Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Predictive modeling”

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 1,603 records · Page 89
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

State-Specific Kinetic Modeling for Predictions of Radiative Heating in H 2 /He Entry Flows

A 23-species State-to-State (StS) thermochemical model for H 2 /He mixtures is developed and used to simulate 1-D shocks at conditions relevant for ice and gas giant entry flows. To implement this StS model, a literature review of the state-specific excitation and ionization rates of atomic H is first performed. While electron impact rates from various sources are found to be in relatively good agreement, large discrepancies are found in the limited data available on heavy particle impact rates. To investigate the impact of these discrepancies on the predicted shock and radiance profiles, simulations are performed for three different versions of the kinetic model, each with a different set of heavy particle impact rates from the literature. Of these three models, two are found to over-predict and one is found to under-predict the radiance values seen in corresponding experimental data from the NASA Ames Electric Arc Shock Tube (EAST) facility. A sensitivity analysis to the electron and heavy particle impact rates is then performed, from which an improved kinetic model with modified rates is proposed. This modified kinetic model is found to reproduce the total integrated radiance seen in the EAST experiments accurately. This suggests that the associated radiative heating that would be encountered by an entry probe in these environments would be well predicted by this kinetic model. However, some discrepancies are still found i the relative contributions to the total radiance from different spectral features, suggesting that additional improvements to the kinetic model still need to be made.

Outer Planet↗
DOE OSTI2026

HydraGNN_Predictive_GFM_2026 - Ensemble of predictive graph foundation models for atomistic materials modeling

