Search NASA⌕ Search

SEARCH · Search NASA

Results for “Benchmark dataset”

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 649 records · Page 36
All sourcesNASA NTRSDOE OSTI
NASA NTRS2021

Exploring Sentinel-1 and Sentinel-2 diversity for Flood inundation mapping using deep learning

Identification of flood water extent from satellite images has historically relied on either synthetic aperture radar (SAR) or multi-spectral (MS) imagery. MS sensors are limited to cloud free conditions, whereas SAR imagery is plagued by noise-like speckle. Prior studies that use combinations of MS and SAR data to overcome individual limitations of these sensors have not fully examined sensitivity of flood mapping performance to different combinations of SAR and MS derived spectral indices or band transformations in color space. This study explores the use of diverse bands of Sentinel 2 (S2) through well-established water indices and Sentinel 1 (S1) derived SAR imagery along with their combinations to assess their capability for generating accurate flood inundation maps. The robustness in performance of S-1 and S-2 band combinations was evaluated using 446 hand labeled flood inundation images spanning across 11 flood events from Sen1Floods11 dataset which are highly diverse in terms of land cover as well as location. A modified K-fold cross validation approach is used to evaluate the performance of 32 combinations of S1 and S2 bands using a fully connected deep convolutional neural network known as U-Net. Our results indicated that usage of elevation information has improved the capability of S1 imagery to produce more accurate flood inundation maps. Compared to a median F1 score of 0.62 when using only S1 bands, the combined use of S1 and elevation information led to an improved median F1 score of 0.73. Water extraction indices based on S2 bands have a statistically significant superior performance in comparison to S1. Among all the band combinations, HSV (Hue, Saturation, Value) transformation of S2 bands provides a median F1 score of 0.9, outperforming the commonly used water spectral indices owing to HSV’s transformation’s superior contrast distinguishing abilities. Additionally, U-Net algorithm was able to learn the relationship between raw S2 based water extraction indices and their corresponding raw S2 bands, but not of HSV owing to relatively complex computation involved in the latter. Results of the paper establishes important benchmarks for the extension of S1 and S2 data-based flood inundation mapping efforts over large spatial extents.

Goutam Konapala↗
DOE OSTI2022

Tackling the Challenges in Scene Graph Generation With Local-to-Global Interactions

In this work, we seek new insights into the underlying challenges of the scene graph generation (SGG) task. Quantitative and qualitative analysis of the visual genome (VG) dataset implies: 1) ambiguity: even if interobject relationship contains the same object (or predicate), they may not be visually or semantically similar; 2) asymmetry: despite the nature of the relationship that embodied the direction, it was not well addressed in previous studies; and 3) higher-order contexts: leveraging the identities of certain graph elements can help generate accurate scene graphs. Motivated by the analysis, we design a novel SGG framework, Local-to-global interaction networks (LOGINs). Locally, interactions extract the essence between three instances of subject, object, and background, while baking direction awareness into the network by explicitly constraining the input order of subject and object. Globally, interactions encode the contexts between every graph component (i.e., nodes and edges). Finally, Attract and Repel loss is utilized to fine-tune the distribution of predicate embeddings. By design, our framework enables predicting the scene graph in a bottom-up manner, leveraging the possible complementariness. To quantify how much LOGIN is aware of relational direction, a new diagnostic task called Bidirectional Relationship Classification (BRC) is also proposed. Overall, experimental results demonstrate that LOGIN can successfully distinguish relational direction than existing methods (in BRC task), while showing state-of-the-art results on the VG benchmark (in SGG task).

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2014

On-Orbit Radiometric Characterization of OLI (Landsat 8) for Applications in Aquatic Remote Sensing

Landsat-8 carries two separate sensors, namely the Operational Land Imager (OLI) and the Thermal Infrared Radiometer Suite (TIRS), that image the earth surface throughout the visible and thermal portions of the spectrum. Compared to Landsat heritage sensors, the OLI has enhanced features, which include its 12-bit radiometric resolution and the addition of a band centered at 443 nm. The dramatically improved data quality/quantity expands existing applications of Landsat imagery in aquatic sciences from the retrieval of bio-geochemical properties, such as near-surface concentrations of chlorophyll-a (CHL) and total suspended solids (TSS), to benthic mapping. This study offers analysis of OLI's absolute radiometric performance over bodies ofwater using benchmark observations, namely the top-of-atmosphere (TOA) ocean color observations and marine in situ radiometric measurements. Sensor-to-sensor comparisons are performed to derive gain factors (g1) from near-concurrent observations in TOA radiance and reflectance domains. The gains in the radiance domain were further validated/adjusted by determining a second set of gains (g2) via analysis of OLI-derived water-leaving radiance, i.e., L(sub w) (gamma), against in situ measurements made either at the Ocean Color AErosol RObotic NETwork (AERONETOC) sites or during field campaigns. The analyses yield the OLI calibration uncertainties that need to be accounted forwhen studying aquatic environments. Itwas found that, for the visible and near-infrared channels, the OLI radiometric responses, on average, are well in agreement (b 2 % discrepancies) with the TOA radiances estimated by ocean color satellites or those predicted by models based onmeasurements of aquatic and atmospheric properties. However, the TOA radiance at the new 443-nm band is found to be, on average, 3.4 % larger than the reference observations. The inter-sensor comparisons in the reflectance domain, however, indicated slightly different results with the OLI responses being low in the blue bands. To enhance the retrieval accuracy of aquatic-science products from OLI datasets, sets of temporally averaged gains (radiance and reflectance) are derived and recommended for use prior to the retrieval of in-water products.

