SEARCH · Engineering Papers
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.
Explore the source record for details and available documents.
Explore the source record for details and available documents.
In this article, we introduce a modular hybrid analysis and modeling (HAM) approach to account for hidden physics in reduced order modeling (ROM) of parameterized systems relevant to fluid dynamics. The hybrid ROM framework is based on using first principles to model the known physics in conjunction with utilizing the data-driven machine learning tools to model the remaining residual that is hidden in data. This framework employs proper orthogonal decomposition as a compression tool to construct orthonormal bases and Galerkin projection (GP) as a model to build the dynamical core of the system. Our proposed methodology hence compensates structural or epistemic uncertainties in models and utilizes the observed data snapshots to compute true modal coefficients spanned by these bases. The GP model is then corrected at every time step with a data-driven rectification using a long short-term memory (LSTM) neural network architecture to incorporate hidden physics. A Grassmannian manifold approach is also adopted for interpolating basis functions to unseen parametric conditions. The control parameter governing the system's behavior is thus implicitly considered through true modal coefficients as input features to the LSTM network. The effectiveness of the HAM approach is then discussed through illustrative examples that are generated synthetically to take hidden physics into account. Furthermore, our approach thus provides insights addressing a fundamental limitation of the physics-based models when the governing equations are incomplete to represent underlying physical processes.
Determination of the model order is a challenging problem in system identification, especially in output-only or operational modal identification where some modes are weakly excited. While existing methods such as the stabilization diagram method (spectral information) are effective, they do not scale to high-dimensional data, which is usually needed for high-fidelity characterization of structural dynamics and has been made available in the emerging full-field measurement techniques using optical methods such as photogrammetry and laser vibrometers. In this proof-of-concept study we present a new non-parametric, data-driven approach for robust output-only identification of high-spatial-dimensional modal parameters of basic structures by efficiently processing and interactively exploiting the full-field measurement (i.e., very dense spatial measurement points). Specifically, we first over-estimate the system model once, producing a pool of candidate modes associated with their modal frequencies and full-field, high-spatial-dimensional mode shapes. This is accomplished by a data-driven method termed affinity propagation clustering (APC), where the active clusters, which are the active modes in our formulations, emerge from the "message-passing" procedure and does not require a pre-determination of the cluster number (mode or model order). Next, rather than using the spectral information to distinguish the physical and spurious modes in the stabilization diagram method, we exploit and visualize the spatial, full-field mode shape associated with each candidate mode to do so. We conduct extensive experiments on basic structural models with comparisons to a few existing methods. The results indicate that the new method is computationally efficient for identifying high-spatial-dimensional modal parameters, and robust to identify weak modes by exploiting the full-field measurement. We also discuss its applicability and limitations for structures with complex geometry (shapes).
Abstract Machine learning (ML) models often fail with data that deviates from their training distribution. This is a significant concern for ML-enabled devices as data drift may lead to unexpected performance. This work introduces a new framework for out of distribution (OOD) detection and data drift monitoring that combines ML and geometric methods with statistical process control (SPC). We investigated different design choices, including methods for extracting feature representations and drift quantification for OOD detection in individual images and as an approach for input data monitoring. We evaluated the framework for both identifying OOD images and demonstrating the ability to detect shifts in data streams over time. We demonstrated a proof-of-concept via the following tasks: 1) differentiating axial vs. non-axial CT images, 2) differentiating CXR vs. other radiographic imaging modalities, and 3) differentiating adult CXR vs. pediatric CXR. For the identification of individual OOD images, our framework achieved high sensitivity in detecting OOD inputs: 0.980 in CT, 0.984 in CXR, and 0.854 in pediatric CXR. Our framework is also adept at monitoring data streams and identifying the time a drift occurred. In our simulations tracking drift over time, it effectively detected a shift from CXR to non-CXR instantly, a transition from axial to non-axial CT within few days, and a drift from adult to pediatric CXRs within a day—all while maintaining a low false positive rate. Through additional experiments, we demonstrate the framework is modality-agnostic and independent from the underlying model structure, making it highly customizable for specific applications and broadly applicable across different imaging modalities and deployed ML models.
