Search NASA⌕ Search

SEARCH · Search NASA

Results for “Surrogate 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 469 records · Page 26

Efficient Loads Surrogates for Waked Turbines in an Array

Accurately and efficiently predicting wind turbine structural loading is a crucial step in wind farm design. Without considering structural loading, wind farm optimization could negatively impact turbine fatigue and ultimate loads, especially for waked and partially waked turbines, which could result in higher maintenance costs and reduced turbine lifetime. However, predicting turbine loads throughout an array is a costly step, as these quantities require time-accurate results across long time histories, which is often intractable for large array optimization. Therefore, surrogate models that link array spacing to load outputs are often used, but the surrogates are then unique to the inflow conditions and array configurations in the training library. This work develops surrogate models for many wind turbine load outputs based solely on rotor plane velocity measurements, with no required input about array configuration or freestream inflow parameters. Surrogate models were constructed for many turbine quantities of interest (QoI), considering mean, standard deviation, ultimate, and fatigue loads. In general, most QoI statistics were accurately captured, as measured by predicted vs. actual correlation coefficient, confirming the suitability of the approach. Temporal mean values of the QoI required only temporal mean measurements of the rotor plane inflow velocity. However, accurate prediction of temporal standard deviation, ultimate, and fatigue values of QoI also required temporal standard deviations of the rotor plane velocity field. Poor surrogate performance was observed when too many correlated inputs were used, such as multiple velocity components. If the fewest inflow parameters are used to construct the surrogates, the average correlation coefficient value for all output QoI statistics is 0.89. Surrogates for standard deviations and damage equivalent loads (DELs) of turbine QoIs generally had lower accuracy and tower-base and shaft load channels posed the most difficult to capture accurately. The results suggest that these surrogates could be easily paired with analytic wake models, which are frequently used for pre-construction wind farm array optimization, to account for turbine loading in addition to power production. By including the optimal inflow conditions, the surrogate accuracy can improve to an average correlation coefficient value for all output QoI statistics of 0.92. This work has established the ability to build accurate surrogates for mean, standard deviation, ultimate load, and DEL turbine QoI values based on the rotor plane inflow velocity, and identified which inflow conditions lead to greater surrogate accuracy.

17 WIND ENERGY↗

Chemically authentic surrogate mixture model for the thermophysical properties of a coal-derived liquid fuel

We developed a surrogate mixture model to represent the physical properties of a coal-derived liquid fuel using only information obtained from a gas chromatography-mass spectrometry analysis of the fuel and a recently developed 'advanced distillation curve'. We then predicted the density, speed of sound, and viscosity of the fuel and compared them to limited experimental data. The surrogate contains five components (n-propylcyclohexane, trans-decalin, {alpha}-methyldecalin, bicyclohexane, and n-hexadecane), yet comparisons to limited experimental data demonstrate that the model is able to represent the density, sound speed, and viscosity to within 1, 4, and 5%, respectively. 102 refs., 2 figs., 5 tabs.

01 COAL, LIGNITE, AND PEAT↗

Mitigating Errors in External Respiratory Surrogate-Based Models of Tumor Position

Purpose: To investigate the effect of tumor site, measurement precision, tumor-surrogate correlation, training data selection, model design, and interpatient and interfraction variations on the accuracy of external marker-based models of tumor position. Methods and Materials: Cyberknife Synchrony system log files comprising synchronously acquired positions of external markers and the tumor from 167 treatment fractions were analyzed. The accuracy of Synchrony, ordinary-least-squares regression, and partial-least-squares regression models for predicting the tumor position from the external markers was evaluated. The quantity and timing of the data used to build the predictive model were varied. The effects of tumor-surrogate correlation and the precision in both the tumor and the external surrogate position measurements were explored by adding noise to the data. Results: The tumor position prediction errors increased during the duration of a fraction. Increasing the training data quantities did not always lead to more accurate models. Adding uncorrelated noise to the external marker-based inputs degraded the tumor-surrogate correlation models by 16% for partial-least-squares and 57% for ordinary-least-squares. External marker and tumor position measurement errors led to tumor position prediction changes 0.3-3.6 times the magnitude of the measurement errors, varying widely with model algorithm. The tumor position prediction errors were significantly associated with the patient index but not with the fraction index or tumor site. Partial-least-squares was as accurate as Synchrony and more accurate than ordinary-least-squares. Conclusions: The accuracy of surrogate-based inferential models of tumor position was affected by all the investigated factors, except for the tumor site and fraction index.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Accurate and uncertainty-aware multi-task prediction of HEA properties using prior-guided deep Gaussian processes

