Results for “Neural operator” — Page 24

DOE OSTI2025

Advantages of imperfect dice rolls over coin flips for random number generation

With an eye toward neural-inspired probabilistic computation, recent work has examined the development of true random number generators via stochastic devices. Typically, these devices are operated in a two-state regime to produce a sequence of binary outcomes (i.e., coin flips). However, there is no guarantee that stochastic devices will infallibly produce fair outputs and small deviations from a uniform distribution may have unwanted complications in applications. Using mathematical analysis, we contend that opting instead for a multi-state device (i.e., a dice roll) has benefits in these unfair paradigms. To demonstrate these benefits, we apply this framework to the analysis of a tunnel diode operated in a stochastic regime. In particular, interpreting the binary stochastic output of the tunnel diode as a multi-state die roll output also sees advantages in remaining closer to uniform. Overall, our approach provides a compelling argument for mathematical driven co-design and development of novel probabilistic computing devices and hardware.

applied mathematics↗

DOE OSTI2026

nnopf

SAND2026-19433O The nnopf tool addresses the optimal power flow (OPF) problem by optimizing electricity delivery from generating plants to consumers. At the same time, it minimizes costs and adheres to power grid constraints. While traditional methods for solving OPF can be computationally intensive, the tool mitigates this challenge by training neural networks on power grids to predict optimal solutions for the OPF problem. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DE-NA0003525.

Hart, William [Sandia National Lab. (SNL-CA), Live↗

NASA NTRSDate not supplied

Statistical learning framework for safety and failure analysis of a DNN-based autonomous aircraft system

Deep Neural Networks (DNNs) and Machine Learning technology is increasingly used for safety-critical applications in the Aerospace domain. To ensure safe operations, the DNN and the system must undergo rigorous verification and validation, including advanced statistical analyses. Performance and safety of the DNN and system behavior must not only be analyzed for the nominal case, but under numerous off-nominal and failure cases. In this paper we will describe how our statistical learning framework SYSAI can efficiently perform such analyses using the tool’s unique combination of advanced learning modeling and statistical analysis techniques. SYSAI can effectively explore the high-dimensional state and failure space of the system under test; geometrical shape detection of safety regions and boundaries support explainability of the results to the designer. In this paper, we report experiments and results obtained with a vision-based DNN control system (ACT) that is capable of autonomously steering an aircraft down a runway.

Yuning He↗

NASA NTRSDate not supplied

BRAINSTACK – A Platform for Artificial Intelligence & Machine Learning Collaborative Experiments on a Nano-Satellite

As space missions continue to become more ambitious, complex, and distant to Earth, the need for advanced on-board intelligent decision making to guide everything from mission operations to fault detection and recovery has become a major front of space research. While the prevalence of research on such Artificial Intelligence / Machine Learning (AI/ML) modules has exploded, the capacity to experimentally validate such modules in space in a rapid and inexpensive format has not. To this end, the Nano Orbital Workshop (NOW) group at NASA Ames Research Center has been at the forefront of performing initial flight evaluation tests of ‘commercially’ available AI/ML computational platforms via the TechEdSat (TES-n) flight series as part of what is programmatically referred to as the BRAINSTACK. BRAINSTACK will provide an orbital AI/ML evaluation laboratory where computational experiments are pre-loaded into memory prior to launch, and then executed as desired during the mission, with results reported back and program tweaks or new data sets uploaded as needed. Processors selected as part of the BRAINSTACK are of ideal size, packaging, and power consumption for easy integration into a cube satellite structure. These experiments have included the evaluation of small, high-performance GPUs and more recently, neuromorphic processors in LEO operations. Neuromorphic processors are of particular interest due to their superior computational power efficiency over GPUs. The first TES-n flight test of an Intel first-generation Loihi neuromorphic processor launched on January 13, 2022 and continues to operate in orbit despite almost no space environment modifications. The Intel Loihi Gen-1 is characterized by a 14nm 128-core Spiking Neural Network (SNN) able to support on-chip training. This experiment utilized a Loihi packaged in the ‘Kapoho Bay’ USB module, providing a relatively straight-forward interface to the bus avionics system. The Kapoho Bay was in turn managed by a host Intel Pentium single-board computer to handle scheduling of the AI/ML application payloads, and communications with the satellite vehicle manager. The recently released Intel Loihi Gen-2, able to support integer-valued spike payloads and produced using 7nm process, will form part of the basis of the evolving BRAINSTACK in the upcoming three TES-n/NOW flights. Additionally, it is planned to measure the radiation environment these processors experience to understand any degradation or computational artifacts caused by long term space radiation exposure on these novel architectures. This evolving flexible and collaborative environment involving various research teams across NASA and other organizations is intended to be a convenient orbital test platform from which many anticipated future space AI/ML applications may be initially tested.

