Search NASA⌕ Search

SEARCH · Search NASA

Results for “Generalizable models”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Generalizable machine learning potentials for quantum-accurate predictions of non-equilibrium behavior in 2D materials

Machine learning interatomic potentials (ML-IAPs) are emerging as transformative tools in materials modeling, promising quantum-level accuracy at a fraction of the computational cost. However, their ability to generalize beyond equilibrium configurations and to reliably capture defect- and temperature-driven behavior remains underexplored. Here, we develop and benchmark two state-of-the-art ML-IAPs, Spectral Neighbor Analysis Potential (SNAP) and Allegro, on a comprehensive dataset for monolayer MoSe₂. Using density functional theory (DFT) as the reference, we evaluate their performance in capturing stress–strain behavior, phase transition energetics, defect evolution, edge stability, and fracture toughness. Allegro, a deep equivariant neural network potential, surpasses both SNAP and the classical Tersoff potential in accuracy, efficiency, and transferability. Importantly, both ML potentials accurately reproduce experimental fracture measurements and ab initio predictions of inversion domain formation—phenomena well beyond their training sets. Our findings establish ML-IAPs as viable replacements for traditional force fields in the study of non-equilibrium mechanical phenomena, enabling large-scale, high-fidelity simulations in 2D materials and beyond. In conclusion, this work provides a broadly applicable framework for data-driven modeling of structural and functional transformations under extreme conditions.

2D materials↗
DOE OSTI2026

MSD CoP Webinar: Modeling the Operations of Reservoir Systems with LLMs and Inverse Reinforcement Learning

Context: This panel featured three presentations centered on the common theme of applying LLMs and inverse reinforcement learning (IRL) to capture the complex human-environment interactions that are central to the operation of reservoir systems. Dr. Wyatt Arnold will kick off the webinar with a talk on how analyzing LLM chain-of-thought reasoning reveals sophisticated quantitative justification and risk awareness, showing promise as a bridge between quantitative models and value-driven water management decisions. Next, Dr. Matteo Giuliani will build on this with a discussion demonstrating that AI- and IRL-driven approaches can infer the trade-offs between flood control and water supply using historical observations. Finally, Dr. Rohan Singh Wilkho will close the webinar with a talk establishing IRL as a generalizable diagnostic tool for decoding decision-making in managed hydrologic and human-infrastructure systems. Across the three presentations, the application of LLMs and IRL opens new possibilities for the development of adaptive, transparent, and human-aware models supporting water management in an increasingly uncertain future. Presenters: Wyatt Arnold (Politecnico di Milano); Matteo Giuliani (Politecnico di Milano); Rohan Singh Wilkho (Cornell University) Moderator: Patrick M. Reed (MSD CoP Facilitation Team); Stefano Galelli (MSD CoP AI Working Group Co-Chair); David Gold (MSD CoP AI Working Group Co-Chair) This webinar was held on: June 23rd, 2026 from 12-1 PM EST.

Arnold, Wyatt [Politecnico di Milano]↗
DOE OSTI2025

Physics-informed latent neural operator for real-time predictions of time-dependent parametric PDEs

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied to systems with high-dimensional input-output mappings arising from large numbers of spatial and temporal collocation points, these models often require heavily overparameterized networks, leading to long training times. Latent DeepONet addresses some of these challenges by introducing a two-step approach: first learning a reduced latent space using a separate model, followed by operator learning within this latent space. While efficient, this method is inherently data-driven and lacks mechanisms for incorporating physical laws, limiting its robustness and generalizability in data-scarce settings. Here, in this work, we propose PI-Latent-NO, a physics-informed latent neural operator framework that integrates governing physics directly into the learning process. Our architecture features two coupled DeepONets trained end-to-end: a Latent-DeepONet that learns a low-dimensional representation of the solution, and a Reconstruction-DeepONet that maps this latent representation back to the physical space. By embedding PDE constraints into the training via automatic differentiation, our method eliminates the need for labeled training data and ensures physics-consistent predictions. The proposed framework is both memory and compute-efficient, exhibiting near-constant scaling with problem size and demonstrating significant speedups over traditional physics-informed operator models. We validate our approach on a range of parametric PDEs, showcasing its accuracy, scalability, and suitability for real-time prediction in complex physical systems.

