SEARCH · Engineering Papers

Results for “image generation”

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 1,153 records · Page 64

All sources NASA NTRS DOE OSTI

DOE OSTI2026

PFLOTRAN modeling data and scripts associated with “Refining the Hydrogeologic Framework of a Large River Corridor Model Using Waterborne Transient Electromagnetics”

NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the publication “Refining the Hydrogeologic Framework of a Large River Corridor Model Using Waterborne Transient Electromagnetics” submitted to Water Resources Research (Terry et al. 2025). The data package contains the groundwater modeling dataset from PFLOTRAN software. It includes the python script for mesh generation, boundary condition setting, PFLOTRAN input deck formation and postprocessing. It couples groundwater flow and species transport for Hanford Reach river corridor and pipelines the model generation and processing. This model can be used to easily generate the model and analysis for Hanford site. It can also be adjusted to other hydrologic area with ease. For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About. The data package consists of 6 folders: (1) “data” contains all necessary data as input and intermediate data for processing; (2) “mesh” contains all mesh related files to generate mesh in Hanford Reach river corridor; (3) “model_run” contains the generated script for PFLOTRAN modeling; (4) “notebooks” contains all the Python script to generate the model; (5) “output” contains all the output from the computation; (6) “postprocessing” contains the Python script to generate scientific figure for manuscript. All files are .csv (comma-separated values), .h5 (HDF5 format), .in (input files), .ipynb (Jupyter notebooks), .p (Python pickle), .png (images), .PNG (images), .py (Python scripts), .pyc (Python bytecode), .r (R scripts), .sh (shell scripts), .txt (text files), .vtu (3D mesh/visualization format), .xz (compressed archive), or .zip (compressed archive).

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Optimization of WAAM Process to Produce AUSC Components with Increased Service Life

Additive manufacturing has the potential to revolutionize industrial hardware and unlock efficiency gains through the fabrication of geometries and architectures not possible by conventional processing. Wire Arc Additive manufacturing (WAAM) process is a class of directed energy deposition process enabling higher build rate and allowing custom wire feedstock allowing spatial variation of microstructure. The larger spot size and lower speed creates a larger melt pool, reducing residual stress and often time creating directional/columnar microstructure for Ni-superalloy. The use of flexible platform provides freedom in deposition strategy, which can accommodate complex substrates, including feature addition onto existing structures, non-flat layers, and repair methods. However, the certification of the final component needs to match the strength requirement. Hence, the quality of the component produced is stringently monitored to avoid buildup of residual stress, cracks, porosity and to reduce detrimental segregated phases commonly observed during alloy solidification. Simulation plays a huge role in predicting the melt pool dimension and can be used to optimize the process parameter. Similar development is also required to perform physics-based modeling of microstructural development in WAAM that can predict the microstructural features during solidification and can be used to optimize the process more effectively. To move toward this goal, Raytheon Technologies Research Center together with Siemens worked to create a set of computational tools to control the process parameters, enable on-line measurements and acquisition with feedback to the optimized process parameters, and eventually track material evolution through each step of the additive process. Computational fluid dynamics is used for accurate prediction and calibration of the thermal field during WAAM process. and phase field models for microstructure evolution as a function of processing parameters to establish a connection between additive parameters and the final microstructure. Here we report cellular automata (CA) model development to predict the dendritic microstructure evolution with surface and bulk nuclei for single track and multiple layers. The CA model was developed to account for secondary element addition and predict segregation, local melting, and latent heat release as well as prediction of Euler angles from orientation information and validated against experiments. This framework was utilized to tailor spatially-varying composition in a part by appropriately controlling the microstructure evolution during the additive process. Functionally graded Haynes 282 alloy with high Cr content at the surface was tested for oxidation and mechanical properties. An advanced physics-based reaction-diffusion model predicting the simultaneous creation of chromium oxide and alumina is developed and validated to extend life expectancy of the WAAM manufactured high temperature part. A machine-learning data-driven framework establishing the process-structure relationship from a dataset of real microstructure images and corresponding process history data has been developed and implemented in the NX Siemens design system. The digital twin configuration along with the tool path generation enabled prediction of WAAM component buildup time and the techno-economic analysis provided a favorable option for all 4 cases with 15-40% cost reduction.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2025

Optical Test Bench (SYSM 5620 Final Report)