Artificial Intelligence↗

NASA NTRSDate not supplied

BRAINSTACK – A Platform for Artificial Intelligence & Machine Learning Collaborative Experiments on a Nano-Satellite

As space missions continue to become more ambitious, complex, and distant to Earth, the need for advanced on-board intelligent decision making to guide everything from mission operations to fault detection and recovery has become a major front of space research. While the prevalence of research on such Artificial Intelligence / Machine Learning (AI/ML) modules has exploded, the capacity to experimentally validate such modules in space in a rapid and inexpensive format has not. To this end, the Nano Orbital Workshop (NOW) group at NASA Ames Research Center has been at the forefront of performing initial flight evaluation tests of ‘commercially’ available AI/ML computational platforms via the TechEdSat (TES-n) flight series as part of what is programmatically referred to as the BRAINSTACK. BRAINSTACK will provide an orbital AI/ML evaluation laboratory where computational experiments are pre-loaded into memory prior to launch, and then executed as desired during the mission, with results reported back and program tweaks or new data sets uploaded as needed. Processors selected as part of the BRAINSTACK are of ideal size, packaging, and power consumption for easy integration into a cube satellite structure. These experiments have included the evaluation of small, high-performance GPUs and more recently, neuromorphic processors in LEO operations. Neuromorphic processors are of particular interest due to their superior computational power efficiency over GPUs. The first TES-n flight test of an Intel first-generation Loihi neuromorphic processor launched on January 13, 2022 and continues to operate in orbit despite almost no space environment modifications. The Intel Loihi Gen-1 is characterized by a 14nm 128-core Spiking Neural Network (SNN) able to support on-chip training. This experiment utilized a Loihi packaged in the ‘Kapoho Bay’ USB module, providing a relatively straight-forward interface to the bus avionics system. The Kapoho Bay was in turn managed by a host Intel Pentium single-board computer to handle scheduling of the AI/ML application payloads, and communications with the satellite vehicle manager. The recently released Intel Loihi Gen-2, able to support integer-valued spike payloads and produced using 7nm process, will form part of the basis of the evolving BRAINSTACK in the upcoming three TES-n/NOW flights. Additionally, it is planned to measure the radiation environment these processors experience to understand any degradation or computational artifacts caused by long term space radiation exposure on these novel architectures. This evolving flexible and collaborative environment involving various research teams across NASA and other organizations is intended to be a convenient orbital test platform from which many anticipated future space AI/ML applications may be initially tested.

Artificial Intelligence↗

NASA NTRS1991

A neural network architecture for implementation of expert systems for real time monitoring

Since neural networks have the advantages of massive parallelism and simple architecture, they are good tools for implementing real time expert systems. In a rule based expert system, the antecedents of rules are in the conjunctive or disjunctive form. We constructed a multilayer feedforward type network in which neurons represent AND or OR operations of rules. Further, we developed a translator which can automatically map a given rule base into the network. Also, we proposed a new and powerful yet flexible architecture that combines the advantages of both fuzzy expert systems and neural networks. This architecture uses the fuzzy logic concepts to separate input data domains into several smaller and overlapped regions. Rule-based expert systems for time critical applications using neural networks, the automated implementation of rule-based expert systems with neural nets, and fuzzy expert systems vs. neural nets are covered.