Surrogate modeling techniques have become indispensable in accelerating the discovery and optimization of high-entropy alloys (HEAs), especially when integrating computational predictions with sparse experimental observations. This study systematically evaluates the training and testing performance of four prominent surrogate models—conventional Gaussian processes (cGP), Deep Gaussian processes (DGP), encoder-decoder neural networks for multi-output regression and eXtreme Gradient Boosting (XGBoost)—applied to a hybrid dataset of experimental and computational properties of the 8-component HEA system Al-Co-Cr-Cu-Fe-Mn-Ni-V. We specifically assess their capabilities in predicting correlated material properties, including yield strength, hardness, modulus, ultimate tensile strength, elongation, and average hardness under dynamic/quasi-static conditions, alongside auxiliary computational properties. The comparison highlights the strengths of hierarchical deep modeling approaches in handling heteroscedastic, heterotopic, and incomplete data commonly encountered in materials science. Our findings illustrate that combined surrogate models such as DGPs infused with machine-learned priors outperform other surrogates by effectively capturing inter-property correlations and by assimilating prior knowledge. This enhanced predictive accuracy positions the combined surrogate models as powerful tools for robust and data-efficient materials design.

36 MATERIALS SCIENCE↗

Polynomial Chaos–Based Bayesian Inference of K -Profile Parameterization in a General Circulation Model of the Tropical Pacific

The authors present a polynomial chaos (PC)–based Bayesian inference method for quantifying the uncertainties of the K-profile parameterization (KPP) within the MIT general circulation model (MITgcm) of the tropical Pacific. The inference of the uncertain parameters is based on a Markov chain Monte Carlo (MCMC) scheme that utilizes a newly formulated test statistic taking into account the different components representing the structures of turbulent mixing on both daily and seasonal time scales in addition to the data quality, and filters for the effects of parameter perturbations over those as a result of changes in the wind. To avoid the prohibitive computational cost of integrating the MITgcm model at each MCMC iteration, a surrogate model for the test statistic using the PC method is built. Because of the noise in the model predictions, a basis-pursuit-denoising (BPDN) compressed sensing approach is employed to determine the PC coefficients of a representative surrogate model. The PC surrogate is then used to evaluate the test statistic in the MCMC step for sampling the posterior of the uncertain parameters. Results of the posteriors indicate good agreement with the default values for two parameters of the KPP model, namely the critical bulk and gradient Richardson numbers; while the posteriors of the remaining parameters were barely informative.

54 ENVIRONMENTAL SCIENCES↗

Water Quality Projects Summary for the Mid-Columbia and Cumberland River Systems

Scheduling and operational control of hydropower systems is accompanied with a keen awareness of the management of water use, environmental effects, and policy, especially within the context of strict water rights policy and generation maximization. This is a multi-objective problem for many hydropower systems, including the Cumberland and Mid-Columbia river systems. Though each of these two systems have distinct operational philosophies, hydrologic characteristics, and system dynamics, they both share a responsibility to effectively manage hydropower and the environment, which requires state-of-the art improvements in the approaches and applications for water quality modeling. The Department of Energy and Oak Ridge National Laboratory have developed tools for total dissolved gas (TDG) prediction on the Mid-Columbia River and a decision-support system used for hydropower generation and environmental optimization on the Cumberland River. In conjunction with IIHR - Hydroscience & Engineering, The University of Iowa and University of Colorado s Center for Advanced Decision Support for Water and Environmental Systems (CADSWES), ORNL has managed the development of a TDG predictive methodology at seven dams along the Mid-Columbia River and has enabled the ability to utilize this methodology for optimization of operations at these projects with the commercially available software package Riverware. ORNL has also managed the collaboration with Vanderbilt University and Lipscomb University to develop a state-of-the art method for reducing high-fidelity water quality modeling results into surrogate models which can be used effectively within the context of optimization efforts to maximize generation for a reservoir system based on environmental and policy constraints. The novel contribution of these efforts is the ability to predict water quality conditions with simplified methodologies at the same level of accuracy as more complex and resource intensive computing methods. These efforts were designed to incorporate well into existing hydropower and reservoir system scheduling models, with runtimes that are comparable to existing software tools. In addition, the transferability of these tools to assess other systems is enhanced due the use of simplistic and easily attainable values for inputs, straight-forward calibration of predictive equation coefficients, and standardized comparison of traditionally familiar outputs.

