Deep learning based optical image super-resolution via generative diffusion models for layerwise in-situ LPBF monitoring
Not Available
SEARCH · Search NASA
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.
Not Available
Not Available
This dataset provides supplementary molecular dataset of Deep Learning Workflow for the Inverse Design of Molecules with Specific Optoelectronic Properties. The dataset comprises three main directories such as GDB-9_dataset, Low_HL_Gap_dataset, and High_HL_Gap_dataset which individually has csv files, smiles_txt files, pdb files and xyz files containing information of molecular structures, properties and coordinates generated from deep learning workflow using generative model, surrogate model and DFTB calculation results. GDB-9_dataset contains the molecular data extracted from the original GDB-9 dataset with additional data of DFTB HL gap, surrogate HL gap and molecular property analysis. (the number of atoms, aromaticity and double bond equivalent) Low_HL_Gap_dataset and High_HL_Gap_dataset contains series of dataset for different generations with further split to train and test dataset that were obtained from the iterative workflow described in the manuscript. Additional directory Chemiscope_visualization in Low_HL_Gap_dataset directory contains compressed json files to visualize molecules using chemiscope.org page or application to help readers examine generated molecules.
RTRC and UMD have developed novel machine learning based methods under the ARPA-E DIFFERENTIATE program for rapid acceleration of hypothesis generation in complex architecture design spaces involving both discrete choices of component inclusion and interconnection and continuous parametric decisions. The project named Learning Enabled Network Synthesis (LENS) further demonstrated the developed methods on challenging electrical power converter design problems by identifying the most suitable circuit topologies and simultaneously selecting the most appropriate components to achieve optimized design of power converter with improved performances. We demonstrated that LENS could enable exploration of very large design space of circuit topologies and components by addressing the limitations of conventional design process in non-linear, high switching speed, multi-dimensional power converter design and optimization. The key innovation developed in LENS is the seamless integration of statistical learning and logical reasoning techniques and building on the individual strengths of these techniques for rapid hypothesis discovery. The main component of LENS comprises of: 1) Graph Reasoning Engine (GRE) to enforce composition rules that rapidly reject all discrete architectures that are composed incorrectly and generates an adaptive database of feasible designs which can be used by ML modules, 2) Graph Generative Learning module which is a deep neural network based generative model for graph architectures which can enable design space exploration beyond the dataset generated by the GRE, 3) Graph Reduced Order Model (ROM) for graph domains for accelerating computation of output metrics, and 4) Active learning and Rule Discovery module for sample efficient learning and extracting logical rules from the learned ML models which will be integrated in the GRE to enhance the filtering effectiveness. LENS approach can be applied to any design domains where designs can be represented as multi-attribute graphs. The LENS team integrated the various technical innovations listed above into an optimization pipeline and exercised the optimization pipeline on the converter design problem. The LENS project demonstrated that the developed AI/ML technologies can be used to generate novel converter circuits >45x faster than experts on chosen use-cases. This can enable faster design space exploration and identification of new designs which are not considered by experts due to the increasing design space complexity. This has significant potential impact on the public and energy needs of the country. It is currently estimated that 30% of all electrical powers generated passes through power converters. The future estimate is that 80% of all power generated would be passing through converters. LENS fills a critical gap in this space since by accelerating the design process the designers would be able to generate more efficient converters which can lead to significant energy savings for the country.
This study examines model-specific assumptions and projections of methane (CH 4 ) emissions in deep mitigation scenarios generated by integrated assessment models (IAMs). For this, scenarios of nine models are compared in terms of sectoral and regional CH 4 emission reduction strategies, as well as resulting climate impacts. The models’ projected reduction potentials are compared to sector and technology-specific reduction potentials found in literature. Significant cost-effective and non-climate policy related reductions are projected in the reference case (10–36% compared to a “frozen emission factor” scenario in 2100). Still, compared to 2010, CH 4 emissions are expected to rise steadily by 9–72% (up to 412 to 654 Mt CH 4 /year). Ambitious CO 2 reduction measures could by themselves lead to a reduction of CH 4 emissions due to a reduction of fossil fuels (22–48% compared to the reference case in 2100). However, direct CH 4 mitigation is crucial and more effective in bringing down CH 4 (50–74% compared to the reference case). Given the limited reduction potential, agriculture CH 4 emissions are projected to constitute an increasingly larger share of total anthropogenic CH 4 emissions in mitigation scenarios. Enteric fermentation in ruminants is in that respect by far the largest mitigation bottleneck later in the century with a projected 40–78% of total remaining CH 4 emissions in 2100 in a strong (2 °C) climate policy case.
