Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learned priors”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

SQMS Quantum R&D in Machine Learning, Optimization and Sensing beyond Fundamental Physics Applications

This newly formed team at SQMS under the Ecosystem Thrust is looking to develop capabilities impacting societal advances outside the core domain of HEP and condensed matter physics. We explicitly leverage the experimental and algorithmic innovations developed across all groups as well as connect to broad-scope external projects of the diverse team of PIs. As the inaugural set of projects, we are studying numerically quantum machine learning models inspired by efficiently trainable echo-state and orthogonal neural networks and developing designs for related experiments to be performed on quantum processors based on SQMS SRF cQED technology and Rigetti s transmon arrays. Investigated models exploit ideas and lessons learned from multiple prior work by SQMS team members in a variety of internal and external activities [R1]. Target initial applications include noisy signal processing, potentially captured by quantum sensors or noisy QPUs, as well as simulation and classification of healthcare data. For instance, image reconstruction of the brain s electrical properties by solving the inverse Maxwell equation problem with uncertainty [R2] through a hybrid quantum-classical physics-informed architecture for time-dependent processes [R3]. The group is also investigating the application and development of novel quantum sensors based on magnetic levitation of a superconducting sphere coupled to a superconducting qubit. This coupling enables high-precision measurements of the position of the sphere, which can be used for sensitive detection of forces, enabling practical applications such as gravimetry for geophysics analysis, or accelerometry for GPS-denied navigation [R4] [R1] Rieffel, Eleanor G., Ata Akbari Asanjan, M. Sohaib Alam, Namit Anand, David E. Bernal Neira, Sophie Block, Lucas T. Brady et al. "Assessing and advancing the potential of quantum computing: A NASA case study." Future Generation Computer Systems (2024). [R2] Yu, X., Serrall s, J.E., Giannakopoulos, I.I., Liu, Z., Daniel, L., Lattanzi, R. and Zhang, Z., 2023. Pifon-ept: Mr-based electrical property tomography using physics-informed fourier networks. IEEE Journal on Multiscale and Multiphysics Computational Techniques. [R3] Wudarski, Filip, Daniel OConnor, Shaun Geaney, Ata Akbari Asanjan, Max Wilson, Elena Strbac, P. Aaron Lott, and Davide Venturelli. "Hybrid quantum-classical reservoir computing for simulating chaotic systems." arXiv preprint arXiv:2311.14105 (2023). [R4] Higgins, Gerard, Saarik Kalia, and Zhen Liu. "Maglev for dark matter: Dark-photon and axion dark matter sensing with levitated superconductors." Physical Review D 109.5 (2024): 055024.

Venturelli, Davide↗
NASA NTRS1992

Queries for Bias Testing

Selecting a good bias prior to concept learning can be difficult. Therefore, dynamic bias adjustment is becoming increasingly popular. Current dynamic bias adjustment systems, however, are limited in their ability to identify erroneous assumptions about the relationship between the bias and the target concept. Without proper diagnosis, it is difficult to identify and then remedy faulty assumptions. We have developed an approach that makes these assumptions explicit, actively tests them with queries to an oracle, and adjusts the bias based on the test results.

