Deep-Learning-Enabled Fast Optical Identification and Characterization of 2D Materials
Not provided.
Chemistry↗
SEARCH · Engineering Papers
Results for “Prediction Accuracy”
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.
Uncertainty quantification of the convolutional neural networks on permeability estimation from micro-CT scanned sandstone and carbonate rock images
Rock permeability is one of the most crucial properties affecting subsurface fluid flow behaviors. To accurately and robustly estimate the permeability, Digital Rock Physics, including micro-CT scanning technology and direct flow simulations on scanned images, has prevailed in recent years. Besides, machine learning techniques such as convolutional neural networks (CNNs) have been widely adopted and achieved success in permeability estimations directly from rock images. However, existing ML methods used for permeability estimation from rock images lack uncertainty quantification that causes unreliable predictions and overconfident estimations on out-of-distribution (OOD) samples. Here, in this work, we propose a PI3NN-CNN framework to address this problem. PI3NN-CNN consists of a CNN model for absolute permeability estimation and a PI3NN method to quantify the estimation uncertainty. It is able to quantify the uncertainty for in-distribution (InD) data with a desired confidence level, and identify OOD samples to avoid overconfident predictions. We demonstrate the method using micro-CT scanned images from two sandstone and two carbonate rocks. We found that PI3NN-CNN generates accurate predictions for InD samples, while producing high-quality prediction uncertainties regardless of the prediction accuracy. Meanwhile, PI3NN-CNN identifies OOD samples using its special network initialization scheme. The unique feature of PI3NN-CNN makes it applicable to more complex real-world image-based data for robust learning and predictions without overconfident estimations when the ground-truth information is unavailable.
58 GEOSCIENCES↗
Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems
Abstract Predicting complex dynamics in physical applications governed by partial differential equations in real-time is nearly impossible with traditional numerical simulations due to high computational cost. Neural operators offer a solution by approximating mappings between infinite-dimensional Banach spaces, yet their performance degrades with system size and complexity. We propose an approach for learning neural operators in latent spaces, facilitating real-time predictions for highly nonlinear and multiscale systems on high-dimensional domains. Our method utilizes the deep operator network architecture on a low-dimensional latent space to efficiently approximate underlying operators. Demonstrations on material fracture, fluid flow prediction, and climate modeling highlight superior prediction accuracy and computational efficiency compared to existing methods. Notably, our approach enables approximating large-scale atmospheric flows with millions of degrees, enhancing weather and climate forecasts. Here we show that the proposed approach enables real-time predictions that can facilitate decision-making for a wide range of applications in science and engineering.
97 MATHEMATICS AND COMPUTING↗
Application of Machine Learning and Data Augmentation Algorithms in the Discovery of Metal Hydrides for Hydrogen Storage
The development of efficient and sustainable hydrogen storage materials is a key challenge for realizing hydrogen as a clean and flexible energy carrier. Among various options, metal hydrides offer high volumetric storage density and operational safety, yet their application is limited by thermodynamic, kinetic, and compositional constraints. In this work, we investigate the potential of machine learning (ML) to predict key thermodynamic properties—equilibrium plateau pressure, enthalpy, and entropy of hydride formation—based solely on alloy composition using Magpie-generated descriptors. We significantly expand an existing experimental dataset from ~400 to 806 entries and assess the impact of dataset size and data augmentation, using the PADRE algorithm, on model performance. Models including Support Vector Machines and Gradient Boosted Random Forests were trained and optimized via grid search and cross-validation. Results show a marked improvement in predictive accuracy with increased dataset size, while data augmentation benefits are limited to smaller datasets and do not improve accuracy in underrepresented pressure regimes. Furthermore, clustering and cross-validation analyses highlight the limited generalizability of models across different material classes, though high accuracy is achieved when training and testing within a single hydride family (e.g., AB2). The study demonstrates the viability and limitations of ML for accelerating hydride discovery, emphasizing the importance of dataset diversity and representation for robust property prediction.
