SEARCH · Engineering Papers
Results for “data driven”
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.
A General Spatiotemporal Imputation Framework for Missing Sensor Data
Many applications from precision agriculture, environmental monitoring and transportation networks rely on data collected across space and time over a large geographic area. Missing data poses a significant challenge for any data-driven inference and control tasks. Data imputation or the estimation of missing data can help fill these gaps by utilizing inherent spatial relationships and temporal patterns. A variety of spatiotemporal imputation models have been developed to address missing data in spatiotemporal datasets. However, these classical methods rely on the assumption that the underlying data follows a smooth trend and fail to provide accurate estimates when there is a large number of missing points in the data. Even though there are machine learning driven tensor completion approaches such as convolutional neural network based tensor completion (CoSTCo) that capture the non-linear relationships in the dataset, the transductive nature makes the algorithm less scalable. Thus, existing approaches for estimating the missing information do not effectively capture all dimensions of the spatiotemporal data structure, resulting in erroneous predictions and poor performance. The main contributions of this paper are: (1) We propose a novel inductive framework (G-LSTM) for missing data imputation that integrates a graph neural network with LSTMs to effectively capture both spatial and temporal dependencies. (2) Experimental results on a traffic dataset demonstrate that the proposed GNN integrated with an LSTM framework achieves improved imputation and maintains steady performance even when there are extreme missing conditions in comparison with the state-of-the-art imputation framework (i.e, CoSTCo). (3) The simulation results on a traffic network show up to 69% reduction in mean absolute error and 61% reduction in root mean square error when compared to CoSTCo.
Unsupervised Parsing of Gaze Data with a Beta-process Vector Auto-regressive Hidden Markov Model
The first stage of analyzing eye-tracking data is commonly to code the data into sequences of fixations and saccades. This process is usually automated using simple, predetermined rules for classifying ranges of the time series into events, such as “if the dispersion of gaze samples is lower than the threshold, then code as a fixation; otherwise code as a saccade.” More recent approaches incorporate additional eye-movement categories in automated parsing algorithms, particularly glissades, by using time-varying, data-driven thresholds. We describe an alternative approach using the beta-process auto-regressive hidden Markov model (BP-AR-HMM). The BP-AR-HMM offers two main advantages over existing frameworks. First, it provides a statistical model for eye movement classification rather than a single estimate. Second, the BP-AR-HMM uses a latent process to model the number and nature of the types of eye-movements and hence is not constrained to predetermined categories. We applied the BP-AR-HMM both to high-sampling rate gaze data from Andersson, Larsson, Holmqvist, Stridh, and Nyström (2016) and to low-sampling rate data from the DIEM project (Mital, Smith, Hill, & Henderson, 2011). Driven by the data properties, the BP-AR-HMM identified clusters of samples resembling saccades, fixations and smooth pursuit, and a category that approximately corresponds to glissades (as well as blinks, errors, etc.). The BP-AR-HMM serves as an effective algorithm for data-driven event parsing alone or as an initial step in exploring the characteristics of gaze data sets.
Constrained or unconstrained? Neural-network-based equation discovery from data
Throughout many fields, practitioners often rely on differential equations to model systems. Yet, for many applications, the theoretical derivation of such equations and/or the accurate resolution of their solutions may be intractable. Instead, recently developed methods, including those based on parameter estimation, operator subset selection, and neural networks, allow for the data-driven discovery of both ordinary and partial differential equations (PDEs), on a spectrum of interpretability. The success of these strategies is often contingent upon the correct identification of representative equations from noisy observations of state variables and, as importantly and intertwined with that, the mathematical strategies utilized to enforce those equations. Specifically, the latter has been commonly addressed via unconstrained optimization strategies. Representing the PDE as a neural network, we propose to discover the PDE (or the associated operator) by solving a constrained optimization problem and using an intermediate state representation similar to a physics-informed neural network (PINN). The objective function of this constrained optimization problem promotes matching the data, while the constraints require that the discovered PDE is satisfied at a number of spatial collocation points. We present a penalty method and a widely used trust-region barrier method to solve this constrained optimization problem, and we compare these methods on numerical examples. Our results on several example problems demonstrate that the latter constrained method outperforms the penalty method, particularly for higher noise levels or fewer collocation points. This work motivates further exploration into using sophisticated constrained optimization methods in scientific machine learning, as opposed to their commonly used, penalty-method or unconstrained counterparts. For both of these methods, we solve these discovered neural network PDEs with classical methods, such as finite difference methods, as opposed to PINNs-type methods relying on automatic differentiation. Here, we briefly highlight how simultaneously fitting the data while discovering the PDE improves the robustness to noise and other small, yet crucial, implementation details.
