Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “training data quality”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks : *Full/Regular Research Paper submission for the symposium CSCI-ISAI: Artificial Intelligence

We use a stable parallel approach to train Wasserstein Conditional Generative Adversarial Neural Networks (W-CGANs). The parallel training reduces the risk of mode collapse and enhances scalability by using multiple generators that are concurrently trained, each one of them focusing on a single data label. The use of the Wasserstein metric reduces the risk of cycling by stabilizing the training of each generator. We apply the approach on the CIFAR10 and the CIFAR100 datasets, two standard benchmark datasets with images of the same resolution, but different number of classes. Performance is assessed using the inception score, the Fréchet inception distance, and image quality. An improvement in inception score and Fréchet inception distance is shown in comparison to previous results obtained by performing the parallel approach on deep convolutional conditional generative adversarial neural networks (DC-CGANs). Weak scaling is attained on both datasets using up to 100 NVIDIA V100 GPUs on the OLCF supercomputer Summit.

Lupo Pasini, Massimiliano↗
DOE OSTI2024

Comparative Performance of Three Eye-Tracking Devices in Detection of Mild Traumatic Brain Injury in Acute Versus Chronic Subject Populations

ABSTRACT Introduction Presently, traumatic brain injury (TBI) triage in field settings relies on symptom-based screening tools such as the updated Military Acute Concussion Evaluation. Objective eye-tracking may provide an alternative means of neurotrauma screening due to sensitivity to neurotrauma brain-health changes. Previously, the US Army Medical Research and Development Command Non-Invasive NeuroAssessment Devices (NINAD) Integrated Product Team identified 3 commercially available eye-tracking devices (SyncThink EYE-SYNC, Oculogica EyeBOX, NeuroKinetics IPAS) as meeting criteria toward being operationally effective in the detection of TBI in service members. We compared these devices to assess their relative performance in the classification of mild traumatic brain injury (mTBI) subjects versus normal healthy controls. Materials and Methods Participants 18 to 45 years of age were assigned to Acute mTBI, Chronic mTBI, or Control group per study criteria. Each completed a TBI assessment protocol with all 3 devices counterbalanced across participants. Acute mTBI participants were tested within 72 hours following injury whereas time since last injury for the Chronic mTBI group ranged from months to years. Discriminant analysis was undertaken to determine device classification performance in separating TBI subjects from controls. Area Under the Curves (AUCs) were calculated and used to compare the accuracy of device performance. Device-related factors including data quality, the need to repeat tests, and technical issues experienced were aggregated for reporting. Results A total of 63 participants were recruited as Acute mTBI subjects, 34 as Chronic mTBI subjects, and 119 participants without history of TBI as controls. To maximize outcomes, poorer quality data were excluded from analysis using specific criteria where possible. Final analysis utilized 49 (43 male/6 female, mean [x̅] age = 24.3 years, SD [s] = 5.1) Acute mTBI subjects, and 34 (33 male/1 female, x̅ age = 38.8 years, s = 3.9) Chronic mTBI subjects were age- and gender-matched as closely as possible with Control subjects. AUCs obtained with 80% of total dataset ranged from 0.690 to 0.950 for the Acute Group and from 0.753 to 0.811 for the Chronic mTBI group. Validation with the remaining 20% of dataset produced AUCs ranging from 0.600 to 0.750 for Acute mTBI group and 0.490 to 0.571 for the Chronic mTBI group. Conclusions Potential eye-tracking detection of mTBI, per training model outcomes, ranged from acceptable to excellent for the Acute mTBI group; however, it was less consistent for the Chronic mTBI group. The self-imposed targeted performance (AUC of 0.850) appears achievable, but further device improvements and research are necessary. Discriminant analysis models differed for the Acute versus Chronic mTBI groups, suggesting performance differences in eye-tracking. Although eye-tracking demonstrated sensitivity in the Chronic group, a more rigorous and/or longitudinal study design is required to evaluate this observation. mTBI injuries were not controlled for this study, potentially reducing eye-tracking assessment sensitivity. Overall, these findings indicate that while eye-tracking remains a viable means of mTBI screening, device-specific variability in data quality, length of testing, and ease of use must be addressed to achieve NINAD objectives and DoD implementation.