augmentation↗
Center-TRACON Automation System (CTAS) En Route Trajectory Predictor Requirements and Capabilities
This requirements framework document is designed to support the capture of requirements and capabilities for state-of-the-art trajectory predictors (TPs). This framework has been developed to assist TP experts in capturing a clear, consistent, and cross-comparable set of requirements and capabilities. The goal is to capture capabilities (types of trajectories that can be built), functional requirements (including inputs and outputs), non-functional requirements (including prediction accuracy and computational performance), approaches for constraint relaxation, and input uncertainties. The sections of this framework are based on the Common Trajectory Predictor structure developed by the FAA/Eurocontrol Cooperative R&D Action Plan 16 Committee on Common Trajectory Prediction. It is assumed that the reader is familiar with the Common TP Structure.1 This initial draft is intended as a first cut capture of the En Route TS Capabilities and Requirements. As such, it contains many annotations indicating possible logic errors in the CTAS code or in the description provided. It is intended to work out the details of the annotations with NASA and to update this document at a later time.
framework↗
Blade-Wake Interaction Noise for Small Hovering Rotors, Part I: Characterization Study
This work illustrates the use of artificial neural network modeling to study and characterize broadband blade-wake interaction noise from hovering small unmanned aerial systems rotors subject to varying airfoil geometries, rotor geometries, and operating conditions. Design of experiments was used to create input feature spaces, and a high-fidelity strategy was implemented at the discrete data points defined by the input feature spaces to design airfoils and rotor blades, predict the unsteady rotor aerodynamics and aeroacoustics, and isolate the blade-wake interaction noise from the acoustic broadband noise. A metric for the blade-wake interaction noise was developed, and the ANOPP2 Artificial Neural Network Tool was used to identify an optimal prediction model for the nonlinear relationship between the input features and the metric for blade-wake interaction noise. This optimal artificial neural network was then validated over training/test data and exhibited prediction accuracy over 91% for data previously unseen by the model. A sensitivity analysis was conducted, which showed that input features that directly modify the thrust coefficient had a dominant effect over blade-wake interaction noise. The optimal prediction model along with aerodynamic simulations were used to further study the effect of varying input features on blade-wake interaction noise, and three types of blade-wake interaction noise were identified
Christopher S. Thurman↗
Automated vehicle microscopic energy consumption study (AV-Micro): Data collection and model development
While the Adaptive Cruise Control (ACC) system in automated vehicles (AVs) is expected to impact transportation energy significantly, existing AV energy consumption models only directly adopt those developed with Human-driven Vehicle (HV) data without even slight adaptation or calibration to accommodate unique AV energy consumption features. This study will investigate how accurately HV data-based models can predict the energy consumption of AVs. Empirical trajectory data and corresponding instantaneous energy consumption rates from both AVs and HVs were collected. We adopted two classical HV data-based models to fit these data. The calibration results indicated that these models yield around 20 30% prediction errors for AVs. To further improve the prediction accuracy, this study designed an AV-Micro model by incorporating components of multiple classic energy consumption models that better capture ACC energy consumption features, including piecewise driving behavior. With this, the AV-Micro model achieves lower than 10% prediction errors. The AV-Micro model’s high consistency across different test runs was verified with statistical significance tests, demonstrating its adaptability in different driving profiles. To confirm the discrepancies between the energy consumption features of AVs and HVs, more statistical significance tests were conducted to show that the AV-Micro model cannot be directly applied to HV data. The findings by calibrated AV-Micro models revealed that AVs consume approximately 80.5–146.4 J more energy than HVs for each meter traveled. Furthermore, the frequency analysis of energy consumption indicates that there is still some room for AVs to improve energy efficiency, particularly given their larger amplitude high-frequency fluctuations.
