Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Labeling”

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 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Scalable balanced training of conditional generative adversarial neural networks on image data

Here, we propose a distributed approach to train deep convolutional generative adversarial neural network (DC-CGANs) models. Our method reduces the imbalance between generator and discriminator by partitioning the training data according to data labels, and enhances scalability by performing a parallel training where multiple generators are concurrently trained, each one of them focusing on a single data label. Performance is assessed in terms of inception score, Fréchet inception distance, and image quality on MNIST, CIFAR10, CIFAR100, and ImageNet1k datasets, showing a significant improvement in comparison to state-of-the-art techniques to training DC-CGANs. Weak scaling is attained on all the four datasets using up to 1000 processes and 2000 NVIDIA V100 GPUs on the OLCF supercomputer Summit.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Instance Segmentation for Direct Measurements of Satellites in Metal Powders and Automated Microstructural Characterization from Image Data

In this work, we propose instance segmentation as a useful tool for image analysis in materials science. Instance segmentation is an advanced technique in computer vision which generates individual segmentation masks for every object of interest that is recognized in an image. Using an out-of-the-box implementation of Mask R-CNN, instance segmentation is applied to images of metal powder particles produced through gas atomization. Leveraging transfer learning allows for the analysis to be conducted with a very small training set of labeled images. As well as providing another method for measuring the particle size distribution, we demonstrate the first direct measurements of the satellite content in powder samples. After analyzing the results for the labeled data dataset, the trained model was used to generate measurements for a much larger set of unlabeled images. The resulting particle size measurements showed reasonable agreement with laser scattering measurements. The satellite measurements were self-consistent and showed good agreement with the expected trends for different samples. Finally, we present a small case study showing how instance segmentation can be used to measure spheroidite content in the UltraHigh Carbon Steel DataBase, demonstrating the flexibility of the technique.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Text Mining for Process–Structure–Properties Relationships in Metals

With the advent of large language models (LLMs), the vast unstructured text within millions of academic papers is increasingly accessible for materials discovery—although significant challenges remain. While LLMs offer promising few- and zero-shot learning capabilities, particularly valuable in the materials domain where expert annotations are scarce, general-purpose LLMs often fail to address key materials-specific queries without further adaptation. To bridge this gap, fine-tuning LLMs on human-labeled data is essential for effective structured knowledge extraction (Liu in The Importance of Human-Labeled Data in the Era of LLMs, 2023). Here, in this study, we introduce a novel annotation schema designed to extract generic process–structure–properties relationships from scientific literature. We demonstrate the utility of this approach using a dataset of 128 abstracts, with annotations drawn from two distinct domains: high-temperature materials (Domain I) and uncertainty quantification in simulating materials microstructure (Domain II). Initially, we developed a conditional random field (CRF) model based on MatBERT—a domain-specific BERT variant—and evaluated its performance on Domain I. Subsequently, we compared this model with a fine-tuned LLM (GPT-4o from OpenAI) under identical conditions. Our results indicate that fine-tuning LLMs can significantly improve entity extraction performance over the BERT-CRF baseline on Domain I. However, when additional examples from Domain II were incorporated, the performance of the BERT-CRF model became comparable to that of the GPT-4o model. These findings underscore the potential of our schema for structured knowledge extraction and highlight the complementary strengths of both modeling approaches.

Materials science↗
DOE OSTI2021

Street context of various demographic groups in their daily mobility

Abstract We present an urban science framework to characterize phone users’ exposure to different street context types based on network science, geographical information systems (GIS), daily individual trajectories, and street imagery. We consider street context as the inferred usage of the street, based on its buildings and construction, categorized in nine possible labels. The labels define whether the street is residential, commercial or downtown, throughway or not, and other special categories. We apply the analysis to the City of Boston, considering daily trajectories synthetically generated with a model based on call detail records (CDR) and images from Google Street View. Images are categorized both manually and using artificial intelligence (AI). We focus on the city’s four main racial/ethnic demographic groups (White, Black, Hispanic and Asian), aiming to characterize the differences in what these groups of people see during their daily activities. Based on daily trajectories, we reconstruct most common paths over the street network. We use street demand (number of times a street is included in a trajectory) to detect each group’s most relevant streets and regions. Based on their street demand, we measure the street context distribution for each group. The inclusion of images allows us to quantitatively measure the prevalence of each context and points to qualitative differences on where that context takes place. Other AI methodologies can further exploit these differences. This approach presents the building blocks to further studies that relate mobile devices’ dynamic records with the differences in urban exposure by demographic groups. The addition of AI-based image analysis to street demand can power up the capabilities of urban planning methodologies, compare multiple cities under a unified framework, and reduce the crudeness of GIS-only mobility analysis. Shortening the gap between big data-driven analysis and traditional human classification analysis can help build smarter and more equal cities while reducing the efforts necessary to study a city’s characteristics.