Ramamoorthy, P. A.↗

DOE OSTI2024

Model-free stabilization via Extremum Seeking using a cost neural estimator

In this paper, a fully model-free architecture for vertical stabilization of thermonuclear plasmas in tokamak experimental reactors is presented. For the first time, an Extremum Seeking control algorithm is combined with neural networks to estimate the Lyapunov function to be minimized, resulting in a fully data-driven control architecture. The performance of different neural networks are compared. Specifically, Multilayer Perceptrons and Extreme Learning Machines are considered. The proposed architecture is tested in simulation to show that it can counteract relevant plasma disturbances, resulting in a significant improvement in terms of the achievable operative space compared to the Extremum Seeking algorithm, which still relies on model-based cost estimator.

42 ENGINEERING↗

DOE OSTI2025

Identifying environmentally induced calibration changes in cryogenic RF axion detector systems using deep neural networks

The axion is a compelling hypothetical particle that could account for the dark matter in our universe while simultaneously solving the strong CP problem in quantum chromodynamics. The most sensitive axion detection technique demonstrated so far makes use of a high Q cavity immersed in a strong magnetic field, where axions are converted to microwave photons. This is called an axion haloscope and has primarily targeted the 1–10 GHz range. As searches scan up in axion mass, toward the parameter space favored by theoretical predictions, individual cavity sizes decrease in order to achieve higher frequencies. This shrinking cavity volume translates directly to a loss in signal-to-noise, motivating the plan to replace individual cavity detectors with arrays of cavities. When the transition from one to (N) multiple cavities occurs, haloscope searches are anticipated to become much more complicated to operate, requiring N times as many measurements but also the new requirement that N detectors operate in unison, which can be achieved by locking them to a common frequency. To offset this anticipated increase in detector complexity, we aim to develop new tools for diagnosing experiments using neural networks. Current experiments monitor scattering parameters of their receiver for periodically measuring cavity quality factor and coupling. However, off-resonant data remain relatively useless. In this paper, we ask if it is possible that off-resonant information contained in vector network analyzer scans could be used to diagnose equipment failures/anomalies and measure physical conditions (e.g., temperatures and ambient magnetic field). We demonstrate a proof-of-concept that AI techniques can help manage the complexity of an axion haloscope search for operators.

Engel, Andrew W. [Pacific Northwest National Labor↗

DOE OSTI2025

NNFDivergence

The code implements f divergence regularization for neural networks in the Python-based Pytorch framework. The methods are the main focus but the repository will also contain examples that operate on purely synthetic "toy" data or on openly available, public data from NASA.

Klein, Natalie [@lanl]↗

NASA NTRS1995

Human Interfaces In Teleoperations And Virtual Environments

Conference report contains compilation of papers relating to interactions between humans and machines from perspectives of telepresence and sensorimotor adaptation, measurement and evaluation of performance, and design principles and predictive models. Topics discussed include neural networks, sensory technology, display, and feedback controls. Covers state of art of remote sensing and control by humans for space or other operations.

Durlach, Nathaniel I.↗

NASA NTRS2003

Estimating Blade Section Airloads from Blade Leading-Edge Pressure Measurements

The Tilt-Rotor Aeroacoustic Model (TRAM) test in the Duitse-Nederlandse Wind (DNW) Tunnel acquired blade pressure data for forward flight test conditions of a tiltrotor in helicopter mode. Chordwise pressure data at seven radial locations were integrated to obtain the blade section normal force. The present investigation evaluates the use of linear regression analysis and of neural networks in estimating the blade section normal force coefficient from a limited number of blade leading-edge pressure measurements and representative operating conditions. These network models are subsequently used to estimate the airloads at intermediate radial locations where only blade pressure measurements at the 3.5% chordwise stations are available.

vanAken, Johannes M.↗

DOE OSTI2025

Data-Driven State of Health Estimation for Second-Life Batteries Using Interpolated Synthetic Data and Feature Selection

Accurate estimation of the State of Health (SOH) for second-life batteries (SLBs) is crucial given their increasing use in energy storage applications. Precise SOH prediction is essential for safe operation and robust battery management systems. A major challenge is the limited availability of datasets for building reliable degradation models. To address this, synthetic data generation through linear interpolation is performed to extend the available data, making it more representative of real-world battery operating conditions. By analyzing feature correlation with SOH, the most relevant features are selected for the model. The proposed approach employs a convolutional neural network (CNN) model trained on this interpolated, feature-selected dataset, using time series data of voltage, temperature, and current over a cycle. By focusing on highly correlated features, the model achieves over 95% accuracy, with mean absolute error and root mean squared error up to 2.27% and 2.64%, respectively, in SOH estimation for two battery datasets tested. These results highlight the potential of combining synthetic data generation and feature selection to enhance SOH predictions, showcasing the superior performance of the proposed CNN model for both new batteries and SLBs.