54 ENVIRONMENTAL SCIENCES↗

A hybrid numerical and machine learning framework for evaluating the performance of a 780 cm 2 aqueous organic redox flow battery

Aqueous organic redox flow battery (AORFB) is a promising cost-competitive technology for large-scale energy storage. Among existing work, the dihydroxyphenazine (DHP)-based AORFB has demonstrated high energy density and low capacity degradation in 10 cm2 cells during lab tests. However, its commercial-scale performance in more complex environments remains unknown, posing a barrier for commercialization. To address this gap, this work presents a comprehensive performance evaluation of a 780 cm 2 DHP-based AORFB by combining physics-based numerical model, machine learning (ML)-based surrogate models, and ML-derived sensitivity quantification. Specifically, we first select 12 key battery parameters that include 10 physicochemical quantities and 2 operation quantities, then select 6 performance metrics that include energy efficiency (EE), discharging capacity, charging energy, and power losses due to concentration, activation, and ohmic over-potentials. With such selection, 12800 combinations of the 12 parameters are subsequently generated using the Latin Hypercube Sampling method. These combinations, together with 38 pre-defined State of Charge, are then integrated to a validated AORFB model developed in COMSOL to compute the performance metrics. With both input parameters and performance metrics, 60 deep neural network (DNN) surrogate models are then trained to approximate the relationship between the 10 physicochemical quantities and 6 performance metrics at each flow rate and current density. Sensitivity scores are then calculated based on the DNN models. Two additional sensitivity analysis tools, i.e., MARS, and SHAP, are also used to cross-validate the sensitivity scores from the DNN. The results demonstrate that 1) the standard potential ranks the first in controlling EE and charging energy, 2) the membrane conductivity is most critical for power loss and EE, and 3) specific area and reaction rate control activation power loss.

25 ENERGY STORAGE↗

Evaluating large scale aqueous organic redox flow battery performance with a hybrid numerical and machine learning framework

Aqueous organic redox flow battery (AORFB) is a promising cost-competitive technology for large-scale energy storage. Among existing work, the dihydroxyphenazine (DHP)-based AORFB has demonstrated high energy density and low-capacity degradation in 10 cm$^2$ cells during lab tests. However, its commercial-scale performance in more complex environments remains unknown, posing a barrier to commercialization. To address this gap, this work presents a comprehensive performance evaluation of a 780 cm$^2$ DHP-based AORFB by combining a physics-based numerical model, machine learning (ML)-based surrogate models, and ML-derived sensitivity quantification. Specifically, we first select 12 key battery parameters that include 10 physicochemical and 2 operation quantities, then select 6 performance metrics that include energy efficiency (EE), discharging capacity, charging energy, and power losses due to concentration, activation, and ohmic over-potentials. With such selection, 12800 combinations of the 12 parameters are subsequently generated using the Latin Hypercube Sampling method. Such combinations, together with 38 pre-defined State of Charge, are then integrated to a validated AORFB model developed in COMSOL to compute the performance metrics. With both input parameters and performance metrics, 60 deep neural network (DNN) surrogate models are then trained to approximate the relationship between the 10 physicochemical quantities and 6 performance metrics at each flow rate and current density. Sensitivity scores are then calculated based on the DNN models. Two additional sensitivity analysis tools, i.e., MARS, and SHAP, are also used to cross-validate the sensitivity scores from the DNN. The results demonstrate that 1) the standard potential ranks first in controlling EE and charging energy, 2) the membrane conductivity is most critical for power loss and EE, and 3) specific area and reaction rate control activation power loss.

25 ENERGY STORAGE↗

Probing Sensitivity of Discharge Characteristics to Model Selection using Uncertainty Quantification in an aprotic Li-Oxygen Battery

Currently, there are several models in the literature, such as kinetic models, microstructural models, and mass transport models that describe a Li-air battery's discharge behavior. Many of these models are calibrated and tested at low current densities and cannot be easily transferred to high current densities. Even at low current densities, there is no quantitative method for a researcher to choose a reaction kinetic model such as classical Butler-Volmer and its derivatives, and modified Marcus-Hush-Chidsey, a resistance model for lithium peroxide such as electron transport via tunneling or linear resistivity, a surface coverage model (lithium peroxide growth) such as partial coverage or full coverage, and mass transport model (discussed in Ref. [1]). Also, it is time-consuming to test different models at high current density (1C) due to a lack of well-tested models and well-calibrated model parameters. For this presentation, we will develop an analytical model, which acts as a surrogate model for a sophisticated finite element model to predict discharge time and discharge voltage. Next, we use an uncertainty quantifying technique called reduced-order stochastic optimization [2, 3] to determine the uncertainty in model parameters for rate kinetics, lithium peroxide resistivity, and parasitic resistance. Finally, a finite element simulation is performed to determine the error introduced by the surrogate model and its influence on the uncertainty in the model parameters.