We use deep optical photometry from the Next Generation Virgo Cluster Survey (NGVS) to investigate the color–magnitude diagram for the galaxies inhabiting the core of this cluster. The sensitivity of the NGVS imaging allows us to continuously probe galaxy colors over a factor of ∼2 × 10{sup 5} in luminosity, from brightest cluster galaxies to scales overlapping classical satellites of the Milky Way (M{sub g{sup ′}} ∼ −9; M {sub *} ∼ 10{sup 6} M {sub ⊙}), within a single environment. Remarkably, we find the first evidence that the red sequence (RS) flattens in all colors at the faint-magnitude end (starting between −14 ≤ M{sub g{sup ′}} ≤ −13, around M {sub *} ∼ 4 × 10{sup 7} M {sub ⊙}), with the slope decreasing to ∼60% or less of its value at brighter magnitudes. This could indicate that the stellar populations of faint dwarfs in Virgo’s core share similar characteristics (e.g., constant mean age) over ∼3 mag in luminosity, suggesting that these galaxies were quenched coevally, likely via pre-processing in smaller hosts. We also compare our results to galaxy formation models, finding that the RS in model clusters have slopes at intermediate magnitudes that are too shallow, and in the case of semianalytic models, do not reproduce the flattening seen at both extremes (bright/faint) of the Virgo RS. Deficiencies in the chemical evolution of model galaxies likely contribute to the model-data discrepancies at all masses, while overly efficient quenching may also be a factor at dwarf scales. Deep UV and near-IR photometry are required to unambiguously diagnose the cause of the faint-end flattening.
Hadronization models used in event generators are physics-inspired functions with many tunable parameters. Since we do not understand hadronization from first principles, there have been multiple proposals to improve the accuracy of hadronization models by utilizing more flexible parametrizations based on neural networks. These recent proposals have focused on the kinematic properties of hadrons, but a full model must also include particle flavor. In this paper, we show how to build a deep learning-based hadronization model that includes both kinematic (continuous) and flavor (discrete) degrees of freedom. Our approach is based on generative adversarial networks and we show the performance within the context of the cluster hadronization model within the erwig event generator.
The objective of this article is to design novel multi-layer neural networks for multiscale simulations of flows taking into account the observed fine data and physical modeling concepts. Our approaches use deep learning techniques combined with local multiscale model reduction methodologies to predict flow dynamics. Using reduced-order model concepts is important for constructing robust deep learning architectures since the reduced-order models provide fewer degrees of freedom. We consider flow dynamics in porous media as multi-layer networks in this work. More precisely, the solution (e.g., pressures and saturation) at the time instant n+1 depends on the solution at the time instant n and input parameters, such as permeability fields, forcing terms, and initial conditions. One can regard the solution as a multi-layer network, where each layer, in general, is a nonlinear forward map and the number of layers relates to the internal time steps. We will rely on rigorous model reduction concepts to define unknowns and connections between layers. It is critical to use reduced-order models for this purpose, which will identify the regions of influence and the appropriate number of variables. Furthermore, due to the lack of available observed fine data, the reduced-order model can provide us sufficient inexpensive data as needed. The designed deep neural network will be trained using both coarse simulation data which is obtained from the reduced-order model and observed fine data. We will present the main ingredients of our approach and numerical examples. Numerical results show that using deep learning with data generated from multiscale models as well as available observed fine data, we can obtain an improved forward map which can better approximate the fine scale model.
The Generic Aquifer Model calculates the concentrations of dissolved salt and dissolved CO 2 surrounding a leaking legacy well. The Generic Aquifer model can also estimate the size of an “impact plume” where concentration changes exceed user-specified thresholds. The model is a component of NRAP-Open-IAM, an open-source Integrated Assessment Model (IAM) developed by the National Risk Assessment Partnership (NRAP) to perform risk assessment for geologic CO 2 storage. The input parameters were selected to cover a wide range of groundwater aquifers and leakage rates. The generic aquifer model was developed using a generative adversarial deep learning network, trained using a large synthetic dataset of STOMP multiphase flow simulations. The deep learning model predictions of dissolved salt and dissolved CO 2 in the aquifer compare well to the original STOMP simulation results. The extent of aquifer impacted by leaking CO 2 or brine is calculated using a user-defined mass fraction threshold. The aquifer impact volumes calculated based on STOMP simulation results compare well to those calculated based on the deep learning model. In a provided python script, gridded observation results from the generic aquifer component of NRAP-Open-IAM are converted to HDF5 format files for monitoring design with the DREAM code.
