SEARCH · Engineering Papers

Results for “deep generative models”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 883 records · Page 49

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Discovering faint and high apparent motion rate near-Earth asteroids using a deep learning program

ABSTRACT Although many near-Earth objects have been found by ground-based telescopes, some fast-moving ones, especially those near detection limits, have been missed by observatories. We developed a convolutional neural network for detecting faint fast-moving near-Earth objects. It was trained with artificial streaks generated from simulations and was able to find these asteroid streaks with an accuracy of 98.7 per cent and a false positive rate of 0.02 per cent on simulated data. This program was used to search image data from the Zwicky Transient Facility (ZTF) in four nights in 2019, and it identified six previously undiscovered asteroids. The visual magnitudes of our detections range from ∼19.0 to 20.3 and motion rates range from ∼6.8 to 24 deg d−1, which is very faint compared to other ZTF detections moving at similar motion rates. Our asteroids are also ∼1–51 m diameter in size and ∼5–60 lunar distances away at close approach, assuming their albedo values follow the albedo distribution function of known asteroids. The use of a purely simulated data set to train our model enables the program to gain sensitivity in detecting faint and fast-moving objects while still being able to recover nearly all discoveries made by previously designed neural networks which used real detections to train neural networks. Our approach can be adopted by any observatory for detecting fast-moving asteroid streaks.

Wang, Franklin (ORCID:0000000344887355)↗

DOE OSTI2025

GrainPaint: A multi-scale diffusion-based generative model for microstructure reconstruction of large-scale objects

Simulation-based approaches to microstructure generation can suffer from a variety of limitations, such as high memory usage, long computational times, and difficulties in generating complex geometries. Generative machine learning models present a way around these issues, but they have previously been limited by the fixed size of their generation area. Here, we present a new microstructure generation methodology leveraging advances in inpainting using denoising diffusion models to overcome this generation area limitation. We show that microstructures generated with the presented methodology are statistically similar to grain structures generated with a kinetic Monte Carlo simulator, SPPARKS.

36 MATERIALS SCIENCE↗

DOE OSTI2021

A machine learning approach to galaxy properties: joint redshift–stellar mass probability distributions with Random Forest

We demonstrate that highly accurate joint redshift–stellar mass probability distribution functions (PDFs) can be obtained using the Random Forest (RF) machine learning (ML) algorithm, even with few photometric bands available. As an example, we use the Dark Energy Survey (DES), combined with the COSMOS2015 catalogue for redshifts and stellar masses. We build two ML models: one containing deep photometry in the griz bands, and the second reflecting the photometric scatter present in the main DES survey, with carefully constructed representative training data in each case. We validate our joint PDFs for 10 699 test galaxies by utilizing the copula probability integral transform and the Kendall distribution function, and their univariate counterparts to validate the marginals. Benchmarked against a basic set-up of the template-fitting code bagpipes, our ML-based method outperforms template fitting on all of our predefined performance metrics. In addition to accuracy, the RF is extremely fast, able to compute joint PDFs for a million galaxies in just under 6 min with consumer computer hardware. Such speed enables PDFs to be derived in real time within analysis codes, solving potential storage issues. As part of this work we have developed galpro 1, a highly intuitive and efficient python package to rapidly generate multivariate PDFs on-the-fly. galpro is documented and available for researchers to use in their cosmology and galaxy evolution studies.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Integrated Biorefinery of Brewer’s Spent Grain for Second-Generation Ethanol, Mycoprotein, and Bioactive Vinasse Production

Brewer’s spent grain (BSG), the main lignocellulosic by-product of the beer industry, represents an abundant yet underutilized resource with high potential for valorization. This study presents an integrated biorefinery approach to convert BSG into second-generation (2G) ethanol, bioactive vinasse for plant growth promotion, and fungal biomass as a potential mycoprotein source. The biomass was first subjected to biological delignification using the white-rot fungus Ganoderma lucidum, after which two valorization routes were explored: (i) evaluation of the fungal biomass as a mycoprotein candidate and (ii) alcoholic fermentation for ethanol production. For the latter, three pretreatment strategies were assessed (diluted sulfuric acid and two deep eutectic solvents (DESs) based on choline chloride combined with either glycerol or lactic acid) followed by a one-pot enzymatic saccharification and fermentation using Kluyveromyces marxianus SLP1. The highest ethanol yield on substrate (YP/S) was achieved with [Ch]Cl:lactic acid pretreatment (0.46 g/g, 89.32% of theoretical). Vinasse, recovered after distillation, was characterized for organic acid content and tested on Solanum lycopersicum seed germination, showing promising biostimulant activity. Overall, this work highlights the potential of BSG as a sustainable feedstock within circular economy models, enabling the production of multiple bio-based products from a single residue.