General & Internal Medicine↗
DOE OSTI2024

Tetris-inspired detector with neural network for radiation mapping

Abstract Radiation mapping has attracted widespread research attention and increased public concerns on environmental monitoring. Regarding materials and their configurations, radiation detectors have been developed to identify the position and strength of the radioactive sources. However, due to the complex mechanisms of radiation-matter interaction and data limitation, high-performance and low-cost radiation mapping is still challenging. Here, we present a radiation mapping framework using Tetris-inspired detector pixels. Applying inter-pixel padding for enhancing contrast between pixels and neural networks trained with Monte Carlo (MC) simulation data, a detector with as few as four pixels can achieve high-resolution directional prediction. A moving detector with Maximum a Posteriori (MAP) further achieved radiation position localization. Field testing with a simple detector has verified the capability of the MAP method for source localization. Our framework offers an avenue for high-quality radiation mapping with simple detector configurations and is anticipated to be deployed for real-world radiation detection.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Selection of high-redshift Lyman-Break Galaxies from broadband and wide photometric surveys

In this paper, we investigate the possibility of selecting high-redshift Lyman-Break Galaxies (LBG) using current and future broadband wide photometric surveys, such as the Ultraviolet Near Infrared Optical Northern Survey (UNIONS) or the Vera C. Rubin Legacy Survey of Space and Time (LSST), using a Random Forest algorithm. This work is conducted in the context of future large-scale structure spectroscopic surveys like DESI-II, the next phase of the Dark Energy Spectroscopic Instrument (DESI), which will start around 2029.We use deep imaging data from the Hyper Suprime Camera (HSC) and the Canada-France-Hawaii Telescope Large Area U-band Deep Survey (CLAUDS) on the COSMOS and XMM-LSS fields. To predict the selection performance of LBGs with image quality similar to UNIONS, we degrade the u,g,r,i and z bands to UNIONS depth.The Random Forest algorithm is trained with the u,g,r,i and z bands to classify LBGs in the 2.5 < z < 3.5 range.We find that fixing a target density budget of 1,100 deg$^{-2}$, the Random Forest approach gives a density of z > 2 targets of 873 deg$^{-2}$, and a density of 493 deg$^{-2}$ of confirmed LBGs after spectroscopic confirmation with DESI. This UNIONS-like selection was tested in a dedicated spectroscopic observation campaign of 1,000 targets with DESI on the COSMOS field, providing a safe spectroscopic sample with a mean redshift of 3. This sample is used to derive forecasts for DESI-II, assuming a sky coverage of 5,000 deg$^{2}$. We predict uncertainties on Alcock-Paczynski parameters α$_{⊥}$ and α$_{∥}$ to be 0.7% and 1% for 2.6 < z < 3.2, resulting in a potential 2% measurement of the dark energy fraction at high redshift. Additionally, we estimate the uncertainty in local non-Gaussianity and predict σ$_{fNL}$ ≈ 7, which would be comparable to the current best precision achieved by Planck. The latter forecast suggests that achieving the precision required to place stringent constraints on inflationary models (σ$_{fNL}$ ≈ 1) using spectroscopic galaxy surveys necessitates the development of a next-generation (Stage V) spectroscopic survey.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2022