Gordon, Diana F.↗
NASA NTRS2008

Using the Space Glove to Teach Spatial Thinking

The challenge of extending students' skills in spatial thinking to astronomical scales was the central focus of our K-8 curriculum development. When the project's lead teacher requested a curriculum that cumulatively built on each prior year's learning in a spiral fashion, I knew exactly what the school was asking for. Second and third graders began by noticing the cyclical patters that the sun, moon, and stars make in the sky. Fourth graders explored the phases of the moon by taking turns modeling and sketching them in their classroom and then comparing them to the real sky. Sixth !graders used real telescopes to observe a moving model of our solar system and walked a scale model of the planets' orbits. The curriculum is designed to expand students' capacity to visualize space in a hierarchical fashion that asks them to imagine themselves from a broader number of spatial perspectives through hands-on activities. The "situational awareness" Peter's story describes is a hallmark of high-performance engineering and innovation. Keeping in mind the potential outcomes of multiple paths of pursuit from multiple perspectives while keeping track of their relative merits and performance requirements is a demanding spatial task. What made it possible for Peter to transform the failure of his first glove into triumph was the mental space in which that failure provided exactly the information needed for a new breakthrough. In at least two cases, Peter could immediately "see" the full implications of what his hands were telling him. He tells the story of how putting his hands in a Phase VI astronaut glove instantly transformed his understanding of the glove challenge. Six months into his development, the failure of circumferentially wrapped cords to produce a sufficiently flexible glove again forced him to abandon his assumptions. His situational awareness was so clear and compelling it became a gut-level response. Peter's finely developed spatial skills enabled him to almost instinctively focus his full energy on a carefully constructed set of experiments. The finger's ability to sense pressure, force, and work gave him the immediate feedback required to solve this one central problem. Once properly understood, his failure quickly led to the magical "Aha!" moment of discovery; the rest is history. Just as children need opportunities to develop hands-on understanding, engineers need to explore new possibilities through incremental hands-on failure. High-performance innovation is all about learning to make maximum use of thinking spatially to direct this process. Peter Homer's glove also reminds us that efficient engineering decisions need to be made as close to the hardware as possible. Whether we're doing hands-on education or hands-on engineering, it is when we trust in our ability to "feel our way" through failure that we reach our highest potential.

Lord, Peter↗
NASA NTRS2018

Gradient Field Imploding Liner Fusion Propulsion System: NASA Innovative Advanced Concepts Phase I Final Report

The advancement of human deep space exploration requires the continued development of energetic in-space propulsion systems, from current chemical engines to nuclear thermal rockets to future high energy concepts such as nuclear fusion. As NASA embarks on a program to develop near-term nuclear thermal propulsion, this NASA Innovative Advanced Concepts (NIAC) Phase I activity was funded to investigate the feasibility of an innovative approach toward highly energetic pulsed fusion propulsion. Previous concept studies have proposed the conversion of fusion energy for in-space propulsion, ranging from laser-ignited fusion systems such as Gevaltig and VISTA, to the British Interplanetary Society's Daedalus concept and its more recent incarnation under Project Icarus, to steady-state spherical torus fusion systems. Recent NIAC studies have also evaluated several innovative fusion concepts, including the acceleration and compression of field reversed configuration plasmas in time-changing magnetic fields, magnetically driven liners imploding onto plasma targets, and high current z-pinch compression of material liners onto fission-fusion fuel targets. While each of these studies firmly established the potential benefits of fusion systems for interplanetary travel, they also identified significant challenges in successfully engineering such systems for spacecraft propulsion. The concept outlined in this Technical Publication (TP) builds on the lessons learned from these prior activities, approaching the quest for fusion-powered propulsion through an innovative variation of magneto-inertial fusion concepts developed for terrestrial power applications.

Lapointe, M. R.↗
DOE OSTI2025

Ansatz-Free Hamiltonian Learning with Heisenberg-Limited Scaling

Learning the unknown interactions that govern a quantum system is crucial for quantum information processing, device benchmarking, and quantum sensing. The problem, known as Hamiltonian learning, is well understood under the assumption that interactions are local, but this assumption may not hold for arbitrary Hamiltonians. Previous methods all require high-order inverse polynomial dependency with precision, unable to surpass the standard quantum limit and reach the gold-standard Heisenberg-limited scaling. Whether Heisenberg-limited Hamiltonian learning is possible without prior assumptions about the interaction structures, a challenge we term ansatz-free Hamiltonian learning , remains an open question. In this work, we present a quantum algorithm to learn arbitrary sparse Hamiltonians without any structure constraints using only black-box queries of the system’s real-time evolution and minimal digital controls to attain Heisenberg-limited scaling in estimation error. Our method is also resilient to state-preparation-and-measurement errors, enhancing its practical feasibility. We numerically demonstrate our ansatz-free protocol for learning physical Hamiltonians and validating analog quantum simulations, benchmarking our performance against the state-of-the-art Heisenberg-limited learning approach. Moreover, we establish a fundamental trade-off between total evolution time and quantum control on learning arbitrary interactions, revealing the intrinsic interplay between controllability and total evolution-time complexity for any learning algorithm. These results pave the way for further exploration into Heisenberg-limited Hamiltonian learning in complex quantum systems under minimal assumptions, potentially enabling new benchmarking and verification protocols.