This release contains data and parameters of HydraGNN-based graph foundation models trained as a result of the work published in the pre-print "Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data" by M. Lupo Pasini et al. (https://arxiv.org/abs/2604.15380). We jointly train on 16 open first-principles datasets (544+ million structures covering 85+ elements) using a multi-task architecture with per-dataset heads and a scalable ADIOS2/DDStore data pipeline. On Frontier, we execute six large-scale DeepHyper hyperparameter optimization campaigns in FP64 and promote the top-performing message-passing models to sustained 2,048-node training, yielding a PaiNN-based lead model. The version of HydraGNN used to generate the outputs provided in this release is HydraGNN v5.0 (https://github.com/ORNL/HydraGNN/releases/tag/v5.0) The list of datasets used for the training of the graph foundation model is the following: 1) Alexandria [1] 2) ANI1x [2] 3) MPTrj [3] 4) Open Catalyst 2020 (OC20) [4] 5) Open Catalyst 2022 (OC22) [5] 6) Open Catalyst 2025 (OC25) [6] 7) Open Direct ir Capture 2023 (ODAC23) [7] 8) Open Materials 2024 (OMat24) [8] 9) Open Molecules 2025 (OMol25) [9] 10) OMol25-neutral (subset of OMol25 that contains only molecules with zero total charge) 11) OMol25-non-neutral (subset of OMol25 that contains only molecules with non-zero total charge) 12) Open Polymers 2026 (OPoly2026) [10] 13) Nabla2DFT [11] 14) QCML [12] 15) QM7X [reference 13] 16) transition1x [14] Dataset references: [1] J. Schmidt et al., “A dataset of 175k stable and metastable materials calculated with the PBEsol and SCAN functionals,” Scientific Data, vol. 9, p. 64, 2022. [2] J. S. Smith et al., “The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules,” Scientific Data, vol. 7, p. 134, 2020. [Online]. Available: https: //www.nature.com/articles/s41597-020-0473-z [3] A. Jain et al., “Commentary: The Materials Project: A materials genome approach to accelerating materials innovation,” APL Materials, vol. 1, no. 1, p. 011002, 07 2013. [Online]. Available: https://doi.org/10.1063/1.4812323 [4] L. Chanussot et al., “Open catalyst 2020 (oc20) dataset and community challenges,” ACS Catalysis, vol. 11, no. 10, pp. 6059–6072, 2021. [Online]. Available: https://doi.org/10.1021/acscatal.0c04525 [5] K. Tran et al., “Open catalyst 2022 (oc22) dataset and challenges for oxidation electrocatalysts,” ACS Catalysis, vol. 13, no. 5, pp. 3066–3084, 2023. [Online]. Available: https://doi.org/10.1021/acscatal.2c05426 [6] S. J. Sahoo et al., “The open catalyst 2025 (oc25) dataset and models for solid-liquid interfaces,” arXiv preprint arXiv:2509.17862, 2025. [Online]. Available: https://arxiv.org/abs/2509.17862 [7] A. Sriram et al., “The open DAC 2023 dataset and challenges for sorbent discovery in direct air capture,” ACS Central Science, vol. 10, no. 5, pp. 923–941, 2024. [8] L. Barroso-Luque et al., “Open materials 2024 (omat24) inorganic materials dataset and models,” 2024. [Online]. Available: https://arxiv.org/abs/2410.12771 [9] D. S. Levine et al., “The open molecules 2025 (OMol25) dataset, evaluations, and models,” 2025. [Online]. Available: https://arxiv.org/abs/2505.08762 [10] D. S. Levine et al., The open polymers 2026 (OPoly26) dataset and evaluations,” arXiv preprint arXiv:2512.23117, 2025. [Online]. Available: https://arxiv.org/abs/2512.23117 [11] K. Khrabrov et al., “Nabla2dft: A universal quantum chemistry dataset of drug-like molecules and a benchmark for neural network potentials,” in NeurIPS 2024 Datasets and Benchmarks Track, 2024. [Online]. Available: https://openreview.net/forum?id=ElUrNM9U8c [12] S. Ganscha et al., “The QCML dataset, quantum chemistry reference data from 33.5M DFT and 14.7B semi-empirical calculations,” Scientific Data, vol. 12, p. 406, 2025. [13] J. Hoja et al., “QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules,” Scientific Data, vol. 8, p. 43, 2021. [Online]. Available: https://www.nature.com/articles/s41597-021-00812-2 [14] M. Schreiner et al., “Transition1x - a dataset for building generalizable reactive machine learning potentials,” Scientific Data, vol. 9, p. 779, 2022. The folder "datasets_ADIOS2_format" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "datasets_ADIOS2_format" directory contains 2 sub-directories, one for the version "v1" of the datasets and one for the version "v2" of the datasets. The version "v1" of the datasets provides values of the total energy as they are extracted from the original data as it was released by the respective institutions. The version "v2" of the datasets provides values of the energy that have been realigned. The realignment was performed by training a linear regression model that predicts the total energy as a function of the chemical composition of the atomistic structure, and then subtract such prediction from the original value of the total energy. Both folders "v1" and "v2" contain 16 sub-directories, each corresponding to an ADIOS2-formatted dataset The folder "DeepHyper-results" contains the configurational files and model's parameters for all the 186 HPO trials that were successfully completed by the scalable hyperparameter optimization (HPO) runs on Frontier. The content of the folder "DeepHyper-results" I structured as follows: 1) task-list.txt: list of mpnn name, jobid, and deephyper task id 2) gfm_${MPNN}_${JOBID}_0.${TASKID}: run directory with checkpoint files 3) gfm_${MPNN}: deephyper summary directory (*.csv) for each specific MPNN type 4) deephyper-experiment-${JOBID}: output and error logs for each job The file "deephyper-sorted.csv" contains the details of each HydraGNN model built and tested by HPO, obtained by merging the (*.csv) filed from each HPO run executed. Out of all the HPO trials, we selected 10 to continue the training of the respective HydraGNN models. Due to limited computational budget available in the LRN070 allocation we could not complete the training till convergence for all these 10 selected models. The folder "models" contains multiple sub-folders, one per each HydraGNN model trained. Each model sub-folder contains the parameters of each HydraGNN model, with multiple checkpoint-restarts. The list of sub-folders are as follows: 1) multidataset_hpo-BEST1-fp64 2) multidataset_hpo-BEST2-fp64 3) multidataset_hpo-BEST3-fp64 4) multidataset_hpo-BEST4-fp64 5) multidataset_hpo-BEST5-fp64 6) multidataset_hpo-BEST6-fp64 7) multidataset_hpo-BEST7-fp64 8) multidataset_hpo-BEST8-fp64 9) multidataset_hpo-BEST9-fp64 10) multidataset_hpo-BEST10-fp64 Within each one of these folders, additional auxiliary log files are provided with descriptions about how the training proceeded. The lead PaiNN-model is contained inside "multidataset_hpo-BEST6-fp64". The file "mlp_branch_weights" contains the parameters of the multi-layer perceptron (MLP) used to reconcile the predictions of the 16 output decoding heads of the HydragNN architectures. The MLP takes in input the chemical composition of the atomistic structure and predicts averaging weights to linearly mix the predictions of each output decoding head toward consolidating them into a single one. The folder "1.1billion-structure-inference" contains 1.1 billion atomistic structures randomly generated. Each structures is associated with energy and forces predicted with the lead-PaiNN model combined with the MLP model for reconciliation of the multi-branch predictions generated by the 16 output decoding heads. The folder "1.1billion-structure-inference" contains 9,300 (*.tar.gz) subdirectories, one per Frontier compute node used to execute the inference at exascale. Once uncompressed, each (*.tar.gz) subdirectory contains an ADIOS2 (*.bp) file container, where each atomistic structure is stored as a PyTorch-Geometric Data object. The file "export_dataset_environment_variables.sh" contains the environment variables that need to be set before running the HydraGNN code to reproduce the results provided in this dataset release. The code that can be used to load the ADIOS2 files, load HydraGNN models, and run inference is available at: https://github.com/ORNL/HydraGNN/releases/tag/v5.0