With the rapid growth of information and communication technologies, Connected and Automated Vehicles (CAVs) are deemed to be disruptive with the potential to significantly improve overall transportation system efficiency, however, may bring Vehicle Miles Traveled (VMT) increase or other issues. Further, shared mobility systems are another disruptive force that is reshaping our travel patterns. To quantify the combined impact of CAV and shared mobility on travel behavior, traffic performance and energy efficiency, we develop a mesoscopic simulation-based framework for mobility and energy efficiency evaluation considering the disruptive transportation technologies. Under this framework, we develop novel models for energy intensity and modal activity, and evaluated a variety of energy scenarios for different combinations of CAV applications, various levels of automation, roadway characteristics, and traffic conditions, while also varying different vehicle types and fuel/powertrain technologies. Based applying this modeling suite to a calibrated BEAM simulation network in Riverside California, it was found that cooperative automated driving in general will improve mobility, but automated vehicles, even when deployed in a shared autonomous fleet, will likely bring an increase of VMT (up to 36%) due to mode shifts and deadheading. Ride-hailing vehicles typically have better energy efficiency and a higher share of electric vehicles, which helps offset the negative impact from VMT increases when estimating the system-level energy consumption. In general, simulation results show a 6% increase in energy consumption for the scenarios with an increasing shift to ride-hailing modes.
Foundation models are rapidly transforming Earth observation by enabling scalable pretraining across diverse unlabeled geospatial modalities. However, their architectural diversity—ranging from encoder-only to encoder-decoder and masked autoencoding paradigms—makes it challenging to assess performance trade-offs in a consistent manner. In this work, we present an apples-to-apples comparison of leading FM architectures designed for geospatial multimodal reasoning, with a particular focus on flexibility across varied spectral band configurations. We standardize pretraining using identical self-supervised learning objectives and training datasets, and evaluate all models under consistent parameterization on the GEOBench benchmark across classification and segmentation tasks. Our results offer new insights into the design trade-offs between model flexibility, modality alignment, and downstream task performance. By highlighting architectural strengths and limitations under controlled conditions, this study provides practical guidance for building next-generation geospatial foundation models capable of robust multimodal reasoning.
T cell states are prognostic in different cancer types. Recent technologies enable joint profiling of T cell RNA and T cell receptor (TCR) sequences at single-cell resolution. Here we present the TCR-RNA Integrating Model (TRIM), a multi-modal variational autoencoder framework that integrates RNA-TCR data and predicts T cell clonality and transcriptional states. TRIM learns a shared representation of the data conditioned on patient, tissue source, and treatment timepoint. We applied TRIM to three independent datasets that included T cells collected before and after checkpoint inhibitor treatment, sourced either from blood and tumor biopsies in patients with head and neck squamous cell carcinoma and colorectal cancer, or from tumor and adjacent tissue in a pan-cancer dataset. In all settings, TRIM accurately predicted intra-tumor T cell clonal expansion and transcriptional status based on T cells from blood or normal tissue before treatment, demonstrating its utility in modeling multimodal T cell data and predicting T cell response to treatment and disease progression.
With the advent of Mobility-as-a-Service packages to reduce car usage and (by extension) greenhouse gas emissions, it is crucial that researchers and practitioners consider mutual determinants and outcomes that link the adoption of multiple alternative modes. This study therefore investigates the joint usage of active travel (walking, cycling, bike-sharing) and public transit (bus, rail) modes with respect to personal and situational contexts. Online survey data (n = 826) were collected across six Midwestern U.S. states using Amazon MTurk. Respondents indicated their average weekly usage of eight travel modes across three trip purposes so that multimodality could be assessed. Several psychological constructs were extracted via (a) the stages of change framework, used to indicate willingness to adopt new behavior, and (b) confirmatory factor analysis conducted on Likert scales rooted in theories of community, identity, norms, personality, and well-being. A multiple-indicators multiple-causes structural equation model is then employed to investigate the process of adopting a modality style that incorporates active and transit modes. The model confirms that compatible physical and social contexts, as well as navigational skills and openness to learning, are key primers of multimodalism. However, a path juncture stemming from neighborhood support for mobility innovation illustrates a potential polarity in outcomes between individuals and communities. In addition, the stage of active mobility adoption is linked to identity and norm activation, offering further guidance on what influences readiness for change. The seamless integration of mobility services is critical to matching the convenience and comfort of the private vehicle; understanding potential pathways to sustainable mobility, though, requires analyses and interventions that are driven by well-being outcomes and grounded in rigorous psychological frameworks. Here, the research findings offer practical guidance for identifying intervention opportunities to be linked with MaaS enrollment while demonstrating the need to illuminate how mobility might relate to social cohesion, identity expression, and various sources of satisfaction.