Ganoderma lucidum↗

DOE OSTI2020

Cadmium Selective Etching in CdTe Solar Cells Produces Detrimental Narrow-Gap Te in Grain Boundaries

Recent advances in design and processing technology have made possible commercialization of polycrystalline (px)-CdTe as a photovoltaic absorber. Grain boundaries (GBs) are the most prominent structural defects in these devices and undergo significant changes during device fabrication. However, the effects of device fabrication processes on these GBs are not entirely understood. Prevailing models of GBs in thin-film photovoltaics consider individual GBs to have homogeneous properties in their area. Here, using an aberration-corrected scanning transmission electron microscope (STEM)-based low-loss and core-loss electron energy-loss spectroscopy (EELS), we show that back-surface etching of CdTe leads to inhomogeneity within individual grain boundaries. We observe that etching the back surface leads to the conversion of a region of GBs from CdTe to an elemental Te, which has an only 0.33 eV band gap, as deep as 1 μm from the back surface. The presence of elemental Te in GBs this deep into the absorber layer will increase recombination in the absorber layer and limit the extractable open-circuit voltage, thus reducing device efficiency. However, additive methods for back contact formation such as deposition of Te, ZnTe, or other materials preserve the CdTe stoichiometry of the GBs. Thus, especially for the next generations of CdTe-based cells having longer minority carrier diffusion length and/or thinner absorber layers, additive back contacting methods are superior.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Attention-based functional-group coarse-graining: a deep learning framework for molecular prediction and design

Machine learning (ML) offers considerable promise for the design of new molecules and materials. In real-world applications, the design problem is often domain-specific, and suffers from insufficient data, particularly labeled data, for ML training. In this study, we report a data-efficient, deep-learning framework for molecular discovery that integrates a coarse-grained functional-group representation with a self-attention mechanism to capture intricate chemical interactions. Our approach exploits group-contribution concepts to create a graph-based intermediate representation of molecules, serving as a low-dimensional embedding that substantially reduces the data demands typically required for training. Using a self-attention mechanism to learn the subtle but highly relevant chemical context of functional groups, the method proposed here consistently outperforms existing approaches for predictions of multiple thermophysical properties. In a case study focused on adhesive polymer monomers, we train on a limited dataset comprising only 6,000 unlabeled and 600 labeled monomers. The resulting chemistry prediction model achieves over 92% accuracy in forecasting properties directly from SMILES strings, exceeding the performance of current state-of-the-art techniques. Furthermore, the latent molecular embedding is invertible, enabling the design pipeline to automatically generate new monomers from the learned chemical subspace. We illustrate this functionality by targeting several properties, including high and low glass transition temperatures (Tg), and demonstrate that our model can identify new candidates with values that surpass those in the training set. The ease with which the proposed framework navigates both chemical diversity and data scarcity offers a promising route to accelerate and broaden the search for functional materials.

Han, Ming [Univ. of Chicago, IL (United States)]↗

DOE OSTI2024

Using spatio-temporal graph neural networks to estimate fleet-wide photovoltaic performance degradation patterns

Accurate estimation of photovoltaic (PV) system performance is crucial for determining its feasibility as a power generation technology and financial asset. PV-based energy solutions offer a viable alternative to traditional energy resources due to their superior Levelized Cost of Energy (LCOE). A significant challenge in assessing the LCOE of PV systems lies in understanding the Performance Loss Rate (PLR) for large fleets of PV systems. Estimating the PLR of PV systems becomes increasingly important in the rapidly growing PV industry. Precise PLR estimation benefits PV users by providing real-time monitoring of PV module performance, while explainable PLR estimation assists PV manufacturers in studying and enhancing the performance of their products. However, traditional PLR estimation methods based on statistical models have notable drawbacks. Firstly, they require user knowledge and decision-making. Secondly, they fail to leverage spatial coherence for fleet-level analysis. Additionally, these methods inherently assume the linearity of degradation, which is not representative of real world degradation. To overcome these challenges, we propose a novel graph deep learning-based decomposition method called the Spatio-Temporal Graph Neural Network for fleet-level PLR estimation (PV-stGNN-PLR). PV-stGNN-PLR decomposes the power timeseries data into aging and fluctuation components, utilizing the aging component to estimate PLR. PV-stGNN-PLR exploits spatial and temporal coherence to derive PLR estimation for all systems in a fleet and imposes flatness and smoothness regularization in loss function to ensure the successful disentanglement between aging and fluctuation. We have evaluated PV-stGNN-PLR on three simulated PV datasets consisting of 100 inverters from 5 sites. Experimental results show that PV-stGNN-PLR obtains a reduction of 33.9% and 35.1% on average in Mean Absolute Percent Error (MAPE) and Euclidean Distance (ED) in PLR degradation pattern estimation compared to the state-of-the-art PLR estimation methods.