The National Ignition Facility (NIF) is a research facility that focuses on High Energy Density Science and Inertial Confinement Fusion. In the NIF, 192 laser beams are directed into a miniscule Target Capsule to generate an implosion – this is called a NIF Shot. Many NIF Users conduct experiments using different Targets and laser inputs to generate reactions that are of interest to the scientific community. Those reactions are monitored using various Target Diagnostic instruments, including Shot Time Photography – which provides crucial images of the Target as the implosion occurs. A subset of these NIF Users is less interested in the reaction itself and more interested in subjecting materials or devices to the intense environment that these reactions can create. Using the Target as a source of x-rays, neutrons, or blast loading for particular materials has been significant to the shock physics community and to those who work in extreme design spaces. However, the Material and Radiation Effects team – that performs these experiments on behalf of the NIF Users – has not been able to make good use of the existing Shot Time Photography Diagnostics. The STP cameras are focused on the Targets rather than the MRE Customers’ materials, the current system is not oriented to have a good view of the MRE Customers’ materials, and the cameras are limited in their capabilities (black and white, poor resolution, etc.). As MRE experiments increase in quantity and importance to the scientific community, the desire for visual monitoring of the experiments to substantiate models and inform other data is also rising.

42 ENGINEERING↗

DOE OSTI2023

How do magnetized HED flows transition to collimated plasma jets? (Final Report)

We present results from a pulsed-power experiment designed to generate accretion-like flows in the laboratory that may be used to study the dynamics of astrophysical accretion-driven outflows. To emulate systems like Young Stellar Object (YSO) outflows, we create radially converging plasma flows in a short disk that transition into much longer bipolar outflows. Our experiment uses a ~1 MA pulsed-power driver to generate plasma from an array of thin aluminum wires mounted to a 3D-printed current path that controls the angular momentum and magnetic field topology. In this paper, we show that experimental data scale favorably to observed properties of YSO jets. This set of experiments tests the simplest version of our possible plasma dynamics, where outflows are generated without rotation or axial magnetic field present. The temperature, velocity and density of the disk and outflows are characterized using interferometry, gated optical and ultraviolet imaging, and Thomson scattering diagnostics. We discuss the Reynolds number, magnetic Reynolds number and Mach numbers calculated in three different stages of the experiment, and compare our results to 3D numerical simulations in the PERSEUS magnetohydrodynamics code. This report is a summary of the work done by the graduate students who were supported by the project.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2024

Bridging the time scale in exascale computing of chemical systems (Final Technical Report)

This report summarizes the work carried out with support of the United States Department of Energy under Award DE-SC0019441. The theme of this project was to develop and apply methods that allowed for the acceleration of atomistic calculations, particularly in challenging areas such as multiphase systems, electrified interfaces, uncertainty estimation, and applications requiring chemical accuracy, which tend to be applications where simulation time is severely bottlenecked by the computational time requirements. Much of the focus was on the application of emerging machine-learning methodologies, although a wide range of methodologies were employed. This report has two major sections. The first focuses on the methodological advances themselves. Within this part, we report a number of major advances, a few examples of which are described here. We report the first machine-learning scheme for the acceleration of electronically grand-canonical calculations (that is, those applicable to electrochemistry). We report new methods of performing transfer learning, in which physics-based priors can be used to provide predictions, often with uncertainty estimates, of images well outside of training sets; we also offer ways to fine-tune these transfer-learning models. We provide a new systematic means to generate and apply minimal training data sets to very large (10,000’s of atoms) systems, with only small training sets appropriate for electronic structure. We developed new methodologies to integrate surface vibrations into surface adsorption calculations. We made advances to the applicability of diffusion Monte Carlo methods to allow (learned) force prediction, finite-size error correction, and force-free means of searching for transition states. We integrated machine-learned atomistic predictions into mechanism generation codes. Additionally, we released new software including AmpTorch, a modernized version of our original atomistic machine-learning code Amp. The second part of this report focuses on the scientific applications that accompanied, and were often enabled by, the methodological advances described earlier. A few examples follow, but full details are in the individual chapters of the report. For example, we developed a general theory of phonon-induced friction on molecular adsorbates. We showed fundamentally how solvent influences the adsorption and desorption process and how it differs from the processes typically involved at the solid–gas interface, making aqueous-phase and electrocatalysis different from traditional thermocatalysis. We examined how metal–insulator and magnetic transitions can be probed, and accelerated exciton dynamics via Frenkel Hamiltonian parameters. We showed that the nearsighted force-training approach, developed within this project, can predict both the stability and reactivity of large nanoparticles, and can also lead to insights on catalyst coverage on binding energies and entropies. These applied studies, which generally integrated with our method development, allowed us to push forward the theoretical understanding of several reaction classes.