Quasars are bright active galactic nuclei powered by the accretion of matter around supermassive black holes at the center of galaxies. Their stochastic brightness variability depends on the physical properties of the accretion disk and black hole. The upcoming Rubin Observatory Legacy Survey of Space and Time (LSST) is expected to observe tens of millions of quasars, so there is a need for efficient techniques like machine learning that can handle the large volume of data. Quasar variability is believed to be driven by an X-ray corona, which is reprocessed by the accretion disk and emitted as UV/optical variability. We are the first to introduce an auto-differentiable simulation of the accretion disk and reprocessing. We use the simulation as a direct component of our neural network to jointly model the driving variability and reprocessing, trained with supervised learning on simulated LSST-like 10 yr quasar light curves. We encode the light curves using a transformer encoder, and the driving variability is reconstructed using latent stochastic differential equations, a physically motivated generative deep learning method that can model continuous-time stochastic dynamics. By embedding the physical processes of the driving signal and reprocessing into our network, we achieve a model that is more robust and interpretable. We demonstrate that our model outperforms a Gaussian process regression baseline and can infer accretion disk parameters and time delays between wave bands, even for out-of-distribution driving signals. Our approach provides a powerful framework that can be adapted to solve other inverse problems in multivariate time series.
Deep learning has demonstrated an exceptional ability to solve complex tasks (an engineering success); however, it has done so at the expense of the ability to generate new knowledge (a scientific failure). We propose an alternative framework—entitled Deep Symbolic Regression (DSR)—in which artificial neural networks (NNs) rapidly generate hypotheses about physical relationships among inputs. This framework bypasses the need to interpret an NN altogether, while still leveraging the representational power of deep learning. The resulting models are tractable mathematical expressions, which are inherently and readily human interpretable and can provide insights into underlying physical phenomena. Further, we fold this methodology into the scientific process by allowing the scientist to directly integrate a priori knowledge and beliefs to accelerate learning. We demonstrate this methodology on symbolic regression—the problem of rediscovering underlying expressions describing a dataset—and achieve state-of-the-art performance across a wide variety of symbolic regression problems. Further, we generalize our DSR framework to apply to the more general class of symbolic optimization problems, in which one seeks to optimize a sequence of symbols or “tokens” under a black-box reward function. Examples of other symbolic optimization problems include neural architecture search and computational antibody design. Our generalized tool, Deep Symbolic Optimization (DSO), has been demonstrated on the task of learning symbolic control policies for reinforcement learning environments, and has been adopted as an enabling capability for computational antibody design.
The Hückel Hamiltonian is an incredibly simple tight-binding model known for its ability to capture qualitative physics phenomena arising from electron interactions in molecules and materials. Part of its simplicity arises from using only two types of empirically fit physics-motivated parameters: the first describes the orbital energies on each atom and the second describes electronic interactions and bonding between atoms. By replacing these empirical parameters with machine-learned dynamic values, we vastly increase the accuracy of the extended Hückel model. The dynamic values are generated with a deep neural network, which is trained to reproduce orbital energies and densities derived from density functional theory. The resulting model retains interpretability, while the deep neural network parameterization is smooth and accurate and reproduces insightful features of the original empirical parameterization. Altogether, this work shows the promise of utilizing machine learning to formulate simple, accurate, and dynamically parameterized physics models.
Deep generative neural networks have enabled modeling complex distributions, but incorporating physics knowledge into the neural networks is still challenging and is at the core of current physics-based machine learning research. To this end, we propose a physics generative neural network (PhysGNN), a new class of generative neural networks for learning unknown distributions in a physical system described by partial differential equations (PDE). PhysGNN couples PDE systems with generative neural networks. It is a fully differentiable model that allows back-propagation of gradients through both numerical PDE solvers and generative neural networks, and is trained by minimizing the discrete Wasserstein distance between generated and observed probability distributions of the PDE outputs using the stochastic gradient descent method. Moreover, PhysGNN does not require adversarial training like standard generative neural networks, which offers better stability than adversarial training. We show that PhysGNN can learn complex distributions in stochastic inverse problems, where conventional methods such as maximum likelihood estimation and momentum matching methods may be inapplicable when little knowledge is known about the form of unknown distributions or the physical model is too complex. Furthermore, our method allows physics-based generative neural network training for learning complex distributions in the context of differential equations.
