Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Robust artificial intelligence”

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.

173 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Knowledge-guided graph machine learning for spatially distributed prediction of daily discharge and nitrogen export dynamics

Spatially distributed prediction of streamflow and nitrogen export dynamics is essential for precision management of agricultural watersheds. While temporal deep learning models such as Long Short-Term Memory (LSTM) have shown strong performance at basin scales, their ability to generalize spatially is limited by insufficient representation of spatial dependencies and flow paths, particularly under data-scarce conditions. To address this gap, we propose HydroGraphNet, a knowledge-guided graph machine learning framework that integrates process-based knowledge and explicit spatial learning into temporal modeling. This framework incorporates directed graph topology to encode watershed connectivity and upstream inflows, with mass balance constraints to improve physical consistency. To enhance generalization in sparsely monitored regions, HydroGraphNet is pretrained on synthetic data generated by the SWAT+ (Soil and Water Assessment Tool Plus) model. We evaluated HydroGraphNet in the Upper Sangamon River Basin (44 HUC-12 subwatersheds, 2001–2020) against two LSTM baselines: a lumped basin-level model and a distributed variant. When benchmarked on SWAT+ simulations in pretraining, HydroGraphNet improved test NSEs by 8.9% (discharge) and 13.7% (NO₃–N load) in temporal extrapolation, and by 27.1% and 34.7% in spatial extrapolation, relative to the Lumped LSTM baseline. After fine-tuning with USGS monitoring data, the model achieved mean test NSE (KGE) scores of 0.768 (0.861) for discharge and 0.626 (0.664) for NO₃–N load, substantially outperforming baselines. Attribution analysis further highlighted the importance of upstream inflow representation and graph-based spatial learning in capturing cross-subwatershed dependencies. The model also reproduced seasonal hydrological and biogeochemical patterns consistent with known processes, demonstrating its robustness and process fidelity for spatially distributed prediction. Altogether, HydroGraphNet advances the integration of physical knowledge and spatially explicit learning in hydrological modeling, offering a generalizable framework for distributed modeling to support spatially targeted water quality management in data-scarce watersheds.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Two-Stage Wildlife Event Classification for Edge Deployment

Camera-based wildlife monitoring is often overwhelmed by non-target triggers and slowed by manual review or cloud-dependent inference, which can prevent timely intervention for high stakes human–wildlife conflicts. Our key contribution is a deployable, fully offline edge vision sensor that achieves near-real-time, highly accurate wildlife event classification by combining detector-based empty-image suppression with a lightweight classifier trained with a staged transfer-learning curriculum. Specifically, Stage 1 uses a pretrained You Only Look Once (YOLO)-family detector for permissive animal localization and empty-trigger suppression, and Stage 2 uses a lightweight EfficientNet-based binary classifier to confirm puma on detector crops and gate downstream actions. Our design is robust to low-quality nighttime monochrome imagery (motion blur, low contrast, illumination artifacts, and partial-body captures) and operates using commercially available components in connectivity-limited settings. In field deployments running since May 2025, end-to-end latency from camera trigger to action command is approximately 4 s. Ablation studies using a dataset of labeled wildlife images (pumas, not pumas) show that the two-stage approach substantially reduces false alarms in identifying pumas relative to a full-image classifier while maintaining high recall. On the held-out test set (N = 1434 events), the proposed two-stage cascade achieves precision 0.983, recall 0.975, F1 0.979, accuracy 0.986, and balanced accuracy 0.983, with only 8 false positives and 12 false negatives. The system can be easily adapted for other species, as demonstrated by rapid retraining of the second stage to classify ringtails. Downstream responses (e.g., notifications and optional audio/light outputs) provide flexible actuation capabilities that can be configured to support intervention.