08 HYDROGEN↗

DOE OSTI2021

Open Data and Deep Semantic Segmentation for Automated Extraction of Building Footprints

Advances in machine learning and computer vision, combined with increased access to unstructured data (e.g., images and text), have created an opportunity for automated extraction of building characteristics, cost-effectively, and at scale. These characteristics are relevant to a variety of urban and energy applications, yet are time consuming and costly to acquire with today’s manual methods. Several recent research studies have shown that in comparison to more traditional methods that are based on features engineering approach, an end-to-end learning approach based on deep learning algorithms significantly improved the accuracy of automatic building footprint extraction from remote sensing images. However, these studies used limited benchmark datasets that have been carefully curated and labeled. How the accuracy of these deep learning-based approach holds when using less curated training data has not received enough attention. The aim of this work is to leverage the openly available data to automatically generate a larger training dataset with more variability in term of regions and type of cities, which can be used to build more accurate deep learning models. In contrast to most benchmark datasets, the gathered data have not been manually curated. Thus, the training dataset is not perfectly clean in terms of remote sensing images exactly matching the ground truth building’s foot-print. A workflow that includes data pre-processing, deep learning semantic segmentation modeling, and results post-processing is introduced and applied to a dataset that include remote sensing images from 15 cities and five counties from various region of the USA, which include 8,607,677 buildings. The accuracy of the proposed approach was measured on an out of sample testing dataset corresponding to 364,000 buildings from three USA cities. The results favorably compared to those obtained from Microsoft’s recently released US building footprint dataset.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Correlated spin-wave generation and domain-wall oscillation in a topologically textured magnetic film

Spin waves, or magnons, are essential for next-generation energy-efficient spintronics and magnonics. Yet, visualizing spin-wave dynamics at nanoscale and microwave frequencies remains a formidable challenge due to the lack of spin-sensitive, time-resolved microscopy. Here, in this study, we report a breakthrough in imaging dipole-exchange spin waves in a ferromagnetic film owing to the development of laser-free ultrafast Lorentz electron microscopy, which is equipped with a microwave-mediated electron pulser for high spatiotemporal resolution. Using topological spin textures, we captured the emission, propagation, reflection and interference of spin waves from spin anti-vortices under radio-frequency excitations. Remarkably, we show that spin-wave generation is closely tied to the oscillatory motion of specific magnetic domain walls, providing the missing link between wave emission and wall dynamics near magnetic singularities. This work opens new possibilities in magnonics, offering a nanoscopic view of spin dynamics via transmission electron microscopy and enabling controlled excitation via radio-frequency fields for exploring non-equilibrium states in magnetic and multiferroic systems.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

DOE OSTI2025

System Engineers and Decisions: It?s All about Knowledge

In order to guarantee that a system meets adequate levels of reliability and availability, system performances are continuously monitored and analyzed thanks to the technological advancements driving the Industry 4.0 revolution. An Industry 4.0 approach is typically based on advanced statistical, big data mining, machine learning, and internet-of-things methods designed to detect anomalies in the behavior of system, detect the most likely failure modes, and provide indications to system engineers on when maintenance activities should be performed before system performance are deemed unacceptable (which can be generated by diagnostic and prognostic methods). However, these analyses, which are designed to automatize and increase the efficacy of the system maintenance program, require large amount of data which can come in various forms: numeric, textual, images, sounds etc. Such data constitutes the historic knowledge benchmark to track system performances and support system engineer decisions. Here we claim that data is not sufficient to support this kind of analyses when applied to systems characterized by complex architectures and behaviors. Robust system engineer decisions require the ability to understand the system operational context that lies behind the observed data elements. In this respect, system models are in fact necessary to “put data in context” and capture relationships between data elements. Industry 4.0 methods require in fact contextual knowledge as a basis upon which hypotheses can be generated and assumptions tested. In our view, for complex systems, model-based system engineering (MBSE) models can afford this contextual knowledge, as they are typically used to describe systems architecture and dynamic behaviors. System knowledge is here intended as the blending of collected data and system architecture which takes the form of a “knowledge graph”. A knowledge graph is a database which consists of a large set of nodes (in our case an entity can be either a data or an MBSE element) which are linked to each other. The types of nodes and links follow a pre-defined topology, sometimes also refers as an ontology, that is designed to fit the actual decisions that needs to be performed. We show here how a knowledge graph can be defined to support system engineer maintenance decisions and how the same graph can be built based on system MBSE models and pre-processed data from numeric (through anomaly detections and diagnostic methods) and textual elements (through technical language processing TLP).

