Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data driven modeling”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,639 records · Page 91
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

CryoFold: Determining protein structures and data-guided ensembles from cryo-EM density maps

Cryoelectron microscopy requires molecular modeling for refinement of structures. Ensemble models arrive at low free-energy molecular structures, but are computationally expensive and limited to resolving only small proteins. Here, we introduce CryoFold, a pipeline of molecular dynamics simulations that determines ensembles of protein structures by integrating density data of varying sparsity at 3–5 Å resolution with sequence information and coarse-grained topological knowledge of the protein folds. We present six examples, folding proteins between 72 and 2,000 residues, including large membrane and multi-domain systems, and results from two Electron Microscopy Data Bank (EMDB) competitions. Driven by data from a single state, CryoFold discovers ensembles of common low-energy models together with rare low-probability structures that capture the equilibrium distribution of proteins constrained by the density maps. Many of these conformations are experimentally validated and functionally relevant. We arrive at a set of best practices for data-guided protein folding that are controlled using a Python graphical user interface (GUI).

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2004

Sensor Web Dynamic Measurement Techniques and Adaptive Observing Strategies

Sensor Web observing systems may have the potential to significantly improve our ability to monitor, understand, and predict the evolution of rapidly evolving, transient, or variable environmental features and events. This improvement will come about by integrating novel data collection techniques, new or improved instruments, emerging communications technologies and protocols, sensor mark-up languages, and interoperable planning and scheduling systems. In contrast to today's observing systems, "event-driven" sensor webs will synthesize real- or near-real time measurements and information from other platforms and then react by reconfiguring the platforms and instruments to invoke new measurement modes and adaptive observation strategies. Similarly, "model-driven" sensor webs will utilize environmental prediction models to initiate targeted sensor measurements or to use a new observing strategy. The sensor web concept contrasts with today's data collection techniques and observing system operations concepts where independent measurements are made by remote sensing and in situ platforms that do not share, and therefore cannot act upon, potentially useful complementary sensor measurement data and platform state information. This presentation describes NASA's view of event-driven and model-driven Sensor Webs and highlights several research and development activities at the Goddard Space Flight Center.

Talabac, Stephen J.↗
NASA NTRS2018

A Case Study Comparing Citizen Science Aurora Data with Global Auroral Boundaries Derived from Satellite Imagery and Empirical Models

Aurorasaurus is a citizen science project that offers a new, global data source consisting of ground-based reports of the aurora. For this case study, aurora data collected during the 17-18 March 2015 geomagnetic storm are examined to identify their conjunctions with Defense Meteorological Satellite Program (DMSP) satellite passes over the high latitude auroral regions. This unique set of aurora data can provide ground-truth validation of existing auroral precipitation models. Particularly, the solar wind driven, Oval Variation, Assessment, Tracking, Intensity, and Online Nowcasting (OVATION) Prime 2013 (OP-13) model and a Kp-dependent model of Zhang-Paxton (Z-P) are utilized for our boundary validation efforts. These two similar models are compared for the first time. Global equatorward auroral boundaries are derived from the OP 13 model and the DMSP Special Sensor Ultraviolet Spectrographic Imager (SSUSI) far ultraviolet (FUV) data using the Z-P model at a fixed flux level of 0.2 erg cm(exp -2)s(exp -1). These boundaries are then compared with citizen science reports as well as with each other. Even though there are some large differences between the global boundaries for a few cases, the average difference is about 1.5 deg in geomagnetic latitude, with OP-13 being equatorward of Z-P model. When these boundaries are compared with each other as a function of local time, no clear overall trend as a function of local time was observed. It is also found that the ground based reports are more consistent with the predictions of the OP-13 model.