Ideas on the NASA Senior Review and Mission Extension Process

Extended mission budgets fund a significant part of our community, particularly young scientists who in a relatively short time are exposed to a broad range of experiences and opportunities available in space science and other STEM fields. In particular, mission-funded science offers a relatively stable funding stream that enables meaningful mentoring efforts and interactions, including apprenticeships ranging from project management, to mission operations, to data processing and analysis, to hardware and software development, to STEM-related education and outreach. It moreover provides professional contacts that fuel diversity in mission leadership and in the science and technical workforce at-large. Last but not least, it sustains the scientific productivity of NASA’s missions, which constitute major national investments meriting their full exploitation. Budgets cuts, however, are exercising pressure on the science and operations of the extended mission fleet despite being only a small portion of the overall Division budget. The history of Heliophysics has demonstrated that maintaining the operation of missions beyond their prime phase invariably leads to a much deeper knowledge of the original mission science goals, together with new applications often not foreseen during their original design. Their operation as part of the Heliophysics System Observatory (HSO)---a coordinated, 1eliophysics, multipoint observing system of the heliosphere, is a prime example. Some of the first activities undertaken by the Parker Solar Probe and Solar Orbiter missions required recreating the larger context of their new observations by using the diversity of HSO mission capabilities. The marginal cost of maintaining this valuable, working science resource, in the form of both continuing high quality data access and expertise, is small compared to the cost of the original missions or of new missions to achieve similar objectives, making the operation of extended missions, the best “science per dollar” investment in Heliophysics. We argue that reducing both extended mission operations and science budgets will have a ripple effect across the community, including reducing employment and training opportunities for young scientists, to lowering the quality/impact of the Heliophysics Systems Observatory. Instead, we suggest that the proposal process for mission extension should be re-examined. We offer several ideas for reducing costs of extended missions toward maintaining science output and streamlining the management process.

A. Vourlidas↗
NASA NTRSDate not supplied

Neural Network Atmospheric Correction of Remote Sensing Imagery Over Water Using a Synthetic Dataset

Remote sensing atmospheric correction methods have primarily focused on imagery over land. However, accurate correction over water is important for monitoring and research of aquatic environments. More research in this area is ongoing, though one of the biggest challenges is enough quality data to develop and validate correction methods. This is especially true for neural network (NN) -based models which have shown promise in this area given enough quality data. To address this deficiency of data, we are leveraging a synthetic dataset produced by a model called SWIPE that uses radiative transfer modeling to simulate the atmospheric effects on water-leaving (WL) reflectance to estimate top-of-atmosphere (TOA) reflectance. This allows us to produce almost unlimited pairs of WL reflectance and corresponding TOA reflectance for model training across a variety of atmospheric conditions. We use two approaches for our atmospheric correction model. One uses a conditional variational autoencoder (VAE) to estimate a single WL reflectance value from a single TOA reflectance value. The second is based on a UNET architecture and estimates an array of WL reflectance values from an array of TOA reflectance values. The goal of the second method is to capture atmospheric effects that occur spatially between values within the array as compared to the first method.

deep learning↗
DOE OSTI2025

Laser powder bed fusion parameter estimation with k-NN

Abstract Laser powder bed fusion (L-PBF) is a technique within additive manufacturing that uses a high power density laser to build parts from fused powdered metal alloy. This technology is well equipped to produce complex parts with otherwise impossible features, such as hidden voids or lattice structures. Alongside capability, reliability and quality are key characteristics considered when choosing a manufacturing method, and these are gaining attention as this method becomes more prevalent in industry. One main indicator of a stable L-PBF process is consistent melt pool geometry, and the properties of which are likely to determine the quality of the part produced. As computing power and sensing technologies become more advanced, this melt pool geometry could be studied in real time. This work addresses the challenge by leveraging a k-nearest neighbor (k-NN) model to identify key features within melt pool imagery and predict the energy density. The k-NN model was trained on data provided by the National Institute of Standards and Technology (NIST). Data preprocessing was performed on the images to extract features that were used in the k-NN model. This approach was used to accurately infer the energy density of unseen layers within the same part. The algorithm was subsequently tested with unique scan strategies and found to reasonably estimate the energy density of different parts. A fivefold cross validation found the algorithm to be consistently predicting the class of 91.4% of the in situ melt pool images.