Abstract We present a dataset of structural relaxations of bulk ternary transition metal dichalcogenides (TMDs) computed via plane-wave density functional theory (DFT). We examined combinations of up to two chalcogenides with seven transition metals from groups 4–6 in octahedral (1T) or trigonal prismatic (2H) coordination. The full dataset consists of 672 unique stoichiometries, with a total of 50,337 individual configurations generated during structural relaxation. Our motivations for building this dataset are (1) to develop a training set for the generation of machine and deep learning models and (2) to obtain structural minima over a range of stoichiometries to support future electronic analyses. We provide the dataset as individual VASP xml files as well as all configurations encountered during relaxations collated into an ASE database with the corresponding total energy and atomic forces. In this report, we discuss the dataset in more detail and highlight interesting structural and electronic features of the relaxed structures.
Small beta barrel proteins are attractive targets for computational design because of their considerable functional diversity despite their very small size (<70 amino acids). However, there are considerable challenges to designing such structures, and there has been little success thus far. Because of the small size, the hydrophobic core stabilizing the fold is necessarily very small, and the conformational strain of barrel closure can oppose folding; also intermolecular aggregation through free beta strand edges can compete with proper monomer folding. Here, we explore the de novo design of small beta barrel topologies using both Rosetta energy–based methods and deep learning approaches to design four small beta barrel folds: Src homology 3 (SH3) and oligonucleotide/oligosaccharide-binding (OB) topologies found in nature and five and six up-and-down-stranded barrels rarely if ever seen in nature. Both approaches yielded successful designs with high thermal stability and experimentally determined structures with less than 2.4 Å rmsd from the designed models. Using deep learning for backbone generation and Rosetta for sequence design yielded higher design success rates and increased structural diversity than Rosetta alone. The ability to design a large and structurally diverse set of small beta barrel proteins greatly increases the protein shape space available for designing binders to protein targets of interest.
This report summarizes the activities performed under the data analytics Vertex in the Materials Characterization, Prediction and Control Project funded under laboratory directed research and development at Pacific Northwest National Laboratory. The data analytics Vertex developed models for associating global or local process parameters, microstructural features, and performance properties of friction-stir-processed 316L stainless steel plates. Statistical, machine learning, and deep learning models, as well as generative artificial intelligence approaches, were used to develop the associations between the process-structure-property data streams. These associations formed the basis for predicting global properties of parts manufactured under different process envelopes, providing a basis for predicting performance using data driven as well as physics-informed and physics-constrained approaches. Additionally, the associations were used to predict local process parameters and microstructural features of the product, predictive relationships that have the potential to form the basis of a control framework that could eventually modulate a friction-stir process to maintain product quality.
Additive Manufacturing (AM), referred to as 3D printing, has emerged as a key pillar of Industry 4.0 enabling layer-by-layer fabrication of intricate geometries from CAD models. In parallel, Large Language Models (LLMs), deep learning models for natural language generation trained on vast text corpora, have demonstrated unprecedented capabilities in understanding and generating human-like text. The convergence of these trends opens new opportunities at the intersection of AM and AI/ML, where LLMs can assist engineers and researchers in design, manufacture planning, and knowledge discovery. Recent academic work has begun to explore LLM applications in AM and adjacent fields, such as material science, mechanical engineering, and design for additive manufacturing. This exploration ranges from intelligent process planning to domain-specific knowledge retrieval. This survey provides a comprehensive review of current developments, focusing on peer-reviewed literature contributions that apply, adapt, and advance LLMs in general and domain-specific domains. We analyze state-of-the-art (SOTA) techniques, such as fine-tuning foundational models for specific domains, retrieval-augmented generation (RAG) pipelines, knowledge graph integration, and delve into the architectures and evaluation methods employed. The goal of this survey is to inform researchers and practitioners of the current capabilities and limitations of LLMs in general and in domain-specific applications, and to outline how these models are being tailored to meet the requirements of these applications.
The E1039/SpinQuest experiment at Fermi National Accelerator Laboratory uses a 120~GeV proton beam from the Main Injector incident on transversely polarized proton and deuteron targets, using $NH_3$ and $ND_3$, respectively. In addition to measuring the Sivers asymmetry in Drell--Yan $pp$ and $pd$ scattering from sea quarks, SpinQuest will study transverse-spin effects, particularly the transverse single-spin asymmetry (TSSA) in $J/\psi$ production. The angular distributions from the $J/\psi$ decay could play an important role in understanding the gluon contribution to the proton spin structure. However, before extracting these angular distributions, it is necessary to isolate signal events originating from the target from events produced by other sources and from the combinatorial background. To effectively and accurately classify the target events, it is important to ensure that the simulated events are properly tuned to the experimental physics channels. We have introduced an iterative technique to match simulated and experimental events and to classify the physics channels using deep neural networks and a generative model based on normalizing flows.