36 MATERIALS SCIENCE↗
DOE OSTI2016

Investigation on porosity and permeability change of Mount Simon sandstone (Knox County, IN, USA) under geological CO 2 sequestration conditions: a numerical simulation approach

In this paper, a numerical model was developed to simulate reactive transport with porosity and permeability change of Mount Simon sandstone (samples from Knox County, IN) after 180 days of exposure to CO 2 -saturated brine under CO 2 sequestration conditions. The model predicted formation of a high-porosity zone adjacent to the surface of the sample in contact with bulk brine, and a lower porosity zone just beyond that high-porosity zone along the path from sample/bulk brine interface to sample core. The formation of the high porosity zone was attributed to dissolution of quartz and muscovite/illite, while the formation of the lower porosity zone adjacent to the aforementioned high porosity zone was attributed to precipitation of kaolinite and feldspar. The model predicted a 40% permeability increase for the Knox sandstone sample after 180 days of exposure to CO 2 -saturated brine, which was consistent with laboratory-measured permeability results. Model-predicted solution chemistry results were also found to be consistent with laboratory-measured solution chemistry data. Finally, initial porosity, initial feldspar content and the exponent n value (determined by pore structure and tortuosity) used in permeability calculations were three important factors affecting permeability evolution of sandstone samples under CO 2 sequestration conditions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Spatiotemporal Learning in Power Modules: Wavelet-Enhanced Forecasting of Thermomechanical Degradation