33 ADVANCED PROPULSION SYSTEMS↗
Curvilinear Displacement Transfer Functions for Deformed Shape Predictions of Curved Structures Using Distributed Surface Strains
Curvilinear Displacement Transfer Functions were formulated for deformed shape predictions of different curved structures using surface strains. The embedded curved beam (depth-wise cross section of a curved structure along a surface strain-sensing line) was discretized into multiple small domains, with domain junctures matching the strain-sensing stations. Thus, the surface strain distribution can be described with a piecewise linear or a piecewise nonlinear function. The discrete approach enabled piecewise integrations of a curvature-strain differential equation for the embedded curved beam to yield closed-form Curvilinear Displacement Transfer Functions, which are written in terms of embedded curved-beam geometrical parameters and surface strains. By inputting the surface strain data, the Curvilinear Displacement Transfer Functions can transform surface strains into deflections along each embedded curved beam for mapping out the overall structural deformed shapes. The finite-element method was used to analytically generate the surface strains of the curved beams. The deformed shape prediction accuracies were then determined by comparing the theoretical deflections with the finite-element-generated deflections, which were used as yardsticks. By introducing the correction factors in simple mathematical forms, the Curvilinear Displacement Transfer Functions can be quite accurate for shape predictions of different curved-beam structures ranging from limit case of straight beam up to semicircular curved beam.
Ko, William L.↗
Hybrid Recurrent Neural Network Modeling for Traffic Delay Prediction at Signalized Intersections Along an Urban Arterial
This paper studies the traffic delay prediction modeling for multiple signalized intersections along the Ala Moana Boulevard and Nimitz Highway in Hawaii. Several machine learning (ML) based approaches have been studied in the literature, and most of them focused on prediction accuracy rather than the end use of real-time control and implementation. These ML models tend to be very complex and non-linear in nature, making it challenging to achieve fast inferences and are computationally heavy for real-time signal control implementation. As such, in this paper, a simple yet accurate hybrid modeling method is proposed to predict traffic delay one-step ahead with the model made suitable for real-time implementation to control traffic flow. Since real-time road-side measurements are recorded in unstructured form, the paper also discusses other issues related to data extraction and the pre-processing process. Finally, a simple signal control loop is developed to demonstrate the proposed modeling approach, which has shown advantages in model accuracy and computation efficiency compared against several existing modeling methods.
42 ENGINEERING↗
Large-eddy simulation of a multi-injection flame in a diesel engine environment using an unsteady flamelet/progress variable approach
In this work, large-eddy simulations (LESs) are conducted for a multiple-injection flame in a diesel engine environment using an unsteady flamelet/progress variable (UFPV) approach in which differential diffusion is considered. The suitability of the UFPV tabulation approach is first evaluated through a priori analyses using the state-of-the-art direct numerical simulation (DNS) dataset. Both the instantaneous data and the conditional values for the major and minor species' mass fractions are compared between the UFPV and the DNS. The comparisons show that the proposed UFPV tabulation approach can give good predictions for the multiple-injection flame at different injection phases. While the gas temperature and major species mass fractions can be accurately predicted with or without differential diffusion being considered in the UFPV flamelet library, the prediction accuracy for the highly diffusive species (e.g., hydrogen) in the main injection phase can be noticeably improved when differential diffusion is taken into account. The fully coupled LES/UFPV simulations show that the overall structure of the multiple-injection flame can be predicted, and the conditional thermo-chemical values are close to the filtered DNS dataset. The reasons for the remaining discrepancies found in the a priori analyses and the a posteriori simulations using the UFPV approach are analyzed.
Wen, Xu (ORCID:0000000331334292)↗
Estimation of the accuracy of dynamic flight-determined coefficients
This paper discusses means of assessing the accuracy of maximum likelihood parameter estimates obtained from dynamic flight data. The commonly used analytical predictors of accuracy are compared from both statistical and simplified geometric standpoints. Emphasizing practical considerations, such as modeling error, the accuracy predictions are evaluated with real and simulated data. Improved computations of the Cramer-Rao bound to correct large discrepancies caused by colored noise and modeling error are presented. This corrected Cramer-Rao bound is the best available analytical predictor of accuracy. Engineering judgement, aided by such analytical tools, is the final arbiter of accuracy estimation.