Remote Sensing↗
DOE OSTI2026

Measuring the neutrino-oxygen neutral current quasielastic cross section using the accelerator neutrino neutron interaction experiment

The Accelerator Neutrino Neutron Interaction Experiment (ANNIE) is a 26-ton gadolinium-doped water Cherenkov detector located on-axis to Fermilab’s Booster Neutrino Beam (BNB). ANNIE is uniquely positioned to perform high-statistics measurements of neutrino-nucleus interactions in water, benefiting from a large neutrino flux due to a short (100-meter) baseline. A central focus of ANNIE’s physics program is the measurement of both charged current (CC) and neutral current (NC) cross sections on water, including neutral current quasielastic (NCQE) and CC-inclusive channels. The NCQE measurement is particularly critical for constraining uncertainties in rare-event searches such as the Diffuse Supernova Neutrino Background (DSNB), where atmospheric $\nu$NCQE interactions constitute a significant and poorly constrained background. This dissertation presents a measurement of the flux-averaged neutrino-oxygen neutral current quasielastic ($\nu$NCQE) cross section using $2.573 \times 10^{20}$~POT of BNB exposure from the 2022 and 2023 beam years. The $\nu$NCQE interaction is identified through the primary $\gamma$-rays produced by nuclear de-excitation of the residual $^{15}$N$^*$ or $^{15}$O$^*$ nucleus following nucleon knockout from $^{16}$O. A dedicated Monte Carlo (MC) re-tuning campaign was conducted using an americium-beryllium (AmBe) calibration source, Michel electrons from stopped muons, and throughgoing dirt muons originating upstream of the detector. This multi-sample approach provided a wide-ranging $\mathcal{O}(\text{MeV})$--$\mathcal{O}(\text{GeV})$ dataset for tuning the simulated detector response, which was subsequently validated against AmBe neutron and Michel electron data for use in the $\nu$NCQE analysis. A dedicated laser calibration campaign was carried out to reduce timing uncertainties across the PMT system, enabling reconstruction of the BNB bunch substructure with sufficient resolution to serve as a background rejection tool. By selecting events in-time with individual neutrino bunches, beam-correlated $\nu$NCQE events are separated from diffuse and accelerator-induced backgrounds, notably skyshine neutrons and externally-originating events, that would otherwise dominate traditional charge-based selections within a small-scale, surface-level, short-baseline detector. A data-driven estimation of the skyshine neutron and external background rates was performed and incorporated into the systematic uncertainty budget. The flux-averaged $\nu$NCQE cross section on oxygen is measured to be $1.57 \pm 0.06\,(\text{stat.})$ $^{+0.91}_{-0.67}\,(\text{syst.})$ $\times 10^{-38}\ \text{cm}^{2}$. A full systematic budget is constructed by propagating uncertainties in the secondary hadronic interaction modeling, background cross section normalizations, detector response, neutrino flux, and the primary $\gamma$-ray emission probabilities from oxygen nuclear de-excitation. An idealized de-excitation model, constructed from existing measurements in the literature is developed to benchmark the predictions of the \textsc{GENIE} event generator. A comparison reveals that \textsc{GENIE} systematically overpredicts the primary $\gamma$-ray emission probability from oxygen de-excitation by a factor of $1.49\times$ for $E_\gamma > 6$~MeV and $3.07\times$ in the $3$--$6$~MeV band. This comparison motivates the dominant systematic uncertainty in this analysis, where a conservative uncertainty of $^{+39.9\%}_{-0\%}$ on the primary $\gamma$-ray signal prediction is assigned. The ANNIE result is consistent with and complementary to existing flux-averaged $\nu$NCQE cross section measurements from T2K and Super-Kamiokande, providing an independent measurement with a different detector, neutrino beam, and analysis methodology. Looking ahead, an upgrade to the ANNIE DAQ infrastructure enabling continuous extended readout will allow a complementary $\nu$NCQE neutron multiplicity measurement, directly relevant to constraining the NCQE background in DSNB searches, competitive with the recent T2K measurement at SK-Gd. The planned Super-SANDI upgrade, deploying a large Water-based Liquid Scintillator (WbLS) volume, will further extend ANNIE's reach to hadronic final states and exclusive NC channels, and enable joint measurements with liquid argon detectors sharing the BNB beamline ahead of DUNE and Hyper-Kamiokande.