Detecting internal defects in power electronics packages is critical for their performance and reliability, especially under extreme operating conditions, as these defects can lead to catastrophic failure if not properly addressed. Confocal scanning acoustic microscopy (C-SAM) plays a key role in the nondestructive evaluation of bond layer degradation within a power electronics package by detecting defects such as delamination, voids, and cracks. However, accurately quantifying and predicting these defects from C-SAM images remains a significant challenge due to the low noise-to-signal ratio, which typically arises from both imaging process and bond patterns itself. In this paper, we explore machine learning strategies for processing C-SAM images and providing predictive models of defect growth. We use C-SAM images of sintered copper and sintered silver samples, which are obtained under accelerated thermal experiments, as the representative dataset for our study. We investigate the effect of Fourier transforms and wavelet transforms on these datasets to remove high-frequency noise and address noise across multiple scales with histogram equalization to enhance the contrast and improve the visibility of defects. As a result, defect boundaries can be clearly distinguished, enabling more accurate tracking of their growth over time. We then employ different time-series forecasting algorithms on the denoised images to formulate an image-based lifetime prediction model. Statistical models and deep-learning techniques are trained on images obtained in the early stages of thermal shock, and defect growth in the later stages is predicted. Our work serves as a preliminary attempt to improve the accuracy of lifetime prediction models of power electronics packages, which is critical under extreme operating environments.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Lung cancer mortality among construction workers: implications for early detection

Objectives This study examined predictors of lung cancer mortality, beyond age and smoking, among construction workers employed at US Department of Energy (DOE) sites to better define eligibility for low-dose CT (LDCT) lung cancer screening. Methods Predictive models were based on 17 069 workers and 352 lung cancer deaths. Risk factors included age, gender, race/ethnicity, cigarette smoking, years of trade or DOE work, body mass index (BMI), chest X-ray results, spirometry results, respiratory symptoms, beryllium sensitisation and personal history of cancer. Competing risk Cox models were used to obtain HRs and to predict 5-year risks. Results Factors beyond age and smoking included in the final predictive model were chest X-ray changes, abnormal lung function, chronic obstructive pulmonary disease (COPD), respiratory symptoms, BMI, personal history of cancer and having worked 5 or more years at a DOE site or in construction. Risk-based LDCT eligibility demonstrated improved sensitivity, specificity and positive predictive value compared with current US Preventive Services Task Force guidelines. The risk of lung cancer death from 5 years of work in the construction industry or at a DOE site was comparable with the risk from a personal cancer history, a family history of cancer or a diagnosis of COPD. LDCT eligibility criteria used for DOE construction workers, which includes factors beyond age and smoking, identified 86% of participants who eventually would die from lung cancer compared with 51% based on age and smoking alone. Conclusions Results support inclusion of risk from occupational exposures and non-malignant respiratory clinical findings in LDCT clinical guidelines.

Public, Environmental & Occupational Health↗
DOE OSTI2021

Transfer-Learnt Energy Models for Predicting Electricity Consumption in Buildings with Limited and Sparse Field Data

Modeling energy consumption is critical for energy-efficient utilization of the electric appliances in a building, smart grid programs (like demand-response), and many other smart home applications. State-of-the-art energy modeling techniques either rely on theoretical models, or extensive instrumentation of the building envelope to gather ``big" data to train a deep neural network. While theoretical models are often limited by their estimation accuracy, it is not always feasible to gather a significant amount of field data. In this paper, we explore transfer learning-based strategies to train much more accurate model for energy estimation when using a sparse field data. We transferred knowledge, in the form of data and parameters, from the simulation framework to the field data. We evaluated the efficacy of our approach on field data collected from six commercial buildings and our results indicate that transfer learning-based models trained over one month data can perform comparative (and in some cases better) than the state-of-the-art machine learning and deep learning solutions.

Jain, Milan↗
DOE OSTI2015

SU-E-J-186: Using 4DCT-Based Motion Modeling to Predict Motion and Duty Cycle On Successive Days of Gated Radiotherapy