machine learning↗
DOE OSTI2025

Machine learning-enabled discovery of ionic liquid–solvent electrolytes exhibiting high ionic conductivity

Ionic liquids (ILs), which are a class of materials with versatile nature and growing popularity, are facing impediments toward widespread usage as electrolytes due to various factors such as low ionic conductivity, high viscosity, high market price etc. One of the ways these limitations can be addressed is by mixing ILs with a molecular solvent. In a combinatorial sense, there exists an immense number of specific IL–solvent combinations. An exhaustive experimental or even simulation-based investigation of the chemical space spanned by such combinations can be extremely time-consuming, expensive, and nearly impossible. An alternative approach is to employ machine learning-based models developed from available databases. Although there exists prior literature that integrates machine learning to investigate mixtures of specific solvents with ILs, these models lack generalization necessitating development of a large number of ML models to handle various solvents. To remedy this shortcoming, as a part of designing green electrolytes with high ionic conductivity that can have potential applications in next-generation batteries and solar cells, this work aims to develop a unified machine learning model to predict ionic conductivity of any IL–solvent mixture system. In this regard, three models, namely, Random Forest, extreme gradient boosting (XGBoost), and artificial neural network (ANN) were formulated using the NIST ILThermo database. The dataset contained 549 unique ionic liquids from 16 cation families and 81 unique solvents, representing a total of 23 712 datapoints. SHAPLEY additive explanation (SHAP) method was used to assess the impact of various features on model prediction and their significance was compared with literature to gain physical insight about the model behavior. Finally, using the developed models, approximately 2.5 million IL–solvent mixtures at five different compositions were screened at room temperature. The high-throughput screening yielded nearly 19 000 IL–solvent mixtures for which ionic conductivity was found to exceed the ionic conductivity of conventional Li-ion battery electrolyte.

25 ENERGY STORAGE↗
DOE OSTI2022

Monitoring of Temperature Measurements for Different Flow Regimes in Water and Galinstan with Long Short-Term Memory Networks and Transfer Learning of Sensors

Temperature sensing is one of the most common measurements of a nuclear reactor monitoring system. The coolant fluid flow in a reactor core depends on the reactor power state. We investigated the monitoring and estimation of the thermocouple time series using machine learning for a range of flow regimes. Measurement data were obtained, in two separate experiments, in a flow loop filled with water and with liquid metal Galinstan. We developed long short-term memory (LSTM) recurrent neural networks (RNNs) for sensor predictions by training on the sensor’s own prior history, and transfer learning LSTM (TL-LSTM) by training on a correlated sensor’s prior history. Sensor cross-correlations were identified by calculating the Pearson correlation coefficient of the time series. The accuracy of LSTM and TL-LSTM predictions of temperature was studied as a function of Reynolds number (Re). The root-mean-square error (RMSE) for the test segment of time series of each sensor was shown to linearly increase with Re for both water and Galinstan fluids. Using linear correlations, we estimated the range of values of Re for which RMSE is smaller than the thermocouple measurement uncertainty. For both water and Galinstan fluids, we showed that both LSTM and TL-LSTM provide reliable estimations of temperature for typical flow regimes in a nuclear reactor. The LSTM runtime was shown to be substantially smaller than the data acquisition rate, which allows for performing estimation and validation of sensor measurements in real time.

Pantopoulou, Stella↗
DOE OSTI2020

Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide

We propose an active learning scheme for automatically sampling a minimum number of uncorrelated configurations for fitting the Gaussian Approximation Potential (GAP). Our active learning scheme consists of an unsupervised machine learning (ML) scheme coupled with a Bayesian optimization technique that evaluates the GAP model. We apply this scheme to a Hafnium dioxide (HfO 2 ) dataset generated from a "melt-quench" ab initio molecular dynamics (AIMD) protocol. Our results show that the active learning scheme, with no prior knowledge of the dataset, is able to extract a configuration that reaches the required energy fit tolerance. Further, molecular dynamics (MD) simulations performed using this active learned GAP model on 6144 atom systems of amorphous and liquid state elucidate the structural properties of HfO 2 with near ab initio precision and quench rates (i.e., 1.0 K/ps) not accessible via AIMD. The melt and amorphous X-ray structural factors generated from our simulation are in good agreement with experiment. In addition, the calculated diffusion constants are in good agreement with previous ab initio studies.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Combining data and theory for derivable scientific discovery with AI-Descartes