Maine, R. E.↗
CORSAIR: A Framework for Human Mobility Prediction through Visit Characterization and Spatial Behavior Modeling
The rapid advancement of location acquisition technologies has led to the daily collection of vast amounts of mobile trajectory data, facilitating in-depth research on human mobility and enabling more accurate mobility prediction models. However, existing methodologies often fall short in capturing the intricate dynamics of human navigation and spatial behavior. This paper addresses this gap by exploring the multifaceted relationships between individuals and their environments, considering the diverse influences of personal preferences and experiences. Some places hold sentimental value and are visited frequently, while others serve as transient points of passage. To model these differences, we introduce CORSAIR, a novel visit characterization framework that leverages visitation patterns and dwell times to delineate an individual’s relationship with specific places. CORSAIR classifies visits into seven distinct types: casual, occasional, routine, special, anchor, important, and resettling. Also, we show that explicitly recognizing these distinct visit types and incorporating nuanced visit intents into mobility prediction models leads to a substantial improvement in prediction accuracy. This distinction allows for more precise modeling of the individual’s transitions, enhancing the personalization and relevance of location-based services. Our findings suggest that a deeper understanding of the complexities of individual-environment interactions is crucial for developing effective predictive tools in mobility research.
Amichi, Licia [ORNL] (ORCID:0000000177631394)↗
Machine Learning-Based Prediction of Distribution Network Voltage and Sensor Allocation
Increasing penetration levels of fast-varying energy resources might negatively affect power system operation. At the same time, sensor deployment throughout distribution networks improves system awareness and enables the development of new and advanced voltage control solutions. Such control techniques rely on accurate prediction in anticipation of voltage violation scenarios. This paper analyzes various approaches to voltage prediction in a distribution system, and it is shown that combining multiple techniques into a single regressor improves its predictive power. Moreover, a two-step regressor is proposed in which initial predictions based on a global regressor are refined by local regressors; in this case, prediction errors decrease significantly. Additionally, a clustering approach is employed to perform sensor allocation so that only the most influential buses are selected for monitoring without diminishing prediction accuracy.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
A data-driven framework for predicting machining stability: employing simulated data, operational modal analysis, and enhanced transfer learning
Chatter, a self-excited vibration phenomenon, presents a significant challenge in machining operations, particularly in high-speed milling, where it can degrade tool life, reduce material removal efficiency, and compromise workpiece quality. Addressing this challenge requires a reliable predictive model that can accommodate the complex dynamics of various machining scenarios. This study introduces a novel, data-driven approach to predicting machining stability, leveraging over 140,000 simulated datasets and employing advanced techniques such as operational modal analysis (OMA), enhanced transfer learning (TL), and receptance coupling substructure analysis (RCSA). By integrating these methodologies, the framework effectively classifies and predicts chatter across diverse operational modes, achieving robust and accurate outcomes. Our model utilizes a Random Forest (RF) classifier trained with the comprehensive dataset, which demonstrates substantial improvements in both predictive accuracy and robustness. Specifically, the RF model achieved an accuracy rate of 85%, an area under the curve (AUC) of 0.90, and an F1 score of 0.88, underscoring its capability to adapt to varying machining configurations. These results highlight the framework’s potential to enhance operational efficiency and machining quality by providing reliable chatter predictions across a broad range of machining parameters. In conclusion, this research thus offers a significant advancement in predictive maintenance for machining processes, enabling more stable and efficient manufacturing operations.