Purpose: To determine if 4DCT-based motion modeling and external surrogate motion measured during treatment simulation can enhance prediction of residual tumor motion and duty cycle during treatment delivery. Methods: This experiment was conducted using simultaneously recorded tumor and external surrogate motion acquired over multiple fractions of lung cancer radiotherapy. These breathing traces were combined with the XCAT phantom to simulate CT images. Data from the first day was used to estimate the residual tumor motion and duty cycle both directly from the 4DCT (the current clinical standard), and from external-surrogate based motion modeling. The accuracy of these estimated residual tumor motions and duty cycles are evaluated by comparing to the measured internal/external motions from other treatment days. Results: All calculations were done for 25% and 50% duty cycles. The results indicated that duty cycle derived from 4DCT information alone is not enough to accurately predict duty cycles during treatment. Residual tumor motion was determined from the recorded data and compared with the estimated residual tumor motion from 4DCT. Relative differences in residual tumor motion varied from −30% to 55%, suggesting that more information is required to properly predict residual tumor motion. Compared to estimations made from 4DCT, in three out of four patients examined, the 30 seconds of motion modeling data was able to predict the duty cycle with better accuracy than 4DCT. No improvement was observed in prediction of residual tumor motion for this dataset. Conclusion: Motion modeling during simulation has the potential to enhance 4DCT and provide more information about target motion, duty cycles, and delivered dose. Based on these four patients, 30 seconds of motion modeling data produced improve duty cycle estimations but showed no measurable improvement in residual tumor motion prediction. More patient data is needed to verify this Result. I would like to acknowledge funding from MRA, VARIAN Medical Systems, Inc.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Development of QSAR models to predict blood-brain barrier permeability

Assessing drug permeability across the blood-brain barrier (BBB) is important when evaluating the abuse potential of new pharmaceuticals as well as developing novel therapeutics that target central nervous system disorders. One of the gold-standard in vivo methods for determining BBB permeability is rodent log BB; however, like most in vivo methods, it is time-consuming and expensive. In the present study, two statistical-based quantitative structure-activity relationship (QSAR) models were developed to predict BBB permeability of drugs based on their chemical structure. The in vivo BBB permeability data were harvested for 921 compounds from publicly available literature, non-proprietary drug approval packages, and University of Washington’s Drug Interaction Database. The cross-validation performance statistics for the BBB models ranged from 82 to 85% in sensitivity and 80–83% in negative predictivity. Additionally, the performance of newly developed models was assessed using an external validation set comprised of 83 chemicals. Overall, performance of individual models ranged from 70 to 75% in sensitivity, 70–72% in negative predictivity, and 78–86% in coverage. The predictive performance was further improved to 93% in coverage by combining predictions across the two software programs. These new models can be rapidly deployed to predict blood brain barrier permeability of pharmaceutical candidates and reduce the use of experimental animals.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

A Multiple Filter Based Neural Network Approach to the Extrapolation of Adsorption Energies on Metal Surfaces for Catalysis Applications

Computational catalyst discovery involves the development of microkinetic reactor models based on estimated parameters determined from density functional theory (DFT). For complex surface chemistries, the number of reaction intermediates can be very large, and the cost of calculating the adsorption energies by DFT for all surface intermediates even for one active site model can become prohibitive. In this paper, we have identified appropriate descriptors and machine learning models that can be used to predict a significant part of these adsorption energies given data on the rest of them. Furthermore, our investigations also included the case when the species data used to train the predictive model are of different size relative to the species the model tries to predict—this is an extrapolation in the data space which is typically difficult with regular machine learning models. Due to the relative size of the available data sets, we have attempted to extrapolate from the larger species to the smaller ones in the current work. Here, we have developed a neural network based predictive model that combines an established additive atomic contribution based model with the concepts of a convolutional neural network that, when extrapolating, achieves a statistically significant improvement over the previous models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Machine learning prediction of glass transition temperature of conjugated polymers from chemical structure

Predicting the glass transition temperature (T g ) is of critical importance as it governs the thermomechanical performance of conjugated polymers (CPs). Here, we report a predictive modeling framework to predict T g of CPs through the integration of machine learning (ML), molecular dynamics (MD) simulations, and experiments. With 154 T g data collected, an ML model is developed by taking simplified “geometry” of six chemical building blocks as molecular features, where side-chain fraction, isolated rings, fused rings, and bridged rings features are identified as the dominant ones for T g . MD simulations further unravel the fundamental roles of those chemical building blocks in dynamical heterogeneity and local mobility of CPs at a molecular level. The developed ML model is demonstrated for its capability of predicting T g of several new high-performance solar cell materials to a good approximation. The established predictive framework facilitates the design and prediction of T g of complex CPs, paving the way for addressing device stability issues that have hampered the field from developing stable organic electronics.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2016

