Search NASA⌕ Search

SEARCH · Search NASA

Results for “interpretable machine 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.

309 records · Page 7
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Developmental and Cryogenic Thermal Vacuum (TVAC) Testing Lessons Learned

Developmental thermal vacuum (TVAC) testing is a critical step in maturing hardware designs and validating performance prior to flight qualification. Unlike qualification or acceptance testing, developmental testing provides flexibility to explore design margins, uncover integration challenges, and refine test approaches before formal verification activities begin. This presentation highlights the value of developmental testing while sharing common pitfalls encountered during developmental TVAC campaigns. Lessons learned from hands-on testing experience, including extensive developmental testing at cryogenic temperatures, will be shared in this presentation. Topics include test planning and preparation, instrumentation strategies, contamination control considerations, troubleshooting unexpected anomalies, and approaches for staying on schedule while meeting test objectives. The audience will gain practical insights and best practices that can improve test efficiency, reduce risk, and enhance the overall success of future developmental TVAC efforts.

Mackenzie Byrnes↗
DOE OSTI2025

Generative learning of densities on manifolds

A generative modeling framework is proposed that combines diffusion models and manifold learning to efficiently sample data densities on manifolds. The approach utilizes Diffusion Maps to uncover possible low-dimensional underlying (latent) spaces in the high-dimensional data (ambient) space. Two approaches for sampling from the latent data density are described. The first is a score-based diffusion model, which is trained to map a standard normal distribution to the latent data distribution using a neural network. The second one involves solving an Itô stochastic differential equation in the latent space. Additional realizations of the data are generated by lifting the samples back to the ambient space using Double Diffusion Maps , a recently introduced technique typically employed in studying dynamical system reduction; here the focus lies in sampling densities rather than system dynamics. The proposed approaches enable sampling high dimensional data densities restricted to low-dimensional, a priori unknown manifolds. The efficacy of the proposed framework is demonstrated through a benchmark problem and a material with multiscale structure.

Double diffusion maps↗
DOE OSTI2026

Optimization of the FRIB beam dump: a hybrid genetic algorithm and reinforcement learning approach

The operational envelope of high-power-density systems, such as particle accelerators and advanced nuclear energy systems, is critically constrained by the need to manage extreme thermal loads. To address this, we present a novel hybrid optimization framework combining a genetic algorithm (GA) with a soft actor-critic (SAC) deep reinforcement learning agent. This framework was applied to a practical high-heat-flux problem: redesigning the beam dump at the Facility for Rare Isotope Beams (FRIB) for a power upgrade from 20 kW to 50 kW. The resulting design, validated by three-dimensional conjugate heat transfer simulations, suppresses hazardous hot spots and yields a markedly more uniform temperature distribution. This provides a robust operating margin, increasing the average power-handling capability by 72% relative to the current design, demonstrating the framework’s potential to solve complex thermal management challenges in both accelerator technology and advanced nuclear systems.

Accelerator↗
DOE OSTI2024

Learning Nonlinear Reduced Models from Data with Operator Inference

This review discusses Operator Inference, a nonintrusive reduced modeling approach that incorporates physical governing equations by defining a structured polynomial form for the reduced model, and then learns the corresponding reduced operators from simulated training data. The polynomial model form of Operator Inference is sufficiently expressive to cover a wide range of nonlinear dynamics found in fluid mechanics and other fields of science and engineering, while still providing efficient reduced model computations. The learning steps of Operator Inference are rooted in classical projection-based model reduction; thus, some of the rich theory of model reduction can be applied to models learned with Operator Inference. This connection to projection-based model reduction theory offers a pathway toward deriving error estimates and gaining insights to improve predictions. Furthermore, through formulations of Operator Inference that preserve Hamiltonian and other structures, important physical properties such as energy conservation can be guaranteed in the predictions of the reduced model beyond the training horizon. This review illustrates key computational steps of Operator Inference through a large-scale combustion example.