M Mehta↗

National Security Forensics

The objective of this effort is to research and develop inversion methods for mapping observations to the input parameters of the underlying physical system that could have generated these observations. This report describes our FY11 progress in developing a surrogate model of the forward model, using this surrogate forward model to develop inversion capabilities, and partitioning the input-output space to facilitate assessment and implementation of our inversion capabilities, as well as adaptively propose new computer code runs to enhance our training data. This work was funded by NA22/SAM in the NN2001- 06 area, under project number LL10-Forensics-PD06.

97 MATHEMATICS AND COMPUTING↗

Development of multi-objective core optimization framework and application to sodium-cooled fast test reactors

The optimization of a Sodium-cooled Fast Reactor (SFR) core is a challenging process, due to the large number of design parameters, the nonlinearities among inputs and outputs, and the complicated correlation among output parameters. This study attempts to develop a generalized framework for the SFR core optimization by coupling the sensitivity analysis, advanced optimization algorithm, and optionally the surrogate modeling. The framework is built based on the fast reactor modeling capability of the Argonne Reactor Computation (ARC) suite and the sensitivity analysis and optimization modules embedded in the DAKOTA code, both have been integrated within the NEAMS Workbench. The genetic algorithm is selected as the optimization method for its robustness, while the option of surrogate modeling is also explored to alleviate the computational burden caused by employing the ARC direct core physics simulation and thus enhance the efficiency of the optimization. Finally, the normalized deviations of performance parameters of the near-optimal solution from those of the ideal core are calculated and used as criteria to down select the final core design. The developed framework is applied to the Advanced Burner Test Reactor (ABTR) core, and optimal solutions are determined by balancing various objectives simultaneously, including peak fast flux, core volume, power, reactivity swing, plutonium mass feed, while at the same time satisfying the predefined constraints due to safety or economics considerations. The optimal ABTR core design obtained using the direct physical simulation and surrogated model are compared and discussed. It is found that using the accurately constructed surrogate models can significantly reduce the required computational time while maintaining satisfactory accuracy.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Computational Workflow for Accelerated Molecular Design Using Quantum Chemical Simulations and Deep Learning Models

Efficient methods for searching the chemical space of molecular compounds are needed to automate and accelerate the design of new functional molecules such as pharmaceuticals. Given the high cost in both resources and time for experimental efforts, computational approaches play a key role in guiding the selection of promising molecules for further investigation. Here, we construct a workflow to accelerate design by combining approximate quantum chemical methods [i.e. density-functional tight-binding (DFTB)], a graph convolutional neural network (GCNN) surrogate model for chemical property prediction, and a masked language model (MLM) for molecule generation. Property data from the DFTB calculations are used to train the surrogate model; the surrogate model is used to score candidates generated by the MLM. The surrogate reduces computation time by orders of magnitude compared to the DFTB calculations, enabling an increased search of chemical space. Furthermore, the MLM generates a diverse set of chemical modifications based on pre-training from a large compound library. We utilize the workflow to search for near-infrared photoactive molecules by minimizing the predicted HOMO-LUMO gap as the target property. Our results show that the workflow can generate optimized molecules outside of the original training set, which suggests that iterations of the workflow could be useful for searching vast chemical spaces in a wide range of design problems.

Blanchard, Andrew↗

TCAD-Machine Learning Enabled TID Compact Model Development for Commercial SiC MOSFET