14 SOLAR ENERGY↗

DOE OSTI2026

AI-driven neutrino diagnostics and radiation-hard beam instrumentation for next-generation neutrino experiments

The Long Baseline Neutrino Facility (LBNF) at Fermilab will deliver a high-intensity, multi-megawatt neutrino beam to the Deep Underground Neutrino Experiment (DUNE), enabling precision tests of the three-neutrino paradigm, CP violation searches, neutrino mass ordering determination, and supernova neutrino studies. To accelerate DUNE’s physics reach and ensure robust beam operations, we propose an integrated AI-driven framework with real-time diagnostics and radiation-hardened instrumentation. At its core is a Real-Time Beam Integrity Monitor using a physics-informed Digital Twin. By reconstructing pion phase space from muon profiles and exploiting magnetic horn optic linearity, it enables spill-by-spill beam correction and flux stabilization. By using this approach, flux-related systematics could be reduced from 5% to 1%, potentially accelerating the discovery of CP violations by four to six years. Complementing this, a US–Japan R&D effort will deploy a LAPPD-based muon monitor in the NuMI beamline. ToF measurements can be acquired with picosecond precision using this radiation-hard system, enhancing sensitivity to horn chromatic effects. Simulations confirm strong response to these effects. ML models predict beam quality and horn current to sub-percent accuracy from muon data, enhancing anomaly detection and stability. This scalable, AI-enabled strategy improves beam fidelity, reduces systematics, and sets a new standard for high-power accelerator operations.

Ganguly, Sudeshna [Fermilab] (ORCID:00000003163482↗

DOE OSTI2020

How Low Can You Go? Using Synthetic 3D Imagery to Drastically Reduce Real-World Training Data for Object Detection

Deep convolutional neural networks (DCNNs) currently provide state-of-the-art performance on image classification and object detection tasks, and there are many global security mission areas where such models could be extremely useful. Crucially, the success of these models is driven in large part by the widespread availability of high-quality open source data sets such as Image Net, Common Objects in Context (COCO), and KITTI, which contain millions of images with thousands of unique labels. However, global security relevant objects-of-interest can be difficult to obtain: relevant events are low frequency and high consequence; the content of relevant images is sensitive; and adversaries and proliferators seek to obscure their activities. For these cases where exemplar data is hard to come-by, even fine-tuning an existing model with available data can be effectively impossible. Recent work demonstrated that models can be trained using a combination of real-world and synthetic images generated from 3D representations; that such models can exceed the performance of models trained using real-world data alone; and that the generated images need not be perfectly realistic (Tremblay, et al., 2018). However, this approach still required hundreds to thousands of real-world images for training and fine tuning, which for sparse, global security-relevant datasets can be an unrealistic hurdle. In this research, we validate the performance and behavior of DCNN models as we drive the number of real-world images used for training object detection tasks down to a minimal set. We perform multiple experiments to identify the best approach to train DCNNs from an extremely small set of real-world images. In doing so, we: Develop state-of-the-art, parameterized 3D models based on real-world images and sample from their parameters to increase the variance in synthetic image training data; Use machine learning explainability techniques to highlight and correct through targeted training the biases that result from training using completely synthetic images; and Validate our results by comparing the performance of the models trained on synthetic data to one another, and to a control model created by fine-tuning an existing ImageNet-trained model with a limited number (hundreds) of real-world images.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

AI-driven neutrino diagnostics and radiation-hard beam instrumentation for next-generation neutrino experiments

