI beamline. Key topics include the optimization of beam performance and challenges in maintaining beamline stability. The paper aims to share best practices and provide a road-map for future beamline projects, including the Long-Baseline Neutrino Facility (LBNF).

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Updates and Lessons Learned from NuMI Beamline at Fermilab

The Neutrinos at the Main Injector (NuMI) beamline at Fermilab generates an intense muon neutrino beam for the NOvA (NuMI Off-axis 𝜈𝑒 Appearance) long baseline neutrino experiment. Over the years, the NuMI beamline has been pivotal in advancing neutrino physics, providing invaluable data and insights. This presentation offers updates and a comprehensive review of the lessons learned from the operation, maintenance, and monitoring of the NuMI beamline. Key topics include the optimization of beam performance, challenges in maintaining beamline stability, and proposed Machine Learning implementations to enhance monitoring. The talk aims to share best practices and provide a roadmap for future beamline projects, including the Long-Baseline Neutrino Facility (LBNF).

Wickremasinghe, Athula↗
NASA NTRS2012

A First Person Shooter/Real Time Strategy Hybrid: Lessons Learned

Today's military training bears little resemblance to the methods of previous generations. The Cold War is over and the enemy has changed. Doctrine that was once useful is now woefully out of date. No longer are we confronting a predictable nation but instead a diverse collection of independent fighters spread out over several countries. The enemy has changed, his tactics have changed amI cin.:urnsLance dictates that we must change as well. The wars in Iraq and Afghanistan have tested virtually all aspects of the military's support infrastructure. After fighting continuously for over a decade, many weaknesses have been revealed by the steady grind of war. Chief among them is the inability of the military to rapidly and adequately train its soldiers in the latest doctrines. In response to the enemy developing new strategies on a near monthly basis, the Joint Training Counter-IED Operations Integration Center (JTCOIC) was first created. Designed to supplement the current training system, it would attempt to address the current training shortfalls. As a result, new methods were devised to streamline training.

Stoup, James R.↗
DOE OSTI2026

Machine Learning on Heterogeneous, Edge, and Quantum Hardware for Particle Physics (ML-HEQUPP)

The next generation of particle physics experiments will face a new era of challenges in data acquisition, due to unprecedented data rates and volumes along with extreme environments and operational constraints. Harnessing this data for scientific discovery demands real-time inference and decision-making, intelligent data reduction, and efficient processing architectures beyond current capabilities. Crucial to the success of this experimental paradigm are several emerging technologies, such as artificial intelligence and machine learning (AI/ML) and silicon microelectronics, and the advent of quantum algorithms and processing. Their intersection includes areas of research such as low-power and low-latency devices for edge computing, heterogeneous accelerator systems, reconfigurable hardware, novel codesign and synthesis strategies, readout for cryogenic or high-radiation environments, and analog computing. This white paper presents a community-driven vision to identify and prioritize research and development opportunities in hardware-based ML systems and corresponding physics applications, contributing towards a successful transition to the new data frontier of fundamental science.

Gonski, Julia [SLAC]↗
DOE OSTI2024

Polymer Additive Manufacturing for Marine Renewable Energy Applications: Best Practices, Research Trends, and Current Challenges

Additive manufacturing (AM) is a rapidly growing technology space, not only for prototyping, but is also becoming more feasible at larger scales and increasing component quantities. There are a large variety of AM processes and materials available to users and effectively applying those processes and materials to a specific use case can be challenging. One specific area where AM could be particularly beneficial is marine renewable energy (MRE). Not only is MRE a relatively nascent industry with a near-term need for rapid deployments and prototype testing, but developers could also see long-term benefits from the broad variety of environmentally resistant materials available and the ability to manufacture complex geometries that AM technologies offer. Over the past 4 years, AM materials have played an increasing role in the Advanced Materials project; a multi-year, multi-laboratory research project funded by the U.S. Department of Energy's Water Power Technologies Office, with the main goal of reducing barriers to the adoption of complex materials in the MRE industry. The primary focus of this project is to develop test methods and generate datasets to understand the long-term performance of advanced materials in marine environmental and address specific material challenges as they arise. This report provides an extensive overview of the research that has been performed specific to AM polymers as part of the Advanced Materials project. The intention of this document is to provide recommendations of best practices with regards to material selection, mechanical test method development, and design practices, lessons learned along the way, current research trends, and ongoing challenges with regards to AM polymers in marine environments. In particular, this report focuses on several key aspects: Material and process selection, Environmental conditioning and subsequent degradation quantification through mechanical characterization, Composite reinforcements on AM polymer substrates, Adhesion of instrumentation for mechanical characterization and loads measurements, Protective coatings for preventing biofouling and water ingress, Other MRE case studies where AM has proved particularly useful. Ultimately, we hope that the test methods that have been developed, data generated, and lessons learned from this research will be valuable to the MRE community (researchers and developers alike), as well as other industries, and can be used as a reference point as the respective MRE and AM industries continue to grow and mature.

