Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Learning Theory”

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 451 records · Page 25

Deep neural network for the dielectric response of insulators

In this work, we introduce a deep neural network to model in a symmetry preserving way the environmental dependence of the centers of the electronic charge. The model learns from ab initio density functional theory, wherein the electronic centers are uniquely assigned by the maximally localized Wannier functions. When combined with the deep potential model of the atomic potential energy surface, the scheme predicts the dielectric response of insulators for trajectories inaccessible to direct ab initio simulation. The scheme is nonperturbative and can capture the response of a mutating chemical environment. We demonstrate the approach by calculating the infrared spectra of liquid water at standard conditions, and of ice under extreme pressure, when it transforms from a molecular to an ionic crystal.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Stochastic Gradient-Based Distributed Bayesian Estimation in Cooperative Sensor Networks

Distributed Bayesian inference provides a full quantification of uncertainty offering numerous advantages over point estimates that autonomous sensor networks are able to exploit. However, fully-decentralized Bayesian inference often requires large communication overheads and low network latency, resources that are not typically available in practical applications. In this paper, we propose a decentralized Bayesian inference approach based on stochastic gradient Langevin dynamics, which produces full posterior distributions at each of the nodes with significantly lower communication overhead. We provide analytical results on convergence of the proposed distributed algorithm to the centralized posterior, under typical network constraints. Finally, we also provide extensive simulation results to demonstrate the validity of the proposed approach.

42 ENGINEERING↗

DOE STTR Phase I Final Report Report: Machine-learning Based Prediction of Thermal Limits for Conjugated Organic Materials

The SCANN-DT Phase I STTR project led by NLM Photonics and partnering with the National Renewable Energy Laboratory (NREL) sought to apply machine learning techniques based on graph neural networks (GNNs) towards the prediction of decomposition temperatures (Td) of organic semiconductors, based on prior work on bond dissociation energy (BDE) prediction as implemented in NREL’s ALFABET prediction tool. Using a curated set of experimental decomposition energies, the project examined GNN-based, classical quantitative structure-property relationship (QSPR) based on DFT calculations, and combinations of both methods to predict Td. While the best MAEs in Td achieved were near 40°C, below project targets, the project led to improvements in the ALFABET model, improvements in cloud-based implementations of NWChem software, and a substantial dataset of calculations on medium-sized conjugated organic molecules.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Management and Operation of the Lawrence Livermore National Laboratory (Final Report)

Optimize existing characterization and control methods by developing methods for rapid synthesis of multi-qubit control for error mitigation and complex gate design using optimal control theory. The Subcontractor shall develop Hamiltonian learning methods that can be used for characterizing super-conducting quantum devices, in particular develop strategies for effective probing of such devices.

97 MATHEMATICS AND COMPUTING↗

Material Discovery and Design Principles of Perovskite Oxides for Reversible Solid Oxide Cells (R-SOC)

Reversible solid oxide cells (R-SOCs) are highly efficient devices for energy conversion and storage, capable of operating for both hydrogen utilization and production. In fuel cell mode, an R-SOC consumes hydrogen or natural gas to generate electricity, while in electrolysis mode, it produces hydrogen from steam. The discover of new materials with rapid oxygen surface exchange kinetics and enduring stability is crucial for the economically viable commercialization of R-SOCs. To facilitate this pursuit, we conducted extensive Density Functional Theory (DFT) calculations and developed Machine Learning (ML) models to predict critical catalytic properties essential for R-SOCs, such as oxygen surface exchange/diffusivity, and area-specific resistance (ASR). BaCoxFeyZrzO3-d(BFCZ)(x+y+z=1) emerged as a promising family of electrode materials with high activity and stability, validated through systematic experimental study. Moreover, a robust numerical multiphysics model was developed to optimize materials and microstructure parameters, providing the ability to predict the performance of functional R-SOCs.

Liu, Jian↗

International Workshop on Electronic Structure 2024 (ES 24)

The 36th annual Workshop on Recent Developments in Electronic Structure Theory commenced on June 2-5, 2024 at Boston University with 136 in-person and 75 virtual attendees. The organizing committee was composed of five faculty at Boston University with seven local area faculty comprising the greater Boston area advisory committee. On the first day, two hands-on workshops, NEXMD and ComDMFT were held on June 2, two full days of presentations were held on June 3-4 and one half day on June 5. There were 19 invited speakers who spoke about the state-of-the-art in electronic structure methods, including density functional theory, many-body perturbation theory, and the incorporation of machine learning into electronic structure calculations. In addition, 45 young scientists presented posters on June 4. Housing at a reduced rate was provided at the Boston University dormitories. This conference provided a valuable opportunity for scientists, students, postdocs, and senior researchers alike, to disseminate their latest research results, discuss their ideas and best practices, learn from each other, and form new collaborations.