Ganguly, Sudeshna [Fermilab] (ORCID:00000003163482↗

DOE OSTI2024

Uncertainty-aware particle segmentation for electron microscopy at varied length scales

Electron microscopy is indispensable for examining the morphology and composition of solid materials at the sub-micron scale. To study the powder samples that are widely used in materials development, scanning electron microscopes (SEMs) are increasingly used at the laboratory scale to generate large datasets with hundreds of images. Parsing these images to identify distinct particles and determine their morphology requires careful analysis, and automating this process remains challenging. In this work, we enhance the Mask R-CNN architecture to develop a method for automated segmentation of particles in SEM images. We address several challenges inherent to measurements, such as image blur and particle agglomeration. Moreover, our method accounts for prediction uncertainty when such issues prevent accurate segmentation of a particle. Recognizing that disparate length scales are often present in large datasets, we use this framework to create two models that are separately trained to handle images obtained at low or high magnification. By testing these models on a variety of inorganic samples, our approach to particle segmentation surpasses an established automated segmentation method and yields comparable results to the predictions of three domain experts, revealing comparable accuracy while requiring a fraction of the time. These findings highlight the potential of deep learning in advancing autonomous workflows for materials characterization.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Machine Learning for DUNE Supernova Trigger

One of the major scientific goals of the Deep Underground Neutrino Experiment (DUNE) is to detect and measure the neutrino flux from galactic core-collapse supernovae. These neutrinos, which exist in the low energy range of up to a few tens of MeV and are responsible for carrying away over 99% of the gravitational binding energy of the supernova, provide an opportunity to study the end of life evolution of massive stars, as well as unique properties and interactions of neutrinos. Because galactic supernovae are expected to occur only on the timespan of every few decades, it is crucial that DUNE is able to detect supernova neutrino interactions when they occur. However, detecting these supernova interactions requires sifting through a large amount of data, and DUNE detectors require a trigger to signal when supernova neutrino events occur. Machine learning provides a potential approach to creating this trigger. This project generates ADC and ground truth images of neutrino interactions in a LArTPC detector as simulated by the Model of Argon Reaction Low Energy Yields (MARLEY) to be used for machine learning. The eventual goal of this work is to facilitate DUNE s detection of supernova neutrino interactions by building a machine learning pipeline that will train the trigger algorithm.

Damish, Stephanie↗

DOE OSTI2024

Machine Learning for DUNE Supernova Trigger

Damish, Stephanie↗

DOE OSTI2021

Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2021

ChemPix: automated recognition of hand-drawn hydrocarbon structures using deep learning

Inputting molecules into chemistry software, such as quantum chemistry packages, currently requires domain expertise, expensive software and/or cumbersome procedures. Leveraging recent breakthroughs in machine learning, we develop ChemPix: an offline, hand-drawn hydrocarbon structure recognition tool designed to remove these barriers. A neural image captioning approach consisting of a convolutional neural network (CNN) encoder and a long short-term memory (LSTM) decoder learned a mapping from photographs of hand-drawn hydrocarbon structures to machine-readable SMILES representations. We generated a large auxiliary training dataset, based on RDKit molecular images, by combining image augmentation, image degradation and background addition. Additionally, a small dataset of ~600 hand-drawn hydrocarbon chemical structures was crowd-sourced using a phone web application. These datasets were used to train the image-to-SMILES neural network with the goal of maximizing the hand-drawn hydrocarbon recognition accuracy. By forming a committee of the trained neural networks where each network casts one vote for the predicted molecule, we achieved a nearly 10 percentage point improvement of the molecule recognition accuracy and were able to assign a confidence value for the prediction based on the number of agreeing votes. The ensemble model achieved an accuracy of 76% on hand-drawn hydrocarbons, increasing to 86% if the top 3 predictions were considered.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2026

Extreme Temperature Cryptography Based On Nitrogen-Incorporated Ultrananocrystalline Diamond