A high-throughput workflow to analyze sequence-conformation relationships and explore hydrophobic patterning in disordered peptoids
Understanding how a macromolecule’s primary sequence governs its conformational landscape is crucial for elucidating its function, yet these design principles are still emerging for macromolecules with intrinsic disorder. Herein, we introduce a high-throughput workflow that implements a practical colorimetric conformational assay, introduces a semi-automated sequencing protocol using matrix-assisted laser desorption/ionization and tandem mass spectrometry (MALDI-MS/MS), and develops a generalizable sequence-structure algorithm. Using a model system of 20mer peptidomimetics containing polar glycine and hydrophobic N-butylglycine residues, we identified nine classifications of conformational disorder and isolated 122 unique sequences across varied compositions and conformations. Conformational distributions of three compositionally identical library sequences were corroborated through atomistic simulations and ion mobility spectrometry coupled with liquid chromatography. A data-driven strategy was developed using existing sequence variables and data-derived “motifs” to inform a machine-learning algorithm toward conformation prediction. Here, this multifaceted approach enhances our understanding of sequence-conformation relationships and offers a powerful tool for accelerating the discovery of materials with conformational control.
A comparison of surrogate constitutive models for viscoplastic creep simulation of HT-9 steel
Mechanistic microstructure-informed constitutive models for the mechanical response of polycrystals are a cornerstone of computational materials science. However, as these models become increasingly more complex – often involving coupled differential equations describing the effect of specific deformation modes – their associated computational costs can become prohibitive, particularly in optimization or uncertainty quantification tasks that require numerous model evaluations. To address this challenge, surrogate constitutive models that balance accuracy and computational efficiency are highly desirable. Data-driven surrogate models, that learn the constitutive relation directly from data, have emerged as a promising solution. In this work, we develop two local surrogate models for the viscoplastic response of a steel: a piecewise response surface method and a mixture of experts model. These surrogates are designed to adapt to complex material behavior, which may vary with material parameters or operating conditions. The surrogate constitutive models are applied to creep simulations of HT-9 steel, an alloy of considerable interest to the nuclear energy sector due to its high tolerance to radiation damage, using training data generated from viscoplastic self-consistent (VPSC) simulations. In conclusion, we define a set of test metrics to numerically assess the accuracy of our surrogate models for predicting viscoplastic material behavior, and show that the mixture of experts model outperforms the piecewise response surface method in terms of accuracy.
Derivation of physical equations for high-speed laser welding using large language models
It is challenging to formulate complex physical phenomena that occur in a manufacturing process, particularly when the available data are limited, rendering conventional data-driven approaches ineffective. This study aims to predict humping onset in high-speed laser welding by introducing a novel framework, namely text-to-equations generative pre-trained transformer (T2EGPT). This method leverages the capabilities of large language models (LLMs), in combination with sparse experimental data and enriched literature data, to derive an interpretable and generalizable equation for predicting humping initiation. By capturing key correlations among physical parameters, T2EGPT generates a compact and dimensionless expression that accurately predicts hump formation. The equation reveals that humping arises from the interplay between inertia-driven backward melt flow and capillary-driven surface stabilization, where inertial forces drive molten metal backward and capillary forces resist surface deformation. Furthermore, compared to traditional data-driven models, T2EGPT demonstrates enhanced predictive accuracy and cross-material transferability. More broadly, this study highlights the potential of LLMs to integrate textual information with data-driven discovery, enabling the extraction of physical laws in data-scarce scientific domains.
Anomaly Detection, Localization and Classification using Drifting Synchrophasor Data Streams
With ongoing automation and digitization of the electric power system, several Phasor Measurement Units(PMUs) have been deployed for monitoring and control. PMU data can have multiple anomalies, and many of the researchers in the past have concentrated on training machine/deep learning algorithms offline for anomaly detection over PMU data (i.e., not in real time). These machine/deep learning algorithms, when trained offline on a sample rather than a population of the dataset, fail to consider the dynamic behavior of the power grid in real-time, resulting in low accuracy. Considering the dynamic behavior of the power grid (e.g., change in load, generation, distributed energy resources (DERs) switching, network, controls), the definition of data anomalies varies in time and requires online training. A fundamental challenge is to enable online (i.e., real-time) training of machine/deep learning algorithms for anomaly detection over streaming PMU data. While machine/deep learning is often desirable to manage data streams, training a deep learning algorithm over streaming PMU data is nontrivial due to changes in data statistics caused by dynamic streaming data. This paper proposes PMUNET: a novel device-level deep learning-based data-driven approach for anomaly detection, localization, and classification over streaming PMU data, using online learning and multivariate data-drift detection algorithm .Two variants of PMUNET, Dynamic data Change Driven Learning (DCDL) and Continuity Driven Learning (CDL), are proposed and compared. DCDL aims to train the deep learning algorithm whenever the definition of anomaly changes due to the power grid dynamics. On the other hand, CDL continuously trains the deep learning algorithm over the PMU data-stream. The experimental results verify that DCDL outperforms CDL and other efficient anomaly detection methods over multiple events such as faults and load/ generator/capacitor/DERs variations/switching for IEEE 14 and 39 Bus test system as well as real PMU industrial data. The result verifies that DCDL variant of PMUNET improves over existing approach with a gain of 2% - 10% in terms of accuracy, false-positive rate, and false-negative rate.