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Exploration of Water Jets in Supersonic Crossflow Using X-Ray Diagnostics

Here, near-field structures of pure- and aerated-liquid jets injected into Mach 2 crossflow environments were experimentally investigated at the 7-BM beamline of the Advanced Photon Source at Argonne National Laboratory using high-speed shadowgraph imaging, high-speed x-ray imaging, and pathlength-integrated x-ray fluorescence. Liquid was flush injected into a blowdown supersonic wind tunnel. Test section top and side windows were fitted with a polycarbonate plate for high x-ray transmittance. An axisymmetric aerated-liquid injector was fitted with an exchangeable nozzle adaptor to generate a liquid jet. Water and nitrogen, the gas used for aerated-liquid jets, were doped with specially selected dopants to facilitate x-ray measurements. Liquid column structures for a pure-liquid jet, typically masked by dense droplet clouds in a supersonic crossflow environment, were visualized with the present x-ray imaging setup. Surface-wave formation, movement, and transformation on the column windward surface of the pure-liquid jet, along with column deformation and breakup processes, were qualitatively characterized. We measured time-averaged line-of-sight (LOS) liquid mass distributions within the liquid jet near fields. Cross-sectional liquid column contours of pure-liquid jets at various deformation stages were reconstructed from LOS liquid mass distributions. The pure-liquid jet deformed liquid column reached a maximum width of 1.47 times the orifice diameter before exhibiting rapid mass removal. We also observed the plume-crossing phenomenon in the aerated-liquid jet.

47 OTHER INSTRUMENTATION↗

DOE OSTI2022

Diffraction enhanced imaging utilizing a laser produced x-ray source

Image formation by Fresnel diffraction utilizes both absorption and phase-contrast to measure electron density profiles. The low spatial and spectral coherence requirements allow the technique to be performed with a laser-produced x-ray source coupled with a narrow slit. This makes it an excellent candidate for probing interfaces between materials at extreme conditions, which can only be generated at large-scale laser or pulsed power facilities. Here, we present the results from a proof-of-principle experiment demonstrating an effective ~2 μm laser-generated source at the OMEGA Laser Facility. This was achieved using slits of 1 × 30 μm 2 and 2 × 40 μm 2 geometry, which were milled into 30 μm thick Ta plates. Combining these slits with a vanadium He-like 5.2 keV source created a 1D imaging system capable of micrometer-scale resolution. The principal obstacles to achieving an effective 1 μm source are the slit tilt and taper—where the use of a tapered slit is necessary to increase the alignment tolerance. We demonstrate an effective source size by imaging a 2 ± 0.2 μm radius tungsten wire.

3D printing↗

DOE OSTI2024

Dimensionally Aligned Signal Projection Algorithms Library

Dimensionally aligned signal projection (DASP) algorithms are used to analyze fast Fourier transforms (FFTs) and generate visualizations that help focus on the harmonics for specific signals. At a high level, these algorithms extract the FFT segments around each harmonic frequency center, and then align them in equally sized arrays ordered by increasing distance from the base frequency. This allows for a focused view of the harmonic frequencies, which, among other use cases, can enable machine learning algorithms to more easily identify salient patterns. This work seeks to provide an effective open-source implementation of the DASP algorithms proposed by Vann et al. (2018) as well as functionality to help explore and test how these algorithms work with an interactive dashboard and signal-generation tool. The DASP library is implemented in Python and contains four types of algorithms for implementing these feature engineering techniques: fixed harmonically aligned signal projection (HASP), decimating HASP, interpolating HASP, and frequency aligned signal projection (FASP). Each algorithm returns a numerical array, which can be visualized as an image. The HASP algorithms are variations of the algorithms originally presented by Vann et al. (2018). For consistency, FASP, which is the terminology used for the short-time Fourier transform (STFT), has been implemented as part of the library to provide a similar interface to the STFT of the raw signal. Additionally, the library contains an algorithm to generate artificial signals with basic customizations such as the base frequency, sample rate, duration, number of harmonics, noise, and number of signals. Finally, the library provides multiple interactive visualizations, each of which is implemented using IPyWidgets and works in a Jupyter environment. A dashboard-style visualization is provided, which contains some common signal-processing visual components (signal, FFT, spectogram) updating in unison with the HASP functions (see Figure 1 below). Separate from the dashboard, an independent visualization is provided for each of the DASP algorithms as well as for the artifical signal generator. These visualizations are included in the library to aid in developing an intuitive understanding how the algorithms are affected by different input signals and parameter selections.