42 ENGINEERING↗

Deep Learning Methods for Symbolic Calculations in HEP

This project develops machine learning methods to accelerate symbolic calculations in high-energy physics. Using sequence-to-sequence transformer models, we construct frameworks to predict squared amplitudes and related quantities for Standard Model processes, including quantum electrodynamics, quantum chromodynamics, and electroweak interactions. The results demonstrate that deep learning can successfully learn complex symbolic relationships and provide a scalable approach to symbolic computation with potential applications in precision calculations and collider phenomenology.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Global Framework for Emulation of Nuclear Calculations

We introduce a hierarchical framework that combines ab initio many-body calculations with a Bayesian neural network, developing emulators capable of accurately predicting nuclear properties across isotopic chains simultaneously and being applicable to different regions of the nuclear chart. We benchmark our developments using the oxygen isotopic chain, achieving accurate results for ground-state energies and nuclear charge radii, while providing robust uncertainty quantification. Our framework enables global sensitivity analysis of nuclear binding energies and charge radii with respect to the low-energy constants that describe the nuclear force.

FOS: Computer and information sciences↗

Nuclear Data Adjustment for Nonlinear Applications in the OECD/NEA WPNCS SG14 Benchmark -- A Bayesian Inverse UQ-based Approach for Data Assimilation

The Organization for Economic Cooperation and Development (OECD) Working Party on Nuclear Criticality Safety (WPNCS) proposed a benchmark exercise to assess the performance of current nuclear data adjustment techniques applied to nonlinear applications and experiments with low correlation to applications. This work introduces Bayesian Inverse Uncertainty Quantification (IUQ) as a method for nuclear data adjustments in this benchmark, and compares IUQ to the more traditional methods of Generalized Linear Least Squares (GLLS) and Monte Carlo Bayes (MOCABA). Posterior predictions from IUQ showed agreement with GLLS and MOCABA for linear applications. When comparing GLLS, MOCABA, and IUQ posterior predictions to computed model responses using adjusted parameters, we observe that GLLS predictions fail to replicate computed response distributions for nonlinear applications, while MOCABA shows near agreement, and IUQ uses computed model responses directly. We also discuss observations on why experiments with low correlation to applications can be informative to nuclear data adjustments and identify some properties useful in selecting experiments for inclusion in nuclear data adjustment. Performance in this benchmark indicates potential for Bayesian IUQ in nuclear data adjustments.

FOS: Computer and information sciences↗

Interpreting machine learning prediction of fire emissions and comparison with FireMIP process-based models

Annual burned areas in the United States have increased 2-fold during the past decades. With more large fires resulting in more emissions of fine particulate matter, an accurate prediction of fire emissions is critical for quantifying the impacts of fires on air quality, human health, and climate. This study aims to construct a machine learning (ML) model with game-theory interpretation to predict monthly fire emissions over the contiguous US (CONUS) and to understand the controlling factors of fire emissions. The optimized ML model is used to diagnose the process-based models in the Fire Modeling Intercomparison Project (FireMIP) to inform future development. Results show promising performance for the ML model, Community Land Model (CLM), and Joint UK Land Environment Simulator-Interactive Fire And Emission Algorithm For Natural Environments (JULES-INFERNO) in reproducing the spatial distributions, seasonality, and interannual variability of fire emissions over the CONUS. Regional analysis shows that only the ML model and CLM simulate the realistic interannual variability of fire emissions for most of the subregions (r >0.95 for ML and r =0.14~0.70 for CLM), except for Mediterranean California, where all the models perform poorly (r =0.74 for ML and r <0.30 for the FireMIP models). Regarding seasonality, most models capture the peak emission in July over the western US. However, all models except for the ML model fail to reproduce the bimodal peaks in July and October over Mediterranean California, which may be explained by the smaller wind speeds of the atmospheric forcing data during Santa Ana wind events and limitations in model parameterizations for capturing the effects of Santa Ana winds on fire activity. Furthermore, most models struggle to capture the spring peak in emissions in the southeastern US, probably due to underrepresentation of human effects and the influences of winter dryness on fires in the models. As for extreme events, both the ML model and CLM successfully reproduce the frequency map of extreme emission occurrence but overestimate the number of months with extremely large fire emissions. Comparing the fire PM 2.5 emissions from the ML model with process-based fire models highlights their strengths and uncertainties for regional analysis and prediction and provides useful insights into future directions for model improvements.