Consensus Modeling for Prediction of Estrogenic Activity of Ingredients Commonly Used in Sunscreen Products

Sunscreen products are predominantly regulated as over-the-counter (OTC) drugs by the US FDA. The “active” ingredients function as ultraviolet filters. Once a sunscreen product is generally recognized as safe and effective (GRASE) via an OTC drug review process, new formulations using these ingredients do not require FDA review and approval, however, the majority of ingredients have never been tested to uncover any potential endocrine activity and their ability to interact with the estrogen receptor (ER) is unknown, despite the fact that this is a very extensively studied target related to endocrine activity. Consequently, we have developed an in silico model to prioritize single ingredient estrogen receptor activity for use when actual animal data are inadequate, equivocal, or absent. It relies on consensus modeling to qualitatively and quantitatively predict ER binding activity. As proof of concept, the model was applied to ingredients commonly used in sunscreen products worldwide and a few reference chemicals. Of the 32 chemicals with unknown ER binding activity that were evaluated, seven were predicted to be active estrogenic compounds. Five of the seven were confirmed by the published data. Further experimental data is needed to confirm the other two predictions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Evaluating the Trustworthiness of Explainable Artificial Intelligence (XAI) Methods Applied to Regression Predictions of Arctic Sea Ice Motion

Abstract Recent advances in explainable artificial intelligence (XAI) methods show promise for understanding predictions made by machine learning (ML) models. XAI explains how the input features are relevant or important for the model predictions. We train linear regression (LR) and convolutional neural network (CNN) models to make 1-day predictions of sea ice velocity in the Arctic from inputs of present-day wind velocity and previous-day ice velocity and concentration. We apply XAI methods to the CNN and compare explanations to variance explained by LR. We confirm the feasibility of using a novel XAI method [i.e., global layerwise relevance propagation (LRP)] to understand ML model predictions of sea ice motion by comparing it to established techniques. We investigate a suite of linear, perturbation-based, and propagation-based XAI methods in both local and global forms. Outputs from different explainability methods are generally consistent in showing that wind speed is the input feature with the highest contribution to ML predictions of ice motion, and we discuss inconsistencies in the spatial variability of the explanations. Additionally, we show that the CNN relies on both linear and nonlinear relationships between the inputs and uses nonlocal information to make predictions. LRP shows that wind speed over land is highly relevant for predicting ice motion offshore. This provides a framework to show how knowledge of environmental variables (i.e., wind) on land could be useful for predicting other properties (i.e., sea ice velocity) elsewhere. Significance Statement Explainable artificial intelligence (XAI) is useful for understanding predictions made by machine learning models. Our research establishes trustability in a novel implementation of an explainable AI method known as layerwise relevance propagation for Earth science applications. To do this, we provide a comparative evaluation of a suite of explainable AI methods applied to machine learning models that make 1-day predictions of Arctic sea ice velocity. We use explainable AI outputs to understand how the input features are used by the machine learning to predict ice motion. Additionally, we show that a convolutional neural network uses nonlinear and nonlocal information in making its predictions. We take advantage of the nonlocality to investigate the extent to which knowledge of wind on land is useful for predicting sea ice velocity elsewhere.

Hoffman, Lauren [Scripps Institution of Oceanograp↗
DOE OSTI2022

Rhythm of the Night (and Day): Predictive Metabolic Modeling of Diurnal Growth in Chlamydomonas

We have developed the first transient metabolic model for diurnal growth of algae based on experimental data and capable of predicting phenotype from genotype. This model enables us to evaluate the impact of genetic and environmental changes on the growth, biomass composition and intracellular fluxes of the model green alga, Chlamydomonas reinhardtii . The availability of this model will enable faster and more efficient design of cells for production of fuels, chemicals, and pharmaceuticals.