Mechanics↗
DOE OSTI2026

Predicting Band-Gap of Inorganic Materials Using Neuromorphic Graph Learning

Predicting properties of inorganic materials is a heavily researched topic, with several new prediction approaches emerging as competitors. One such competitor is graph neural networks, which leverage the structure of the graph to aid in the prediction process. In this work, we propose integration of neuromorphic computation into the graph neural network pipeline. We call this approach Neuromorphic Graph Learning (NGL). We utilize the NGL approach to leverage evolutionary algorithms and a novel Spike Pipeline for Raster Analysis (SPIRE) for the prediction of band gap in inorganic materials.

Mulet, Ian [University of Tennessee (UT)]↗
DOE OSTI2024

An Overview of Electric Vehicle Load Modeling Strategies for Grid Integration Studies

The adoption of electric vehicles (EVs) has emerged as a solution to reduce greenhouse gas emissions in the transportation sector, which has motivated the implementation of public policies to promote their use in several countries. However, the high adoption of EVs poses challenges for the electricity sector, as it would imply an increase in energy demand and possible impacts on the power quality (PQ) of the power grid. Therefore, it is important to conduct EV integration studies in the power grid to determine the amount that can be incorporated without causing problems and identify the areas of the power sector that will require reinforcements. Accurate EV load patterns are required for this type of study that, through mathematical modeling, reflect both the dynamic behavior and the factors that influence the decision to recharge EVs. This article aims to present an overview of EVs, examine the different factors considered in the literature for modeling EV load patterns, and review modeling methods. EV load modeling methods are classified into deterministic, statistical, and machine learning. The article shows that each modeling method has its advantages, disadvantages, and data requirements, ranging from simple load modeling to more accurate models requiring large datasets.

Computer Science↗
DOE OSTI2024

Rapid Assessment of Sulfate Resistance in Mortar and Concrete

Extensive research has been conducted on the sulfate attack of concrete structures; however, the need to adopt the use of more sustainable materials is driving a need for a quicker test method to assess sulfate resistance. This work presents accelerated methods that can reduce the time required for assessing the sulfate resistance of mixtures by 70%. Class F fly ash has historically been used in concrete mixtures to improve sulfate resistance. However, environmental considerations and the evolving energy industry have decreased its availability, requiring the identification of economically viable and environmentally friendly alternatives to fly ash. Another challenge in addressing sulfate attack durability issues in concrete is that the standard sulfate attack test (ASTM C1012) is time-consuming and designed for only standard mortars (not concrete mixtures). To expedite the testing process, accelerated testing methods for both mortar and concrete mixtures were adopted from previous work to further the development of the accelerated tests and to assess the feasibility of testing the sulfate resistance of mortar and concrete mixtures rapidly. This study also established criteria for interpreting sulfate resistance for each of the test methods used in this work. A total of 14 mortar mixtures and four concrete mixtures using two types of Portland cement (Type I and Type I/II) and various supplementary cementitious materials (SCMs) were evaluated in this study. The accelerated testing methods significantly reduced the evaluation time from 12 months to 21 days for mortar mixtures and from 6 months to 56 days for concrete mixtures. The proposed interpretation method for mortar accelerated test results showed acceptable consistency with the ACI 318-19 interpretations for ASTM C1012 results. The interpretation methods proposed for the two concrete sulfate attack tests demonstrated excellent consistency with the ASTM C1012 results from mortar mixtures with the same cementitious materials combinations. Metakaolin was shown to improve sulfate resistance for both mortar and concrete mixtures, while silica fume and natural pozzolan had a limited impact. Using 15% metakaolin in mortar or concrete mixtures with Type I/II cement provided the best sulfate resistance.