42 ENGINEERING↗
Boosting Barlow Twins Reduced Order Modeling for Machine Learning‐Based Surrogate Models in Multiphase Flow Problems
Abstract We present an innovative approach called boosting Barlow Twins reduced order modeling (BBT‐ROM) to enhance the reliability of machine learning surrogate models for multiphase flow problems. BBT‐ROM builds upon Barlow Twins reduced order modeling that leverages self‐supervised learning to effectively handle linear and nonlinear manifolds by constructing well‐structured latent spaces of input parameters and output quantities. To address the challenge of high contrast data in multiphase flow problems due to injection wells and faults, we employ a boosting algorithm within BBT‐ROM. This algorithm sequentially trains a set of weak models (i.e., inaccurate models), improving prediction accuracy through ensemble learning. To evaluate the performance of BBT‐ROM, we conduct three three‐dimensional multiphase flow problems, including waterflooding and geologic carbon storage (GCS), with varying numbers of input parameter cases and model domain features. The results demonstrate that BBT‐ROM excels at predicting non‐wetting phase saturation (e.g., oil or saturation) and fluid pressure, with average relative errors ranging from 0.5% to 3%. Importantly, BBT‐ROM showcases robustness when faced with limited input parameter space during GCS testing.
58 GEOSCIENCES↗
Machine Learning-Based Prediction of Distribution Network Voltage and Sensors Allocation: Preprint
Increasing penetration of fast-varying energy resources may negatively affect power systems' operation. At the same time, sensor deployment throughout distribution networks improves system awareness and enables the development of new and advanced voltage control solutions. Such control techniques rely on accurate prediction in anticipation to voltage violation scenarios. This paper analyzes various approaches for voltage prediction in a distribution system; it is shown that combining multiple techniques into a single regressor improves its predictive power. Moreover, a two-step regressor is proposed, where initial predictions based on a global regressor are refined by local regressors; in this case, prediction errors decrease significantly. Additionally, a clustering approach is employed for performing sensor allocation, so that only the most influential buses are selected for monitoring without diminishing prediction accuracy.
24 POWER TRANSMISSION AND DISTRIBUTION↗
Machine Learning-Based Prediction of Distribution Network Voltage and Sensor Allocation
Increasing penetration of fast-varying energy resources may negatively affect power systems' operation. At the same time, sensor deployment throughout distribution networks improves system awareness and enables the development of new and advanced voltage control solutions. Such control techniques rely on accurate prediction in anticipation to voltage violation scenarios. This paper analyzes various approaches for voltage prediction in a distribution system; it is shown that combining multiple techniques into a single regressor improves its predictive power. Moreover, a two-step regressor is proposed, where initial predictions based on a global regressor are refined by local regressors; in this case, prediction errors decrease significantly. Additionally, a clustering approach is employed for performing sensor allocation, so that only the most influential buses are selected for monitoring without diminishing prediction accuracy.
61 RADIATION PROTECTION AND DOSIMETRY↗
Propagation of Input Uncertainties in Numerical Simulations of Laser Powder Bed Fusion
Laser powder bed fusion has the potential of redefining state-of-the-art processing and production methods, but defect formation and inconsistent build quality have limited the implementation of this process. Numerical models are widely used to study this process and predict the formation of these defects. Presently, the uncertainties of model input parameters and thermophysical properties used by these numerical simulations have not been investigated. In the present study, the uncertainty in these input parameters and material properties are quantified for laser powder bed fusion, with and without a simulated powder bed, to determine their influence on the predictive accuracy of an experimentally validated numerical model. Accounting for all possible sources of uncertainty quickly becomes computationally expensive on account of the curse of dimensionality. Uncertainty in laser absorption, solid, and liquid specific heat of the metal were found to have the largest effect on model prediction reliability with or without the use of a powder bed. Results also illustrate that accounting for these three uncertain parameters still captures the majority of model prediction uncertainty. Furthermore, the methodology of this study may be used to understand the uncertainty in as-built microstructure through propagation to microstructure prediction models, or applied under processing conditions where high Péclet numbers are observed and the thermal convection and fluid flow within the molten pool are substantial.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