Jung, Patrick (ORCID:0000000267890859)↗
DOE OSTI2025

Selection of high-redshift Lyman-Break Galaxies from broadband and wide photometric surveys

Here, in this paper, we investigate the possibility of selecting high-redshift Lyman-Break Galaxies (LBG) using current and future broadband wide photometric surveys, such as the Ultraviolet Near Infrared Optical Northern Survey (UNIONS) or the Vera C. Rubin Legacy Survey of Space and Time (LSST), using a Random Forest algorithm. This work is conducted in the context of future large-scale structure spectroscopic surveys like DESI-II, the next phase of the Dark Energy Spectroscopic Instrument (DESI), which will start around 2029. We use deep imaging data from the Hyper Suprime Camera (HSC) and the Canada-France-Hawaii Telescope Large Area U-band Deep Survey (CLAUDS) on the COSMOS and XMM-LSS fields. To predict the selection performance of LBGs with image quality similar to UNIONS, we degrade the u,g,r,i and z bands to UNIONS depth. The Random Forest algorithm is trained with the u,g,r,i and z bands to classify LBGs in the 2.5 < z < 3.5 range. We find that fixing a target density budget of 1,100 deg -2 , the Random Forest approach gives a density of z > 2 targets of 873 deg -2 , and a density of 493 deg -2 of confirmed LBGs after spectroscopic confirmation with DESI. This UNIONS-like selection was tested in a dedicated spectroscopic observation campaign of 1,000 targets with DESI on the COSMOS field, providing a safe spectroscopic sample with a mean redshift of 3. This sample is used to derive forecasts for DESI-II, assuming a sky coverage of 5,000 deg 2 . We predict uncertainties on Alcock-Paczynski parameters α ⊥ and α ∥ to be 0.7% and 1% for 2.6 < z < 3.2, resulting in a potential 2% measurement of the dark energy fraction at high redshift. Additionally, we estimate the uncertainty in local non-Gaussianity and predict σ fNL ≈ 7, which would be comparable to the current best precision achieved by Planck. The latter forecast suggests that achieving the precision required to place stringent constraints on inflationary models (σ fNL ≈ 1) using spectroscopic galaxy surveys necessitates the development of a next-generation (Stage V) spectroscopic survey.

cosmological parameters from LSS↗
DOE OSTI2025

Performance evaluation of automated data-driven feature extraction and selection methods for practical and scalable building energy consumption prediction models

Here, this study quantifies the impact of automated feature engineering methods (feature extraction and selection) on the quality and accuracy of machine learning models that predict building energy consumption. The case study compares model performance for three main scenarios: baseline (no feature extraction and selection), feature extraction only, and feature extraction combined with feature selection (filter and/or wrapper methods) for fully trained machine learning models for 200 metered/sub-metered energy measurements across 118 real buildings. For consistency, the same machine learning model architecture (a black box deep learning neural network with probabilistic forecast output) was used for all scenarios. Based on results, all feature engineering methods provided noticeable prediction accuracy improvements (e.g., 29%-68% median prediction improvement) compared to baseline scenarios. However, in this application, feature selection methods provide little practical value due to their limited performance gains and high computational cost. Smarter algorithm development supported by better computational environments will be needed before feature selection methods can reliably and efficiently improve predictive model performance.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2014

Global Carbon Monoxide Products from Combined AIRS, TES and MLS Measurements on A-Train Satellites

This study tests a novel methodology to add value to satellite data sets. This methodology, data fusion, is similar to data assimilation, except that the background modelbased field is replaced by a satellite data set, in this case AIRS (Atmospheric Infrared Sounder) carbon monoxide (CO) measurements. The observational information comes from CO measurements with lower spatial coverage than AIRS, namely, from TES (Tropospheric Emission Spectrometer) and MLS (Microwave Limb Sounder). We show that combining these data sets with data fusion uses the higher spectral resolution of TES to extend AIRS CO observational sensitivity to the lower troposphere, a region especially important for air quality studies. We also show that combined CO measurements from AIRS and MLS provide enhanced information in the UTLS (upper troposphere/lower stratosphere) region compared to each product individually. The combined AIRS-TES and AIRS-MLS CO products are validated against DACOM (differential absorption mid-IR diode laser spectrometer) in situ CO measurements from the INTEX-B (Intercontinental Chemical Transport Experiment: MILAGRO and Pacific phases) field campaign and in situ data from HIPPO (HIAPER Pole-to-Pole Observations) flights. The data fusion results show improved sensitivities in the lower and upper troposphere (20-30% and above 20%, respectively) as compared with AIRS-only version 5 CO retrievals, and improved daily coverage compared with TES and MLS CO data.