Chemistry↗
NASA NTRSDate not supplied

CLDP/ISS Glovebox Technical Interchange Meeting

This presentation is designed to provide a high-level overview of the Microgravity Science Glovebox (MSG) and the Life Sciences Glovebox (LSG) facilities onboard the International Space Station. In addition, it provides metrics and lessons-learned information intended for the Commercial Low-Earth Orbit Development Program (CLDP) Partners.

glovebox↗
DOE OSTI2024

User-Centric Communication With Aerial Network for 6G: A Reinforcement Learning Approach

Meeting the diverse needs of user verticals requires innovative cellular architectures that can offer additional degrees of freedom to provide on-demand services. The terrestrial user-centric radio access network (UC-RAN) stands out as an excellent choice for this purpose. However, a drawback of UC-RAN is its tendency to prioritize high-priority verticals, often resulting in a subpar quality of experience for low-priority verticals. This issue is particularly exacerbated in hotspot areas. Here, to address this problem, we introduce an aerial network integrated with terrestrial UC-RAN to provide coverage to users which are not served by the terrestrial network. Furthermore, we analyze the impact of key configuration and optimization parameters (COPs), such as location, transmit power, altitude, and beamwidth of aerial base stations (ABSs) on system key performance indicators (KPIs), such as coverage, latency satisfaction, average spectral efficiency, and energy efficiency. We formulate a robust multiobjective function to maximize these KPIs without biasing toward any specific KPI(s). Finally, we propose a deep reinforcement learning optimization framework based on the state-of-the-art soft actor-critic algorithm to control ABS COPs and optimize system KPIs. Experimental evaluations demonstrate that the proposed optimization framework can converge to near-optimal solutions derived from the pseudo brute force in a few thousand epochs.

6G↗
DOE OSTI2024

Neuromorphic overparameterisation and few-shot learning in multilayer physical neural networks

Abstract Physical neuromorphic computing, exploiting the complex dynamics of physical systems, has seen rapid advancements in sophistication and performance. Physical reservoir computing, a subset of neuromorphic computing, faces limitations due to its reliance on single systems. This constrains output dimensionality and dynamic range, limiting performance to a narrow range of tasks. Here, we engineer a suite of nanomagnetic array physical reservoirs and interconnect them in parallel and series to create a multilayer neural network architecture. The output of one reservoir is recorded, scaled and virtually fed as input to the next reservoir. This networked approach increases output dimensionality, internal dynamics and computational performance. We demonstrate that a physical neuromorphic system can achieve an overparameterised state, facilitating meta-learning on small training sets and yielding strong performance across a wide range of tasks. Our approach’s efficacy is further demonstrated through few-shot learning, where the system rapidly adapts to new tasks.

Science & Technology - Other Topics↗
NASA NTRS2026

NASA Talks: Space Shuttle Columbia - Lessons Learned

On February 25, 2026, two NASA Talks were held regarding the Space Shuttle Columbia (Columbia Launch & Recovery, Columbia Reconstruction, Investigation, Causes & Key Takeaways). Crew & Thermal System Division (EC) partnered with Kennedy Space Center (KSC) and Engineering Directorate (EA) to bring these talks to Johnson Space Center (JSC) centering on what led up to and transpired after the Space Shuttle Columbia accident. Some recovered debris was on exhibit during the talks. NASA Mishap Program Specialist David Erickson and retired NASA Columbia Vehicle Manager Scott Thurston presented these talks. Mr. Erickson supports NASA mishap investigations and assists with the development of NASA's new Columbia Learning Center at KSC. Mr. Thurston brought a wealth of knowledge from his mission experience. These talks were timely and a solemn reminder of the critical importance of diligence, safety, and excellence in our work. EA Director Julie Kramer White welcomed the 400+ center-wide in-person audience, and EC Division Chief Rubik Sheth introduced the speakers. This event was held in the JSC Teague Auditorium, recorded, and executed by the EC in-house STAR Productions team.

