AI Surrogate Model for Distributed Computing Workloads
Explore the source record for details and available documents.
97 MATHEMATICS AND COMPUTING↗
SEARCH · Engineering Papers
Results for “machine learning optimization”
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.
Leveraging data mining, active learning, and domain adaptation for efficient discovery of advanced oxygen evolution electrocatalysts
Developing advanced catalysts for acidic oxygen evolution reaction (OER) is crucial for sustainable hydrogen production. This study presents a multistage machine learning (ML) approach to streamline the discovery and optimization of complex multimetallic catalysts. Our method integrates data mining, active learning, and domain adaptation throughout the materials discovery process. Unlike traditional trial-and-error methods, this approach systematically narrows the exploration space using domain knowledge with minimized reliance on subjective intuition. Then, the active learning module efficiently refines element composition and synthesis conditions through iterative experimental feedback. The process culminated in the discovery of a promising Ru-Mn-Ca-Pr oxide catalyst. Our workflow also enhances theoretical simulations with domain adaptation strategy, providing deeper mechanistic insights aligned with experimental findings. By leveraging diverse data sources and multiple ML strategies, we demonstrate an efficient pathway for electrocatalyst discovery and optimization. This comprehensive, data-driven approach represents a paradigm shift and potentially benchmark in electrocatalysts research.
Science & Technology - Other Topics↗
PPPL Laboratory Directed Research and Development (Project Final Reports, FY2018 - FY2020)
The U.S. Department of Energy’s (DOE) Princeton Plasma Physics Laboratory (PPPL) is a collaborative national center for fusion energy science, basic sciences, and advanced technology. The Laboratory has three major missions: (1) to develop the scientific knowledge and advanced engineering to enable fusion to power the U.S. and the world; (2) to advance the science of nanoscale fabrication for technologies of tomorrow; and (3) to further the development of the scientific understanding of the plasma universe from laboratory to astrophysical scales. PPPL’s Laboratory Directed Research and Development (LDRD) program supports and encourages creativity and innovation and contributes to its long-term viability. New scientific and technical research areas emerge and are nurtured through the program. Furthermore, new capabilities are developed to enable the Laboratory to meet its and DOE’s missions. The program is used to systematically diversify the Laboratory’s programs and mission. In the last few years, the program has started projects in nanomaterial synthesis, microelectronics, advanced x-ray spectroscopy, high-energy-density physics, superconducting magnet technology, machine learning and artificial intelligence, 3D magnetic fields to optimize fusion plasmas, integration of permanent magnets with simple high-field magnets to reduce the cost of producing complex 3D magnetic fields, advanced computational methods for predictive understanding and control of fusion plasma, development of quantum computing algorithms for plasma physics, liquid metal plasma-facing components for fusion reactors, virtual engineering, and plasma-based space propulsion. The program is also the vehicle to recruit and train talented scientists and engineers with the new skills needed to perform the Laboratory’s mission. Many of the new hires through the program go on to become world-class scientists and engineers in their fields. This report provides descriptions and accomplishments of those LDRD projects that were completed during fiscal years 2018 through 2020.
36 MATERIALS SCIENCE↗
A Novel Hollow Fiber Membrane Reactor for High Purity H 2 Generation from Thermal Catalytic NH 3 Decomposition (Final Report)
Ammonia (NH 3 ), as a promising carbon neutral liquid fuel (CNLF) and an effective H 2 source, can be synthesized from air and water (N 2 extracted from air and H 2 from water) using renewable energy sources. To produce H 2 as an intermediate, it is essential to develop effective and economic NH 3 decomposition technologies. We have been developing an innovative hollow fiber membrane reactor for high purity H 2 generation from thermal catalytic NH 3 decomposition. The objective of the proposed research is to fabricate a compact and robust prototype with high energy efficiency (>80%) to deliver high purity (>99%) H2 at high rate per volume (>0.15 g H 2 /h/cm 3 ) from NH3 decomposition at low temperature (<450 °C) and high conversion (>99%). Our overall technical approach is to effectively combine an active catalyst for NH 3 decomposition with a selective H 2 membrane separation process in a novel, compact modular system to generate high purity H 2 and simultaneously achieve high NH 3 conversion and optimize the entire system energy efficiency. This novel integrated membrane reactor design, together with low-cost, highly active Ru-based catalyst, makes it most appropriate for the project objective. The proposed applied research and development work, therefore, represents an innovative and transformational solution to H 2 generation from thermal catalytic NH 3 decomposition. During the course of our research we i) synthesized and characterized ruthenium(Ru)-based