Kosar, Burcu C.↗
NASA NTRS1989

A 3D visualization system for molecular structures

The properties of molecules derive in part from their structures. Because of the importance of understanding molecular structures various methodologies, ranging from first principles to empirical technique, were developed for computing the structure of molecules. For large molecules such as polymer model compounds, the structural information is difficult to comprehend by examining tabulated data. Therefore, a molecular graphics display system, called MOLDS, was developed to help interpret the data. MOLDS is a menu-driven program developed to run on the LADC SNS computer systems. This program can read a data file generated by the modeling programs or data can be entered using the keyboard. MOLDS has the following capabilities: draws the 3-D representation of a molecule using stick, ball and ball, or space filled model from Cartesian coordinates, draws different perspective views of the molecule; rotates the molecule on the X, Y, Z axis or about some arbitrary line in space, zooms in on a small area of the molecule in order to obtain a better view of a specific region; and makes hard copy representation of molecules on a graphic printer. In addition, MOLDS can be easily updated and readily adapted to run on most computer systems.

Green, Terry J.↗
DOE OSTI2024

Online Model-Free DER Dispatch Via Adaptive Voltage Sensitivity Estimation and Chance Constrained Programming

This paper proposes an online data-driven distributed energy resource management system (DERMS) for distribution system optimal DER dispatch as well as voltage regulation. Here, the key innovation is to leverage the Local Sensitivity Factor (LSF) for transforming the DER control into a computationally efficient linear programming (LP) problem. By taking real-time measurements, the estimation of LSF eliminates the need for an accurate distribution system model as well as full nodal load information, which is difficult to achieve in practice. A robust recursive least squares method is also developed to ensure the robust estimation of LSF, which is initialized using reasonable values from model-derived LSFs. This allows the system to adapt to changing operational conditions effectively. A scenario-based, chance-constrained framework is further employed to ensure voltage remains within acceptable limits in the presence of measurement and estimation uncertainties. Test results on a real-world, 759-node distribution network located in western Colorado, U.S., validate the effectiveness and robustness of the proposed control approach and demonstrate its superior performance as compared to alternative methods.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Strategies for community-sourced biocuration in bioinformatics: a case study on MIBiG 4.0

Biocuration is essential to transform molecular sequence data into standardized, machine-readable resources. Such curated datasets enable comparative analysis, predictive modeling, and data integration across bioinformatics platforms. While professional biocuration is resource-intensive and usually limited to institutional settings, community-driven approaches can mobilize large-scale annotation of specialized datasets and are more resilient to disruptions in scientific funding. Here, we present a model for community-powered curation applied to the Minimum Information about a Biosynthetic Gene Cluster (MIBiG) repository. Through a framework of workflows for metadata capture, annotation validation, and contributor coordination, the MIBiG 4.0 initiative recruited 267 scientists across 178 institutions from 33 countries, volunteering an estimated 4000 h of work. These efforts expanded the MIBiG repository by 22% and enhanced its usability in downstream molecular data analyses in comparative genomic analyses, natural product discovery, and machine learning applications. We provide strategies and actionable lessons for adopting this model, supporting the sustainability of curated bioinformatics resources central to nucleic acid research and related fields.

biocuration↗
DOE OSTI2022

A theory of dark pions

We present a complete model of a dark QCD sector with light dark pions, broadly motivated by hidden naturalness arguments. The dark quarks couple to the Standard Model via irrelevant Z- and Higgs-portal operators, which encode the low-energy effects of TeV-scale fermions interacting through Yukawa couplings with the Higgs field. The dark pions, depending on their CP properties, behave as either composite axion-like particles (ALPs) mixing with the Z or scalars mixing with the Higgs. The dark pion lifetimes fall naturally in the most interesting region for present and proposed searches for long-lived particles, at the LHC and beyond. This is demonstrated by studying in detail three benchmark scenarios for the symmetries and structure of the theory. Within a coherent framework, we analyze and compare the GeV-scale signatures of flavor-changing meson decays to dark pions, the weak-scale decays of Z and Higgs bosons to hidden hadrons, and the TeV-scale signals of the ultraviolet theory. New constraints are derived from B decays at CMS and from Z-initiated dark showers at LHCb, focusing on the displaced dimuon signature. We also emphasize the strong potential sensitivity of ATLAS and CMS to dark shower signals with large multiplicities and long lifetimes of the dark pions. As a key part of our phenomenological study, we perform a new data-driven calculation of the decays of a light ALP to exclusive hadronic Standard Model final states. The results are provided in a general form, applicable to any model with arbitrary flavor-diagonal couplings of the ALP to fermions.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Results and lessons learned from accelerating radio frequency modeling using machine learning [slides]