58 GEOSCIENCES↗
DOE OSTI2026

Reduced‐Order Modeling of Energetic Materials Using Physics‐Aware Recurrent Convolutional Neural Networks in a Latent Space (LatentPARC)

Physics-aware deep learning (PADL) has gained popularity for use in spatiotemporal dynamics simulations, such as those in computational modeling of energetic materials (EM). We show that the challenge PADL methods face while learning complex field evolution problems can be simplified and accelerated by decoupling it into two tasks: learning complex geometric features in evolving fields and modeling dynamics over these features in a lower-dimensional feature space. We build upon our previous work on physics-aware recurrent convolutional neural networks (PARC). PARC embeds knowledge of underlying physics into its neural network architecture for more robust and accurate prediction of evolving physical fields. PARC was shown to effectively learn complex nonlinear features such as the formation of hotspots and coupled shock fronts in various initiation scenarios of EMs, as a function of microstructures, serving effectively as a microstructure-aware burn model. Here, we further accelerate PARC and reduce its computational cost by projecting the original dynamics onto a lower-dimensional invariant manifold, or “latent space.” The projected latent representation encodes the complex geometry of evolving fields (e.g., temperature and pressure) in a set of data-driven features. The reduced dimension of this latent space allows us to learn the dynamics during the initiation of EM with a lighter and more efficient model. We observe a significant decrease in training and inference time while maintaining results comparable to PARC at inference. This work takes steps towards enabling rapid prediction of EM thermomechanics at larger scales and characterization of EM structure–property–performance linkages at a full application scale.

Mathematics and Computing↗
DOE OSTI2025

Nonlinear Ensemble Filtering with Diffusion Models: Application to the Surface Quasigeostrophic Dynamics

The intersection between classical data assimilation methods and novel machine learning techniques has attracted significant interest in recent years. Here, we explore another promising solution in which diffusion models are used to formulate a robust nonlinear ensemble filter for sequential data assimilation. Unlike standard machine learning methods, the proposed ensemble score filter (EnSF) is completely training free and can efficiently generate a set of analysis ensemble members. Here, in this study, we apply the EnSF to a surface quasigeostrophic model and compare its performance against the popular local ensemble transform Kalman filter (LETKF), which makes Gaussian assumptions in the analysis step. Numerical tests demonstrate that EnSF maintains stable performance in the absence of localization and for a variety of experimental settings. We find that while LETKF maintains optimal performance in the case of linear observations of the entire state and a perfect model, EnSF shows improvements over LETKF when nonlinear observations are assimilated and the system is subject to unexpected model errors. A spectral decomposition of the analysis results in this nonlinear observation regime shows that the largest improvements over LETKF occur at large scales (small wavenumbers), where LETKF lacks sufficient ensemble spread. Overall, this initial application of EnSF to a geophysical model of intermediate complexity motivates further development of the algorithm for more realistic problems.

Artificial intelligence↗
DOE OSTI2025

Integration of LIBS with Machine Learning for Real-Time Monitoring of Feedstock in H 2 Gasification Applications

This project, funded by the U.S. Department of Energy (DOE) – Office of Fossil Energy under Award Number DE-FE0032177, aimed to assess the feasibility of an integrated Laser-Induced Breakdown Spectroscopy (LIBS) system with advanced machine learning (ML) models for real-time characterization and potential control of hydrogen gasifiers running on waste materials as feedstocks. This was a multidisciplinary effort that encompassed the acquisition and standardized analysis of individual and blended feedstocks—comprising biomass, coal waste, and plastic waste, followed by the development of a dynamic LIBS bench system for material sample analysis and development of predictive ML models. Comprehensive laboratory testing enabled the creation of a robust elemental dataset that served as the foundation for ML model training. Techniques such as Random Forest, Gradient Boosting, Support Vector Regression, and Neural Networks were employed to predict key feedstock properties, including higher heating value (HHV), moisture content, thermal conductivity, and ash composition with high accuracy. The results were validated against experimental data and demonstrated strong potential for real-time application in gasifier control systems. The project concluded with a study on the integration of the LIBS+ML approach for gasifier control and a techno-economic analysis of the implementation of the approach into hydrogen (H 2 ) gasification systems. Dissemination of results was carried out at a DOE meeting. This work establishes a scalable framework for automated, in-line feedstock quality assessment, offering significant implications for process optimization and emissions reduction in hydrogen production.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2025

A Digital Twin Framework Utilizing Machine Learning for Robust Predictive Maintenance: Enhancing Tire Health Monitoring