Abstract Scientists aim to discover meaningful formulae that accurately describe experimental data. Mathematical models of natural phenomena can be manually created from domain knowledge and fitted to data, or, in contrast, created automatically from large datasets with machine-learning algorithms. The problem of incorporating prior knowledge expressed as constraints on the functional form of a learned model has been studied before, while finding models that are consistent with prior knowledge expressed via general logical axioms is an open problem. We develop a method to enable principled derivations of models of natural phenomena from axiomatic knowledge and experimental data by combining logical reasoning with symbolic regression. We demonstrate these concepts for Kepler’s third law of planetary motion, Einstein’s relativistic time-dilation law, and Langmuir’s theory of adsorption. We show we can discover governing laws from few data points when logical reasoning is used to distinguish between candidate formulae having similar error on the data.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Fine-tuning TrailMap: The utility of transfer learning to improve the performance of deep learning in axon segmentation of light-sheet microscopy images

Light-sheet microscopy has made possible the 3D imaging of both fixed and live biological tissue, with samples as large as the entire mouse brain. However, segmentation and quantification of that data remains a time-consuming manual undertaking. Machine learning methods promise the possibility of automating this process. This study seeks to advance the performance of prior models through optimizing transfer learning. We fine-tuned the existing TrailMap model using expert-labeled data from noradrenergic axonal structures in the mouse brain. By changing the cross-entropy weights and using augmentation, we demonstrate a generally improved adjusted F1-score over using the originally trained TrailMap model within our test datasets.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

A machine learning approach for particle accelerator errant beam prediction using spatial phase deviation

Particle accelerators are extremely complex systems that are expected to operate on high availability. Predicting impending failures only by utilizing data collected from diagnostic equipment already on board can help operators to avoid installing expensive sensors, unscheduled downtime and associated costs. For this purpose we explore the predictive power of Machine Learning algorithms to detect faulty beams prior to the failure. In this study, we propose a Machine Learning approach to model mapping from a pair of sensors located across the accelerator. While the model is trained to represent normal operation, we evaluate the predictive performance on known faulty beam pulses. We also investigate the model performance on unseen data through k-fold cross-validation. Then we recap the analysis with a neural architecture search and hyperparameter optimization study to fine tune our initial model. In conclusion, this paper will also introduce a sustainable framework that can standardize Machine Learning workflow applied to particle accelerators.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Practical galaxy morphology tools from deep supervised representation learning

Astronomers have typically set out to solve supervised machine learning problems by creating their own representations from scratch. We show that deep learning models trained to answer every Galaxy Zoo DECaLS question learn meaningful semantic representations of galaxies that are useful for new tasks on which the models were never trained. We exploit these representations to outperform several recent approaches at practical tasks crucial for investigating large galaxy samples. The first task is identifying galaxies of similar morphology to a query galaxy. Given a single galaxy assigned a free text tag by humans (e.g. ‘#diffuse’), we can find galaxies matching that tag for most tags. The second task is identifying the most interesting anomalies to a particular researcher. Our approach is 100 per cent accurate at identifying the most interesting 100 anomalies (as judged by Galaxy Zoo 2 volunteers). The third task is adapting a model to solve a new task using only a small number of newly labelled galaxies. Models fine-tuned from our representation are better able to identify ring galaxies than models fine-tuned from terrestrial images (ImageNet) or trained from scratch. We solve each task with very few new labels; either one (for the similarity search) or several hundred (for anomaly detection or fine-tuning). This challenges the longstanding view that deep supervised methods require new large labelled data sets for practical use in astronomy. To help the community benefit from our pretrained models, we release our fine-tuning code zoobot. Zoobot is accessible to researchers with no prior experience in deep learning.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2010