Space Shuttle Columbia↗
NASA NTRS2026

NASA Talks: Space Shuttle Columbia - Lessons Learned: Columbia Reconstruction, Investigation, Causes and Key Takeaways

On February 25, 2026, this NASA Talk was held regarding the Space Shuttle Columbia (Columbia Launch & Recovery, Columbia Reconstruction, Investigation, Causes & Key Takeaways). Crew & Thermal System Division (EC) partnered with Kennedy Space Center (KSC) and Engineering Directorate (EA) to bring these talks to Johnson Space Center (JSC) centering on what led up to and transpired after the Space Shuttle Columbia accident. Some recovered debris was on exhibit during the talks. NASA Mishap Program Specialist David Erickson presented this talk. Mr. Erickson supports NASA mishap investigations and assists with the development of NASA's new Columbia Learning Center at KSC. This talk was timely and a solemn reminder of the critical importance of diligence, safety, and excellence in our work. EA Director Julie Kramer White welcomed the 400+ center-wide in-person audience, and EC Division Chief Rubik Sheth introduced the speakers. This event was held in the JSC Teague Auditorium, recorded, and executed by the EC in-house STAR Productions team. This record includes an mp4 video with a run time of 32 min. 31 sec.; in color; with sound.

NASA Talks↗
DOE OSTI2024

Active Learning for Rapid Targeted Synthesis of Compositionally Complex Alloys

The next generation of advanced materials is tending toward increasingly complex compositions. Synthesizing precise composition is time-consuming and becomes exponentially demanding with increasing compositional complexity. An experienced human operator does significantly better than a novice but still struggles to consistently achieve precision when synthesis parameters are coupled. The time to optimize synthesis becomes a barrier to exploring scientifically and technologically exciting compositionally complex materials. This investigation demonstrates an active learning (AL) approach for optimizing physical vapor deposition synthesis of thin-film alloys with up to five principal elements. We compared AL-based on Gaussian process (GP) and random forest (RF) models. The best performing models were able to discover synthesis parameters for a target quinary alloy in 14 iterations. We also demonstrate the capability of these models to be used in transfer learning tasks. RF and GP models trained on lower dimensional systems (i.e., ternary, quarternary) show an immediate improvement in prediction accuracy compared to models trained only on quinary samples. Furthermore, samples that only share a few elements in common with the target composition can be used for model pre-training. We believe that such AL approaches can be widely adapted to significantly accelerate the exploration of compositionally complex materials.

Chemistry↗
NASA NTRS2026

NASA Talks: Space Shuttle Columbia - Lessons Learned: Columbia Launch and Recovery

On February 25, 2026, this NASA Talk was held regarding the Space Shuttle Columbia (Columbia Launch & Recovery). Crew & Thermal System Division (EC) partnered with Kennedy Space Center (KSC) and Engineering Directorate (EA) to bring this talk to Johnson Space Center (JSC) centering on what led up to and transpired after the Space Shuttle Columbia accident. Some recovered debris was on exhibit during the talk. Retired NASA Columbia Vehicle Manager Scott Thurston presented this talk. Mr. Thurston brings a wealth of knowledge from his mission experience. This talk was timely and a solemn reminder of the critical importance of diligence, safety, and excellence in our work. EA Director Julie Kramer White welcomed the 400+ center-wide in-person audience, and EC Division Chief Rubik Sheth introduced the speakers. This event was held in the JSC Teague Auditorium, recorded, and executed by the EC in-house STAR Productions team. This record includes an mp4 video presentation with a run time of 36 min. 20 sec.; in color; with sound.

NASA Talks↗
DOE OSTI2026

Lessons learned from the development and implementation of a workforce training curriculum for advanced controls for high performance HVAC systems

Over the past decade, academic research on advanced controls has slowly transitioned into new software platforms, giving rise to various companies developing and deploying these innovative products, including solutions for light commercial HVAC systems. However, the current workforce remains widely unprepared to install, maintain and operate these systems, particularly complex software-based control platforms, as most workforce training programs still focus on traditional building automation for large commercial buildings. This paper presents the development and piloting of curriculum for three key types of professionals: ● Technicians (trade-level): installing and maintaining modern high-performance HVAC systems and controls ● Programmers (undergrad-level): developing and implementing advanced controls ● Engineers and energy professionals (undergrad/grad-level): managing and evaluating system performance We share details of the material developed including training videos, open-source software, instruction manuals. We also present the results of a pilot implementation of the training materials with real students.