Towards a machine-readable literature: finding relevant papers based on an uploaded powder diffraction pattern
A prototype application for machine-readable literature is investigated. The program is called pyDataRecognition and serves as an example of a data-driven literature search, where the literature search query is an experimental data set provided by the user. The user uploads a powder pattern together with the radiation wavelength. The program compares the user data to a database of existing powder patterns associated with published papers and produces a rank ordered according to their similarity score. The program returns the digital object identifier and full reference of top-ranked papers together with a stack plot of the user data alongside the top-five database entries. The paper describes the approach and explores successes and challenges.
OpenSolar: Promoting the Openness and Accessibility of Diverse Public Solar Datasets
Observational solar data is the foundation of data-driven research in solar power grid integration and power system operations. Compared to other fields in data science, the openness and accessibility of solar data is lacking, which prevents solar data science from catching up with the emerging trends of data science (e.g., deep learning). In this paper, OpenSolar, a package with both R and Python versions, is developed to enhance the openness and accessibility of publicly available solar datasets. The OpenSolar package provides access to multiple types of solar data, primarily from four datasets: (1) the National Renewable Energy Laboratory (NREL) Solar Power Data for Integration Studies dataset, (2) the NREL Solar Radiation Research Laboratory dataset, (3) the Sheffield Solar-Microgen database, and (4) the Dataport database. Unlike other open solar datasets that only contain meteorological data, the four datasets in the OpenSolar package also contain behind-the-meter power data, sky images, and solar power data with satisfactory temporal and spatial resolution and coverage. The overview, quality-control methods, and potential usage of the datasets, in conjunction with sample code implementing the OpenSolar functions, are described in this paper. The package is expected to assist in bridging the gaps between the research fields of solar energy, power systems, and data science.
Information-driven control of product generation and reconciliation: generating Cassini ISS and VIMS data products on a budget
This paper discusses the design and implementation of the automated Cassini control function, a concept which is extensible to any subsystem required to perform systematic, well-defined, data-driven or time-driven processing.
Prediction of atomization energy using graph kernel and active learning
Data-driven prediction of molecular properties presents unique challenges to the design of machine learning methods concerning data structure/dimensionality, symmetry adaption, and confidence management. In this paper, we present a kernel-based pipeline that can learn and predict the atomization energy of molecules with high accuracy. The framework employs Gaussian process regression to perform predictions based on the similarity between molecules, which is computed using the marginalized graph kernel. To apply the marginalized graph kernel, a spatial adjacency rule is first employed to convert molecules into graphs whose vertices and edges are labeled by elements and interatomic distances, respectively. We then derive formulas for the efficient evaluation of the kernel. Specific functional components for the marginalized graph kernel are proposed, while the effects of the associated hyperparameters on accuracy and predictive confidence are examined. We show that the graph kernel is particularly suitable for predicting extensive properties because its convolutional structure coincides with that of the covariance formula between sums of random variables. Using an active learning procedure, we demonstrate that the proposed method can achieve a mean absolute error of 0.62 ± 0.01 kcal/mol using as few as 2000 training samples on the QM7 dataset.
Beyond interpolation: Physics-inspired gating transformers for extrapolating irradiation conditions to novel nuclear fuels
The qualification of advanced nuclear fuels relies on irradiation experiments in test reactors that emulate commercial conditions. Designing these tests requires accurate prediction of key irradiation quantities, particularly heat generation rate and burnup, yet obtaining them typically involves computationally expensive multi-step simulation workflows. We propose a physics-inspired gating transformer (PIGT) that integrates an inverse-square, distance-based attenuation into the encoder representation to bias attention toward physically relevant spatial relationships while retaining data-driven flexibility. Using MiniFuel irradiation data from the High Flux Isotope Reactor at Oak Ridge National Laboratory, we benchmark against ensemble methods, feedforward and recurrent networks, convolutional models, and standard transformers. While baseline models perform well under interpolation, they exhibit a pronounced generalization gap when evaluated on fuels not included in the training set. The proposed model consistently improves extrapolative accuracy and stability, yielding the strongest performance on unseen fuel configurations. These results indicate that a lightweight physics structure embedded within attention mechanisms can substantially improve robustness, enabling more reliable surrogate predictions to accelerate the design of nuclear fuel irradiation experiments.