Physical entropy sources that remain stable under extreme temperatures are essential for cryptography in emerging technological frontiers in deep space exploration, geothermal energy harvesting, and nuclear energy. However, conventional semiconductor platforms fail to generate stable and reliable cryptographic keys above 200 degrees C due to performance degradation. Here, we report a diamond-based cryptographic primitive that exploits the defect-rich sp 2 -bonded grain boundary network in nitrogen-incorporated ultrananocrystalline diamond (n-UNCD) film as a robust entropy source to generate cryptographic keys that remain operationally stable even after enduring extreme temperatures of 700 degrees C for 54 h while also surviving thermal cycling between room temperature and 700 degrees C for 48 h. The strength of the generated keys is assessed through several cryptographic metrics such as bit uniformity, entropy, hamming distances, and correlation coefficients, all of which are found to be near their respective ideal values. Moreover, the generated keys pass the NIST SP 800 and SP 800-90B tests and are also resilient to supply bias variations and a regression-based machine learning attack model based on the Fourier series. The robustness of the keys is attributed to the better thermal stability and chemical inertness of the n-UNCD film. This is supported by high-resolution energy-dispersive X-ray spectroscopy (EDS), which shows no significant lateral diffusion of metal atoms into the n-UNCD layer, and by Raman spectroscopy, which reveals no significant changes in the bonding configuration of the n-UNCD structure. Our findings highlight the remarkable potential of n-UNCD film for extreme environment cryptography by expanding the operational limits of conventional hardware security platforms.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2020

Reification of latent microstructures: On supervised unsupervised and semi-supervised deep learning applications for microstructures in materials informatics

Machine learning (ML), including deep learning (DL), has become increasingly popular in the last few years due to its continually outstanding performance. In this context, we apply machine learning techniques to "learn" the microstructure using both supervised and unsupervised DL techniques. In particular, we focus (1) on the localization problem bridging (micro)structure (localized) property using supervised DL and (2) on the microstructure reconstruction problem in latent space using unsupervised DL. The goal of supervised and semi-supervised DL is to replace crystal plasticity finite element model (CPFEM) that maps from (micro)structure (localized) property, and implicitly the (micro)structure (homogenized) property relationships, while the goal of unsupervised DL is (1) to represent high-dimensional microstructure images in a non-linear low-dimensional manifold, and (2) to discover a way to interpolate microstructures via latent space associating with latent microstructure variables. At the heart of this report is the applications of several common DL architectures, including convolutional neural networks (CNN), autoencoder (AE), and generative adversarial network (GAN), to multiple microstructure datasets, and the quest of neural architecture search for optimal DL architectures.

36 MATERIALS SCIENCE↗

DOE OSTI2020

Evaluation of Techniques for Vegetation Removal from UAV-Based Photogrammetric DSM near WIPP Land Withdrawal Act Boundary, NM

The Waste Isolation Pilot Plant is located within New Mexico's karst landscape and is the United States' only deep geologic radioactive waste repository which isolates transuranic waste from defense activities underground in a bedded salt formation. Characteristic karst topography in this region is made up of material (such as limestone) that can be dissolved by water over a long period of time, and includes features such as springs, surface streams, sinking streams, caves, and sinkholes. Karst features can potentially impact the integrity of the waste repository in the future and compromise WIPP's performance, particularly when coupled with incompatible land-use activities within the Land Withdrawal Act (LWA) boundary as well as increased water withdrawals outside the LWA. In order to better capture the ground surface topography to support hydrology modeling efforts, the U.S. DOE has enlisted FIU to develop a high-resolution digital elevation model (DEM). In a previous field study, a high-resolution digital surface model (DSM) of an adjacent representative site, Basin 6, was developed by photogrammetry using aerial images captured with unmanned aerial vehicles. The DSM generated was based on point clouds representing the entire landscapes, including points of terrain, vegetation and infrastructure. These above-ground features need to be removed to create a DSM/DEM with good representation of the bare ground. In recent years, many techniques including both pre- and post-processing of DSMs, were developed for vegetation removal with varied success. This research focuses on applying and comparing various vegetation removal methods using point clouds generated of the Basin 6 pilot study area. The 3D RGB-based point cloud classification using Python scripts was a modification of the procedure by Themistocleous (2019). The method using Liblas classifies the point cloud three-dimensionally, whereas the method by Themistocleous (2019) is two-dimensional. The preliminary result of the method using Liblas, however, still had a large amount of vegetation remaining compared to the Pix4D Machine Learning method. The vegetation layer remains highly visible in the DEMs processed using the vegetation indices as opposed to the Pix4D Machine Learning method, which produces a DEM where mostly bare ground is seen. Further modifications to the input parameters are required to improve the vegetation vs. bare ground classification using this approach. The next step will be to improve the method using Liblas and to also test other vegetation removal methods found in the literature review to compare them against the two described here.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