The “advanced tokamak” reactor concept is a leading candidate for a steady state fusion pilot plant. An advanced tokamak (AT) sustains a majority of the required plasma current with effects resulting from maintenance of the peaked pressure at the device center. This current is augmented by auxiliary current drive sources. These auxiliary actuators may consist of neutral particle beams and/or radio frequency (RF) systems such as lower hybrid current drive (LHCD) and high harmonic fast wave (HHFW) current drive using radio and microwaves from antennas. The primary focus of this work is to develop models of RF current profile control suitable for use in integrated modeling frameworks and for real-time control in experiments. Direct physics models of RF current drive can be computationally intensive. In order to achieve predictive times appropriate for the thousands of calls needed in real-time control of experiments and for use in integrated models, we will apply modern machine learning (ML) techniques to accelerate these models and interpolate their results. To generate the fast and accurate models for use in control level algorithms and integrated modeling we need to replace present models with high dimensional interpolation of their results. We will perform additional simulations across a broader parameter range for EAST and other tokamaks in different physics regimes (Alcator C-Mod, DIII-D, WEST, CFETR, ARC, ITER) and combine them into a larger database for training and testing of the ML models. Further testing of the control level models with experimental current profile data from EAST and C-Mod tokamaks will provide additional confirmation of the control level model before integration in a tokamak control system or integrated modeling suite. ML will be used to optimize the selection of training data consisting of RF current driven at different values of density profile, temperature profile, plasma current, and wavenumber. ML will also be used to facilitate classification of current drive from these input data. The output of this effort will be a validated classifier capable of determining the current drive profiles for HHFW CD and LHCD on a mille-second timescale. This will provide a breakthrough capability enabling real-time control of RF driven current profiles in experiments including ITER ICRF and use integrated modeling frameworks requiring thousands of current profile calculations in discharge simulations.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Physics-coupled data-driven design of high-temperature alloys

We present a materials design loop, which streamlines physics-coupled machine learning (ML) surrogate models to discover new alloy chemistries with improved properties. The efficacy is demonstrated by discovering a high-temperature alumina-forming austenitic (AFA) stainless steel with enhanced creep, followed by experimental validation. The ML models have been trained using a well-curated, highly consistent experimental dataset augmented with synthetic microstructural features from a computational thermodynamic approach. We have populated a large number of hypothetical AFA alloys to explore the high-dimensional composition space and have predicted their creep properties by providing the same synthetic input features obtained from the trained ML models. Uncertainties from the ML training were taken as thresholds for truncating predicted results to identify alloys with improved or deteriorated creep. Individual elemental compositions have been determined via probability density distribution analysis from the group of alloys at the top and bottom of the predicted creep values for further virtual and experimental validations. In conclusion, we anticipate that this workflow can be applied to screen desired conditions, such as chemistry and processing parameters, in high-dimensional space through physics-guided data analytics.

Alloy design↗
DOE OSTI2025

Wind and Weather Variability within the Californian Offshore Wind Energy Areas

Weather variability over the Northeast Pacific (NEP) region and its influence on wind resources within the Californian offshore wind energy areas (WEAs) at Humboldt and Morro Bay are characterized using 20-years reanalysis model and satellite data. The hub-height (180 m) winds at both locations are predominantly northwesterly driven by the NEP high pressure system, with strong coastal gradients in surface pressure, fluxes, planetary boundary layer (PBL) depths and cloudiness. These sharp coastal gradients and strong annual cycles of temperature and moisture advections pose potential challenges in accurately modeling the local wind resource. Hub-height wind speeds and power capacity factors significantly vary for different regimes of PBL depths, surface fluxes and rain area fractions. This highlights the importance of studying the physical mechanisms driving these weather regimes, hence our analysis of how large-scale NEP weather variability drives the local meteorology at the WEAs. Furthermore, at both WEAs, PBL tops and cloud boundaries intersect the rotor layer (80-280 m) more than 30% and 20% of the time, respectively. While PBL depths significantly modulates hub-height winds and power, cloud boundaries do not have a similar impact, likely due to reanalysis errors in simulating cloud boundaries accurately. These findings underscore the challenges in deploying tall wind turbines in shallow cloudy boundary layers, where the interaction between clouds, precipitation, and atmospheric layers can impact turbine efficiency. As turbines grow taller and are deployed in more complex meteorological conditions, understanding these interactions is crucial for improving wind power forecasting and optimizing energy production in coastal regions.