Evaluating the Potential and Challenges of an Uncertainty Quantification Method for Long Short–Term Memory Models for Soil Moisture Predictions
Recently, recurrent deep networks have shown promise to harness newly available satellite–sensed data for long–term soil moisture projections. However, to be useful in forecasting, deep networks must also provide uncertainty estimates. Here we evaluated Monte Carlo dropout with an input–dependent data noise term (MCD+N), an efficient uncertainty estimation framework originally developed in computer vision, for hydrologic time series predictions. MCD+N simultaneously estimates a heteroscedastic input–dependent data noise term (a trained error model attributable to observational noise) and a network weight uncertainty term (attributable to insufficiently constrained model parameters). Although MCD+N has appealing features, many heuristic approximations were employed during its derivation, and rigorous evaluations and evidence of its asserted capability to detect dissimilarity were lacking. To address this, we provided an in–depth evaluation of the scheme's potential and limitations. We showed that for reproducing soil moisture dynamics recorded by the Soil Moisture Active Passive (SMAP) mission, MCD+N indeed gave a good estimate of predictive error, provided that we tuned a hyperparameter and used a representative training data set. The input–dependent term responded strongly to observational noise, while the model term clearly acted as a detector for physiographic dissimilarity from the training data, behaving as intended. However, when the training and test data were characteristically different, the input–dependent term could be misled, undermining its reliability. Additionally, due to the data–driven nature of the model, data noise also influences network weight uncertainty, and therefore the two uncertainty terms are correlated. Altogether, this approach has promise, but care is needed to interpret the results.
Data Jockey: Automatic Data Management for HPC Multi-Tiered Storage Systems
We present the design and implementation of Data Jockey, a data management system for HPC multi-tiered storage systems. As a centralized data management control plane, Data Jockey automates bulk data movement and placement for scientific workflows and integrates into existing HPC storage infrastructures. Data Jockey simplifies data management by eliminating human effort in programming complex data movements, laying datasets across multiple storage tiers when supporting complex workflows, which in turn increases the usability of multitiered storage systems emerging in modern HPC data centers.Specifically, Data Jockey presents a new data management scheme called “goal driven data management” that can automatically infer low-level bulk data movement plans from declarative high-level goal statements that come from the lifetime of iterative runs of scientific workflows. While doing so, Data Jockey aims to minimize data wait times by taking responsibility for datasets that are unused or to be used, and aggressively utilizing the capacity of the upper, higher performant storage tiers.We evaluated a prototype implementation of Data Jockey under a synthetic workload based on a year’s worth of Oak Ridge Leadership Computing Facility’s (OLCF) operational logs. Our evaluations suggest that Data Jockey leads to higher utilization of the upper storage tiers while minimizing the programming effort of data movement compared to human involved, per-domain adhoc data management scripts.
Mixture Model Framework for Traumatic Brain Injury Prognosis Using Heterogeneous Clinical and Outcome Data
Prognoses of Traumatic Brain Injury (TBI) outcomes are neither easily nor accurately determined from clinical indicators. This is due in part to the heterogeneity of damage inflicted to the brain, ultimately resulting in diverse and complex outcomes. Using a data-driven approach on many distinct data elements may be necessary to describe this large set of outcomes and thereby robustly depict the nuanced differences among TBI patients’ recovery. In this work, we develop a method for modeling large heterogeneous data types relevant to TBI. Our approach is geared toward the probabilistic representation of mixed continuous and discrete variables with missing values. The model is trained on a dataset encompassing a variety of data types, including demographics, blood-based biomarkers, and imaging findings. In addition, it includes a set of clinical outcome assessments at 3, 6, and 12 months post-injury. The model is used to stratify patients into distinct groups in an unsupervised learning setting. We use the model to infer outcomes using input data, and show that the collection of input data reduces uncertainty of outcomes over a baseline approach. In addition, we quantify the performance of a likelihood scoring technique that can be used to self-evaluate the extrapolation risk of prognosis on unseen patients.
Frequency Event Categorization in Power Distribution Systems Using Micro PMU Measurements
Frequency is an important metric for power stability. To enhance the situational awareness in power distribution systems, this article proposes a data-driven approach that utilizes the data from micro phasor measurement units (μPMU) to categorize frequency events observed in distribution feeders. The proposed approach has three layers, each of which analyzes if a frequency event is propagated from the transmission system, formed inside a distribution feeder or falsely produced by instantaneous frequency (IF) estimation algorithms, respectively. In the first layer, the Granger causality is utilized to compare the causal relations from measurements across different locations to decide if an event is propagated from the transmission side. In the second layer, a trained sparse coding dictionary is utilized to unmix the physical causes of a frequency event. In the third layer, a moving z-score based event-pair detector is applied to identify if a frequency event is algorithm-induced. The proposed approach is tested using the μPMU measurements collected from Lawrence Berkeley National Laboratory (LBNL) and Riverside Public Utility (RPU).