Casillas, Armando↗
DOE OSTI2025

Micrometer: Micromechanics transformer for predicting full field mechanical responses of heterogeneous materials

Predicting mechanical responses of heterogeneous materials across scales remains a significant challenge. Traditional computational methods often struggle with complex and multiscale nature of these materials, limiting their effectiveness in real-world applications. Here, in this paper, we introduce Micrometer, a vision transformer based deep learning model designed to predict full field mechanical responses of heterogeneous materials, bridging the gap between computer vision and solid mechanics problems. We show that Micrometer, trained on a large-scale high-resolution dataset of 2D fiber-reinforced composites, can achieve state-of-the-art performance in predicting microscale strain fields across a wide range of material properties and loading conditions. Our model demonstrates accuracy and computational efficiency in applications such as computational homogenization and multiscale modeling, reducing computational time by up to two orders of magnitude compared to conventional numerical solvers while maintaining less than 1 % errors in predicting macroscale stress fields. Furthermore, we showcase Micrometer’s adaptability through transfer learning experiments on new materials with limited data, highlighting its potential to tackle diverse scenarios in computational solid mechanics. These results represent a significant step towards AI-driven innovation in materials science, addressing the limitations of traditional numerical methods and paving the way for more efficient simulations of heterogeneous materials across various industrial applications.

Composite materials↗
DOE OSTI2026

Polarized target nuclear magnetic resonance measurements with deep neural networks

Continuous-wave Nuclear Magnetic Resonance (CW-NMR) operated in constant-current mode has served as a foundational technique for polarization measurement in solid-state dynamically polarized targets within nuclear and high-energy physics experiments for several decades, and it remains an essential tool. Conventional Q-meter-based phase-sensitive detection is critical for precise real-time determination of target polarization during scattering runs. However, the accuracy and reliability of these measurements are frequently compromised by elevated noise levels, baseline drift, and systematic uncertainties arising from signal isolation and fitting, ultimately degrading the overall experimental figure of merit. In this work, we report the first successful application of neural network architectures to continuous-wave NMR polarization metrology. By leveraging advanced machine learning techniques for signal extraction and denoising, we achieve a substantial reduction of fitting uncertainties under a variety of realistic simulated and experimental conditions. These improvements translate directly into more robust real-time (online) polarization monitoring and higher precision in subsequent offline analysis. By reducing analysis-induced uncertainty, the resulting methodology can improve the effective figure of merit for scattering experiments employing dynamically polarized targets and provides a new toolset for NMR-based polarimetry in high-energy and nuclear physics.

Metrology↗
NASA NTRS2026

Deep RL for Fast Long-Horizon Operations Scheduling on NASA's Carruthers Geocorona Observatory Mission

Spacecraft operations scheduling is a highly constrained, long-horizon combinatorial optimization problem that traditionally relies on heuristics, constraint programming, or manual planning. We present a scalable deep reinforcement learning framework developed and deployed for NASA’s Carruthers Geocorona Observatory mission. Our framework introduces a macro-action abstraction known as activity blocks coupled with dynamic action-masking to navigate the intractably large search space and strictly enforce complex power, thermal, and instrument constraints. The resulting architecture generates globally feasible schedules with overwhelming probability, establishes operational trust, and executes a full training cycle in under six hours, circumventing the need for policy robustness by enabling rapid, on-demand retraining. Further, resulting schedules outperform baseline heuristics in scheduled science quality. The deep reinforcement learning framework was deployed as the default operational scheduler for the Carruthers Geocorona Observatory mission from the outset of the mission, demonstrating that deep reinforcement learning can be trusted for real spacecraft operations under complex, evolving constraints.

Geocorona↗