feature selection↗

NASA NTRSDate not supplied

Machine Learning Algorithms for Aerosol and Cloud Detection Using CATS on the ISS

Clouds and aerosols are one of the largest uncertainties in understanding and forecasting the Earth’s changing climate system. The type and height of aerosols are important factors in determining the top-of-atmosphere (TOA) radiation budget, either direct reflection of solar radiation back to space and/or absorption of solar radiation. In addition to their impact on the Earth’s climate system, aerosols near the surface from wildfires, man-made pollution events, and dust storms are hazardous to human health. The phase and height of clouds also play a critical role in determining the role of clouds in the Earth’s climate system. Cirrus clouds in the upper troposphere can induce a significant daytime TOA warming effect, while liquid water clouds near the surface cause a large corresponding cooling effect. Lidar measurements provide accurate vertically resolved information about clouds and aerosols, including complex multi-layer scenes where passive sensors are challenged and at night, when passive sensors are unable to measure cloud and aerosol properties. The Cloud-Aerosol Transport System (CATS) is a lidar instrument that operated for 33 months on the International Space Station (ISS) at the 1064 nm wavelength to measure attenuated total backscatter and depolarization ratio. These fundamental measurements are used to derive “vertical feature mask” cloud and aerosol products, including layer top/base heights, layer geometrical thickness, aerosol type, and cloud phase. While space-based lidar systems like CATS provide cloud and aerosol vertical distributions that improve our understanding of the climate system, averaging of the daytime data from these sensors is required, at the expense of spatial resolution, to improve the daytime signal-to noise (SNR) and thus atmospheric layer detection. This presentation shows results from machine learning (ML) techniques that, when applied to CATS data: 1. improve the 1064 nm SNR 2. enable detection of atmospheric features during daytime with a horizontal resolution of 350 m or 5 km (compared to the 60 km required for standard CATS data products) 3. increase the number of atmospheric layers detected in the CATS data. A Convolutional Neural Network (CNN) trained using CATS standard data products also demonstrated the potential for improved cloud-aerosol discrimination, cloud phase, and aerosol typing compared to the operational CATS algorithms for cloud edges and complex near-surface scenes during daytime. The ML tools described in this paper can facilitate the development of smaller, low-cost lidar systems in the future and enable real-time accessibility of lidar data products from future lidar systems for monitoring and forecasting of hazardous events.

John Yorks↗

NASA NTRSDate not supplied

Inverse Text Normalization of Air Traffic Control System Command Center Planning Telecon Transcriptions

We present a hybrid neural network and rule-based Inverse Text Normalization (ITN) method for domains containing unique technical phraseology, specifically ATCSCC planning telecon audio transcriptions. The Air Traffic Control System Command Center (ATCSCC) hosts bihourly planning telephone conferences (or planning telecons) to ensure smooth operations within the National Airspace (NAS). Access to both live and post meeting transcripts of this speech audio would enable quick review of meetings. ITN is the process of converting un-formatted "raw'' speech-to-text transcripts into a human (expert) readable written form. Our hybrid ITN framework utilizes a neural network to format conversational English, and rule-based methods to format domain-specific aviation text. With a preliminary overall Word Error Rate with Punctuation and Capitalization (WER PC) of 8.26, we show that this method has vast potential in being applied to ATCSCC planning telecon audio and other audio/text based data available in ATM.

Air Traffic Management↗

NASA NTRSDate not supplied

Usage-based Lifing of Lithium-Ion Battery with HybridPhysics-Informed Neural Networks

Lithium-ion batteries are commonly used to power unmanned aircraft vehicles (UAVs).The ability to model and forecast the remaining useful life of these batteries enables UAV reliability assurance. Building accurate models for battery state of charge and state of health based on first principles is challenging due to the complex electrochemistry that governs battery operations and computational complexity required to solve them. Therefore, reduced order models are often used due to their ability to capture the overall battery discharge. Un-fortunately, these simplifications lead to residual discrepancy between model predictions and observed data. In this paper, we present a hybrid modeling approach merging reduced-order models and neural networks. In this approach, while most of the input-output relationship is captured by Nernst and Butler-Volmer equations, data-driven kernels reduce the gap between predictions and observations. We validate our approach using data publicly available through the NASA Prognostics Center of Excellence repository. Results showed that our hybrid battery prognosis model can be successfully calibrated, even with a limited number of observations.