harmonics↗

DOE OSTI2020

Advancing Fusion with Machine Learning Research Needs Workshop Report

Abstract Machine learning and artificial intelligence (ML/AI) methods have been used successfully in recent years to solve problems in many areas, including image recognition, unsupervised and supervised classification, game-playing, system identification and prediction, and autonomous vehicle control. Data-driven machine learning methods have also been applied to fusion energy research for over 2 decades, including significant advances in the areas of disruption prediction, surrogate model generation, and experimental planning. The advent of powerful and dedicated computers specialized for large-scale parallel computation, as well as advances in statistical inference algorithms, have greatly enhanced the capabilities of these computational approaches to extract scientific knowledge and bridge gaps between theoretical models and practical implementations. Large-scale commercial success of various ML/AI applications in recent years, including robotics, industrial processes, online image recognition, financial system prediction, and autonomous vehicles, have further demonstrated the potential for data-driven methods to produce dramatic transformations in many fields. These advances, along with the urgency of need to bridge key gaps in knowledge for design and operation of reactors such as ITER, have driven planned expansion of efforts in ML/AI within the US government and around the world. The Department of Energy (DOE) Office of Science programs in Fusion Energy Sciences (FES) and Advanced Scientific Computing Research (ASCR) have organized several activities to identify best strategies and approaches for applying ML/AI methods to fusion energy research. This paper describes the results of a joint FES/ASCR DOE-sponsored Research Needs Workshop on Advancing Fusion with Machine Learning, held April 30–May 2, 2019, in Gaithersburg, MD (full report available at https://science.osti.gov/-/media/fes/pdf/workshop-reports/FES_ASCR_Machine_Learning_Report.pdf ). The workshop drew on broad representation from both FES and ASCR scientific communities, and identified seven Priority Research Opportunities (PRO’s) with high potential for advancing fusion energy. In addition to the PRO topics themselves, the workshop identified research guidelines to maximize the effectiveness of ML/AI methods in fusion energy science, which include focusing on uncertainty quantification, methods for quantifying regions of validity of models and algorithms, and applying highly integrated teams of ML/AI mathematicians, computer scientists, and fusion energy scientists with domain expertise in the relevant areas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2022

Radiolabeling and in vitro studies of scandium-44 with HOPO chelator for PET imaging

44 Sc has been attracting interest as a clinically viable PET (positron emission tomography) imaging radionuclide due to its high positron branching ratio, 3.97 hour half-life, ideal positron energy of 632 keV and ability to be produced from a generator as well as from a cyclotron. Scandium is also of interest since the coordination is similar to the lanthanides and Ga 3+ that have demonstrated labeling methods. Further, 47 Sc (a potential therapeutic radionuclide) can serve as a matched isotope pair for theranostic applications. While the labeling studies of 44 Sc with DOTA and DOTA derivatives are quite extensive, there is little data on complexation of scandium with the chelator 3,4,3-(LI-1,2-HOPO). This ligand has been used successfully to radiolabel 89 Zr where it was shown to have high stability in vivo. Additionally, preliminary studies with 86 Y, and non-radioactive scandium show promising complexation constants similar to those found with DOTA derivatives. One major advantage of using HOPO is that radiolabeling can be achieved at room temperature while DOTA requires elevated temperatures, that may be detrimental when radiolabeling biomolecules. Radiolabeling of generator produced 44 Sc versus cyclotron produced 44 Sc is also under investigation as there are currently several different post-elution purification methods of generator 44 Sc, and the potential radiolabeling complications of these eluents has not yet been studied. This work focuses on radiolabeling HOPO with generator produced 44 Sc and the in vitro and radioanalytical evaluation of the resulting complexes.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2021