16 TIDAL AND WAVE POWER↗
DOE OSTI2025

Monitoring Fracture Hydromechanical Evolution in the Lab and Field Using Unsupervised Metric Learning

Fractures evolve in time through thermal‐hydraulic‐mechanical‐chemical (THMC) processes that alter their long‐range hydraulic transport properties and modify subsurface behavior and activities. The location of subsurface fractures makes it necessary to use remote sensing techniques such as passive or active seismic monitoring for fracture characterization. In this paper, we develop a machine learning approach to monitor the evolution of fracture properties using passive seismic sources in a laboratory setting and using active seismic monitoring from the Sanford Underground Research Facility in Lead, South Dakota, at a depth of 1.25 km in amphibolite rock during stimulation of natural fractures as well as during induced fracturing. The unsupervised metric learning technique applies tandem neural networks (twin (Siamese) or triplet) with contrastive loss and adaptive margins to track slowly varying systems for which class or similarity labels are not available. The approach adopts locality‐sensitive hashing to divide time‐ordered contiguous data into an arbitrary number of pseudo‐classes. Contrastive‐loss training with many hash bins generates an evolving latent‐space trajectory. This approach enables unsupervised metric learning for seismic data stacks under the condition of contiguous state sampling and slowly varying fracture properties. The displacement discontinuity theory provides a mechanistic foundation for the fracture‐dependent trajectories that are related to relaxation of fractures with time‐dependent specific stiffness responding to changes in stress or fluid saturation.

02 PETROLEUM↗
DOE OSTI2025

RLMolLM: Reinforcement Learning-Enhanced Language Model Framework for Inverse Molecular Design

Inverse molecular design faces significant challenges due to vast chemical space and complex property requirements. While language models show promise for molecular generation, they struggle with validity, multi-property optimization, and structural constraints. This work presents RLMolLM, a reinforcement learning framework combining Proximal Policy Optimization (PPO) with genetic algorithms to address these limitations. Our approach optimizes multiple user-specified properties including quantitative estimates of drug-likeness (QED), synthetic accessibility (SA), and ADMET (absorption, distribution, metabolism, excretion, and toxicity) endpoints without requiring complete model retraining, while maintaining capability for scaffold-constrained generation where specific substructures must be preserved. We outperform state-of-the-art methods for molecular optimization, achieving best QED scores across GDB13, Moses, and Zinc datasets with up to 31% improvement over previous methods while maintaining excellent validity, uniqueness, and novelty metrics. For simultaneous multi-property optimization, our framework achieves substantial improvements in ADMET properties including 4.5-fold reduction in hERG toxicity and enhanced Caco-2 permeability compared to Moses dataset. Under structural constraints, the framework significantly improves molecular validity while preserving scaffolds and effectively optimizing properties. In conclusion, this versatile solution advances pharmaceutical and materials molecular design through effective integration of reinforcement learning and genetic algorithms with multi-property optimization and scaffold preservation.

Genetic algorithms↗
DOE OSTI2025

Enhancing generative molecular design via uncertainty-guided fine-tuning of variational autoencoders

In recent years, deep generative models have been successfully applied to various molecular design tasks, particularly in the life and materials sciences. One critical challenge for pre-trained generative molecular design (GMD) models is to fine-tune them to be better suited for downstream design tasks that aim at optimizing specific molecular properties. However, redesigning and training an existing effective generative model from scratch for each new design task are impractical. Furthermore, the black-box nature of typical downstream tasks that involve property prediction makes it nontrivial to optimize the generative model in a task-specific manner. In this work, we propose an uncertainty-guided fine-tuning strategy that can effectively enhance a pre-trained variational autoencoder (VAE) for GMD through performance feedback in an active learning setting. The strategy begins by quantifying the model uncertainty of the generative model using an efficient active subspace-based UQ (uncertainty quantification) scheme. Next, the decoder diversity within the characterized model uncertainty class is explored to expand the viable space of molecular generation. The low-dimensionality of the active subspace makes this exploration tractable using a black-box optimization scheme, which in turn enables us to identify and leverage a diverse set of high-performing models to generate enhanced molecules. Empirical results across six target molecular properties using multiple VAE-based generative models demonstrate that our uncertainty-guided fine-tuning strategy consistently leads to improved models that outperform the original pre-trained models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Delamination-informed lifecycle decisions: A dielectric and machine learning framework for composite sorting and recycling