Heterogeneous catalysis presents a distinct challenge for artificial intelligence (AI). Data sets are often small and inconsistently reported, catalyst representations are not standardized, and extracting fundamental knowledge requires integrating performance data, spectroscopic characterizations, and mechanistic models across multiple scales. Language offers a unifying representation across these modalities, making catalysis well suited for leveraging large language models (LLMs). By standardizing how catalytic data is represented, LLMs make dispersed experimental results more accessible to downstream statistical modeling. In this perspective, we focus our discussion around three opportunities where LLMs can significantly contribute to catalysis: (1) text to properties; (2) text to structure; and (3) text to mechanistic models. The discussion is followed by a perspective section on LLM-readiness of data, aligning LLM outputs with scientific correctness, and bridging lab-scale discovery to industrial deployment. Across each area, the most productive applications couple dispersed chemical knowledge with physics-grounded validation to produce verifiable hypotheses and actionable representations.
Enzyme engineering and metabolic engineering drive innovation in energy biotechnology. In recent years, artificial intelligence (AI) has supported successful applications in designing effective enzymes and productive microbial cell factories. This review summarizes recent advances in enzyme redesign using protein language models, de novo enzyme design with generative models, and AI tools for engineering metabolism and related cellular phenotypes. Across these areas, AI models are shifting from single modality inputs to integrated representations of protein function, metabolic pathways, and cell states. We emphasize that unifying the diverse data representations across scales will be necessary for advancements in energy biotechnology.
ABSTRACT The future detection of gravitational waves (GWs) from a Galactic core-collapse supernova will provide information on the physics inside protoneutron stars (PNS). In this work, we apply three different classification methods for the PNS non-radial oscillation modes: Cowling classification, Generalized Cowling Nomenclature (GCN), and a classification based on modal properties (CBMP). Using PNS models from 3D simulations of core-collapse supernovae, we find that in the early stages of the PNS evolution, typically 0.4 s after the bounce, the Cowling classification is inconsistent, but the GCN and the CBMP provide complementary information that helps to understand the evolution of the modes. In the GCN, we note several avoided crossings as the mode frequencies evolve at early times, while the CBMP tracks the modes across the avoided crossings. We verify that the strongest emission of GWs by the PNS corresponds to the f mode in the GCN, indicating that the mode trapping region alternates between the core and the envelope at each avoided crossing. At later times, approximately 0.4 s after the bounce, the three classification methods present a similar description of the mode spectrum. We use our results to test universal relations for the PNS modes according to their classification and find that the behaviour of the universal relations for f and p modes is remarkably simple in the CBMP.
Leveraging the chemical data available in legacy formats such as publications and patents is a significant challenge for the community. Automated reaction mining offers a promising solution to unleash this knowledge into a learnable digital form and therefore help expedite materials and reaction discovery. However, existing reaction mining toolkits are limited to single input modalities (text or images) and cannot effectively integrate heterogeneous data that is scattered across text, tables, and figures. In this work, we go beyond single input modalities and explore multimodal large language models (MLLMs) for the analysis of diverse data inputs for automated electrosynthesis reaction mining. We compiled a test dataset of 65 articles (MERMES-T24 set) and employed it to benchmark five prominent MLLMs against two critical tasks: (i) reaction diagram parsing and (ii) resolving cross-modality data interdependencies. The frontrunner MLLM achieved ≥96% accuracy in both tasks, with the strategic integration of single-shot visual prompts and image pre-processing techniques. We integrate this capability into a toolkit named MERMES (multimodal reaction mining pipeline for electrosynthesis). Our toolkit functions as an end-to-end MLLM-powered pipeline that integrates article retrieval, information extraction and multimodal analysis for streamlining and automating knowledge extraction. This work lays the groundwork for the increased utilization of MLLMs to accelerate the digitization of chemistry knowledge for data-driven research.
The development of data-driven models for human mobility in urban settings requires access to substantial and diverse real-world data. However, existing historical data often presents challenges such as limited volume, variety, and veracity, as well as missing data and privacy preservation concerns. Also, urban mobility modeling is inherently time-variant, complex, and multi-modal, encompassing everything from individual walking and running to private road travel and large-scale public transportation. These challenges call for innovative solutions to overcome data limitations and compute needs to model mobility behaviors accurately. To address these challenges, we propose a distributed, co-simulation-based architecture DURMOSim that integrates real-world data with scalable, high-fidelity simulations, demonstrating distributed co-simulation feasibility with existing mobility models. DURMOSim underpins a modular integration that would enable using any available mobility simulators for greater extensibility and scalability in performing various urban scenarios. In this paper, we present the design, implementation, and performance evaluation of DURMOSim, highlighting its capability to model population-scale mobility patterns. Our initial results show its ability to dynamically synchronize multiple simulation models at runtime with negligible computational overhead. We believe DURMOSim could be a robust tool for advancing urban mobility research and intelligent transportation systems.