Latent representations↗
DOE OSTI2026

A trait syndrome ties cell morphology to glycolysis across the yeast subphylum

Co-variation of traits provides fundamental insights into constraints governing their evolution. An inverse correlation between glucose uptake rates (GURs) and cell surface area-to-volume (SA:V) ratios across 11 yeast species was recently reported. Here, we expand the analysis to 282 species to assess the generalizability of this correlation across Saccharomycotina yeasts and the contribution of shared evolutionary history to the co-variation of these traits. Using phylogenetic regression models, we found extracellular acidification rates (ECARs, used as a proxy for GURs) were weakly, but significantly, correlated with SA:V across Saccharomycotina. ECARs were also correlated with genome sizes and growth rates. Our findings support the reported correlation between GURs and SA:V ratios, but suggest other associated traits, including genome sizes. Specifically, yeasts that consume glucose faster tend to have lower SA:V, faster growth rates, and larger genomes, suggesting a trait syndrome governing several metabolic, genomic, and morphological traits across the yeast subphylum.

biological sciences↗
DOE OSTI2025

Spontaneously formed phonon frequency combs in van der Waals solid CrGeTe 3 and CrSiTe 3

Optical phonon engineering through nonlinear effects has been utilized in ultrafast control of material properties. However, nonlinear optical phonons typically exhibit rapid decay due to strong mode-mode couplings, limiting their effectiveness in temperature or frequency sensitive applications. Here we report the observation of long-lived nonlinear optical phonons through the spontaneous formation of phonon frequency combs in the van der Waals material CrXTe 3 (X=Ge, Si) using high-resolution Raman scattering. Unlike conventional optical phonons, the highest A g mode in CrGeTe 3 splits into equidistant, sharp peaks forming a frequency comb that persists for hundreds of oscillations and survives up to 200K. These modes correspond to localized oscillations of Ge 2 Te 6 clusters, isolated from Cr hexagons, behaving as independent quantum oscillators. Introducing a cubic nonlinear term to the harmonic oscillator model, we simulate the phonon time evolution and successfully replicate the observed comb structure. Similar frequency comb behavior is observed in CrSiTe 3 , demonstrating the generalizability of this phenomenon. Our findings demonstrate that Raman scattering effectively probes high-frequency nonlinear phonon modes, offering insight into the generation of long-lived, tunable phonon frequency combs with potential applications in ultrafast material control and phonon-based technologies.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Advancing stream temperature prediction with a generalizable large-sample framework across CONUS river reaches

Accurately predicting stream temperature in ungauged basins remains a critical challenge for water resource management, thermoelectric power plant cooling, and ecosystem conservation. Large-sample machine learning models trained on hundreds of well-monitored river basins have shown remarkable performance; however, such models have yet to be developed solely using forcing data that can be readily extracted to simulate stream temperatures anywhere in the contiguous United States (CONUS). In this study, we present a scalable, large-sample deep learning framework using Long Short-Term Memory (LSTM) networks to simulate daily stream temperatures in ungauged basins across the CONUS. The framework leverages both modeled reanalysis of meteorological and streamflow inputs as well as static attributes available for all 2.7 million CONUS river reaches in the National Hydrography Dataset Plus (NHDPlusV2). By generating dynamical inputs from predefined thermally relevant upstream contributing areas, rather than the entire upstream basin, the model also offers improvements in very large basins where full-basin averaging can dilute the most important influences on stream temperature. Evaluated across 300 basins, the model achieves a median Mean Absolute Error (MAE) of 1.1 °C and a Nash-Sutcliffe Efficiency (NSE) of 0.95 on temporally and spatially distinct test folds—comparable to models trained exclusively using meteorological and streamflow observational data. The flexible, high-performing framework generalizes to any unmonitored river reach without significant regulation or unnatural thermal input immediately upstream, substantially expanding predictive capabilities in data-scarce regions.