Salgado, Ariel (ORCID:0000000177015372)↗
DOE OSTI2024

Correlating real-world incidents with vessel traffic off the coast of Hawaii, 2017–2020

Abstract Objectives Because of the high-risk nature of emergencies and illegal activities at sea, it is critical that algorithms designed to detect anomalies from maritime traffic data be robust. However, there exist no publicly available maritime traffic data sets with real-world expert-labeled anomalies. As a result, most anomaly detection algorithms for maritime traffic are validated without ground truth. Data description We introduce the HawaiiCoast_GT data set, the first ever publicly available automatic identification system (AIS) data set with a large corresponding set of true anomalous incidents. This data set—cleaned and curated from raw Bureau of Ocean Energy Management (BOEM) and National Oceanic and Atmospheric Administration (NOAA) automatic identification system (AIS) data—covers Hawaii’s coastal waters for four years (2017–2020) and contains 88,749,176 AIS points for a total of 2622 unique vessels. This includes 208 labeled tracks corresponding to 154 rigorously documented real-world incidents.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2026

Host analysis-guided selection and targeted engineering (HASTE) of Lipomyces tetrasporus for the conversion of CO2-derived feedstocks

Efficient and cost-competitive bioproduction calls for utilizing CO2-derived feedstocks, such as products from electro-reduction of CO2 and hydrolysate from lignocellulosic biomass. However, efficiently using all their carbon components, including acetate, glucose, and xylose, remains a challenge. Here, we characterize Lipomyces tetrasporus, a novel, robust yeast strain capable of effectively assimilating these carbon sources. We used an integrated systems biology approach combining ¹³C metabolic flux analysis, dynamic labeling experiments, and RNA sequencing. We conducted the first metabolic flux analysis for glucose, xylose, and acetate catabolism in this species. Dynamic labeling revealed a highly active TCA cycle during acetate metabolism, evidenced by rapid citrate and malate accumulation. The strain demonstrated strong NADH/NADPH production and acetyl-CoA synthase activity. Using insights and gene targets from this analysis, we engineered L. tetrasporus for malate production. The engineered strain produced 7.5 g/L malic acid (0.25 g/g yield) in shake flasks with glucose-acetate media and 28.8 g/L malic acid at a yield of 0.20 g/g in fed-batch mode with corn-stover hydrolysate. Together, these insights and rational strain engineering establish L. tetrasporus as a versatile, Crabtree-negative platform that is an energy-CO2-bioproduction nexus for channeling CO2 carbon into value-added bioproducts.

Xiao, Zhengyang↗
DOE OSTI2024

Separable physics-informed DeepONet: Breaking the curse of dimensionality in physics-informed machine learning

The deep operator network (DeepONet) has shown remarkable potential in solving partial differential equations (PDEs) by mapping between infinite-dimensional function spaces using labeled datasets. However, in scenarios lacking labeled data, the physics-informed DeepONet (PI-DeepONet) approach, which utilizes the residual loss of the governing PDE to optimize the network parameters, faces significant computational challenges, particularly due to the curse of dimensionality. This limitation has hindered its application to high-dimensional problems, making even standard 3D spatial with 1D temporal problems computationally prohibitive. Additionally, the computational requirement increases exponentially with the discretization density of the domain. Here, to address these challenges and enhance scalability for high-dimensional PDEs, we introduce the Separable physics-informed DeepONet (Sep-PI-DeepONet). This framework employs a factorization technique, utilizing sub-networks for individual one-dimensional coordinates, thereby reducing the number of forward passes and the size of the Jacobian matrix required for gradient computations. By incorporating forward-mode automatic differentiation (AD), we further optimize computational efficiency, achieving linear scaling of computational cost with discretization density and dimensionality, making our approach highly suitable for high-dimensional PDEs. We demonstrate the effectiveness of Sep-PI-DeepONet through three benchmark PDE models: the viscous Burgers’ equation, Biot’s consolidation theory, and a parameterized heat equation. Our framework maintains accuracy comparable to the conventional PI-DeepONet while reducing training time by two orders of magnitude. Notably, for the heat equation solved as a 4D problem, the conventional PI-DeepONet was computationally infeasible (estimated 289.35 h), while the Sep-PI-DeepONet completed training in just 2.5 h. These results underscore the potential of Sep-PI-DeepONet in efficiently solving complex, high-dimensional PDEs, marking a significant advancement in physics-informed machine learning.