09 BIOMASS FUELS↗
DOE OSTI2021

Development of a Deep Learning Model for Predicting the Drag Coefficients of Spherical and Non-Spherical Particles,

There is yet to be a well-established drag model for non-spherical particles required in a particle-laden flow that could cover a wide range of sphericities. This talk will explore the development of a general drag model for non-spherical particles by applying deep learning using available experimental data available in the literature. The integration of several raw experimental measurements from different sources and research directions allows the training of robust Artificial Intelligence and Machine Learning (ML) models. Neural networks are an ML approach inspired by the inner biological workings of the brain. This work aims to develop a Deep Neural Network (DNN) that predicts drag coefficient values with the ability to adapt appropriately to unseen data. Given the limited number of data points available and the variance found within the data collected from various sources, challenges may arise when looking to train the model. Our study tests and implements various model regularization techniques and assesses different loss and activation functions for the proposed DNN. The proposed model considers a broader range of features other than sphericity and Reynold number. These features include density ratio, solid volume fraction, lengthwise and crosswise sphericity, and more. Furthermore, we present the features that play a significant role in predicting different drag coefficients through feature importance. Within the investigated parameter ranges in this study, the following conclusions can be achieved and summarized below: • An improved drag coefficient model can be developed by considering more features such as, aspect ratio, lengthwise sphericity, crosswise sphericity, and density ratio. • DNN model can predict better results compared to traditional methods using MAE metric. • The proposed model addresses data challenges such as limited data and extreme data points through expanded feature-set and regularization. • Three major features that mostly affect the drag coefficient were identified from a feature importance analysis.

Presa-Reyes, Maria↗
DOE OSTI2015

ON THE ROLE AND ORIGIN OF NONTHERMAL ELECTRONS IN HOT ACCRETION FLOWS

We study the X-ray spectra of tenuous, two-temperature accretion flows using a model involving an exact, Monte Carlo computation of the global Comptonization effect as well as a general relativistic description of both the flow structure and radiative processes. In our previous work, we found that in flows surrounding supermassive black holes, thermal synchrotron radiation is not capable of providing a sufficient seed photon flux to explain the X-ray spectral indices as well as the cut-off energies measured in several best-studied active galactic nuclei (AGNs). In this work, we complete the model by including seed photons provided by nonthermal synchrotron radiation and we find that it allows us to reconcile the hot flow model with the AGN data. We take into account two possible sources of nonthermal electrons. First, we consider e {sup ±} produced by charged-pion decay, which should always be present in the innermost part of a two-temperature flow due to proton-proton interactions. We find that for a weak heating of thermal electrons (small δ) the synchrotron emission of pion-decay e {sup ±} is much stronger than the thermal synchrotron emission in the considered range of bolometric luminosities, L ∼ (10{sup –4}-10{sup –2}) L {sub Edd}. The small-δ model including hadronic effects, in general, agrees with the AGN data, except for the case of a slowly rotating black hole and a thermal distribution of protons. For large δ, the pion-decay e {sup ±} have a negligible effect and, in this model, we consider nonthermal electrons produced by direct acceleration. We find an approximate agreement with the AGN data for the fraction of the heating power of electrons, which is used for the nonthermal acceleration η ∼ 0.1. However, for constant η and δ, the model predicts a positive correlation of the X-ray spectral index with the Eddington ratio, and hence a fine tuning of η and/or δ with the accretion rate is required to explain the negative correlation observed at low luminosities. We note a significant difference between the dependence of plasma parameters, T {sub e} and τ, on the Eddington ratio that is predicted by the large- and small-δ models. This may be the key property allowing for the estimation of the value of δ. However, a precise measurement of the spectral cut-off is required, and we note that differences between results available in the literature are similar in magnitude to the difference between the model predictions. In flows surrounding stellar-mass black holes, the synchrotron emission of pion-decay e {sup ±} exceeds the thermal synchrotron only above ∼0.01 L {sub Edd}. Furthermore, in such flows, the nonthermal synchrotron radiation is emitted at energies of ≳ 1 keV, and therefore the Compton cooling is less efficient than in flows surrounding supermassive black holes. This may explain spectral differences between AGNs and black-hole transients around ∼0.01 L {sub Edd} (the latter being typically much harder)