combined AIRS↗
DOE OSTI2023

Application of unsupervised deep learning to image segmentation and in-situ contact angle measurements in a CO 2 -water-rock system

Rock surface wettability is a critical property that regulates multiphase flows in porous media, which can be quantified using the surface contact angle (CA). X-ray micro-computed tomography (μCT) provides an effective approach to in-situ measurements of surface CAs. However, the CA measurement accuracy depends significantly on the quality of CT image segmentation, which is the clustering of CT pixels into separate phases. Inspired by this, we developed a deep learning (DL)-based CA measurement workflow. Motivated by the recent tremendous progress in unsupervised learning techniques and aiming to avoid expensive manual data annotations, an unsupervised DL pipeline for CT image segmentation was proposed and implemented, which includes unsupervised model training and post-processing. The unsupervised model training was driven by a novel loss function constrained with feature similarity and spatial continuity and implemented by iterative forward and backward paths; the former clustered the pixel-wise feature vectors extracted by convolution neural networks, whereas the latter updated the parameters using gradient descent. An over-segmentation strategy was adopted for model training. The post-processing steps based on agglomerative hierarchical clustering (AHC) were implemented to further merge the over-segmented model output to the desired cluster number, which is intended to improve the efficiency of image segmentation. The developed unsupervised DL pipeline was compared with other commonly-used image segmentation methods using pixel-wise and physics-based evaluation metrics on a synthetic raw-image dataset, which had a known ground truth. The unsupervised DL pipeline showed the best performance. Next, the segmented images were input to an automatic CA measurement tool, and the results were validated by comparisons with manual measurements. The CA values from the manual and automatic measurements showed similar distributions and statistical properties. The automatic measurement demonstrated a wider spectrum because of the much larger number of measurement data points. The primary novelty of the unsupervised DL pipeline developed in this study lies in the novel loss function and the over-segmentation strategy associated with AHC post-processing. Finally, the workflow has been proven an efficient tool for pore-scale wettability characterization, which has a wide range of applications in fundamental studies of multiphase flows in natural porous media, which have critical implications to geological carbon sequestration, hydrocarbon energy recovery, and contaminant transport in groundwater.

42 ENGINEERING↗
NASA NTRSDate not supplied

Growing Beyond Earth: Student Citizen Science Contributing to Space Crop Production

Fairchild Tropical Botanic Garden and NASA have been partnering since 2015 to conduct a citizen science education program for middle and high school students called Growing Beyond Earth (GBE). Growing Beyond Earth is a multi-classroom science project designed to advance NASA’s research on growing plants in space. GBE was implemented locally and scaled nationally under two NASA Grants. Now serving more than 250 schools and over 10,000 middle and high school students nationwide, GBE successfully improved STEM education. It also contributed student-generated data to NASA, improving NASA research on the ground and on ISS, with two student-selected crops grown in space. GBE is unique in its focus on real scientific research, enabling student “citizen scientists” to contribute data toward NASA mission planning. Each classroom receives a Fairchild-designed plant habitat analogous to the plant growing equipment aboard the International Space Station (ISS). Fairchild and NASA scientists train teachers to conduct in-classroom GBE experiments, and students then share experimental data online with NASA. As NASA looks toward a long-term human presence beyond Earth’s orbit, there are specific science, technology, engineering, and math challenges related to food production in space. During this presentation, learn how GBE is addressing those challenges by expanding the diversity and quality of edible plants that can be grown aboard spacecraft. We will share the significant scientific and educational results that have come out of this partnership and explain how we quickly pivoted to allow students to continue to contribute during the COVID-era. Finally, we will explain how on Earth, GBE is also advancing technologies for growing plants in urban, indoor, and other resource-limited settings through the GBE Maker challenge for High School, University, and Professional communities of Makers across the country to develop the next generation of space crop production technologies. These programs are supported by NASA.