54 ENVIRONMENTAL SCIENCES↗

Data exploration systems for databases

Data exploration systems apply machine learning techniques, multivariate statistical methods, information theory, and database theory to databases to identify significant relationships among the data and summarize information. The result of applying data exploration systems should be a better understanding of the structure of the data and a perspective of the data enabling an analyst to form hypotheses for interpreting the data. This paper argues that data exploration systems need a minimum amount of domain knowledge to guide both the statistical strategy and the interpretation of the resulting patterns discovered by these systems.

Greene, Richard J.↗

An Active RFID Accountability System (RAS) for Constrained Wireless Environments

A team from Oak Ridge National Laboratory (ORNL) has developed an RFID Accountability System (RAS) that allows items with active RFID tags to be tracked in environments where tags may not be able to transmit their location continuously. The system uses activators that transmit a short range signal. Active RFID tags are in a sleep state until they encounter an activator. Then they transmit a signal that is picked up by the antennas installed throughout the building. This paper presents the theory of operation, application areas, lessons learned, and key features developed over the course of seven years of development and use.

Accountability↗

Core Collapse Supernovae and Multi-Messenger Astronomy

Multi-messenger diagnostics for core-collapse supernovae (CCSN) have been used for over half a century when astronomers began using dust grains to probe the yields from supernovae. But the concurrent neutrino and electromagnetic observations of SN 1987A, a core-collapse supernova in the Large Magellanic Cloud, cemented the importance of multi-messenger diagnostics for these transients. Although rare in the Milky Way where supernovae can be probed by multiple messengers, the science enabled in each event is enormous.Most of the gravitational energy released during collapse is emitted in MeV neutrinos that should be detectable within a few Mpc with next generation (NG) neutrino experiments. They may also be detected by future gravitational wave (GW) interferometers. Including dust grains (and other nucleosynthetic yield probes), cosmic rays and high-energy neutrinos that probe shocks, and abroad range of thermal and non-thermal photon emission, these messengers probe nearly all aspects of the supernova physics and its progenitor evolution. Here, the multitude of diagnostics from a nearby supernova will allow us to tightly constrain our theories to maximize what we can learn about the universe from more distant, but less-well diagnosed, supernovae.

79 ASTRONOMY AND ASTROPHYSICS↗

Metric Learning to Accelerate Convergence of Operator Splitting Methods

Recent developments in machine learning have led to promising advances in accelerating the solution of constrained optimization problems. Increasing demand for real-time decision-making capabilities in applications such as artificial intelligence and optimal control has led to a variety of proposed strategies for learning to produce fast solutions to optimization problems. For example, recent works have shown that it is possible to accelerate the convergence of optimization algorithms by learning to select their parameters, such as gradient descent stepsizes. This work proposes a new approach, in which the underlying metric spaces of proximal operator splitting algorithms are learned to maximize convergence rate. While prior works in optimization theory have derived optimal metrics in simple cases, no such result exists for many practical problem forms including general Quadratic Programming (QP). This paper shows how differentiable optimization can enable the end-to-end learning of proximal metrics, enhancing the convergence of proximal algorithms for QP problems beyond what is possible based on known theory. Additionally, the results illustrate a strong connection between the learned proximal metrics and active constraints at the optima, leading to an interpretation in which the predicted proximal metrics can be viewed as a form of active set prediction.

King, Ethan [BATTELLE (PACIFIC NW LAB)]↗

Transforming U.S. Particle Physics Education: A Snowmass 2021 Study

The pursuit of knowledge in particle physics requires constant learning. As new tools become available, new theories are developed, and physicists search for new answers with ever-evolving methods. However, it is the case that formal educational systems serve as the primary training grounds for particle physicists. Graduate school (and undergraduate school to a lesser extent) is where researchers learn most of the technical skills required for research, develop scientific problem-solving abilities, learn how to establish themselves in their field, and begin developing their career. It is unfortunate, then, that the skills gained by physicists during their formal education are often mismatched with the skills actually required for a successful career in physics. We performed a survey of the U.S. particle physics community to determine the missing elements of graduate and undergraduate education and to gauge how to bridge these gaps. In this contributed paper, part of the 2021-22 Snowmass Community Planning Exercise, we report the results of this survey. We also recommend several specific community actions to improve the quality of particle physics education; the "community" here refers to physics departments, national labs, professional societies, funding agencies, and individual physicists.