Doran, Steven [Iowa State U.]↗
DOE OSTI2026

Battery Life Prediction Using Reduced-Order Physics Models and Machine Learning (CRADA Final Report)

Phase 1 (Original CRADA, plus no-cost extension modifications #1-3, 6/1/2017 to 3/13/2021): The Australian Department of Defence (AUDoD) is performing accelerated aging tests of Li-ion batteries to benchmark their reliability and degradation characteristics. Using its previously developed battery lifetime predictive model framework, the National Laboratory of the Rockies (NLR) will develop analytical models based the AUDoD data to predict lifetime of the multiple Li-ion battery chemistries under real-world use scenarios of interest to AUDoD. The NLR model is based on physical degradation mechanisms encountered by Li-ion batteries and has been previously validated. Phase 2 (CRADA modification #4, plus no-cost extension modification #5, 2/22/2021 to 3/30/2025): Train and support Australian Department of Defence personnel to use NLR software for model-based estimation of Li-ion battery lifetime using accelerated battery aging data collected by the Australian Department of Defence. Under separate DOE funding from 2019 to 2021, NLR enhanced its battery life-prediction software using machine learning algorithms to automate portions of the model-fitting process, requiring significantly less labor and expert judgment and also adding uncertainty quantification, increasing statistical rigor. Under Phase 2, NLR will customize NLR Software and provide it to AuDoD. NLR will enhance its NLR Model to capture aging modes of AuDoD's multi-cell modules, including cell-balancing effects. NLR will develop example single-cell and multi-cell models based on one AuDoD battery aging dataset. NLR will train AuDoD personnel on NLR Software. By the conclusion of the project, NLR will have provided AuDoD the training materials, a user manual and software needed to perform their own analysis of additional and/or future battery aging datasets.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2024

The ATLAS experiment software on ARM

With an increased dataset obtained during the Run 3 of the LHC at CERN and the even larger expected increase of the dataset by more than one order of magnitude for the HL-LHC, the ATLAS experiment is reaching the limits of the current data processing model in terms of traditional CPU resources based on x86_64 architectures and an extensive program for software upgrades towards the HL-LHC has been set up. The ARM architecture is becoming a competitive and energy efficient alternative. Some surveys indicate its increased presence in HPCs and commercial clouds, and some WLCG sites have expressed their interest. Chip makers are also developing their next generation solutions on ARM architectures, sometimes combining ARM and GPU processors in the same chip. Consequently it is important that the ATLAS software embraces the change and is able to successfully exploit this architecture. We report on the successful porting to ARM of the Athena software framework, which is used by ATLAS for both online and offline computing operations. Furthermore we report on the successful validation of simulation workflows running on ARM resources. For this we have set up an ATLAS Grid site using ARM compatible middleware and containers on Amazon Web Services (AWS) ARM resources. The ARM version of Athena is fully integrated in the regular software build system and distributed in the same way as other software releases. In addition, the workflows have been integrated into the HEPscore benchmark suite which is the planned WLCG wide replacement of the HepSpec06 benchmark used for Grid site pledges. In the overall porting process we have used resources on AWS, Google Cloud Platform (GCP) and CERN. A performance comparison of different architectures and resources will be discussed.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

On the effectiveness of neural operators at zero-shot weather downscaling

Machine-learning (ML) methods have shown great potential for weather downscaling. These data-driven approaches provide a more efficient alternative for producing high-resolution weather datasets and forecasts compared to physics-based numerical simulations. Neural operators, which learn solution operators for a family of partial differential equations, have shown great success in scientific ML applications involving physics-driven datasets. Neural operators are grid-resolution-invariant and are often evaluated on higher grid resolutions than they are trained on, i.e., zero-shot super-resolution. Given their promising zero-shot super-resolution performance on dynamical systems emulation, we present a critical investigation of their zero-shot weather downscaling capabilities, which is when models are tasked with producing high-resolution outputs using higher upsampling factors than are seen during training. To this end, we create two realistic downscaling experiments with challenging upsampling factors (e.g., 8x and 15x) across data from different simulations: the European Centre for Medium-Range Weather Forecasts Reanalysis version 5 (ERA5) and the Wind Integration National Dataset Toolkit. While neural operator-based downscaling models perform better than interpolation and a simple convolutional baseline, we show the surprising performance of an approach that combines a powerful transformer-based model with parameter-free interpolation at zero-shot weather downscaling. We find that this Swin-Transformer-based approach mostly outperforms models with neural operator layers in terms of average error metrics, whereas an Enhanced Super-Resolution Generative Adversarial Network-based approach is better than most models in terms of capturing the physics of the ground truth data. We suggest their use in future work as strong baselines.