catalysts, evaluated their catalytic performance for NH 3 decomposition and optimized the catalyst composition and performance based on machine learning, ii) prepared SAPO-34, MFI membranes on α-alumina hollow fibers and measured their performance for H 2 /N 2 , H 2 /N 2 /NH 3 separation and evaluated carbon molecular sieve (CMS) and Pd/Ag membranes for H 2 /N 2 , H 2 /N 2 /NH 3 separation at different conditions, iii) designed and evaluated several types of membrane reactors for H 2 production from NH 3 decomposition, and iv) evaluated the H 2 delivery cost base on catalysts development, membrane development and membrane reactor. For 3,1,12 RuYK catalyst, H 2 productivity of 6.35 mmol/min/gcat with NH 3 conversion of 95~98% was achieved at 5 bar and 400 °C; for SAPO-34 membrane, the best membrane showed H 2 permeance of 7.56×10 -7 mol/(m 2 ∙s∙Pa) and H 2 /N 2 selectivity of 23.1 at 20 °C; For CMS and Pd/Ag membranes, both showed superior stability for 71%H 2 /24%N 2 /5%NH 3 mixture separation at 450 °C and 7 bar for over 120 h; for the membrane reactor, high H 2 purity of >99.99% with NH 3 conversion of >99.4% were achieved in Pd/Ag membrane reactor at 450 °C, and the NH 3 concentration was always below 10 ppb in H 2 product. The H 2 generation rate was calculated to be as high as 0.47 g/h/cm 3 and the energy efficiency was calculated to be 88%. The membrane reactor showed superior stability for over 370 h and high H 2 purity, H 2 production rate and NH 3 conversion. Based on calculation, the H 2 delivery cost can be as low as $3.66/kg.
08 HYDROGEN↗
Domain Aware Deep-learning Algorithms Integrated with Scientific-computing Technologies (DADAIST)
This technical report summarized the contribution of the DADAIST project funded by the Data Model Convergence Initiative via the Laboratory Directed Research and Development (LDRD) investments at Pacific Northwest National Laboratory (PNNL). Specifically, we report the development of the NeuroMANCER (Neural Modules with Adaptive Nonlinear Constraints and Efficient Regularizations), a new open-source Scientific Machine Learning library for formulating and solving parametric constrained optimization problems, physics-informed system identification, and parametric optimal control problems. NeuroMANCER is using differentiable programming to combine modern data-driven models and optimization modeling language into a coherent algorithmic and software framework. NeuroMANCER is a Pytorch-based framework and adopts much of its philosophy focused on research and development, rapid prototyping, and streamlined deployment. Strong emphasis is given to extensibility, interoperability with the PyTorch ecosystem, and quick adaptability to custom domain problems. Neuromancer repository contains a comprehensive library of differentiable modules, including custom activation functions, matrix factorizations, deep learning architectures, neural differential equations, differential equation solvers, implicit layers such as iterative solvers, high-level API for symbolic expressions, API for modeling and control of dynamical systems, and extensive set of tutorial code examples in the form of python scripts and jupyter notebooks.
97 MATHEMATICS AND COMPUTING↗
SEARCHING FOR MESONIC DARK MATTER WITH THE HEAVY PHOTON SEARCH EXPERIMENT
Several highly-sensitive astrophysical experiments over the past couple of decades have demonstrated that the current abundance of visible Standard Model matter cannot explain galactic rotation curves, the expansion history of the Universe, or the apparent warping of light in empty space. Instead, one finds strong agreement with this body of experimental results upon positing the existence of an invisible particulate field, dark matter. Namely, a cold, weakly interacting dark matter component can explain all these phenomena. A number of accelerator-based experiments have been developed to search for the weak couplings/interactions of these particles, many of them concentrating on particle models with masses of tens to thousands of GeV. A relatively new, well-motivated model is a dark sector coupled to the Standard Model via a dark photon. The current abundance of dark matter can be obtained if one assumes that dark matter is coupled to light by a MeV to GeV particle with a U(1) symmetry. The parameter space of these models remains largely unexplored because they are difficult to probe experimentally. In this thesis, I analyze data from the Heavy Photon Search (HPS) detector, whose two detector halves closely surround the electron beam, providing acceptance to far-forward boosted interactions. This forward acceptance to highly boosted particles yields unprecedented sensitivity to MeV-scale invariant masses. I exhaustively optimize the offline reconstruction of the HPS detector. Each reconstruction object, from Silicon Vertex Tracker hits to tracks, is studied to maximize acceptance of dark matter events. I then use the 2021 run data to search for one model of dark-photon-mediated matter, the Strongly Interacting Massive Particle (SIMP). SIMP models provide self-interacting dark matter candidates that can form bound states resembling dark mesons. HPS can detect SIMPs through the decay of a dark vector boson (either a dark ¿ or ¿) into e+e- pairs. I obtain exclusion contours for SIMPs using both an optimized cuts-based selection and a machine-learning-based selection, advancing our knowledge of the nature of dark matter.