We present a fast and accurate data-driven surrogate model for divertor plasma detachment prediction leveraging the latent feature space concept in machine learning research. Our approach involves constructing and training two neural networks: an autoencoder that finds a proper latent space representation (LSR) of plasma state by compressing the multi-modal diagnostic measurements and a forward model using multi-layer perception (MLP) that projects a set of plasma control parameters to its corresponding LSR. By combining the forward model and the decoder network from autoencoder, this new data-driven surrogate model is able to predict a consistent set of diagnostic measurements based on a few plasma control parameters. In order to ensure that the crucial detachment physics is correctly captured, highly efficient 1D UEDGE model is used to generate training and validation data in this study. The benchmark between the data-driven surrogate model and UEDGE simulations shows that our surrogate model is capable of providing accurate detachment prediction (usually within a few per cent relative error margin) but with at least four orders of magnitude speed-up, indicating that performance-wise, it has the potential to facilitate integrated tokamak design and plasma control. Comparing with the widely used two-point model and/or two-point model formatting, the new data-driven model features additional detachment front prediction and can be easily extended to incorporate richer physics. This study demonstrates that the complicated divertor and scrape-off-layer plasma state has a low-dimensional representation in latent space. Understanding plasma dynamics in latent space and utilising this knowledge could open a new path for plasma control in magnetic fusion energy research.
Abstract A common setting in astronomy is the availability of a small number of high-quality observations, and larger amounts of either lower-quality observations or synthetic data from simplified models. Time-domain astrophysics is a canonical example of this imbalance, with the number of supernovae observed photometrically outpacing the number observed spectroscopically by multiple orders of magnitude. At the same time, no data-driven models exist to understand these photometric and spectroscopic observables in a common context. Contrastive learning objectives, which have grown in popularity for aligning distinct data modalities in a shared embedding space, provide a potential solution to extract information from these modalities. We present Maven, the first foundation model for supernova science. To construct Maven, we first pre-train our model to align photometry and spectroscopy from 0.5 M synthetic supernovae using a contrastive objective. We then fine-tune the model on 4702 observed supernovae from the Zwicky transient facility. Maven reaches state-of-the-art performance on both classification and redshift estimation, despite the embeddings not being explicitly optimized for these tasks. Through ablation studies, we show that pre-training with synthetic data improves overall performance. In the upcoming era of the Vera C. Rubin observatory, Maven will serve as a valuable tool for leveraging large, unlabeled and multimodal time-domain datasets.
Intermodal freight optimization models support cost-effective, low-emission, and timely goods movement by coordinating trucks, rail, and barges. These models determine optimal flows, routing, and modal switches while respecting infrastructure and operational constraints. However, their real-world utility is often undermined by pervasive uncertainties-such as fluctuating transportation costs and emissions, variable terminal capacities, and uncertain freight demand-that distort key performance outcomes, including total system cost, carbon footprint, and transit time reliability. This study presents a structured framework for quantifying uncertainty in intermodal freight transportation (IFT) optimization. The framework evaluates how input uncertainty affects system performance and reliability, a critical need for ensuring that model-based decisions remain robust under real-world variability, especially amid volatile fuel prices, shifting demand, and growing disruptions. It integrates three complementary methods: (1) Sobol-based global sensitivity analysis to identify influential parameters affecting cost, emissions, and transit time, (2) Monte Carlo-based capacity perturbation analysis to assess robustness under probabilistic facility disruptions, and (3) Monte Carlo filtering with Bayesian inference to detect threshold-based performance vulnerabilities. The results highlight diesel truck unit cost as the dominant driver of variability. To improve system resilience, planners should prioritize uncertainty in fuel-related parameters when designing intermodal strategies.
In today’s digital world, the spread of fake news and the rise of AI-generated text have become major threats to content authenticity and public trust. This thesis addresses both challenges through two complementary research directions: detecting fake news using multimodal features, and identifying AI-generated text using semantic and structural reasoning. The first part of the work focuses on fake news detection by introducing a novel model that combines text and image features through a unique rotational attention mechanism. Unlike traditional attention methods, this approach rotates the roles of query, key, and value across modalities to capture deeper interactions. Additionally, the model incorporates external domain information by linking news posts to top-ranked websites from Google search results, which helps assess the credibility of content based on its broader web context. This results in a more reliable and accurate fake news detection system that outperforms existing state-of-the-art methods. The second part presents SGG-ATD, a new framework for detecting AI-generated text. It uses masked language modeling to measure sentence coherence, followed by constructing a graph where keywords—both original and predicted—are connected based on semantic and contextual similarity. A Graph Convolutional Network (GCN) is then used to learn structural relationships within the text for final classification. Experimental results demonstrate that SGG-ATD achieves high F1-scores and consistently outperforms strong baselines. This method contributes to robust AI text detection, supporting accountability and resilience against AI-driven misinformation.