17 WIND ENERGY↗
NASA NTRSDate not supplied

A Combined Computational, Experimental, and Technology Development Approach to In-Space Laser Manufacturing Maturation at NASA Marshall Space Flight Center

In-space manufacturing (ISM) is emerging as a field vital to continued access and capabilities in the space environment. NASA Marshall Space Flight Center (MSFC) is advancing the frontier of in-space laser manufacturing (ISLM) techniques through work initially focused on maturing laser beam welding (LBW) and laser forming (LF) for use in space. Such techniques proffer the ability to assemble and join structures in space from sheet metal or other stock – extant satellites, in situ resource utilization of Lunar regolith, etc. – by forming to desired shapes and then joining via in-space welding (ISW). ISLM processes are useful for assembly, joining, modification, and repair of structures in free space and on the Lunar surface such as large observatories, antennas, trusses, blast/thermal/radiation shields, pressure vessels, and more. However, these techniques are not yet qualified & certified (Q&C) for regular application in space. It would be prohibitively expensive, laborious, and time-consuming to perform Q&C via traditional experimental approaches as data collection & experimentation in space is resource-intensive. As such, benchmark experiments and focused, properly instrumented technology demonstration efforts in space can collect sufficient data that – when combined with verified computational models in an integrated computational materials engineering (ICME) approach – can validate ICME tools capable of translating more readily obtained ground data to in-space, in situ, computationally informed Q&C of ISLM techniques. Several ISLM projects at MSFC are obtaining the data required to validate ICME tools through both ground and flight experiments. A parabolic flight experiment of LBW under vacuum is manifested for August 2024, including both microgravity and Lunar gravity profiles. This collaboration with the Ohio State University is investigating common aerospace alloys such as 316L stainless steel, 2219 aluminum alloy, and Ti64 titanium alloy. In situ data collection includes videography, thermography, and reference thermocouples to build a thermal model of the welds. This will elucidate the relevant physics when combined with post-flight microstructural examination and mechanical testing. MSFC is also progressing towards a suborbital flight experiment of LBW under vacuum, which could provide reams of data on ISW during sustained, high-quality reduced gravity. The effect of combined thermal (cryogenic and high-temperature) and vacuum exposure on both LBW (NASA-funded) and LF (DARPA-funded) is being investigated through ground experiments. In addition to the copious data collected during these ground experiments, ruggedization of LBW hardware will also be pursued. The datasets from these experiments will be used to validate computational models which will inform future ISLM efforts in an ICME framework. A variety of techniques across lengths scales, from CALPHAD-driven thermodynamics & kinetics to phase field modeling of solidification to kinetic Monte Carlo simulations of grain evolution at the mesoscale, will be employed to accelerate the infusion and eventual Q&C of LBW and LF for use in space. The development of data-driven surrogate models to bridge ground to flight experiments and thereby reduce the need for resource-intensive experiments in space will also be investigated. These ICME techniques, surrogate models, and datasets from ground testing can also be employed to advance manufacturing in terrestrial environments.

in-space welding↗
DOE OSTI2026

Hyaloscypha finlandica Metabolome Repository

This repository provides the curated data tables, manuscript figure and table exports, dependency records, and workflow scripts supporting an integrated comparative genomics and untargeted LC-MS/MS metabolomics analysis of Hyaloscypha finlandica strain PMI 746, a root-associated dark septate endophyte of poplar. The repository includes genome-mining summaries from antiSMASH, FunBGCeX, BGC-Prophet, and BiG-SCAPE; processed metabolomics inputs; metabolite annotation evidence; statistical outputs; and publication-facing figures and tables. Raw LC-MS/MS spectra, full genome/protein downloads, and large generated tool outputs are referenced through public archive/accession records and are not stored in Git.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2019

The Global Fire Atlas of Individual Fire Size, Duration, Speed and Direction

Natural and human-ignited fires affect all major biomes, altering ecosystem structure, biogeochemical cycles and atmospheric composition. Satellite observations provide global data on spatiotemporal patterns of biomass burning and evidence for the rapid changes in global fire activity in response to land management and climate. Satellite imagery also provides detailed information on the daily or sub-daily position of fires that can be used to understand the dynamics of individual fires. The Global Fire Atlas is a new global dataset that tracks the dynamics of individual fires to determine the timing and location of ignitions, fire size and duration, and daily expansion, fire line length, speed, and direction of spread. Here, we present the underlying methodology and Global Fire Atlas results for 2003–2016 derived from daily moderate-resolution (500 m) Collection 6 MCD64A1 burned-area data. The algorithm identified 13.3 million individual fires over the study period, and estimated fire perimeters were in good agreement with independent data for the continental United States. A small number of large fires dominated sparsely populated arid and boreal ecosystems, while burned area in agricultural and other human-dominated landscapes was driven by high ignition densities that resulted in numerous smaller fires. Long-duration fires in boreal regions and natural landscapes in the humid tropics suggest that fire season length exerts a strong control on fire size and total burned area in these areas. In arid ecosystems with low fuel densities, high fire spread rates resulted in large, short-duration fires that quickly consumed available fuels. Importantly, multiday fires contributed the majority of burned area in all biomass burning regions. A first analysis of the largest, longest and fastest fires that occurred around the world revealed coherent regional patterns of extreme fires driven by large-scale climate forcing. Global Fire Atlas data are publicly available through http://www.globalfiredata.org (last access: 9 August 2018) and https://doi.org/10.3334/ORNLDAAC/1642, and individual fire information and summary data products provide new information for benchmarking fire models within ecosystem and Earth system models, understanding vegetation–fire feedbacks, improving global emissions estimates, and characterizing the changing role of fire in the Earth system.