Neural operator↗
DOE OSTI2020

Overcoming small minirhizotron datasets using transfer learning

Minirhizotron technology is widely used to study root growth and development. Yet, standard approaches for tracing roots in minirhiztron imagery is extremely tedious and time consuming. Machine learning approaches can help to automate this task. However, lack of enough annotated training data is a major limitation for the application of machine learning methods. Transfer learning is a useful technique to help with training when available datasets are limited. In this paper, we investigated the effect of pre-trained features from the massives-cale, irrelevant ImageNet dataset and a relatively moderate-scale, but relevant peanut root dataset on switchgrass root imagery segmentation applications. We compiled two minirhizotron image datasets to accomplish this study: one with 17,550 peanut root images and another with 28 switchgrass root images. Both datasets were paired with manually labeled ground truth masks. Deep neural networks based on the U-net architecture were used with different pre-trained features as initialization for automated, precise pixel-wise root segmentation in minirhizotron imagery. We observed that features pre-trained on a closely related but relatively moderate size dataset like our peanut dataset were more effective than features pre-trained on the large but unrelated ImageNet dataset. Here, we achieved high quality segmentation on peanut root dataset with 99.04% accuracy at the pixel-level and overcame errors in human-labeled ground truth masks. By applying transfer learning technique on limited switchgrass dataset with features pre-trained on peanut dataset, we obtained 99% segmentation accuracy in switchgrass imagery using only 21 images for training (fine tuning). Furthermore, the peanut pre-trained features can help the model converge faster and have much more stable performance.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Generative learning for slow manifolds and bifurcation diagrams

In dynamical systems characterized by separation of time scales, the approximation of so called “slow manifolds”, on which the long term dynamics lie, is a useful step for model reduction. Initializing on such slow manifolds is a useful step in modeling, since it circumvents fast transients, and is crucial in multiscale algorithms (like the equation-free approach) alternating between fine scale (fast) and coarser scale (slow) simulations. In a similar spirit, when one studies the infinite time dynamics of systems depending on parameters, the system attractors (e.g., its steady states) lie on bifurcation diagrams (curves for one-parameter continuation, and more generally, on manifolds in state parameter space. Sampling these manifolds gives us representative attractors (here, steady states of ODEs or PDEs) at different parameter values. Algorithms for the systematic construction of these manifolds (slow manifolds, bifurcation diagrams) are required parts of the “traditional” numerical nonlinear dynamics toolkit. In more recent years, as the field of Machine Learning develops, conditional score-based generative models (cSGMs) have been demonstrated to exhibit remarkable capabilities in generating plausible data from target distributions that are conditioned on some given label. It is tempting to exploit such generative models to produce samples of data distributions (points on a slow manifold, steady states on a bifurcation surface) conditioned on (consistent with) some quantity of interest (QoI, observable). In this work, we present a framework for using cSGMs to quickly (a) initialize on a low-dimensional (reduced-order) slow manifold of a multi-time-scale system consistent with desired value(s) of a QoI (a “label”) on the manifold, and (b) approximate steady states in a bifurcation diagram consistent with a (new, out-of-sample) parameter value. This conditional sampling can help uncover the geometry of the reduced slow-manifold and/or approximately “fill in” missing segments of steady states in a bifurcation diagram. Finally, the quantity of interest, which determines how the sampling is conditioned, is either known a priori or identified using manifold learning-based dimensionality reduction techniques applied to the training data.