We introduce a novel digital twin (DT) framework for the predictive maintenance of long-term physical systems. Using monitoring tire health as an application, we show how the DT framework can be used to enhance automotive safety and efficiency, and how the technical challenges can be overcome using a three-step approach. First, to manage the data complexity over a long operation span, we employ data reduction techniques to concisely represent physical tires using historical performance and usage data. Relying on these data, for fast real-time prediction, we train a transformer-based model offline on our concise dataset to predict future tire health over time, represented as remaining casing potential (RCP). Based on our architecture, our model quantifies both epistemic and aleatoric uncertainties, providing reliable confidence intervals around predicted RCP. Second, to incorporate real-time data, we update the predictive model in the DT framework, ensuring its accuracy throughout its lifespan with the aid of hybrid modeling and the use of the discrepancy function. Third, to assist decision-making in predictive maintenance, we implement a tire state decision algorithm, which strategically determines the optimal timing for tire replacement based on RCP forecasted by our transformer model. This approach ensures that our DT accurately predicts system health, continually refines its digital representation, and supports predictive maintenance decisions. Furthermore, our framework effectively embodies a physical system, leveraging big data and machine learning (ML) for predictive maintenance, model updates, and decision-making.

advanced computing infrastructure↗
DOE OSTI2025

High-redshift millennium and astrid galaxies in effective field theory at the field level

Effective field theory (EFT) modeling is expected to be a useful tool in the era of future higher-redshift galaxy surveys such as DESI-II and Spec-S5 due to its robust description of various large-scale structure tracers. However, large values of EFT bias parameters of higher-redshift galaxies could jeopardize the convergence of the perturbative expansion. Here, in this paper we measure the bias parameters and other EFT coefficients from samples of two types of star-forming galaxies in the state-of-the-art MilleniumTNG and astrid hydrodynamical simulations. Our measurements are based on the field-level EFT forward model that allows for precision EFT parameter measurements by virtue of cosmic variance cancellation. Specifically, we consider approximately representative samples of Lyman-break galaxies (LBGs) and Lyman-𝛼 emitters (LAEs) that are consistent with the observed (angular) clustering and number density of these galaxies at 𝑧 = 3. Reproducing the linear biases and number densities observed from existing LAE and LBG data, we find quadratic bias parameters that are roughly consistent with those predicted from the halo model coupled with a simple halo occupation distribution model. We also find nonperturbative velocity contributions (fingers of God) of a similar size for LBGs to the familiar case of luminous red galaxies. However, these contributions are quite small for LAEs despite their large satellite fraction values of up to ∼ 30%. Our results indicate that the effective momentum reach 𝑘 max at 𝑧 = 3 for LAEs (LBGs) will be in the range 0.3−0.6⁢ℎ Mpc −1 (0.2−0.8⁢ℎ Mpc −1 ), suggesting that EFT will perform well for high-redshift galaxy clustering. This work provides the first step toward obtaining realistic simulation-based priors on EFT parameters for LAEs and LBGs.

Sullivan, James M. [Massachusetts Inst. of Technol↗
DOE OSTI2025

SIDDA: SInkhorn Dynamic Domain Adaptation for image classification with equivariant neural networks