global fire atlas↗
DOE OSTI2024

LandScan Global 2023: Silver Edition

For a quarter of a century, the LandScan Global (LSG) project has annually released a global, high-resolution gridded population dataset representing the ambient or unwarned population at a 30 arcsecond resolution. LSG supports a range of applications such as emergency management, disaster response, and human health and security for understanding populations at risk. The 2023 release of LSG, the LandScan Silver Edition, represents a major methodological leap forward while also leveraging previous knowledge—the previous year was the baseline for the current annual update carrying forward valuable knowledge of the built environment for the past quarter century—to train the machine learning models. Compared with annual releases over the past 24years, multiple advancements were made to different aspects of the methodology to achieve reproducibility, transparency, and consistent global propagation of solutions to modeling or population distribution issues identified during the review process. These novel changes include incorporation of the latest available geospatial inputs across the globe, machine learning models instead of manual modifications, population feature importance analysis, open-source solutions vs. proprietary software, generation of multiple global versions, analytic validations, and human-in-the-loop revisions to produce the final version. Additionally, algorithms—such as anomaly detection—were introduced to quickly identify areas of focus to develop a new and robust systematic review. Significant changes in modeled population distributions were observed between the 2022 and 2023 releases, largely attributable to improvements in data and methods and discussed thoroughly within this report. In summation, the LandScan Silver Edition leverages the best of the past quarter century of LSG legacy knowledge and continues a tradition of applying cutting-edge enhancements to serve as a new benchmark for accurate, actionable gridded population data

Lebakula, Viswadeep↗
DOE OSTI2022

The eROSITA Final Equatorial-Depth Survey (eFEDS)

Here, we investigate the physical properties – such as the stellar mass (M * ), star-formation rate, infrared (IR) luminosity (L IR ), X-ray luminosity (L X ), and hydrogen column density (N H ) – of mid-IR (MIR) galaxies and active galactic nuclei (AGN) at z < 4 in the 140 deg 2 field observed by eROSITA on SRG using the Performance-and-Verification-Phase program named the eROSITA Final Equatorial Depth Survey (eFEDS). By cross-matching the WISE 22 μm (W4)-detected sample and the eFEDS X-ray point-source catalog, we find that 692 extragalactic objects are detected by eROSITA. We have compiled a multiwavelength dataset extending from X-ray to far-IR wavelengths. We have also performed (i) an X-ray spectral analysis, (ii) spectral-energy-distribution fitting using X-CIGALE, (iii) 2D image-decomposition analysis using Subaru Hyper Suprime-Cam images, and (iv) optical spectral fitting with QSFit to investigate the AGN and host-galaxy properties. For 7088 WISE 22 μm objects that are undetected by eROSITA, we have performed an X-ray stacking analysis to examine the typical physical properties of these X-ray faint and probably obscured objects. We find that (i) 82% of the eFEDS–W4 sources are classified as X-ray AGN with log L X > 42 erg s –1 ; (ii) 67 and 24% of the objects have log(L IR /L ⊙ ) > 12 and 13, respectively; (iii) the relationship between L X and the 6 μm luminosity is consistent with that reported in previous works; and (iv) the relationship between the Eddington ratio and N H for the eFEDS–W4 sample and a comparison with a model prediction from a galaxy-merger simulation indicates that approximately 5.0% of the eFEDS–W4 sources in our sample are likely to be in an AGN-feedback phase, in which strong radiation pressure from the AGN blows out the surrounding material from the nuclear region. Thanks to the wide area coverage of eFEDS, we have been able to constrain the ranges of the physical properties of the WISE 22 μm-selected sample of AGNs at z < 4, providing a benchmark for forthcoming studies on a complete census of MIR galaxies selected from the full-depth eROSITA all-sky survey.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models

We benchmark performance of long-short term memory (LSTM) network machine learning model and autoregressive integrated moving average (ARIMA) statistical model in temporal forecasting of distributed temperature sensing (DTS). Data in this study consists of fluid temperature transient measured with two co-located Rayleigh scattering fiber optic sensors (FOS) in a forced convection mixing zone of a thermal tee. We treat each gauge of a FOS as an independent temperature sensor. We first study prediction of DTS time series using Vanilla LSTM and ARIMA models trained on prior history of the same FOS that is used for testing. The results yield maximum absolute percentage error (MaxAPE) and root mean squared percentage error (RMSPE) of 1.58% and 0.06% for ARIMA, and 3.14% and 0.44% for LSTM, respectively. Next, we investigate zero-shot forecasting (ZSF) with LSTM and ARIMA trained on history of the co-located FOS only, which is advantageous when limited training data is available. The ZSF MaxAPE and RMSPE values for ARIMA are comparable to those of the Vanilla use case, while the error values for LSTM increase. We show that in ZSF, performance of LSTM network can be improved by training on most correlated gauges between the two FOS, which are identified by calculating the Pearson correlation coefficient. The improved ZSF MaxAPE and RMSPE for LSTM are 4.4% and 0.33%, respectively. Performance of ZSF LSTM can be further enhanced through transfer learning (TL), where LSTM is re-trained on a subset of the FOS that is the target of forecasting. We show that LSTM pre-trained on correlated dataset and re-trained on 30% of testing target dataset achieves MaxAPE and RMSPE values of 2.32% and 0.28%, respectively.