17 WIND ENERGY↗
NASA NTRS2015

An Inversion Analysis of Recent Variability in Natural CO2 Fluxes Using GOSAT and In Situ Observations

About one-half of the global CO2 emissions from fossil fuel combustion and deforestation accumulates in the atmosphere, where it contributes to global warming. The rest is taken up by vegetation and the ocean. The precise contribution of the two sinks, and their location and year-to-year variability are, however, not well understood. We use two different approaches, batch Bayesian synthesis inversion and variational data assimilation, to deduce the global spatiotemporal distributions of CO2 fluxes during 2009-2010. One of our objectives is to assess different sources of uncertainties in inferred fluxes, including uncertainties in prior flux estimates and observations, and differences in inversion techniques. For prior constraints, we utilize fluxes and uncertainties from the CASA-GFED model of the terrestrial biosphere and biomass burning driven by satellite observations and interannually varying meteorology. We also use measurement-based ocean flux estimates and two sets of fixed fossil CO2 emissions. Here, our inversions incorporate column CO2 measurements from the GOSAT satellite (ACOS retrieval, filtered and bias-corrected) and in situ observations (individual flask and afternoon-average continuous observations) to estimate fluxes in 108 regions over 8-day intervals for the batch inversion and at 3 x 3.75 weekly for the variational system. Relationships between fluxes and atmospheric concentrations are derived consistently for the two inversion systems using the PCTM atmospheric transport model driven by meteorology from the MERRA reanalysis. We compare the posterior fluxes and uncertainties derived using different data sets and the two inversion approaches, and evaluate the posterior atmospheric concentrations against independent data including aircraft measurements. The optimized fluxes generally resemble those from other studies. For example, the results indicate that the terrestrial biosphere is a net CO2 sink, and a GOSAT-only inversion suggests a shift in the global sink from the tropics south to the north relative to the prior and to an in-situ-only inversion. We also find a smaller terrestrial sink in higher-latitude northern regions in boreal summer of 2010 relative to 2009.

Carbon dioxide↗
DOE OSTI2022

Machine-Learning Accelerated Studies of Materials with High Performance and Edge Computing

In the studies of materials, experimental measurements often serve as the reference to verify physics theory and modeling; while theory and modeling provide a fundamental understanding of the physics and principles behind. However, the interactions and cross validation between them have long been a challenge even to-date. Not only that inferring a physics model from experimental data is itself a difficult inverse problem, another major challenge is the orders-of-magnitude longer wall-clock time required to carry out high-fidelity computer modeling to match the timescale of experiments. We envisage that by combining high performance computing, data science, and edge computing technology, the current predicament can be alleviated, and a new paradigm of data-driven physics research will open up. For example, we can accelerate computer simulations by first performing the large-scale modeling on high performance computers and train a machine-learned surrogate model. This computationally inexpensive surrogate model can then be transferred to the computing units residing closely to the experimental facilities to perform high-fidelity simulations at a much higher throughout. The model will also be more amenable to analyzing and validating experimental observations in comparable time scales at a much lower computational cost. Further integration of these accelerated computer simulations with an outer machine learning loop can also inform and direct future experiments, while making the inverse problem of physics model inference more tractable. We will demonstrate a proof-of-concept by using a quantum Monte Carlo application, Dynamical Cluster Approximation (DCA++), to machine-learn a surrogate model and accelerate the study of quantum correlated materials.