Bitter, O.↗

Neural network emulation of spontaneous fission

Large-scale computations of fission properties are an important ingredient for nuclear reaction network calculations simulating rapid neutron-capture process (the 𝑟 process) nucleosynthesis. Due to the large number of fissioning nuclei potentially contributing to the 𝑟 process, a microscopic description of fission based on nuclear density functional theory (DFT) is computationally challenging. Here, we explore the use of neural networks (NNs) to construct DFT emulators capable of predicting potential energy surfaces and collective inertia tensors across the whole nuclear chart, starting from a minimal set of DFT calculations. We use constrained Hartree-Fock-Bogoliubov (HFB) calculations to predict the potential energy and collective inertia tensor in the axial quadrupole and octupole collective coordinates, for a set of nuclei in the 𝑟-process region. We then employ NNs to emulate the HFB energy and collective inertia tensor across the considered region of the nuclear chart. Least-action pathways characterizing spontaneous fission half-lives and fragment yields are then obtained by means of the nudged elastic band method. The potential energy predicted by NNs agrees with the DFT value to within a root-mean-square error of 500 keV, and the collective inertia components agree to within an order of magnitude. These results are largely independent of the NN architecture. The exit points on the outer turning line are found to be well emulated. For the spontaneous fission half-lives the NN emulation provides values that are found to agree with the DFT predictions within a factor of 10 3 across more than 70 orders of magnitude. Neural networks are able to emulate the potential energy and collective inertia well enough to reasonably predict physical observables. Future directions of study, such as the inclusion of additional collective degrees of freedom and active learning, will improve the predictive power of microscopic theory and further enable large-scale fission studies.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Noncommutative Bohnenblust–Hille inequalities

Abstract Bohnenblust–Hille inequalities for Boolean cubes have been proven with dimension-free constants that grow subexponentially in the degree (Defant et al. in Math Ann 374(1):653–680, 2019). Such inequalities have found great applications in learning low-degree Boolean functions (Eskenazis and Ivanisvili in Proceedings of the 54th annual ACM SIGACT symposium on theory of computing, pp 203–207, 2022). Motivated by learning quantum observables, a qubit analogue of Bohnenblust–Hille inequality for Boolean cubes was recently conjectured in Rouzé et al. (Quantum Talagrand, KKL and Friedgut’s theorems and the learnability of quantum Boolean functions, 2022. arXiv preprint arXiv:2209.07279 ). The conjecture was resolved in Huang et al. (Learning to predict arbitrary quantum processes, 2022. arXiv preprint arXiv:2210.14894 ). In this paper, we give a new proof of these Bohnenblust–Hille inequalities for qubit system with constants that are dimension-free and of exponential growth in the degree. As a consequence, we obtain a junta theorem for low-degree polynomials. Using similar ideas, we also study learning problems of low degree quantum observables and Bohr’s radius phenomenon on quantum Boolean cubes.

Volberg, Alexander↗

Machine-learning enabled thermodynamic model for the design of new rare-earth compounds

We employ a descriptor based machine-learning approach to assess the effect of chemical alloying on formation-enthalpy of rare-earth intermetallics. Application of machine-learning approaches in rare-earth intermetallic design have been sparse due to limited availability of reliable datasets. In this work, we developed an ‘in-house’ rare-earth database with more than 600 + compounds, each entry was populated with formation enthalpy and related atomic features using high-throughput density-functional theory (DFT). The SISSO (sure independence screening and sparsifying operator) based machine-learning method with meaningful atomic features was used for training and testing the formation enthalpies of rare earth compounds. The complex lattice function coupled with the machine-learning model was used to explore the effect of transition metal alloying on the energy stability of Ce based cubic Laves phases (MgCu 2 type). The SISSO predictions show good agreement with high-fidelity DFT calculations and X-ray powder diffraction measurements. Our study provides quantitative guidance for compositional considerations within a machine-learning model and discovering new metastable materials. The electronic-structure of Ce-Fe-Cu based compound was also analyzed to get an in-depth understanding of the electronic origin of phase stability. The interpretable analytical models in combination with density-functional theory and experiments provide a fast and reliable design guide for discovering technologically useful materials.

36 MATERIALS SCIENCE↗