Modern neural networks (NNs) often do not generalize well in the presence of a ‘covariate shift’; that is, in situations where the training and test data distributions differ, but the conditional distribution of classification labels given the data remains unchanged. In such cases, NN generalization can be reduced to a problem of learning more robust, domain-invariant features. Domain adaptation (DA) methods include a broad range of techniques aimed at achieving this; however, these methods have struggled with the need for extensive hyperparameter tuning, which then incurs significant computational costs. In this work, we introduce SInkhorn Dynamic Domain Adaptation (SIDDA), an out-of-the-box DA training algorithm built upon the Sinkhorn divergence, that can achieve effective domain alignment with minimal hyperparameter tuning and computational overhead. We demonstrate the efficacy of our method on multiple simulated and real datasets of varying complexity, including simple shapes, handwritten digits, real astronomical observations, and remote sensing data. These datasets exhibit covariate shifts due to noise, blurring, differences between telescopes, and variations in imaging wavelengths. SIDDA is compatible with a variety of NN architectures, and it works particularly well in improving classification accuracy and model calibration when paired with symmetry-aware equivariant NNs (ENNs). We find that SIDDA consistently enhances the generalization capabilities of NNs, achieving up to a ${\approx}40\%$ improvement in classification accuracy on unlabeled target data, while also providing a more modest performance gain of $\lesssim 1\%$ on labeled source data. We also study the efficacy of DA on ENNs with respect to the varying group orders of the dihedral group DN, and find that the model performance improves as the degree of equivariance increases. Finally, if SIDDA achieves proper domain alignment, it also enhances model calibration on both source and target data, with the most significant gains in the unlabeled target domain—achieving over an order of magnitude improvement in the expected calibration error and Brier score. SIDDA’s versatility across various NN models and datasets, combined with its automated approach to domain alignment, has the potential to significantly advance multi-dataset studies by enabling the development of highly generalizable models.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

INTEGRATE - Inverse Network Transformations for Efficient Generation of Robust Airfoil and Turbine Enhancements

The INTEGRATE (Inverse Network Transformations for Efficient Generation of Robust Airfoil and Turbine Enhancements) project is developing a new inverse-design capability for the aerodynamic design of wind turbine rotors using invertible neural networks. This AI-based design technology can capture complex non-linear aerodynamic effects while being 100 times faster than design approaches based on computational fluid dynamics. This project enables innovation in wind turbine design by accelerating time to market through higher-accuracy early design iterations to reduce the levelized cost of energy. INVERTIBLE NEURAL NETWORKS Researchers are leveraging a specialized invertible neural network (INN) architecture along with the novel dimension-reduction methods and airfoil/blade shape representations developed by collaborators at the National Institute of Standards and Technology (NIST) learns complex relationships between airfoil or blade shapes and their associated aerodynamic and structural properties. This INN architecture will accelerate designs by providing a cost-effective alternative to current industrial aerodynamic design processes, including: - Blade element momentum (BEM) theory models: limited effectiveness for design of offshore rotors with large, flexible blades where nonlinear aerodynamic effects dominate - Direct design using computational fluid dynamics (CFD): cost-prohibitive - Inverse-design models based on deep neural networks (DNNs): attractive alternative to CFD for 2D design problems, but quickly overwhelmed by the increased number of design variables in 3D problems AUTOMATED COMPUTATIONAL FLUID DYNAMICS FOR TRAINING DATA GENERATION - MERCURY FRAMEWORK The INN is trained on data obtained using the University of Marylands (UMD) Mercury Framework, which has with robust automated mesh generation capabilities and advanced turbulence and transition models validated for wind energy applications. Mercury is a multi-mesh paradigm, heterogeneous CPU-GPU framework. The framework incorporates three flow solvers at UMD, 1) OverTURNS, a structured solver on CPUs, 2) HAMSTR, a line based unstructured solver on CPUs, and 3) GARFIELD, a structured solver on GPUs. The framework is based on Python, that is often used to wrap C or Fortran codes for interoperability with other solvers. Communication between multiple solvers is accomplished with a Topology Independent Overset Grid Assembler (TIOGA). NOVEL AIRFOIL SHAPE REPRESENTATIONS USING GRASSMAN SPACES We developed a novel representation of shapes which decouples affine-style deformations from a rich set of data-driven deformations over a submanifold of the Grassmannian. The Grassmannian representation as an analytic generative model, informed by a database of physically relevant airfoils, offers (i) a rich set of novel 2D airfoil deformations not previously captured in the data , (ii) improved low-dimensional parameter domain for inferential statistics informing design/manufacturing, and (iii) consistent 3D blade representation and perturbation over a sequence of nominal shapes. TECHNOLOGY TRANSFER DEMONSTRATION - COUPLING WITH NREL WISDEM Researchers have integrated the inverse-design tool for 2D airfoils (INN-Airfoil) into WISDEM (Wind Plant Integrated Systems Design and Engineering Model), a multidisciplinary design and optimization framework for assessing the cost of energy, as part of tech-transfer demonstration. The integration of INN-Airfoil into WISDEM allows for the design of airfoils along with the blades that meet the dynamic design constraints on cost of energy, annual energy production, and the capital costs. Through preliminary studies, researchers have shown that the coupled INN-Airfoil + WISDEM approach reduces the cost of energy by around 1% compared to the conventional design approach. This page will serve as a place to easily access all the publications from this work and the repositories for the software developed and released through this pr...