Li, Ying Wai↗
DOE OSTI2023

Differentiable modelling to unify machine learning and physical models for geosciences

Process-based modelling offers interpretability and physical consistency in many domains of geosciences but struggles to leverage large datasets efficiently. Machine-learning methods, especially deep networks, have strong predictive skills yet are unable to answer specific scientific questions. Here, in this Perspective, we explore differentiable modelling as a pathway to dissolve the perceived barrier between process-based modelling and machine learning in the geosciences and demonstrate its potential with examples from hydrological modelling. ‘Differentiable’ refers to accurately and efficiently calculating gradients with respect to model variables or parameters, enabling the discovery of high-dimensional unknown relationships. Differentiable modelling involves connecting (flexible amounts of) prior physical knowledge to neural networks, pushing the boundary of physics-informed machine learning. It offers better interpretability, generalizability, and extrapolation capabilities than purely data-driven machine learning, achieving a similar level of accuracy while requiring less training data. Additionally, the performance and efficiency of differentiable models scale well with increasing data volumes. Under data-scarce scenarios, differentiable models have outperformed machine-learning models in producing short-term dynamics and decadal-scale trends owing to the imposed physical constraints. Differentiable modelling approaches are primed to enable geoscientists to ask questions, test hypotheses, and discover unrecognized physical relationships. Future work should address computational challenges, reduce uncertainty, and verify the physical significance of outputs.

58 GEOSCIENCES↗
DOE OSTI2021

Explicit physics-informed neural networks for nonlinear closure: The case of transport in tissues

In upscaling methods, closures for nonlinear problems present a well-known challenge. While a number of theoretical methods have been proposed for handling such closures, nonlinearities still remain a significant obstacle for many problems. In this work, we use a combination of formal upscaling and data-driven machine learning for explicitly closing a nonlinear transport and reaction process in multiscale tissues. The classical effectiveness factor model is used to formulate the macroscale reaction kinetics. We train a multilayer perceptron network using training data generated by direct numerical simulations over microscale examples. Once trained, the network is used in an algorithm for numerically solving the upscaled (coarse-grained) differential equation describing mass transport and reaction in two example tissues. The network is described as being explicit in the sense that the network is trained using macroscale concentrations and gradients of concentration as components of the feature space rather than incorporating them as part of a constraint in the optimization process. Network training and solutions to the macroscale transport equations were computed for two different tissues. The two tissue types (brain and liver) exhibit markedly different geometrical complexity and spatial scale (cell size and sample size). The upscaled solutions for the average concentration are compared with numerical solutions derived from the microscale concentration fields by a posteriori averaging. There are three outcomes of this work of particular note. 1) Our overall approach results in an upscaled nonlinear PDE. The PDE is closed using a neural network, and our approach results in the definition of the classical effectiveness factor for effecting closure. 2) We identify particular source terms for the closure problem that are important for representing the structure of the closure. These source terms involve macroscale concentrations and their gradients. We adopt these source terms to use as explicit features in the learning algorithm. We find the trained networks that include the macroscale source terms generate models that are able to predict the correction factor with increased fidelity over those that do not. 3) We find that the trained network exhibits good generalizability, and it is able to predict the effectiveness factor with high fidelity for realistically-structured tissues despite the significantly different scale and geometrical complexity of the two example tissue types. This latter result emphasizes our purposeful connection between conventional averaging methods with the use of machine learning for closure; this contrasts with some machine learning methods for upscaling where the exact form of the macroscale equation remains unknown.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2023

Evaluating Greenland Surface-Mass-Balance and Firn-Densification Data Using ICESat-2 Altimetry

Surface-mass-balance (SMB) and firn-densification (FD) models are widely used in altimetry studies as a tool to separate atmospheric-driven from ice-dynamics-driven ice-sheet mass changes and to partition observed volume changes into ice-mass changes and firn-air-content changes. Until now, SMB models have been principally validated based on comparison with ice core and weather station data or comparison with widely separated flight radar-survey flight lines. Firn-densification models have been primarily validated based on their ability to match net densification over decades, as recorded in firn cores, and the short-term time-dependent component of densification has rarely been evaluated at all. The advent of systematic ice-sheet-wide repeated ice-surface-height measurements from ICESat-2 (the Ice Cloud, and land Elevation Satellite, 2) allows us to measure the net surface-height change of the Greenland ice sheet at quarterly resolution and compare the measured surface-height differences directly with those predicted by three FD–SMB models: MARv3.5.11 (Modèle Atmosphérique Régional version 3.5.11) and GSFCv1.1 and GSFCv1.2 (the Goddard Space Flight Center FD–SMB models version 1.1 and 1.2). By segregating the data by season and elevation, and based on the timing and magnitude of modelled processes in areas where we expect minimal ice-dynamics-driven height changes, we investigate the models' accuracy in predicting atmospherically driven height changes. We find that while all three models do well in predicting the large seasonal changes in the low-elevation parts of the ice sheet where melt rates are highest, two of the models (MARv3.5.11 and GSFCv1.1) systematically overpredict, by around a factor of 2, the magnitude of height changes in the high-elevation parts of the ice sheet, particularly those associated with melt events. This overprediction seems to be associated with the melt sensitivity of the models in the high-elevation part of the ice sheet. The third model, GSFCv1.2, which has an updated high-elevation melt parameterization, avoids this overprediction.