O'Dwyer, Rory [Stanford Univ., CA (United States).↗
Multibody for Everybody (M4E): A Symbolic Dynamics Modeling Tool with Applications in Simulation, Control, and Optimization
Developing the analytical model of a multibody system is often the initial step in control and optimization. The analytical model (equations of motion) describes a system’s time evolution under specified forcing conditions. Although developing these equations is easy for simple systems, this process becomes more complex for systems composed of multiple bodies. Deriving equations of motion for complex multibody systems requires specialized expertise in multibody dynamics, is time-consuming, and is susceptible to error. To address this issue, this paper presents an open-source, easy-to-use, systematic framework to derive symbolic equations of motion in both Python and MATLAB using the joint coordinate formulation. This formulation results in a set of ordinary differential equations that use the minimum set of coordinates needed to model a system. The symbolic representation provides better insight into the influence of design parameters on system performance, facilitates sensitivity analysis and parameter studies, and supports direct implementation of control and optimization routines. The tool enables numerical simulation for specified parameter sets, is modular for straightforward integration with other tools and libraries, and allows incorporation of hydrodynamics, mooring, and other external forces. The result is a reproducible, extensible pipeline for modeling, simulation, and design of complex multibody systems. The proposed tool is versatile and can be applied to domains such as robotics, control, and design. In addition, we integrated external libraries that provide capabilities for modeling offshore systems such as underwater robots and marine energy converters.
16 TIDAL AND WAVE POWER↗
Analytic continuation of noisy data using Adams Bashforth residual neural network
We propose a data-driven learning framework for the analytic continuation problem in numerical quantum many-body physics. Designing an accurate and efficient framework for the analytic continuation of imaginary time using computational data is a grand challenge that has hindered meaningful links with experimental data. The standard Maximum Entropy (MaxEnt)-based method is limited by the quality of the computational data and the availability of prior information. Also, the MaxEnt is not able to solve the inversion problem under high level of noise in the data. Here we introduce a novel learning model for the analytic continuation problem using a Adams-Bashforth residual neural network (AB-ResNet). Additionally, the advantage of this deep learning network is that it is model independent and, therefore, does not require prior information concerning the quantity of interest given by the spectral function. More importantly, the ResNet-based model achieves higher accuracy than MaxEnt for data with higher level of noise. Finally, numerical examples show that the developed AB-ResNet is able to recover the spectral function with accuracy comparable to MaxEnt where the noise level is relatively small.
97 MATHEMATICS AND COMPUTING↗
Prediction of DIII-D Pedestal Structure from Externally Controllable Parameters
The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. An experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (ne) and electron temperature (Te) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (Ip), toroidal magnetic field (Bφ), neutral beam heating power (PNBI) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
A Learning-based Supervisory Control Architecture for Electric Vehicle Charging System Paired with Energy Storages
A Machine Learning-based predictive model is developed for optimal dispatching energy storage system integrated with Electric Vehicle battery charger. The model is effectively trained using transfer learning algorithm and successfully validated via measurement data to achieve high fidelity and accuracy. The study findings provide possibilities for future development of the presented approach to implement computational heavy predictive algorithms with multi-step predictions in emerging modular bidirectional charger topologies to realize vehicle-to-grid (V2G) technology. The online tuning can be explored using the new measurements obtained during the operation, henceforth, enhancing the controller performance for integrating multiple DERs into distribution power networks that shows huge interest for the utilities and regulatory agencies. Multiple operation scenatios have been evaluated and simulation results are discussed to verify intended performance of the proposed control solution.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Final Report (October 2024): University of Tennessee, Knoxville (UTK) contribution to: FusMatML: Machine Learning Atomistic Modeling for Fusion Materials Collaborative Project led by Dr. Aidan Thompson, Sandia National Laboratory
The rapid growth of the field of Machine Learning Inter-Atomic Potentials (MLIAP) has lead to a profusion of methods, all of which have some similarity to each other, but each also restricted to particular design choices, often arrived at in a rather ad hoc fashion. Beyond anecdotal evidence, and some benchmarking studies on specific problems, little progress has been made in developing design principles for MLIAPs. The goal of this project is to use machine learning, data science, and uncertainty quantification methods to optimize the design choices for MLIAP.