Dynamical systems↗
DOE OSTI2021

Influence of PRE-emergence herbicides on soybean development, root nodulation and symbiotic nitrogen fixation

We report widespread occurrence of herbicide-resistant weeds has further limited effective POST-emergence herbicide options in soybean (Glycine max (L.) Merr.) leading to an increased adoption of PRE-emergence herbicides. The objective of this study was to investigate the influence of 11 commonly used PRE herbicides on soybean development, root nodulation, and symbiotic N fixation. Soybean plants were grown under greenhouse conditions in pots (10 L; 4 plants per pot) filled with silt loam soil and treated one day after planting with a labeled field rate of imazethapyr, chlorimuron-ethyl, cloransulam-methyl, metribuzin, sulfentrazone, flumioxazin, saflufenacil, acetochlor, S-metolachlor, dimethenamid-P, pyroxasulfone and no herbicide (nontreated control). Sulfentrazone reduced soybean canopy at the VC growth stage but no canopy reduction was observed at the V2 growth stage from any of the herbicide treatments. At the R2 growth stage, herbicides had no effect on soybean development (root and shoot biomass), root nodulation (# nodule per plant, nodule diameter, and nodule biomass) and symbiotic N fixation (acetylene reduction assay and 15 N natural abundance). According to our findings, although PRE herbicides may slightly affect early-season soybean development, the impacts on plant growth, root nodulation, and symbiotic N fixation were negligible. Thus, when sprayed according to the label, the benefits of PRE herbicides for weed control likely outweigh any potential concern regarding soybean development, root nodulation, and N fixation.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Bio-distribution and deposition of wildfire smoke chemicals into olfactory bulb and brain of rats after intranasal instillation

Epidemiological and experimental studies suggest wildfire smoke is a potential contributor to neurological dysfunction and associated with neuroinflammation. Using doses comparable to those encountered during intense wildfire events (200-300 μg/m 3 ), we explore the absorption, distribution, metabolism, and elimination (ADME) and pharmacokinetics of representative members of major chemical classes (acid, phenol, PAH, aldehyde) in inhaled wood smoke condensates. Male Sprague Dawley rats were intranasally instilled with smoldering eucalyptus woodsmoke extract (WSE) reconstituted in saline spiked with 14 C-labeled palmitic acid (PA), benzo[a]pyrene (B[a]P), catechol (CAT) or benzaldehyde (BZ). Serum was collected from 5 min to 2 weeks after exposure and tissues were collected at 0.5, 2, 4, 24 h and 2 weeks after exposure. Urine was collected over the 24 h exposure. Tissues were collected, rinsed in PBS and analyzed by accelerator mass spectrometry (AMS) for 14C-labeled chemicals. PA and B[a]P entered circulation slowly, reached maximum concentration (C max ) near 15 ng/mL at 2 h, and had circulating concentrations near 1/3 C max 24 h after exposure. CAT and BZ rapidly entered circulation and were mostly cleared at 2 h. Excess 14 C from all four chemicals was detected in olfactory bulb and brain over the first 24 h but only PA (or its metabolites) was retained in olfactory bulb, brain and kidney at 2 weeks post exposure. All excess 14 C was cleared from the lung at 2 weeks. Metabolite analysis of urine (CAT, BZ and B(a)P) dosed samples did not detect any parent compound. CAT and BZ were rapidly cleared. The slower uptake and clearance of PA or B[a]P or their reactive metabolites when dosed with WSE in brain and olfactory bulb potentially provide greater opportunity for inflammatory response. This study suggests that wildfire smoke chemicals can enter the brain directly from the nasal cavity to the olfactory bulb and via systemic circulation.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
DOE OSTI2023

Machine learning and deep learning for mineralogy interpretation and CO 2 saturation estimation in geological carbon Storage: A case study in the Illinois Basin

Carbon capture and storage (CCS) is a promising approach to simultaneously maintaining energy security and reducing carbon dioxide (CO 2 ) emissions under the current energy portfolio that is dominated by fossil fuel energy. Pre-injection formation characterization and post-injection CO 2 monitoring are two critical tasks to guarantee storage efficiency in CCS. The CCS projects in the Illinois Basin, the first large-scale CO 2 injection into saline aquifers in the United States, employed conventional and the latest pulsed neutron logging (PNL) tools for mineralogy interpretation and CO 2 saturation estimation, which provide valuable references for future CCS projects. Because of the inherent fuzziness of petrophysical measurements and complex subsurface heterogeneity, interpreting well-logging data is time-consuming, and its accuracy can be user-biased. In recent years, data-driven methods have been widely used to capture the non-linear patterns between input features and interpretation results. This work applied and evaluated four commonly used machine learning (ML) models, including ridge regression (RR), random forest (RF), gradient boosting regression (GBR), support vector regression (SVR), and one deep learning (DL) model, the artificial neural network (ANN). We optimized the hyperparameters of the four ML models and the DL model using the simulated annealing algorithm and the grid search strategy, respectively. The input features of the mineralogy interpretation models were eleven conventional well-logging parameters, and the label data (i.e., ground truth) were the porosity and volumetric fractions of six minerals, including quartz, feldspar, dolomite, calcite, clay, and iron minerals. The results demonstrated that the GBR and RF models were superior in predicting volumetric fractions of minerals and porosity; label data with low coefficient of variation (CV) values tended to yield better performance. For CO 2 saturation estimation, the RF was the best-performing model, followed by SVR, ANN, GBR, and RR. Furthermore, we conducted feature importance ranking using the permutation importance algorithm and found that the formation sigma and well pressure were the most important features in this study. In conclusion, the study of CCS projects in the Illinois Basin bridges the gap between the limited knowledge and understanding of geological carbon storage and the increasing demand for reliable, cost-effective, and sustainable energy solutions.