Benjamin E. Smith↗
DOE OSTI2020

Advancing Fusion with Machine Learning Research Needs Workshop Report

Abstract Machine learning and artificial intelligence (ML/AI) methods have been used successfully in recent years to solve problems in many areas, including image recognition, unsupervised and supervised classification, game-playing, system identification and prediction, and autonomous vehicle control. Data-driven machine learning methods have also been applied to fusion energy research for over 2 decades, including significant advances in the areas of disruption prediction, surrogate model generation, and experimental planning. The advent of powerful and dedicated computers specialized for large-scale parallel computation, as well as advances in statistical inference algorithms, have greatly enhanced the capabilities of these computational approaches to extract scientific knowledge and bridge gaps between theoretical models and practical implementations. Large-scale commercial success of various ML/AI applications in recent years, including robotics, industrial processes, online image recognition, financial system prediction, and autonomous vehicles, have further demonstrated the potential for data-driven methods to produce dramatic transformations in many fields. These advances, along with the urgency of need to bridge key gaps in knowledge for design and operation of reactors such as ITER, have driven planned expansion of efforts in ML/AI within the US government and around the world. The Department of Energy (DOE) Office of Science programs in Fusion Energy Sciences (FES) and Advanced Scientific Computing Research (ASCR) have organized several activities to identify best strategies and approaches for applying ML/AI methods to fusion energy research. This paper describes the results of a joint FES/ASCR DOE-sponsored Research Needs Workshop on Advancing Fusion with Machine Learning, held April 30–May 2, 2019, in Gaithersburg, MD (full report available at https://science.osti.gov/-/media/fes/pdf/workshop-reports/FES_ASCR_Machine_Learning_Report.pdf ). The workshop drew on broad representation from both FES and ASCR scientific communities, and identified seven Priority Research Opportunities (PRO’s) with high potential for advancing fusion energy. In addition to the PRO topics themselves, the workshop identified research guidelines to maximize the effectiveness of ML/AI methods in fusion energy science, which include focusing on uncertainty quantification, methods for quantifying regions of validity of models and algorithms, and applying highly integrated teams of ML/AI mathematicians, computer scientists, and fusion energy scientists with domain expertise in the relevant areas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Surrogate Modeling of Nonlinear Dynamic Systems: A Comparative Study

Surrogate models play a vital role in overcoming the computational challenge in designing and analyzing nonlinear dynamic systems, especially in the presence of uncertainty. This paper presents a comparative study of different surrogate modeling techniques for nonlinear dynamic systems. Four surrogate modeling methods, namely, Gaussian process (GP) regression, a long short-term memory (LSTM) network, a convolutional neural network (CNN) with LSTM (CNN-LSTM), and a CNN with bidirectional LSTM (CNN-BLSTM), are studied and compared. All these model types can predict the future behavior of dynamic systems over long periods based on training data from relatively short periods. The multi-dimensional inputs of surrogate models are organized in a nonlinear autoregressive exogenous model (NARX) scheme to enable recursive prediction over long periods, where current predictions replace inputs from the previous time window. Three numerical examples, including one mathematical example and two nonlinear engineering analysis models, are used to compare the performance of the four surrogate modeling techniques. The results show that the GP-NARX surrogate model tends to have more stable performance than the other three deep learning (DL)-based methods for the three particular examples studied. The tuning effort of GP-NARX is also much lower than its deep learning-based counterparts.

42 ENGINEERING↗