Hydrology↗
DOE OSTI2025

Descriptor: High Temporal Resolution Meteorological Data at Oak Ridge Reservation (ORR-HiResMet)

Access to continuous, quality assessed meteorological data is critical for understanding the climatology and atmospheric dynamics of a region. Research facilities like Oak Ridge National Laboratory (ORNL) rely on such data to assess site-specific climatology, model potential emissions, establish safety baselines, and prepare for emergency scenarios. To meet these needs, on-site towers at ORNL collect meteorological data at 15-minute and hourly intervals. However, data measurements from meteorological towers are affected by sensor sensitivity, degradation, lightning strikes, power fluctuations, glitching, and sensor failures, all of which can affect data quality. To address these challenges, we conducted a comprehensive quality assessment and processing of five years of meteorological data collected from ORNL at 15-minute intervals, including measurements of temperature, pressure, humidity, wind, and solar radiation. The time series of each variable was pre-processed and gap-filled using established meteorological data collection and cleaning techniques, i.e., the time series were subjected to structural standardization, data integrity testing, automated and manual outlier detection, and gap-filling. The data product and highly generalizable processing workflow developed in Python Jupyter notebooks are publicly accessible online. As a key contribution of this study, the evaluated 5-year data will be used to train atmospheric dispersion models that simulate dispersion dynamics across the complex ridge-and-valley topography of the Oak Ridge Reservation in East Tennessee.

Steckler, Morgan R. [Oak Ridge National Laboratory↗
DOE OSTI2026

Substitution or Shared Utilization? Intrahousehold Vehicle Use in Mixed-Powertrain Households

While previous research has focused heavily on understanding the factors deriving alternative fuel vehicle adoption rates, there remains a significant gap in understanding how households distribute mileage across different powertrains. This study utilizes data from the 2022 Next Generation National Household Travel Survey to investigate vehicle miles traveled within a sample of 150 plug-in electric vehicle (PEV)-owning households (in which at least one battery electric vehicle is present), characterizing how different powertrains are integrated into daily mobility. Leveraging a Seemingly Unrelated Regression (SUR) framework the study jointly models the utilization of PEVs, hybrid electric vehicles (HEV), and internal combustion engine vehicles (ICEVs) while accounting for household-level substitution effects. The results provide evidence of an asymmetric substitution effect. In households with mixed-powertrain configurations, the ICEV captures a substantially higher share of household miles (compared with the PEV), acting as a utility sponge. Conversely, the model identifies specific socioeconomic and geographic cohorts that prioritize PEV as the primary household workhorse, indicating a systematic sorting effect. Although the sample size limits broader generalizability, these findings suggest that PEVs are used for frequent, specific routine-intensive roles, whereas the ICEV remains a specialized utility vehicle. These insights highlight distinct intrahousehold vehicle use behaviors that are often obscured by aggregate fleetwide statistics.

25 ENERGY STORAGE↗
DOE OSTI2024

Tapping the treasure trove of atypical phages

With advancements in genomics technologies, a vast diversity of ‘atypical’ phages, that is, with single-stranded DNA or RNA genomes, are being uncovered from different ecosystems. Though these efforts have revealed the existence and prevalence of these nonmodel phages, computational approaches often fail to associate these phages with their specific bacterial host(s), while the lack of methods to isolate these phages has limited our ability to characterize infectivity pathways and new gene function. In this review, we call for the development of generalizable experimental methods to better capture this understudied viral diversity via isolation and study them through gene-level characterization and engineering. Establishing a diverse set of new ‘atypical’ phage model systems has the potential to provide many new biotechnologies, including potential uses of these atypical phages in halting the spread of antibiotic resistance and engineering of microbial communities for beneficial outcomes.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Ecological Insights from Transferable Plant Biomass Mapping across the Arctic using High-resolution Structure-from-Motion and LiDAR Data