58 GEOSCIENCES↗
DOE OSTI2022

Recurrent neural networks for short-term and long-term prediction of geothermal reservoirs

Accurate prediction of geothermal reservoir responses to alternative energy production scenarios is critical for optimizing the development of the underlying resources. While the conventional physics-based models offer a comprehensive prediction tool, data-driven models provide an efficient alternative to build fit-for-purpose predictive models by extracting and using the statistical patterns in the collected data to make predictions. The recurrent neural network (RNN) is a data-driven model that is commonly applied to predict time series sequences. This paper presents a variant of RNN that also utilizes the efficiency of convolutional neural networks (CNN) for the prediction of energy production from geothermal reservoirs. Specifically, a CNN–RNN architecture is developed that takes historical well controls as input (features) and their corresponding production response data as output (labels) to learn an input-output mapping that can predict the future well production responses/performance for any given future well control inputs. The model is paired with a labeling scheme to handle real field disturbances that create data gaps. In addition to the model structure, we introduce a thorough workflow for applying the model, which includes data pre-processing, feature selection, as well as different training strategies for short-term and long-term prediction. Finally, the performance and accuracy of the model are evaluated by applying it to multiple datasets, including a field reservoir model.

15 GEOTHERMAL ENERGY↗
DOE OSTI2020

Losses of CO and CO 2 upon collision-activated dissociation of substituted 2-methoxyphenoxides after methyl radical loss

Some deprotonated, substituted 2-methoxyphenols fragment by methyl radical loss followed by competing losses of CO and CO 2 upon collisional activation in linear quadrupole ion trap mass spectrometers. These reactions were examined experimentally and computationally in order to determine their mechanisms. For deprotonated vanillin, the CO loss was found to involve ring contraction, with the highest free energy barrier of 58.0 kcal mol -1 (for the syn rotamer; here, syn refers to the relationship between the aldehyde oxygen atom and the oxygen atom of the methoxy group) for the entire process. The atoms lost in this fragmentation are the oxygen atom that was bound to the first eliminated methyl group and the aromatic carbon atom bound to this oxygen. Examination of carbon-13 labeled vanillin supports these assignments. Examination of several model compounds revealed that this reaction requires the presence of an electron-withdrawing substituent in the para-position relative to the phenol moiety. In contrast, the CO 2 loss from deprotonated vanillin occurs via ring opening followed by re-cyclization and then ring contraction, leading to the loss of CO 2 in a process wherein the highest free energy barrier is 84.5 kcal mol -1 (for the syn isomer). The atoms lost in this fragmentation are the carbon and oxygen atoms from the phenoxide group and the oxygen atom that was bound to the first eliminated methyl group, which is supported by examination of carbon-13 labeled vanillin. Despite the higher total free energy requirement, the CO 2 loss is competitive with CO loss, possibly due to favorable entropy and low activation energy (free energy barrier of 48.9 kcal mol -1 ) for the first reaction step (the analogous value for CO loss is 58.0 kcal mol -1 ). The extent of CO 2 loss is strongly affected by substituents – it either is not observed or is very slow for the other compounds studied here. For example, it is substantially less favorable than CO loss (highest free energy barrier 60.9 kcal mol -1 ) for deprotonated acetovanillone for which the first reaction step for CO 2 loss has a substantially greater free energy barrier (60.6 kcal mol-1) than for vanillin.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Developing a peptide concatemer (PepCon) as a process control for LC-MS based proteomics