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

An efficient numerical model for predicting residual stress and strain in parts manufactured by laser powder bed fusion

Abstract Computational modeling of additively manufactured structures plays an increasingly important role in product design and optimization. For laser powder bed fusion processes, the accurate modeling of stress and distortion requires large amount of computational cost due to very localized heat input and evolving complex geometries. The current study takes advantage of a graphics processing unit accelerated explicit finite element analysis code and approximated heat conduction analysis to predict the macroscopic thermo-mechanical behavior in laser selective melting. Adjacent layers and tracks were lumped to reduce the number of time steps and elements in the finite element model. The effects of track and layer grouping on prediction accuracy and solution efficiency are investigated to provide a guidance for a cost-effective simulation. Thin-wall builds from Inconel alloy 625 (IN625) powders were simulated by applying the developed modeling approach to get the detailed residual stress and distortion at a computational speed 50 times higher than conventional approach. Under repeated heating and cooling cycles, a high tensile stress was produced near surfaces of a build due to a larger shrinkage on surface than that in central area. It is also shown that horizontal stresses concentrate near the root and top layers of the IN625 build. The predicted residual elastic strain distribution was validated by the experimental measurement using x-ray synchrotron diffraction.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Computer vision models enable mixed linear modeling to predict arbuscular mycorrhizal fungal colonization using fungal morphology

Abstract The presence of Arbuscular Mycorrhizal Fungi (AMF) in vascular land plant roots is one of the most ancient of symbioses supporting nitrogen and phosphorus exchange for photosynthetically derived carbon. Here we provide a multi-scale modeling approach to predict AMF colonization of a worldwide crop from a Recombinant Inbred Line (RIL) population derived from Sorghum bicolor and S. propinquum . The high-throughput phenotyping methods of fungal structures here rely on a Mask Region-based Convolutional Neural Network (Mask R-CNN) in computer vision for pixel-wise fungal structure segmentations and mixed linear models to explore the relations of AMF colonization, root niche, and fungal structure allocation. Models proposed capture over 95% of the variation in AMF colonization as a function of root niche and relative abundance of fungal structures in each plant. Arbuscule allocation is a significant predictor of AMF colonization among sibling plants. Arbuscules and extraradical hyphae implicated in nutrient exchange predict highest AMF colonization in the top root section. Our work demonstrates that deep learning can be used by the community for the high-throughput phenotyping of AMF in plant roots. Mixed linear modeling provides a framework for testing hypotheses about AMF colonization phenotypes as a function of root niche and fungal structure allocations.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2016

Search for high-mass new phenomena in the dilepton final state using proton–proton collisions at s = 13 TeV with the ATLAS detector

A search is conducted for both resonant and non-resonant high-mass new phenomena in dielectron and dimuon final states. The search uses 3.2 fb-1of proton–proton collision data, collected at √s = 13 TeV by the ATLAS experiment at the LHC in 2015. The dilepton invariant mass is used as the discriminating variable. No significant deviation from the Standard Model prediction is observed; therefore limits are set on the signal model parameters of interest at 95% credibility level. Upper limits are set on the cross-section times branching ratio for resonances decaying to dileptons, and the limits are converted into lower limits on the resonance mass, ranging between 2.74 TeV and 3.36 TeV, depending on the model. Lower limits on the ℓℓqq contact interaction scale are set between 16.7 TeV and 25.2 TeV, also depending on the model.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