aerodynamics↗
DOE OSTI2026

The DREAMS Project: Disentangling the Impact of Halo-to-halo Variance and Baryonic Feedback on Milky Way Satellite Galaxies

We analyze the properties of satellite galaxies around 1024 Milky Way–mass hosts from the DREAMS Project, simulated within a ΛCDM cosmology. Utilizing the TNG galaxy-formation model, the DREAMS simulations incorporate both baryonic physics and cosmological uncertainties for a large sample of galaxies with diverse environments and formation histories. We investigate the relative impact of the physical uncertainty from the galaxy-formation model on predicted satellite properties using four metrics: the satellite stellar mass function, radial distribution, inner slope of the dark matter density profile, and stellar half-light radius. We compare these predictions to observations from the SAGA survey and the DREAMS N-body simulations and find that uncertainties from baryonic physics modeling are subdominant to the scatter arising from halo-to-halo variance. Where baryonic modeling does affect satellites, the supernova wind energy has the largest effect on the satellite properties that we investigate. Specifically, increased supernova wind energy suppresses the stellar mass of satellites and results in more extended stellar half-light radii. The adopted wind speed has only a minor impact, and other astrophysical and cosmological parameters show no measurable effect. Our findings highlight the robustness of satellite properties against uncertainties in baryonic physics modeling.