Lithium-ion Battery↗

DOE OSTI2025

A Data-Driven Framework for Predicting the Sorting and Screening Performance of an Integrated Biomass Feedstock Preprocessing System

The characteristics of mechanically sorted and screened lignocellulosic biomass, such as the mass contents of corn stover anatomical fractions (leaves, husks, stalks, cobs, etc.), can be used to calculate the intermediate feedstock quality attributes “yield” and “purity” that indicate the conversion efficiency of biocrude. No prior study has investigated the correlations from the characteristics of raw biomass and preprocessing unit operation parameters to those intermediate feedstock quality attributes. This work presents a data-driven framework for assessing and predicting the intermediate feedstock quality attributes in an integrated biomass feedstock preprocessing system. Our study used corn stover as a typical type of herbaceous biomass because of its abundance in the U.S. It began with data acquisition of moisture content, particle size distribution, and anatomical fractions of the materials after each unit operation in the system. The objective of this preprocessing system is to minimize husks and leaves and maximizing cobs and stalks by mechanically separating the materials into three streams via disc screen and air separator. Prototype neural network models were then developed to evaluate the feasibility of predicting process outcomes based on measurable parameters. It is found that incorporating physical constraints into these prediction models significantly enhances the accuracy of the predicted yield and purity against the ground truth data. The experimental data and model predictions indicate that decreasing throughput increases purity, while higher throughput results in lower purity. Finally, an optimization problem was introduced to search optimal combinations of feed material properties and preprocessing unit operation parameters, as the intermediate feedstock quality attributes – yield and purity, appeared to be competing factors. The study also suggests the continual need to improve the data-driven framework’s predictability by incorporating more accurate physical models to describe the dynamics in the preprocessing units such as the air separator.

09 - BIOMASS FUELS↗

DOE OSTI2026

The Use of Machine Learning Models for Predicting the Dielectric Strength of Gases

Technological advancements in high voltage systems have pushed sulfur hexafluoride (SF6) to its operational limits. Furthermore, this gas has other drawbacks including a high liquefaction temperature and a high global warming potential. Therefore, there has been an urgent need to find alternative gases with high dielectric strength (DS). In this work, density functional theory (DFT) is used to calculate molecular descriptors that are fed into an artificial neural network (ANN) and a random forest (RF). These machine learning (ML) models are then used to predict the DS for hundreds of molecules. A finite element model (FEM) is also used to calculate the electric field profile of multiple simple electrode geometries as the applied voltage to the system is increased. Results indicate that the random forest model has better generalization to unseen data than the neural network. The highest DS value predicted by the RF was 2.16 relative to the experimental DS of SF6. The results also demonstrate how choosing a gas with a higher DS and a geometry with minimal edges and corners can significantly increase the operating voltage of an electrical system. Due to its superior generalization, the RF represents the most promising path toward an accurate DS predictor once sufficient experimental data are available.

Mileski, Matthew [AFIT]↗

DOE OSTI2024

Equivariant graph convolutional neural networks for the representation of homogenized anisotropic microstructural mechanical response

Composite materials with different microstructural material symmetries are common in engineering applications where grain structure, alloying and particle/fiber packing are optimized via controlled manufacturing. In fact these microstructural tunings can be done throughout a part to achieve functional gradation and optimization at a structural level. To predict the performance of particular microstructural configuration and thereby overall performance, constitutive models of materials with microstructure are needed. In this work we provide neural network architectures that provide effective homogenization models of materials with anisotropic components. These models satisfy equivariance and material symmetry principles inherently through a combination of equivariant and tensor basis operations. We demonstrate them on datasets of stochastic volume elements with different textures and phases where the material undergoes elastic and plastic deformation, and show that the these network architectures provide significant performance improvements.

anisotropy↗