ARIMA↗
NASA NTRS2020

Amino Acid Encoding for Deep Learning Applications

Background: The number of applications of deep learning algorithms in bioinformatics is increasing as they usually achieve superior performance over classical approaches, especially, when bigger training datasets are available. In deep learning applications, discrete data, e.g. words or n-grams in language, or amino acids or nucleotides in bioinformatics, are generally represented as a continuous vector through an embedding matrix. Recently, learning this embedding matrix directly from the data as part of the continuous iteration of the model to optimize the target prediction – a process called ‘end-to-end learning’ – has led to state-ofthe-art results in many fields. Although usage of embeddings is well described in the bioinformatics literature, the potential of end-to-end learning for single amino acids, as compared to more classical manually-curated encoding strategies, has not been systematically addressed. To this end, we compared classical encoding matrices, namely one-hot, VHSE8 and BLOSUM62, to end-to-end learning of amino acid embeddings for two different prediction tasks using three widely used architectures, namely recurrent neural networks (RNN), convolutional neural networks (CNN), and the hybrid CNN-RNN. Results: By using different deep learning architectures, we show that end-to-end learning is on par with classical encodings for embeddings of the same dimension even when limited training data is available, and might allow for a reduction in the embedding dimension without performance loss, which is critical when deploying the models to devices with limited computational capacities. We found that the embedding dimension is a major factor in controlling the model performance. Surprisingly, we observed that deep learning models are capable of learning from random vectors of appropriate dimension. Conclusion: Our study shows that end-to-end learning is a flexible and powerful method for amino acid encoding. Further, due to the flexibility of deep learning systems, amino acid encoding schemes should be benchmarked against random vectors of the same dimension to disentangle the information content provided by the encoding scheme from the distinguishability effect provided by the scheme.

Hesham ElAbd↗
NASA NTRS2020

Amino Acid Encoding for Deep Learning Applications

Background: The number of applications of deep learning algorithms in bioinformatics is increasing as they usually achieve superior performance over classical approaches, especially, when bigger training datasets are available. In deep learning applications, discrete data, e.g. words or n-grams in language, or amino acids or nucleotides in bioinformatics, are generally represented as a continuous vector through an embedding matrix. Recently, learning this embedding matrix directly from the data as part of the continuous iteration of the model to optimize the target prediction – a process called ‘end-to-end learning’ – has led to state-of-the-art results in many fields. Although usage of embeddings is well described in the bioinformatics literature, the potential of end-to-end learning for single amino acids, as compared to more classical manually-curated encoding strategies, has not been systematically addressed. To this end, we compared classical encoding matrices, namely one-hot, VHSE8 and BLOSUM62, to end-to-end learning of amino acid embeddings for two different prediction tasks using three widely used architectures, namely recurrent neural networks (RNN), convolutional neural networks (CNN), and the hybrid CNN-RNN. Results: By using different deep learning architectures, we show that end-to-end learning is on par with classical encodings for embeddings of the same dimension even when limited training data is available, and might allow for a reduction in the embedding dimension without performance loss, which is critical when deploying the models to devices with limited computational capacities. We found that the embedding dimension is a major factor in controlling the model performance. Surprisingly, we observed that deep learning models are capable of learning from random vectors of appropriate dimension. Conclusion: Our study shows that end-to-end learning is a flexible and powerful method for amino acid encoding. Further, due to the flexibility of deep learning systems, amino acid encoding schemes should be benchmarked against random vectors of the same dimension to disentangle the information content provided by the encoding scheme from the distinguishability effect provided by the scheme.