Warmer temperatures, permafrost thaw, and increased wildfire activity are driving rapid ecological change across the Arctic, significantly altering plant productivity and aboveground biomass (AGB). These rapid changes highlight the urgent need to improve monitoring of vegetation dynamics in the Earth’s northern ecosystems, where high spatiotemporal heterogeneity occurs at scales finer than those captured by traditional satellite observations. The growing use of Unoccupied Aerial Systems (UASs) presents an opportunity to overcome this limitation. Yet, the diversity of UAS platforms, sensors, and data collection and processing workflows presents challenges for developing standardized, generalizable approaches. To address this challenge, we compiled 672 AGB plots co-located with 183 UAS-based Structure-from-Motion (SfM) or Light Detection and Ranging (LiDAR) surveys collected across the Arctic. Here, we: (1) evaluated the generalizability of UAS-derived canopy structure derived from high-resolution SfM and LiDAR for estimating AGB, (2) assessed scaling errors and their sources in two recent satellite-based AGB products derived from Landsat and MODIS, and (3) demonstrated the use of high-resolution AGB maps to quantify biomass variation across tundra plant functional types (PFTs) and to monitor post-fire recovery. Our results show that both SfM and LiDAR accurately captured AGB and its variability across tundra PFTs using a Random Forest (RF) model (overall RMSE: 0.336 kg/m2), with mapping performance varying slightly by region and data source. Using UAS-derived AGB maps as a benchmark, we identified systematic biases in satellite-derived AGB products, largely attributable to the magnitude of AGB and structural heterogeneity within coarse-resolution pixels. Applying our model to repeat UAS surveys following a tundra fire on Seward Peninsula, we observed rapid AGB recovery in non-shrub patches, with biomass recovering to pre-fire levels within 2 years. In contrast, shrub patches recovered more slowly, with AGB gains continuing over 2–4 years through both in-patch growth and lateral expansion (via dispersal) into remaining burned areas. Overall, these findings demonstrate the generalizability of UAS-based SfM and LiDAR data for estimating tundra AGB and highlight the potential of our approach to be broadly applied to generate high-quality AGB data for ecological monitoring and model benchmarking across the Arctic.

Yang, Daryl [ORNL] (ORCID:0000000317057823)↗
DOE OSTI2026

Mesoscale atomic engineering in a crystal lattice

Controlling individual atoms using lasers, ion traps and scanning probe tips has transformed our understanding of matter and enabled breakthroughs in quantum science. Extending this control into three-dimensional (3D) solids and across mesoscopic scales, however, remains a foundational challenge. Electron irradiation in electron microscopes is known to induce atomic displacements, and atomic manipulation has been proposed and demonstrated. Yet repeated and deterministic control has remained elusive. Here, in this study, we demonstrate deterministic atomic engineering in a 3D crystal, creating ordered arrangements of more than 40,000 user-defined defects within minutes across a 150 nm × 100 nm × 13 nm volume. By steering individual Cr atoms in the magnetic semiconductor CrSBr into selected interstitial sites using an electron beam directed with sub-20-pm-scale accuracy, we create vacancy–interstitial complexes. The resulting impurity array forms a mesoscale crystal embedded within the host lattice, a new form of engineered artificial matter that remains stable at room temperature and outside the microscope. By tracking Cr atom displacements, we identify conditions under which the defect structures are predictable. Our calculations suggest that these defects form correlated impurity states with intra-defect optical transitions and inter-defect kinetic and Coulomb interactions. This establishes a generalizable platform for atomic defect engineering at mesoscopic, and potentially macroscopic, scales, opening opportunities for scalable quantum technologies, including deterministic colour-centre placement, quantum simulation of many-body lattice models and atomic-scale manufacturing.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2025

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

Decoding visual experiences from fMRI offers a powerful avenue to understand human perception and develop advanced brain-computer interfaces. However, current progress often prioritizes maximizing reconstruction fidelity while overlooking interpretability, an essential aspect for deriving neuroscientific insight. To address this gap, we propose MoRE-Brain, a neuro-inspired framework designed for high-fidelity, adaptable, and interpretable visual reconstruction. MoRE-Brain uniquely employs a hierarchical Mixture-of-Experts architecture where distinct experts process fMRI signals from functionally related voxel groups, mimicking specialized brain networks. The experts are first trained to encode fMRI into the frozen CLIP space. A finetuned diffusion model then synthesizes images, guided by expert outputs through a novel dual-stage routing mechanism that dynamically weighs expert contributions across the diffusion process. MoRE-Brain offers three main advancements: First, it introduces a novel Mixture-of-Experts architecture grounded in brain network principles for neuro-decoding. Second, it achieves efficient cross-subject generalization by sharing core expert networks while adapting only subject-specific routers. Third, it provides enhanced mechanistic insight, as the explicit routing reveals precisely how different modeled brain regions shape the semantic and spatial attributes of the reconstructed image. Extensive experiments validate MoRE-Brain’s high reconstruction fidelity, with bottleneck analyses further demonstrating its effective utilization of fMRI signals, distinguishing genuine neural decoding from over-reliance on generative priors. Consequently, MoRE-Brain marks a substantial advance towards more generalizable and interpretable fMRI-based visual decoding.