Growing Beyond Earth↗
NASA NTRS2003

Flight Test of an Intelligent Flight-Control System

The F-15 Advanced Controls Technology for Integrated Vehicles (ACTIVE) airplane (see figure) was the test bed for a flight test of an intelligent flight control system (IFCS). This IFCS utilizes a neural network to determine critical stability and control derivatives for a control law, the real-time gains of which are computed by an algorithm that solves the Riccati equation. These derivatives are also used to identify the parameters of a dynamic model of the airplane. The model is used in a model-following portion of the control law, in order to provide specific vehicle handling characteristics. The flight test of the IFCS marks the initiation of the Intelligent Flight Control System Advanced Concept Program (IFCS ACP), which is a collaboration between NASA and Boeing Phantom Works. The goals of the IFCS ACP are to (1) develop the concept of a flight-control system that uses neural-network technology to identify aircraft characteristics to provide optimal aircraft performance, (2) develop a self-training neural network to update estimates of aircraft properties in flight, and (3) demonstrate the aforementioned concepts on the F-15 ACTIVE airplane in flight. The activities of the initial IFCS ACP were divided into three Phases, each devoted to the attainment of a different objective. The objective of Phase I was to develop a pre-trained neural network to store and recall the wind-tunnel-based stability and control derivatives of the vehicle. The objective of Phase II was to develop a neural network that can learn how to adjust the stability and control derivatives to account for failures or modeling deficiencies. The objective of Phase III was to develop a flight control system that uses the neural network outputs as a basis for controlling the aircraft. The flight test of the IFCS was performed in stages. In the first stage, the Phase I version of the pre-trained neural network was flown in a passive mode. The neural network software was running using flight data inputs with the outputs provided to instrumentation only. The IFCS was not used to control the airplane. In another stage of the flight test, the Phase I pre-trained neural network was integrated into a Phase III version of the flight control system. The Phase I pretrained neural network provided realtime stability and control derivatives to a Phase III controller that was based on a stochastic optimal feedforward and feedback technique (SOFFT). This combined Phase I/III system was operated together with the research flight-control system (RFCS) of the F-15 ACTIVE during the flight test. The RFCS enables the pilot to switch quickly from the experimental- research flight mode back to the safe conventional mode. These initial IFCS ACP flight tests were completed in April 1999. The Phase I/III flight test milestone was to demonstrate, across a range of subsonic and supersonic flight conditions, that the pre-trained neural network could be used to supply real-time aerodynamic stability and control derivatives to the closed-loop optimal SOFFT flight controller. Additional objectives attained in the flight test included (1) flight qualification of a neural-network-based control system; (2) the use of a combined neural-network/closed-loop optimal flight-control system to obtain level-one handling qualities; and (3) demonstration, through variation of control gains, that different handling qualities can be achieved by setting new target parameters. In addition, data for the Phase-II (on-line-learning) neural network were collected, during the use of stacked-frequency- sweep excitation, for post-flight analysis. Initial analysis of these data showed the potential for future flight tests that will incorporate the real-time identification and on-line learning aspects of the IFCS.

Davidson, Ron↗
NASA NTRS1980

Simulators for Safer Shipping

Each year one ship out of every five afloat collides with another vessel, rams a dock, or runs a ground. CAORF (Computer Aided Operations Research Facility), designed and built by Sperry Rand Corporation, incorporates technology developed in a wide variety of aerospace simulation and technical training programs. CAORF can be set up to duplicate the exact handling qualities of any vessel under various conditions of wind, tide and current. Currently a dozen different ships can be "plugged in." Bridge instrumentation is typical of modern shipboard equipment including radar, internal and external c.ommunications and new collision avoidance systems. From repetitive operation of simulated ships, MarAd is building a valuable data base for improving marine safety.