Rose, Jonah C. [Princeton University, NJ (United S↗
DOE OSTI2025

TRAILS Output Files

Overview This data repository contains ZIP files that store compressed versions of the output of running the WaterPaths utility planning and management tool in the DU Re-Evaluation mode (to download the tool, please see this GitHub repository). The tool was used to simulate the six-utility North Carolina Research Triangle problem. Details on the contents of each ZIP file can be seen below. Data details Temporal range: Weekly data for 2,344 weeks from 2015 to 2060 (45 years). Spatial range: Six water utilities in the North Carolina Research Triangle region (0: Chapel Hil/OWASA, 1: Durham, 2: Cary, 3: Raleigh, 4: Pittsboro, and 5: Chatham) File types: CSV and OUT Different solutions available The solution numbers correspond to the different pathway strategies (henceforth referred to as "solutions") discussed in paper's main and supporting text (abstract and link to the paper here). They are as follows: Sol92: The Durham-focused pathway strategy Sol132: The Raleigh-focused pathway strategy Sol140: The regionally-robust pathway strategy Objectives files These files can be accessed by unzipping solXX_objectives_pathways.zip that contains 1,000 Objectives_RDMXX_solsXX_to_XX.csv files. Each CSV file will consist of a row representing all the objective values for that specific solution, while every six columns represents the reliability, restriction frequency, infrastructure net present value ($ mil), peak financial cost, worst-case cost, and unit cost ($ per MG; in that order) for each of the six utilities. There will be 1,000 such files, denoting the performance of the six utilities across the 1,000 deeply uncertain states of the world (DU SOWs). Pathway files These files can be accessed by unzipping solXX_objectives_pathways.zip that contains 1,000 Pathways_sXX_RDMXX.out file. Each OUT corresponds to the set of infrastructure being triggered in a specific DU SOW, and each file will have the name file will consist of four tab-delimited columns that are described as follows: Realization: The realization in which an infrastructure options being triggered utility: The utility currently triggering infrastructure week: The week in which a specific infrastructure option is being triggered infra.: The infrastructure option being triggered If the OUT file contains only the header line, no infrastructure was triggered for that specific DU SOW. Policies files These files can be obtained by unzipping Policies.zip. Each of the 1,000 CSV files within the unzipped folder will contain weekly water use restriction policies for all 1,000 hydroclimatic realizations within a specific DU SOW. The column structure is as follows: 0rest_m: restriction multiplier for utility 0 (values between 0 and 1) 1rest_m: restriction multiplier for utility 1 (values between 0 and 1) 2rest_m: restriction multiplier for utility 2 (values between 0 and 1) 3rest_m: restriction multiplier for utility 3 (values between 0 and 1) 4rest_m: restriction multiplier for utility 4 (values between 0 and 1) 5rest_m: restriction multiplier for utility 5 (values between 0 and 1) 0transf: transfer volume for utility 0 (in MGD) 1transf: transfer volume for utility 1 (in MGD) 2transf: transfer volume for utility 2 (in MGD) 3transf: transfer volume for utility 3 (in MGD) 4transf: transfer volume for utility 4 (in MGD) 5transf: transfer volume for utility 5 (in MGD) Water Sources files These files can be obtained by unzipping WaterSources_subset.zip. Each of the 100 CSV files within the unzipped folder will contain weekly state variables at each water source for all 1,000 hydroclimatic realizations within a specific DU SOW. The column structure is as follows: Xvolume: available water volume from source X (in MGD) Xs_area: surface area of source X (in ACF) Xdemand: demand drawn from a water source from source X (in MGD) Xup_spill: upstream spillage from source X (in MGD) Xww_inflow: wastewater inflow from source X (in MGD) Xcatch_inflow: upstream catchment inflow to source X (in MGD) Xevap: evaporation multiplier for source X (values between 0 and 1) Xds_spill: downstream spillage from source X (in MGD) X_Y_alloc_cap: the allocated capacity from source X to utility Y (values between 0 and 1) X_Y_alloc_dem: the allocated demand from source X to utility Y (values between 0 and 1) Xtrmt_alloc_Y: the allocated treatment capacity from source X to utility Y (values between 0 and 1) Utilities files These files can be obtained by unzipping Utilities_subset.zip. Each of the 100 CSV files within the unzipped folder will contain weekly state variables at each utility for all 1,000 hydroclimatic realizations within a specific DU SOW. The column structure is as follows: Xst_vol: total available storage volume of utility X (in MG) Xcapacity: total storage capacity of utility X (in MG) Xnet_inf: : net inflow for all storage infrastructure for utility X (in MGD) Xst_rof: short term ROF for utility X (values between 0 and 1) Xst_stor_rof: short-term storage ROF for utility X (values between 0 and 1) Xst_trmt_rof: short-term treatment ROF for utility X (values between 0 and 1) Xlt_rof: long-term ROF for utility X (values between 0 and 1) Xlt_stor_rof: long-term storage ROF for utility X (values between 0 and 1) Xlt_trmt_rof: long-term treatment ROF for utility X (values between 0 and 1) Xrest_demand: restricted demand for utility X (in MGD) Xunrest_demand: unrestricted demand for utility X (in MGD) Xunfulf_demand: unfulfilled demand for utility X (in MGD) Xwastewater: wastewater return for utility X (in MGD) Xtreat_capacity: total treatment capacity for utility X (in MG) Xcont_fund: reserve (contingency) fund balance for utility X Xins_pout: insurance payout for utility X (% annual volumetric revenue) Xins_price: insurance price for utility X (% annual volumetric revenue) Xinfra_npv: infrastructure net present value for utility ($mil) Xst_vol: total available storage volume of utility X (in MG) Xdebt_serv: debt service for utility X (usually once per year if the infrastructure is triggered; % annual volumetric revenue) Xstor_vol: total stored volume (in MGD) Xobs_ann_dem: observed annual demand for utility X (in MGD) Xproj_dem: projected annual demand for utility X (in MGD) Xpv_debt_serv: present value of debt service payments for utility X (% annual volumetric revenue) Xgross_rev: gross revenue for utility X ($mil) Acknowledgment IM3 is a multi-institutional effort led by Pacific Northwest National Laboratory and supported by the U.S. Department of Energy's Office of Science as part of research in MultiSector Dynamics, Earth and Environmental Systems Modeling Program.

Artificial Intelligence↗