Deep-learning↗
DOE OSTI2024

DECOVALEX-2023: Task C Final Report

The Full-scale Emplacement (FE) heater experiment at the Mont Terri Underground Rock Laboratory (URL) was designed and conducted by Nagra to replicate an emplacement tunnel of Nagra’s reference repository design at 1:1 scale. Alongside testing the technical feasibility of constructing disposal tunnels, emplacing waste containers in the tunnels and then backfilling them, the main goals of the FE experiment are (1) to obtain a better understanding of the coupled effects of induced thermo-hydro-mechanical (THM) processes that may occur and (2) to validate existing coupled THM models (Müller et al., 2017). A key aspect of ensuring safety for repositories located in low-permeability rock involves minimizing any damage to the rock itself, thereby preserving its integrity and promoting a stable environment Amongst a number of processes that could damage the rock is the increase in pore pressure due to thermal loading caused by heat emitted from the waste. To reduce the potential damage of the rock, it is important to analyse the evolution of heat over time due to the heat load of the containers and assess possible consequences by coupled THM models. The aim of Task C of DECOVALEX-2023 was to build 3D numerical models of the FE experiment, focussing in particular on the heating induced pore pressure change in the Opalinus Clay. Data from a large number of sensors were available from the FE experiment for model comparison. These sensors measured temperature and relative humidity in the bentonite around the heaters, and temperature, pressure and displacement/strain in the surrounding Opalinus clay. Data were available from the start of excavation (April 2012) up to August 2020 for most sensors (more than 5 years from the start of heating in December 2014). To fulfil the overall aim of the task, the work was broken down into a number of steps, starting with simpler models to build confidence in each team’s approach and then moving to more complex models that better represent the FE experiment. Step 0 consisted of 2D benchmark models, gradually increasing the number of processes that are represented from thermal (T) only models in Step 0a, to coupled thermal hydraulic (TH) models in Step 0b with a representation of changing porosity, to coupled thermo-hydro-mechanical (THM) models in Step 0c, where porosity changes are calculated by the mechanical model. A detailed specification of processes, parameters, initial and boundary conditions was provided for this step, with the ambition that all teams would work towards close agreement in their model results, thus building confidence in the model implementations. vi It was not straightforward to achieve agreement between the teams, so additional steps (Step 0b2, 0b3, 0c2, 0c3) were added along with derivation of some analytical solutions against which the models could be compared. The reasons for the differences between teams were investigated and found to be caused primarily by different conceptual model assumptions (including temperature dependence of the thermal expansion of water), different model formulations (including porosity evolution) and differences in modelled domain sizes, boundary conditions and grid discretisation. This demonstrates that comparisons between multiple modelling teams and/or comparison with analytical results and experimental data are highly beneficial in providing an indication of uncertainty in model predictions. At the conclusion of Step 0, almost all teams had achieved a close agreement in model results and those that had not achieved an agreement knew the reason for this. Step 1 moved from 2D models to 3D models of the FE experiment without adding technical features like shotcrete or EDZ, and only considering the heating phase. Initially the 3D model was tightly specified to continue to build confidence in the model implementations (Step 1a). The results of Step 1a were compared to the data from the FE-experiment without the teams seeing the data. The teams were then provided with a sub-set of the data from the FE-experiment and invited to consider how best to use the large dataset for model comparison (Step 1b). Teams were then asked to use the data provided to calibrate their models, only changing material property values rather than adding features or processes to their models (Step 1c). In Step 1, teams were asked to only model the heating phase of the experiment, so pressure in the Opalinus Clay was reported as change in pressure since the initial conditions were specified rather than modelled. The change from 2D to 3D models was accompanied by an increase in the dispersion of results between the teams. Some of this was resolved during the task, but some remained and is potentially due to model discretisation. Calibration of parameters was useful in improving the fit of the models to the data but the remaining differences indicated that the models were missing features or processes. In Step 2, the teams were asked to update their models with additional features and processes as well as calibrating parameters to try and improve the fit of the models to the data. Teams were encouraged to represent ventilation of the open FE tunnel prior to backfilling with heaters and bentonite and in Step 2, the absolute pressure in the Opalinus Clay was compared between the teams. Teams took different approaches, but there was consideration of adding shotcrete and an EDZ into the model, representing stress change during excavation and different approaches to modelling ventilation of the FE tunnel. Overall, the documented results showed a very good agreement for temperature. The results for porewater pressure evolution showed a significant improvement for most teams compared to Step 1c with a good agreement to the measurements for several teams whereas some teams overpredicted the pressure increase and others overpredicted the drainage effect especially for the sensors close to the heater. Step 3 was an opportunity for teams to use the models developed in Step 1 and Step 2 to make predictions about the temperature and pressure changes that will be expected at the FE experiment over the next few years in light of the planned changes in thermal output of the heaters.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
NASA NTRS2013