A Modular Instrumentation System for NASA's Habitat Demonstration Unit

NASA's human spaceflight program is focused on developing technologies to expand the reaches of human exploration and science activities beyond low earth orbit. A critical aspect of living in space or on planetary surfaces is habitation, which provides a safe and comfortable space in which humans can live and work. NASA is seeking out the best option for habitation by exploring several different concepts through the Habitat Demonstration Unit (HDU) project. The purpose of this HDU is to develop a fully autonomous habitation system that enables human exploration of space. One critical feature of the HDU project that helps to accomplish its mission of autonomy is the instrumentation system that monitors key subsystems operating within a Habitat configuration. The following paper will discuss previous instrumentation systems used in analog habitat concepts and how the current instrumentation system being implemented on the HDU1-PEM, or pressurized excursion module, is building upon the lessons learned of those previous systems. Additionally, this paper will discuss the benefits and the limitations of implementing a wireless sensor network (WSN) as the basis for data transport in the instrumentation system. Finally, this paper will address the experiences and lessons learned with integration, testing prior to deployment, and field testing at the JSC rock yard. NASA is developing the HDU1-PEM as a step towards a fully autonomous habitation system that enables human exploration of space. To accomplish this purpose, the HDU project is focusing on development, integration, testing, and evaluation of habitation systems. The HDU will be used as a technology pull, testbed, and integration environment in which to advance NASA's understanding of alternative mission architectures, requirements, and operations concepts definition and validation. This project is a multi-year effort. In 2010, the HDU1-PEM will be in a pressurized excursion module configuration, and in 2011 the module will be reconfigured for a pressurized core module configuration. Each year the HDU configurations will undergo testing at NASA's Desert Research and Technology Studies (D-RaTS) in Arizona [1]. As part of this project, a modular instrumentation system is developed to meet the monitoring needs of the HDU subsystems and to integrate with the current command and data handling infrastructure that has been developed for the project. The main objective of this study is to provide for the monitoring needs of the HDU. The requirements necessary to meet this objective are developed by working with the subsystem managers of the HDU to understand their monitoring needs. Additionally, the instrumentation system design leverages knowledge and lessons learned from previous studies, such as the inflatable habitat health monitoring system that was deployed in Antarctica [2], the integrated health monitoring system developed for NASA's Microhab [3], and the JSC Lunar Habitat Wireless Testbed to demonstrate a "standardsbased" approach to a wireless instrumentation system [4]. The HDU also requires flexibility in reconfiguration options, and it is necessary to demonstrate and evaluate a modular approach to an instrumentation system. Thus, the instrumentation system is designed in two parts: the primary system employs a standard WSN configuration, and the secondary system employs a wired USB hub. The WSN design provides for reconfiguration or replacement of sensors due to malfunctions or upgrades by using a wireless node that accepts ten instrument inputs and wirelessly transmits the data to the command and data handling system. The USB hub is necessary for those instruments that operate using a wired USB connection, although the design attempts to limit the amount of sensors that need to be wired connections.

Rojdev, Kristina↗
DOE OSTI2024

Invertible Temper Modeling using Normalizing Flows and the Effects of Structure Preserving Loss

Advanced manufacturing research and development is typically small-scale, owing to costly experiments associated with these novel processes. Deep learning techniques could help accelerate this development cycle but frequently struggle in small-data regimes like the advanced manufacturing space. While prior work has applied deep learning to modeling visually plausible advanced manufacturing microstructures, little work has been done on data-driven modeling of how microstructures are affected by heat treatment, or assessing the degree to which synthetic microstructures are able to support existing workflows. We propose to address this gap by using invertible neural networks (normalizing flows) to model the effects of heat treatment, e.g., tempering. The model is developed using scanning electron microscope imagery from samples produced using shear-assisted processing and extrusion (ShAPE) manufacturing. This approach not only produces visually and topologically plausible samples, but also captures information related to a sample’s material properties or experimental process parameters. We also demonstrate that topological data analysis, used in prior work to characterize microstructures, can also be used to stabilize model training, preserve structure, and improve downstream results. We assess directions for future work and identify our approach as an important step towards end-to-end deep learning system for accelerating advanced manufacturing research and development.