Composite materials are widely used in aerospace, marine, and automotive sectors due to their high strength-to-weight ratio and durability. However, their long-term reliability can be compromised by damage accumulation. Specifically, delamination initiation serves as a precursor to structural failure, which is often difficult to detect during damage inspection. Identifying and sorting delamination initiation in samples not only increases operational safety while providing critical information for end-of-life decisions, which influences both the service life extension value and the efficiency of fiber extraction during recycling. This research addresses two challenges: (1) developing a nondestructive, ex-situ framework to sort composite materials based on damage severity, particularly delamination, and (2) understanding how damage in composites influences resin removal during pyrolysis. Both experimental work and finite element analysis were performed to predict critical stress levels that are associated with delamination onset. Based on these results, three loading levels 50 %, 75 %, and 90 % of maximum stress, were selected for controlled experiments, generating composite samples with varying extents of damage for machine learning model training. Microscopic imaging of these samples confirmed the damage progression from matrix cracking to delamination, validating the computational predictions. We explored supervised machine learning using dielectric measurements to classify damage states. Preliminary results show an artificial neural network can identify early delamination which is a potential precursor to failure, with 94.44 % accuracy on our dataset. A parallel investigation into the effect of damage severity on pyrolysis recycling showed that heavily delaminated samples required significantly less energy for comparable matrix removal than undamaged samples.

dielectric variables↗
NASA NTRS2016

Brief History of Agricultural Systems Modeling

Agricultural systems science generates knowledge that allows researchers to consider complex problems or take informed agricultural decisions. The rich history of this science exemplifies the diversity of systems and scales over which they operate and have been studied. Modeling, an essential tool in agricultural systems science, has been accomplished by scientists from a wide range of disciplines, who have contributed concepts and tools over more than six decades. As agricultural scientists now consider the next generation models, data, and knowledge products needed to meet the increasingly complex systems problems faced by society, it is important to take stock of this history and its lessons to ensure that we avoid re-invention and strive to consider all dimensions of associated challenges. To this end, we summarize here the history of agricultural systems modeling and identify lessons learned that can help guide the design and development of next generation of agricultural system tools and methods. A number of past events combined with overall technological progress in other fields have strongly contributed to the evolution of agricultural system modeling, including development of process-based bio-physical models of crops and livestock, statistical models based on historical observations, and economic optimization and simulation models at household and regional to global scales. Characteristics of agricultural systems models have varied widely depending on the systems involved, their scales, and the wide range of purposes that motivated their development and use by researchers in different disciplines. Recent trends in broader collaboration across institutions, across disciplines, and between the public and private sectors suggest that the stage is set for the major advances in agricultural systems science that are needed for the next generation of models, databases, knowledge products and decision support systems. The lessons from history should be considered to help avoid roadblocks and pitfalls as the community develops this next generation of agricultural systems models.

agricultural systems↗
DOE OSTI2024

Portable, heterogeneous ensemble workflows at scale using libEnsemble

libEnsemble is a Python-based toolkit for running dynamic ensembles, developed as part of the DOE Exascale Computing Project. The toolkit utilizes a unique generator–simulator–allocator paradigm, where generators produce input for simulators, simulators evaluate those inputs, and allocators decide whether and when a simulator or generator should be called. The generator steers the ensemble based on simulation results. Generators may, for example, apply methods for numerical optimization, machine learning, or statistical calibration. libEnsemble communicates between a manager and workers. Flexibility is provided through multiple manager–worker communication substrates each of which has different benefits. These include Python’s multiprocessing, mpi4py, and TCP. Multisite ensembles are supported using Balsam or Globus Compute. We overview the unique characteristics of libEnsemble as well as current and potential interoperability with other packages in the workflow ecosystem. We highlight libEnsemble’s dynamic resource features: libEnsemble can detect system resources, such as available nodes, cores, and GPUs, and assign these in a portable way. These features allow users to specify the number of processors and GPUs required for each simulation; and resources will be automatically assigned on a wide range of systems, including Frontier, Aurora, and Perlmutter. Such ensembles can include multiple simulation types, some using GPUs and others using only CPUs, sharing nodes for maximum efficiency. We also describe the benefits of libEnsemble’s generator–simulator coupling, which easily exposes to the user the ability to cancel, and portably kill, running simulations based on models that are updated with intermediate simulation output. We demonstrate libEnsemble’s capabilities, scalability, and scientific impact via a Gaussian process surrogate training problem for the longitudinal density profile at the exit of a plasma accelerator stage. In conclusion, the study uses gpCAM for the surrogate model and employs either Wake-T or WarpX simulations, highlighting efficient use of resources that can easily extend to exascale.