Quantitative concatenated peptide (QconCAT) technology is currently used for the absolute quantification of proteins of interest in a biological sample. It relies on artificially created proteins that are concatenations of different, isotopically labeled peptides. Because these isotopically labeled peptides are at a 1:1 ratio and correspond to naturally occurring peptides in the biological sample, each peptide can be used as a standard for the absolute quantitation of all proteins of interest at once. Although the QconCAT technology has utility for quantitation of known peptides in a mixture, it is not helpful for scientists who need a proteomics standard (1) that can be spiked into a protein mixture at an extremely low level, (2) that can be co-purified during sample fractionation, and (3) that is optimized for ESI used in mass spectrometry. Thus, there exists a need for an ideal standard protein that is large enough to behave as a protein but consists of multiple, concatenated copies of the same peptide, which, upon digestion, amplifies (e.g., >10-fold) into a detectable peptide species. Here, this technical report describes the development of “PepCon”, a peptide concatemer that fulfills this unmet need.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Automated 3D cytoplasm segmentation in soft X-ray tomography

Cells’ structure is key to understanding cellular function, diagnostics, and therapy development. Soft X-ray tomography (SXT) is a unique tool to image cellular structure without fixation or labeling at high spatial resolution and throughput. Fast acquisition times increase demand for accelerated image analysis, like segmentation. Currently, segmenting cellular structures is done manually and is a major bottleneck in the SXT data analysis. This paper introduces ACSeg, an automated 3D cytoplasm segmentation model. ACSeg is generated using semi-automated labels and 3D U-Net and is trained on 43 SXT tomograms of immune T cells, rapidly converging to high-accuracy segmentation, therefore reducing time and labor. Furthermore, adding only 6 SXT tomograms of other cell types diversifies the model, showing potential for optimal experimental design. ACSeg successfully segmented unseen tomograms and is published on Biomedisa, enabling high-throughput analysis of cell volume and structure of cytoplasm in diverse cell types.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Intercomparison of flood inundation models across land use types and hydrological flood stages

Flood Inundation Mapping (FIM) model selection is a key operational decision because accurate, rapid mapping underpins early warning and resource allocation. FIM performance is context-dependent and can vary with hydrograph phase, land-use/land-cover (LULC), and the evaluation benchmark. Intercomparison studies typically assess a single near-peak snapshot against one reference dataset. Here, we provide a context-stratified intercomparison across (i) multiple hydrograph phases, (ii) LULC classes, and (iii) benchmark types, for five FIM approaches spanning a wide range of physical complexity and operational cost (TRITON, LISFLOOD-FP, HEC-RAS 2D, ARC-Curve2Flood, and OWP HAND-FIM). We use the Hurricane Matthew flood (2016) in the Neuse River Basin, North Carolina, USA, as a case study. Using high-resolution remote sensing-derived flood inundation maps, hand-labeled points, and building footprints, we assess model skill across two rising and two falling hydrograph limbs and across major LULC types. Results show that model rankings shift systematically across contexts: LISFLOOD-FP ranks highest in three of four flood phases, while TRITON leads during one rising limb phase; LISFLOOD-FP performs best in vegetated areas, whereas HEC-RAS improves relative performance in agricultural and urban areas; and benchmark choice influences conclusions, with LISFLOOD-FP performing best for flooded-building detection in the late falling limb, while TRITON ranks highest against hand-labeled points. We also report representative wall-clock runtimes for each workflow to provide use-case context for operational feasibility. Together, these results offer transferable guidance for model selection and for designing large-scale, benchmark-aware FIM intercomparison studies.

Nikrou, Parvaneh [University of Alabama]↗
DOE OSTI2022

Sensor fusion of pyrometry and acoustic measurements for localized keyhole pore identification in laser powder bed fusion

We report in-situ process monitoring as an aid to part qualification for laser powder-bed fusion (L-PBF) technology is a topic of increasing interest to the additive manufacturing community. In this work, airborne acoustic and inline pyrometry measurements were recorded simultaneously with the laser position. X-ray radiography imaging was used to spatio-temporally register keyhole pore locations to the pyrometry and acoustic signals, enabling binary labeling of data partitions based on pore formation. These labeled partitions were subsequently featurized using a highly comparative time-series analysis toolbox. Acoustic data was found to be much more effective than the pyrometry data for keyhole pore identification. However, when the information contained in both sensing modalities was combined in a sensor fusion strategy, the error rates of the top performing models were significantly reduced.

36 MATERIALS SCIENCE↗