Source record↗
DOE OSTI2025

Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning

Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. However, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field ($B^{+}_{1}$) inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate $B^{+}_{1}$ inhomogeneity, but remain time-consuming. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000 ​× ​speed-up compared to the traditional MLS method. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel $B^{+}_{1}$ fields. Next, we train a Residual Network (ResNet) to map $B^{+}_{1}$ fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. Comparative evaluations with standard MLS optimization underscore notable gains in both processing speed and predictive accuracy, which indicates that our technique shows a promising solution for addressing persistent inhomogeneity challenges.

Deep learning↗
DOE OSTI2022

Classification and Fusion of Two Disparate Data Streams and Nuclear Dissolutions Application

We consider two streams of data or measurements with disparate qualities and time resolutions that need to be classified. The first stream consists of higher quality data at a coarser time resolution, and the other consists of lower quality data at a finer time resolution. We present a fuser-switch method that fuses the set of classifiers of each stream separately and switches between them. We show that this method provides classification decisions at a finer time resolution with superior detection and false alarm probabilities compared to individual classifiers, under the statistical independence and time resolution ratio conditions. When classifiers are trained using machine learning methods, we show that this superior performance is guaranteed with a confidence probability specified by the classifiers' generalization equations. We use these results to provide analytical foundations for previous practical results that achieved significant performance improvements in classifying Pu/Np target dissolution events at a radiochemical processing facility.

Rao, Nageswara↗
DOE OSTI2025

Enhancing Drinking Water Quality Modeling: Leveraging Physics Informed Neural Networks for Learning with Imperfect Reaction Models and Partial Data

Chemical kinetics models, typically formulated as systems of ordinary or partial differential equations, are valuable tools for simulating drinking water quality. However, these models often face inaccuracies due to discrepancies between the laboratory and the real-world conditions, as well as limitations in experimental analytical methods, hindering the accurate representation of the true underlying chemical mechanisms. In this study, we propose a Physics Informed Neural Network (PINN), using the eXtreme Theory of Functional Connections, to improve the prediction of chemical concentrations over time. The PINN method accounts for imperfect chemical models and incorporates partial data to improve predictions. Focusing on reactions describing water disinfection residual and disinfectant byproduct formation, which are crucial for public health and regulatory compliance, we demonstrate that the PINN model is able to accurately predict the concentrations of chemical species across various pH values. Notably, the model extends its accuracy to predict concentrations of chemical species not originally included in its training data. The developed method can be extended to a variety of chemical systems, offering a wide array of potential applications.

13 HYDRO ENERGY↗
DOE OSTI2025

Online thermal profile prediction for large format additive manufacturing: A hybrid CNN-LSTM based approach

Large format additive manufacturing (LFAM) is an advanced 3D printing technique that efficiently fabricates large-scale components through a layer-by-layer extrusion and deposition process. Accurate surface layer temperature monitoring is essential to prevent manufacturing failures and ensure final product quality. Traditional physics-based offline approaches for simulating thermal behavior are often inefficient and complex, posing challenges on real-time, in-situ monitoring. Here, to address this, we propose a data-driven hybrid CNN-LSTM model to predict sequential thermal images of arbitrary length using real-time infrared thermal imaging. In this approach, a Convolutional Neural Networks (CNN) is trained offline to capture spatial features, reduce dimensional complexity, and enhance time efficiency, while a stacked Long Short-Term Memory (LSTM) is applied online to capture temporal information for improved prediction of future thermal behavior in subsequent printing layers. Model performance is evaluated using MSE, SSIM, and PSNR metrics and is benchmarked against stacked LSTM and convolutional LSTM models, demonstrating superior accuracy and applicability. Additionally, to mitigate noise from moving extruders and gantry backgrounds in thermal images, a fine-tuned semantic segmentation model is implemented offline to extract printing geometry, enabling precise temperature tracking along the tool path for further thermal analysis. The frameworks developed in this study significantly advance temperature monitoring, thermal analysis, and in-situ manufacturing control for LFAM, bridging the gap between theoretical modeling and practical application.

Geometry extraction↗