The Collection 6 'dark-target' MODIS Aerosol Products

Aerosol retrieval algorithms are applied to Moderate resolution Imaging Spectroradiometer (MODIS) sensors on both Terra and Aqua, creating two streams of decade-plus aerosol information. Products of aerosol optical depth (AOD) and aerosol size are used for many applications, but the primary concern is that these global products are comprehensive and consistent enough for use in climate studies. One of our major customers is the international modeling comparison study known as AEROCOM, which relies on the MODIS data as a benchmark. In order to keep up with the needs of AEROCOM and other MODIS data users, while utilizing new science and tools, we have improved the algorithms and products. The code, and the associated products, will be known as Collection 6 (C6). While not a major overhaul from the previous Collection 5 (C5) version, there are enough changes that there are significant impacts to the products and their interpretation. In its entirety, the C6 algorithm is comprised of three sub-algorithms for retrieving aerosol properties over different surfaces: These include the dark-target DT algorithms to retrieve over (1) ocean and (2) vegetated-dark-soiled land, plus the (3) Deep Blue (DB) algorithm, originally developed to retrieve over desert-arid land. Focusing on the two DT algorithms, we have updated assumptions for central wavelengths, Rayleigh optical depths and gas (H2O, O3, CO2, etc.) absorption corrections, while relaxing the solar zenith angle limit (up to 84) to increase pole-ward coverage. For DT-land, we have updated the cloud mask to allow heavy smoke retrievals, fine-tuned the assignments for aerosol type as function of season location, corrected bugs in the Quality Assurance (QA) logic, and added diagnostic parameters such as topographic altitude. For DT-ocean, improvements include a revised cloud mask for thin-cirrus detection, inclusion of wind speed dependence in the retrieval, updates to logic of QA Confidence flag (QAC) assignment, and additions of important diagnostic information. At the same time as we have introduced algorithm changes, we have also accounted for upstream changes including: new instrument calibration, revised land-sea masking, and changed cloud masking. Upstream changes also impact the coverage and global statistics of the retrieved AOD. Although our responsibility is to the DT code and products, we have also added a product that merges DT and DB product over semi-arid land surfaces to provide a more gap-free dataset, primarily for visualization purposes. Preliminary validation shows that compared to surface-based sunphotometer data, the C6, Level 2 (along swath) DT-products compare at least as well as those from C5. C6 will include new diagnostic information about clouds in the aerosol field, including an aerosol cloud mask at 500 m resolution, and calculations of the distance to the nearest cloud from clear pixels. Finally, we have revised the strategy for aggregating and averaging the Level 2 (swath) data to become Level 3 (gridded) data. All together, the changes to the DT algorithms will result in reduced global AOD (by 0.02) over ocean and increased AOD (by 0.02) over land, along with changes in spatial coverage. Changes in calibration will have more impact to Terras time series, especially over land. This will result in a significant reduction in artificial differences in the Terra and Aqua datasets, and will stabilize the MODIS data as a target for AEROCOM studie

Aerosol retrieval algorithms↗
DOE OSTI2022

Pulsed Thermal Tomography Nondestructive Examination of Additively Manufactured Reactor Materials and Components (Final Technical Report)

Metal Additive Manufacturing (AM) is a promising method for cost-efficient fabrication of complex shape structures for applications in harsh environment, such as in a nuclear reactor. However, internal defects (pores) occur in high-strength AM alloys, which are manufactured with Laser Powder Bed Fusion (LPBF) AM method. Pulsed Infrared Thermography (PIT) is an efficient nondestructive evaluation (NDE) method to examine actual structures, because this method offers one-sided non-contact measurements, and fast processing of large sample areas. However, imaging of material defects, particularly defects with sizes at microscopic level, is challenging. In this report, we benchmark the performance of several Unsupervised Learning (UL) algorithms designed to enhance imaging of microscopic defects in metals with PIT. UL aims to learn the latent principal patterns (dictionaries) in PIT data to detect defects with minimal human supervision. Performance of Independent Component Analysis (ICA), Sparse Coding (SC), Principal Component Analysis (PCA) and Exploratory Factor Analysis (EFA) was compared using F-score, UL model training time and defects reconstruction time. We obtained the average F-score of 0.75, and a highest F-score of 0.89 for the EFA algorithm. Overall, EFA outperforms other UL algorithms considered in this study. In another approach, we investigate Thermal Tomography (TT), which is a computational method for reconstruction of depth profile of internal material defects from PIT nondestructive evaluation (NDE). TT algorithm obtains depth reconstructions of thermal effusivity, which has been shown to provide visualization of subsurface internals defects in metals. In many applications, one needs to determine the defect shape and orientation from reconstructed effusivity images. Interpretation of TT images is non-trivial because of blurring, which increases with depth due to heat diffusion-based nature of image formation. We have developed a deep learning convolutional neural network (CNN) to classify size and orientation of subsurface material defects in TT images. CNN was trained with TT images produced with computer simulations of 2D metallic structures (thin plates) containing elliptical subsurface voids. Performance of CNN was investigated using test TT images developed with computer simulations of plates containing elliptical defects, and defects with shape imported from scanning electron microscopy (SEM) images. CNN demonstrated the ability to classify radii and angular orientation of elliptical defects in previously unseen test TT images. We have also demonstrated that CNN trained on TT images of elliptical defects is capable of classifying shape and orientation of irregular defects. Training the CNN on irregular defect shapes instead of on elliptical shapes would make the resulting classifications more descriptive of actual defect shapes. However, this requires a much higher volume of SEM images of material defects, which are difficult to obtain because of random occurrence of defects in LPBF. To address this challenge, we developed a generative adversarial network (GAN) to augment the existing dataset of SEM defect images. The GAN model is demonstrated to create novel yet realistic defect shapes that can be used as input for simulated PTT images to train CNN. We also investigate several approaches based on Gaussian Random Circle and Bezier Curves for constructing parametric models of irregular-shape defects.

36 MATERIALS SCIENCE↗