Wei, Yuxiang [Georgia Institute of Technology]↗
DOE OSTI2024

Producing multiple chemicals through biological upcycling of waste poly(ethylene terephthalate)

Poly(ethylene terephthalate) (PET) waste is of low degradability in nature, and its mismanagement threatens numerous ecosystems. To combat the accumulation of waste PET in the biosphere, PET bio-upcycling, which integrates chemical pretreatment to produce PET-derived monomers with their microbial conversion into value-added products, has shown promise. The recently discovered Rhodococcus jostii strain PET (RPET) can metabolically degrade terephthalic acid (TPA) and ethylene glycol (EG) as sole carbon sources, and it has been developed into a microbial chassis for PET upcycling. However, the scarcity of synthetic biology tools, specifically designed for the non-model microbe RPET, limits the development of a microbial cell factory for expanding the repertoire of bioproducts from post-consumer PET. Herein, we describe the development of potent genetic tools for RPET, including (1) two inducible and titratable expression systems for tunable gene expression and (2) Serine Integrase-based Recombinational Tools (SIRT) for genome editing. Using these tools, we systematically engineer the RPET strain to ultimately establish microbial supply chains for producing multiple chemicals, including lycopene, lipids, and succinate, from post-consumer PET waste bottles, achieving the highest titer of lycopene ever reported thus far in RPET (i.e., 22.6 mg/L of lycopene, approximately 10,000-fold higher than that of the wild-type strain). Furthermore, this work highlights the great potential of plastic upcycling as a generalizable means of sustainable production of diverse chemicals.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Statistically-driven Experimental Design to Improve Reference-free Quantification of Small Molecules by Liquid Chromatography-Mass Spectrometry

Non-targeted analysis of small molecules and metabolites in unknown, complex samples using liquid chromatography-tandem mass spectrometry remains challenging. One of the main bottlenecks is the extensive unannotated regions of metabolomics mass spectrometry data, resulting in knowledge gaps. Small molecule annotation in mass spectrometry data has conventionally relied on reference standards and libraries for compound identification and confirmation, which can constrain compound identification to those molecules already known, thus limiting the ability to discover new knowledge and new markers. Retention time prediction can facilitate and expedite unknown compound identification in non-targeted analysis of complex metabolomics samples. Additionally, accurate retention time predictions can also inform sample mixture design for LC-MS/MS analyses. However, current machine learning-based methods for retention time prediction are typically developed for specific chromatographic platforms and are not generalizable across scales. And while technologies and methods to improve reference-free metabolite identification for more comprehensive annotation of unknowns has received much attention, development of the same for quantitation without reference standards has been much more limited, despite its importance in toxicological, environmental, food safety, forensics, and clinical applications. We believe that a reference-free quantitation strategy that exploits mass spectrometry data already collected for reference-free identification can provide much more insight on unknowns, and move the metabolomics field for more complete unknowns characterization. As such, we pursue two efforts to improve upon current state-of-the-art methods in non-targeted analysis: (1) machine learning-based retention time prediction and (2) statistical design of experiments framework for reference-free quantitation. In this work, we develop and demonstrate (1) a generalizable retention time prediction capability across chromatographic conditions and scales, and (2) a statistical design-based framework for response factor contribution elucidation and reference-free quantitation. Evaluation of our retention time prediction model, PrediToR, showed approximately 24% improvement over current models, and we observed approximately 10X improvement in concentration estimation accuracy from our statistical design-based response factor model over a primarily ionization efficiency-based model. We expect that future efforts to improve upon these new capabilities will further advance non-targeted analysis of small molecules towards truly reference-free metabolomics.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Surrogates for Valve-Controlled Pipe Flow: Accelerating Nuclear Reactor Design

Neural surrogate models are developed to replace expensive steady-state RANS CFD simulations for valve-controlled pipe flow in nuclear reactor design. Using parametric CFD data generated with MOOSE Pronghorn across a range of valve geometry and flow conditions, three approaches are compared: a POD-based reduced-order model, a structured UNet on a cylindrical grid, and unstructured models (DeepONet and BiStride MeshGraphNet) on nondimensionalized point clouds. POD achieves the highest accuracy (99%) with fast inference but requires storing all solution snapshots, while the DeepONet and BSMS-GNN both achieve ~89% accuracy at sub-second inference, with the BSMS-GNN offering superior geometric generalizability. These surrogates enable rapid ranking of candidate valve designs and can warm-start CFD solvers to accelerate convergence, supporting agentic design iteration on the Prometheus platform.