Density functional theory, Helium and Hydrogen↗
Active and machine learning-based approaches to rapidly enhance microbial chemical production
In order to make renewable fuels and chemicals from microbes, new methods are required to engineer microbes more intelligently. Computational approaches, to engineer strains for enhanced chemical production typically rely on detailed mechanistic models (e.g., kinetic/stoichiometric models of metabolism)—requiring many experimental datasets for their parameterization—while experimental methods may require screening large mutant libraries to explore the design space for the few mutants with desired behaviors. To address these limitations, we developed an active and machine learning approach (ActiveOpt) to intelligently guide experiments to arrive at an optimal phenotype with minimal measured datasets. In this study, ActiveOpt was applied to two separate case studies to evaluate its potential to increase valine yields and neurosporene productivity in Escherichia coli. In both the cases, ActiveOpt identified the best performing strain in fewer experiments than the case studies used. This work demonstrates that machine and active learning approaches have the potential to greatly facilitate metabolic engineering efforts to rapidly achieve its objectives.
60 APPLIED LIFE SCIENCES↗
Sieving Hydrogen Isotopes via Machine Learning Assisted Chemical Vapor Deposition (CVD) of High‐Quality Monolayer Hexagonal Boron Nitride (h‐BN) on Iron Foils
Atomically thin two-dimensional (2D) ceramics, such as monolayer hexagonal boron nitride (h-BN), present potential for disruptive advances in separations. However, sub-atomic scale separation of hydrogen isotopes (H + /D + ) require near pristine 2D material membranes, and scalable synthesis of such high-quality h-BN comparable to mechanically exfoliated crystals remains a significant challenge. Here, we report a scalable Fe-catalyzed chemical vapor deposition (CVD) process for bottom-up synthesis of large-area, high-quality monolayer h-BN films, overcoming key limitations of conventional ammonia-based routes. By leveraging mechanistic insights and higher CVD temperatures, we suppress multilayer formation and achieve uniform monolayer h-BN coverage on commercially available Fe foils. Machine learning enables systematic exploration of the complex, multi-dimensional CVD parameter space (growth time, temperature, precursor temperature, multilayer faction, coverage), providing data-driven approaches to visualize and identify process regimes facilitating predominantly monolayer h-BN growth with minimal secondary nuclei/ad-layers. The optimized Fe-catalyzed CVD h-BN membranes show high-quality as observed by proton/deuteron (H + /D + ) selectivity ≈8.45, approaching the highest quality benchmark of mechanically exfoliated h-BN (H + /D + selectivity ≈10) as well as significantly outperforming Cu-catalyzed CVD h-BN membranes (H + /D + selectivity ≈3.62, control selectivity ≈1.7). Our work provides a scalable cost-effective route for high-quality monolayer h-BN synthesis for sub-atomic scale separations (H + /D + ) and demonstrates the broader potential of machine learning-guided optimization of CVD for advancing synthesis of 2D materials.
36 MATERIALS SCIENCE↗
Enhancing Gaussian Process Surrogates for Optimization and Posterior Approximation via Random Exploration
This paper proposes novel noise-free Bayesian optimization strategies that rely on a random exploration step to enhance the accuracy of Gaussian process surrogate models. The new algorithms retain the ease of implementation of the classical GP-UCB algorithm, but the additional random exploration step accelerates their convergence, nearly achieving the optimal convergence rate. Furthermore, to facilitate Bayesian inference with intractable likelihoods, we propose to utilize optimization iterates for maximum a posteriori estimation to build a Gaussian process surrogate model for the unnormalized log-posterior density. We provide bounds for the Hellinger distance between the true and the approximate posterior distributions in terms of the number of design points. We demonstrate the effectiveness of our Bayesian optimization algorithms in nonconvex benchmark objective functions, in a machine learning hyperparameter tuning problem, and in a black-box engineering design problem. The effectiveness of our posterior approximation approach is demonstrated in two Bayesian inference problems for parameters of dynamical systems.