Dynamic ensembles↗
NASA NTRSDate not supplied

Designing Molten Salt Eutectics: A Combined Thermodynamic Modeling and Machine Learning Approach

Designing stable electrolytes with target properties is an important challenge in realizing next generation energy storage devices. Molten salt eutectics-based electrolytes are known for their stability with minimal parasitic reactions when compared to traditional organic electrolytes and are an attractive option for different battery chemistries. The operating temperature of the molten salt batteries depends on the melting temperature of the eutectic and hence there is a necessity to discover novel low melting temperature molten salt eutectic mixtures for energy storage applications. In this work we develop a high throughput computational screening approach for molten salt mixtures using thermodynamic modeling and machine learning (ML). COSMO-SAC model and ML approaches were independently developed based on the existing experimental data and these models were further used to predict the eutectic melting temperature and composition of several new binary, ternary, and quaternary mixtures. We show that combining ML and thermodynamic modeling strategies is effective in exploring the vast design space of molten salt mixtures.

Thermodynamics↗
DOE OSTI2025

Women in Nuclear Security: The United Arab Emirates Story

Historically in the United Arab Emirates, security personnel stationed at nuclear sites were typically men with military or policing backgrounds. Although these groups bring important, transferrable skills and experience to the nuclear security mission, some Emirati stakeholders recognize the increased benefit of a greater diversity of voices and backgrounds within the nuclear security team hierarchy. By recruiting from a wider range of disciplines and encouraging gender diversity, the security team could develop broader insight into security challenges, and a greater variety of perspectives could bring forth more innovative solutions. When aligning a diverse, multinational workforce with a common mission, all members of a security organization must fundamentally change their individual approaches to the work; the entire staff must be on the same page. This can be particularly challenging for some people who find it difficult to transition from a framework of beliefs because of past experiences based on prescriptive, exclusionary, hierarchical thought. Also, national cultural values are learned early, held deeply, and change slowly over the course of generations, and inherent biases rooted in these values can create barriers to the collective progress of a team. Creating a more open, diverse, and transparent culture for the team by accepting a unique, egalitarian, professional nuclear security culture that all members adhere to can be a challenging task for some. In this article, I share my experiences related to professional roadblocks, personal challenges, and lessons learned, particularly those regarding the empowerment of women in science and engineering, while developing and establishing the United Arab Emirates nuclear security program. I also discuss the support (and underrepresentation) of women, including those currently in critical leadership positions, and their careers in nuclear security.

Barakah Nuclear Power Plant↗
DOE OSTI2025

Chemical classification program synthesis using generative artificial intelligence

Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non-organic compounds with desirable material properties, or organizing large chemical libraries for drug discovery or environmental monitoring. However, manual classification is labor-intensive and difficult to scale to large chemical databases. Existing automated approaches either rely on manually constructed classification rules, or are deep learning methods that lack explainability. This work presents an approach that uses generative artificial intelligence to automatically write chemical classifier programs for classes in the Chemical Entities of Biological Interest (ChEBI) database. These programs can be used for efficient deterministic run-time classification of SMILES structures, with natural language explanations. The programs themselves constitute an explainable computable ontological model of chemical class nomenclature, which we call the ChEBI Chemical Class Program Ontology (C3PO). We validated our approach against the ChEBI database, and compared our results against deep learning models and a naive SMARTS pattern based classifier. C3PO outperforms the naive classifier, but does not reach the performance of state of the art deep learning methods. However, C3PO has a number of strengths that complement deep learning methods, including explainability and reduced data dependence. C3PO can be used alongside deep learning classifiers to provide an explanation of the classification, where both methods agree. The programs can be used as part of the ontology development process, and iteratively refined by expert human curators.

Artificial Intelligence↗