42 - ENGINEERING↗
NASA NTRSDate not supplied

Nearest-Neighbor Machine Learning Feature Selection for Interpretation of Microbial Molecular Signatures from Isotope Ratio Mass Spectrometry Data

Mass spectrometry (MS) promises to be a powerful tool for potential biosignature detection during astrobiological missions on ocean worlds in our solar system. Accurate and generalizable machine learning methods could enhance science return on investment by predicting seawater chemistry and classifying isotopic biosignatures, either as a signature consistent with microbial life (biotic) or as a novelty (unclassified/unique). However, machine learning models are likely to be complex and involve interactions between MS features, making biosignatures difficult to interpret. Feature selection methods provide biological and chemical context that help interpret the mechanisms of machine learning models, but these methods also need the ability to detect complex interactions. Previously, we developed a machine learning feature selection algorithm called nearest-neighbor projected distance regression (NPDR) that has the ability to identify important model features that involve complex interactions and automatically reduce correlation and the dimensionality in a high-dimensional variable space. The standard distance metrics used in NPDR – Manhattan and Euclidean – assume the multivariate data are isotropic, which is often violated in real data due to differences in the covariance between variables. Thus, we extend NPDR to include a random forest distance, and other anisotropic distance metrics, for computing nearest neighbors. We also augment the isotope-ratio MS data with time-series features from the raw MS signal to improve biotic classification. We test NPDR on our novel experimental ocean world seawater analog MS data. We measure isotope fractionations of volatile CO 2 that could be measured in exospheres or plumes. Samples include baseline abiotic conditions using a range of possible seawater chemistry consistent with Europa and Enceladus, and biotic samples that include microbes in these seawaters. We use penalized NPDR with random forest proximity to identify interpretable microbial molecular signatures. We compare features with random forest importance, and we train a classifier that discriminates between biotic and abiotic samples with high accuracy. These ML-trained ocean-world analog MS data could be used to assist in identifying biosignatures during future missions.

geochemistry↗
DOE OSTI2025

A physics-constrained neural ordinary differential equations approach for robust learning of stiff chemical kinetics

The high computational cost associated with solving for detailed chemistry poses a significant challenge for predictive computational fluid dynamics (CFD) simulations of turbulent reacting flows. While deep learning techniques have been explored to develop faster surrogate models, they often fail to integrate reliably with CFD solvers. This instability arises because traditional deep learning approaches optimize for training error without ensuring compatibility with ordinary differential equation (ODE) solvers, resulting in accumulation of errors over time. Recently, neuralODE (NODE) based approaches have been shown to be a promising technique to emulate and accelerate detailed chemistry computations. Here, in the present work, we extend this NODE framework for stiff chemical kinetics by incorporating mass conservation constraints directly into the loss function during training. This ensures that the total mass as well as the individual elemental species masses are conserved in an a-posteriori manner. Proof-of-concept studies are performed with the novel physics-constrained NODE (PC-NODE) approach for homogeneous autoignition of hydrogen-air mixture over a range of composition and thermodynamic conditions. It is demonstrated that the PC-NODE framework not only improves the physical consistency of the resulting data-driven model with respect to mass conservation criteria, but also improves training efficiency. PC-NODE is shown to achieve 2–100× speedup relative to the hydrogen-air detailed chemical mechanism depending on the type of the ODE solver (implicit or explicit) used during autoregressive inference tests. Lastly, a-posteriori studies are performed wherein the trained PC-NODE model is coupled with a CFD solver. It is shown that higher accuracy is achieved with PC-NODE relative to the purely data-driven NODE approach. Moreover, PC-NODE also exhibits robustness and generalizability to unseen initial conditions from within (interpolative capability) as well as outside (extrapolative capability) the training regime.

computational combustion↗