Howland, Sylvia↗
DOE OSTI2020

Ambient Pressure XPS Investigation of Thermally Stable Halide Perovskite Solar Cells via Post-Treatment

Long-term thermal stability is one limiting factor that impedes the commercialization of perovskite solar cell. Inspired by our prior results from machine learning, we discover that coating a thin layer of 4,4’-dibromotriphenylamine (DBTPA) on top of a CH 3 NH 3 PbI 3 (MAPbI 3 ) thin film can improve the stability of the resultant perovskite solar cells. The passivated perovskite solar cells retained more than 96% of their initial power conversion efficiency over 1000 h at 85 °C in N2 atmosphere without encapsulation. Near-ambient pressure x-ray photoelectron spectroscopy (NAP-XPS) was employed to investigate the evolution of composition and evaluate thermal and moisture stability by in-situ studies. A comparison between pristine MAPbI 3 films and DBTPA-treated films shows the DBTPA treatment suppresses the escape of iodide and methylamine up to 150 °C under 5 mbar humidity. Furthermore, we have used ATR-FTIR and XPS to probe the interactions between DBTPA and MAPbI3 surface. The results prove that DBTPA coordinate with perovskite by Lewis acid-base and cation-π interaction. Compared with the 19.9% efficiency of pristine sample, the champion efficiency of passivated sample reaches 20.6%. Finally, our results reveal DBTPA as a new post-treating molecule that not only leads to the improvement of photovoltaic efficiency but also thermal and moisture stability.

14 SOLAR ENERGY↗
DOE OSTI2024

Error mitigation in variational quantum eigensolvers using tailored probabilistic machine learning

Quantum computing technology has the potential to revolutionize the simulation of materials and molecules in the near future. A primary challenge in achieving near-term quantum advantage is effectively mitigating the noise effects inherent in current quantum processing units (QPUs). This challenge is also decisive in the context of quantum-classical hybrid schemes employing variational quantum eigensolvers (VQEs) that have attracted significant interest in recent years. In this paper, we present a method that employs parametric Gaussian process regression (GPR) within an active learning framework to mitigate noise in quantum computations, focusing on VQEs. Our approach, grounded in probabilistic machine learning, exploits a custom prior based on the VQE ansatz to capture the underlying correlations between VQE outputs for different variational parameters, thereby enhancing both accuracy and efficiency. We demonstrate the effectiveness of our method on a two-site Anderson impurity model and a eight-site Heisenberg model, using the IBM open-source quantum computing framework, Qiskit, showcasing substantial improvements in the accuracy of VQE outputs while reducing the number of direct QPU energy evaluations. This paper contributes to the ongoing efforts in quantum-error mitigation and optimization, bringing us a step closer to realizing the potential of quantum computing in quantum matter simulations. Published by the American Physical Society 2024

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Detecting Anomalies in Time Series Using Kernel Density Approaches

This paper introduces a novel anomaly detection approach tailored for time series data with exclusive reliance on normal events during training. Our key innovation lies in the application of kernel-density estimation (KDE) to scrutinize reconstruction errors, providing an empirically derived probability distribution for normal events post-reconstruction. This non-parametric density estimation technique offers a nuanced understanding of anomaly detection, differentiating it from prevalent threshold-based mechanisms in existing methodologies. In post-training, events are encoded, decoded, and evaluated against the estimated density, providing a comprehensive notion of normality. In addition, we propose a data augmentation strategy involving variational autoencoder-generated events and a smoothing step for enhanced model robustness. The significance of our autoencoder-based approach is evident in its capacity to learn normal representation without prior anomaly knowledge. Through the KDE step on reconstruction errors, our method addresses the versatility of anomalies, departing from assumptions tied to larger reconstruction errors for anomalous events. Our proposed likelihood measure then distinguishes normal from anomalous events, providing a concise yet comprehensive anomaly detection solution. The extensive experimental results support the feasibility of our proposed method, yielding significantly improved classification performance by nearly 10% on the UCR benchmark data.

Frehner, Robin↗