Bayesian inference↗
Pathway Evolution Through a Bottlenecking-Debottlenecking Strategy and Machine Learning-Aided Flux Balancing
The evolution of pathway enzymes enhances the biosynthesis of high-value chemicals, crucial for pharmaceutical, and agrochemical applications. However, unpredictable evolutionary landscapes of pathway genes often hinder successful evolution. Here, the presence of complex epistasis is identifued within the representative naringenin biosynthetic pathway enzymes, hampering straightforward directed evolution. Subsequently, a biofoundry-assisted strategy is developed for pathway bottlenecking and debottlenecking, enabling the parallel evolution of all pathway enzymes along a predictable evolutionary trajectory in six weeks. This study then utilizes a machine learning model, ProEnsemble, to further balance the pathway by optimizing the transcription of individual genes. The broad applicability of this strategy is demonstrated by constructing an Escherichia coli chassis with evolved and balanced pathway genes, resulting in 3.65 g L -1 naringenin. The optimized naringenin chassis also demonstrates enhanced production of other flavonoids. This approach can be readily adapted for any given number of enzymes in the specific metabolic pathway, paving the way for automated chassis construction in contemporary biofoundries.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Mixed Precision Fermi-Operator Expansion on Tensor Cores from a Machine Learning Perspective
Here we present a second-order recursive Fermi-operator expansion scheme using mixed precision floating point operations to perform electronic structure calculations using tensor core units. A performance of over 100 teraFLOPs is achieved for half-precision floating point operations on Nvidia’s A100 tensor core units. The second-order recursive Fermi-operator scheme is formulated in terms of a generalized, differentiable deep neural network structure, which solves the quantum mechanical electronic structure problem. We demonstrate how this network can be accelerated by optimizing the weight and bias values to substantially reduce the number of layers required for convergence. We also show how this machine learning approach can be used to optimize the coefficients of the recursive Fermi-operator expansion to accurately represent the fractional occupation numbers of the electronic states at finite temperatures.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Band gap predictions of double perovskite oxides using machine learning
Abstract The compositional and structural variety inherent to oxide perovskites spawn wide-ranging applications. In perovskites, the band gap E g , a key material parameter for these applications, can be optimally controlled by varying the composition. Here, we implement a hierarchical screening process in which two cross-validated and predictive machine learning models for band gap classification and regression, trained using exhaustive datasets that span 68 elements of the periodic table, are applied sequentially. The classification model separates wide band gap materials, with E g ≥ 0.5 eV, from materials which have zero or relatively small band gaps, namely E g < 0.5 eV, and the second regression model quantitatively predicts the gap value of the wide band gap compounds. The study down-selects 13,589 cubic oxide perovskite compositions that are predicted to be experimentally formable, thermodynamically stable, and have a wide band gap. Of these, a subset of 310 compounds, which are predicted to be stable and formable with a confidence greater than 90%, are identified for further investigation. Our models are methodically analyzed via performance metrics and inter-dependence of model features to gain physical insight into the band gap prediction problem. Design maps to identify the variation of band gap with substitution of different elements are also presented.
36 MATERIALS SCIENCE↗
Toward fusion plasma scenario planning for NSTX-U using machine-learning-accelerated models
One of the most promising devices for realizing power production through nuclear fusion is the tokamak. To maximize performance, it is preferable that tokamak reactors achieve advanced operating scenarios characterized by good plasma confinement, improved magnetohydrodynamic (MHD) stability, and a largely non-inductively driven plasma current. Such scenarios could enable steady-state reactor operation with high \emph{fusion gain} --- the ratio of produced fusion power to the external power provided through the plasma boundary. Precise and robust control of the evolution of the plasma boundary shape as well as the spatial distribution of the plasma current, density, temperature, and rotation will be essential to achieving and maintaining such scenarios. The complexity of the evolution of tokamak plasmas, arising due to nonlinearities and coupling between various parameters, motivates the use of model-based control algorithms that can account for the system dynamics. In this work, a learning-based accelerated model trained on data from the National Spherical Torus Experiment Upgrade (NSTX-U) is employed to develop planning and control strategies for regulating the density and temperature profile evolution around desired trajectories. The proposed model combines empirical scaling laws developed across multiple devices with neural networks trained on empirical data from NSTX-U and a database of first-principles-based computationally intensive simulations. The reduced execution time of the accelerated model will enable practical application of optimization algorithms and reinforcement learning approaches for scenario planning and control development. An initial demonstration of applying optimization approaches to the learning-based model is presented, including a strategy for mitigating the effect of leaving the finite validity range of the accelerated model. The approach shows promise for actuator planning between experiments and in real-time.
machine learning↗