Giant nonlinear optical responses from photon-avalanching nanoparticles

Avalanche phenomena use steeply nonlinear dynamics to generate disproportionately large responses from small perturbations, and are found in a multitude of events and materials. Photon avalanching enables technologies such as optical phase-conjugate imaging, infrared quantum counting and efficient upconverted lasing. However, the photon-avalanching mechanism underlying these optical applications has been observed only in bulk materials and aggregates, limiting its utility and impact. In this study we report the realization of photon avalanching at room temperature in single nanostructures-small, Tm 3+ -doped upconverting nanocrystals-and demonstrate their use in super-resolution imaging in near-infrared spectral windows of maximal biological transparency. Avalanching nanoparticles (ANPs) can be pumped by continuous-wave lasers, and exhibit all of the defining features of photon avalanching, including clear excitation-power thresholds, exceptionally long rise time at threshold, and a dominant excited-state absorption that is more than 10,000 times larger than ground-state absorption. Beyond the avalanching threshold, ANP emission scales nonlinearly with the 26th power of the pump intensity, owing to induced positive optical feedback in each nanocrystal. This enables the experimental realization of photon-avalanche single-beam super-resolution imaging with sub-70-nanometre spatial resolution, achieved by using only simple scanning confocal microscopy and without any computational analysis. Pairing their steep nonlinearity with existing super-resolution techniques and computational methods, ANPs enable imaging with higher resolution and at excitation intensities about 100 times lower than other probes. The low photon-avalanching threshold and excellent photostability of ANPs also suggest their utility in a diverse array of applications, including sub-wavelength imaging and optical and environmental sensing.

36 MATERIALS SCIENCE↗

DOE OSTI2024

Low latency optical-based mode tracking with machine learning deployed on FPGAs on a tokamak

Active feedback control in magnetic confinement fusion devices is desirable to mitigate plasma instabilities and enable robust operation. Optical high-speed cameras provide a powerful, non-invasive diagnostic and can be suitable for these applications. Here, in this study, we process high-speed camera data, at rates exceeding 100 kfps, on in situ field-programmable gate array (FPGA) hardware to track magnetohydrodynamic (MHD) mode evolution and generate control signals in real time. Our system utilizes a convolutional neural network (CNN) model, which predicts the n = 1 MHD mode amplitude and phase using camera images with better accuracy than other tested non-deep-learning-based methods. By implementing this model directly within the standard FPGA readout hardware of the high-speed camera diagnostic, our mode tracking system achieves a total trigger-to-output latency of 17.6 μs and a throughput of up to 120 kfps. This study at the High Beta Tokamak-Extended Pulse (HBT-EP) experiment demonstrates an FPGA-based high-speed camera data acquisition and processing system, enabling application in real-time machine-learning-based tokamak diagnostic and control as well as potential applications in other scientific domains.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2025

DeepLensSBI: Deep inference of simulated strong lenses in ground-based surveys

This code is used to train and test machine learning models and generate results and plots presented in 2501.08524 [astro-ph.IM]. The code is written in python. The goal of this work is to train ML models trained on simulated images of strong gravitational lenses. The trained model can then quickly infer properties of the lensed objects with uncertainty quantification.

Poh, Jason [Univ. of Chicago, IL (United States)] ↗

DOE OSTI2021

Attribute-Guided Adversarial Training for Robustness to Natural Perturbations

We report while existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real world settings. In many such cases although test data might not be available, broad specifications about the types of perturbations (such as an unknown degree of rotation) may be known. We consider a setup where robustness is expected over an unseen test domain that is not i.i.d. but deviates from the training domain. While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes. We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space, without having access to the data from the test domain. Our adversarial training solves a min-max optimization problem, with the inner maximization generating adversarial perturbations, and the outer minimization finding model parameters by optimizing the loss on adversarial perturbations generated from the inner maximization. We demonstrate the applicability of our approach on three types of naturally occurring perturbations --- object-related shifts, geometric transformations, and common image corruptions. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations. We demonstrate the usefulness of the proposed approach by showing the robustness gains of deep neural networks trained using our adversarial training on MNIST, CIFAR-10, and a new variant of the CLEVR dataset.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

AI Denoising to Accelerate Detector Simulation

Detector simulation is critical to experimental HEP; however this simulation (commonly done through toolkits such as Geant4) is computationally intensive. Performance can be improved somewhat through technical optimization, but more is needed. Using machine learning (ML) to accelerate simulation is a promising field, however efforts to use generative adversarial networks (GANs) or optimized autoencoders have faced issues. Using convolutional neural networks (CNNs) for denoising has been successful in non-HEP applications such as image processing. This poster investigates the efficacy of using CNNs to denoise Geant4 simulations. This could increase the accuracy of simulations performed under settings designed to increase computational efficiency.

Franklin, Lena↗