We propose a TCAD (Technology Computer Aided Design)-machine learning coupled approach that combines a TCAD tool (Charon), optimization/uncertainty quantification tool (Dakota), surrogate models, and Bayesian learning capabilities. The coupling approach is used for accurate modeling and calibration of total ionizing dose (TID) induced threshold voltage (V th ) shifts in Commercial-Off-The-Shelf (COTS) semiconductor devices and to develop physics-informed TID compact models. This versatile approach is applied to model the TID effect in an exemplar COTS 3.3 kV SiC power MOSFET (Metal-Oxide-Semiconductor Field-Effect Transistor). With the Charon-Dakota coupling, we can determine key device geometry and doping values based on device physics, which are difficult to obtain or not available for COTS devices but important for TCAD simulation; additionally, we can efficiently generate thousands of simulation results in a large parameter space, which makes it possible to develop data-driven surrogate models and perform Bayesian calibration. Utilizing the full tool-coupling approach, we achieve calibrated TCAD simulation models that accurately capture the average TID-induced V th shifts behavior with total doses and V th shifts saturation at high doses as observed in experimental data. More importantly, the calibrated TCAD simulations are obtained with determined TID model parameters (e.g., hole trap density and capture cross section) values that contain well quantified uncertainties. Furthermore, we can isolate and quantify the noises that are not captured by the TCAD models but exist in the measured data due to measurements and devices variabilities. Lastly, the calibrated surrogate models are used to develop physics-informed TID compact models. The method is generalizable to other devices and/or radiation conditions with few modifications and can provide well-determined uncertainties.

COTS↗

Probabilistic Modeling of a Three-Stage Human Landing System Architecture

Unmitigated uncertainties are known to have previously led to failed development programs; in order to combat these uncertainties, risks and their impacts must be understood and handled to ensure program success. In this paper, a probabilistic methodology to handle uncertainties is demonstrated on a three-element Human Landing System (HLS) concept, which allows tracking of current best estimates of the vehicle’s performance and assessment of its robustness against uncertainties. This methodology has two key parts: first, the creation of a dynamic architecture model of a three-element HLS concept; and second, its use with surrogate modeling and range estimating techniques to capture and propagate uncertainties. The DYnamic Rocket EQuation Tool (DYREQT), a space systems synthesis and sizing framework used by NASA, was used as to model the HLS architecture. For the probabilistic analysis, uncertainties of interest within the HLS concept were enumerated and represented as parameters within the DYREQT model as inputs for vehicle stages or mission profile events. Range estimating — a probabilistic method that combines Monte Carlo sampling, focus on critical parameters, and heuristics to assess risk and opportunities — is then adapted with operational parameters as well as vehicle parameters in the DYREQT model to capture mission uncertainty alongside vehicle uncertainty. To perform the range estimation portion of this methodology, the DYREQT model was sampled using a Design of Experiments (DoE) to efficiently explore the architecture design space with respect to the set of uncertainty parameters. Then, the results were used to create surrogate models, multivariate regressions that can visualize hypercube trends in the design space, of the architecture with respect to the uncertainty parameters. Using a correlation matrix constructed for the uncertainty parameters, previously independent samples were transformed to perform a Correlated Monte Carlo on the surrogate models. This probabilistic methodology was proved to provide insight into the underlying uncertainties of the three-element HLS architecture.

Stephanie Y Zhu↗

Probabilistic Modeling of a Three-Stage Human Landing System Architecture

Unmitigated uncertainties are known to have previously led to failed development programs; in order to combat these uncertainties, risks and their impacts must be understood and handled to ensure program success. In this paper, a probabilistic methodology to handle uncertainties is demonstrated on a three-element Human Landing System (HLS) concept, which allows tracking of current best estimates of the vehicle’s performance and assessment of its robustness against uncertainties. This methodology has two key parts: first, the creation of a dynamic architecture model of a three-element HLS concept; and second, its use with surrogate modeling and range estimating techniques to capture and propagate uncertainties. The DYnamic Rocket EQuation Tool (DYREQT), a space systems synthesis and sizing framework used by NASA, was used as to model the HLS architecture. For the probabilistic analysis, uncertainties of interest within the HLS concept were enumerated and represented as parameters within the DYREQT model as inputs for vehicle stages or mission profile events. Range estimating — a probabilistic method that combines Monte Carlo sampling, focus on critical parameters, and heuristics to assess risk and opportunities — is then adapted with operational parameters as well as vehicle parameters in the DYREQT model to capture mission uncertainty alongside vehicle uncertainty. To perform the range estimation portion of this methodology, the DYREQT model was sampled using a Design of Experiments (DoE) to efficiently explore the architecture design space with respect to the set of uncertainty parameters. Then, the results were used to create surrogate models, multivariate regressions that can visualize hypercube trends in the design space, of the architecture with respect to the uncertainty parameters. Using a correlation matrix constructed for the uncertainty parameters, previously independent samples were transformed to perform a Correlated Monte Carlo on the surrogate models. This probabilistic methodology was proved to provide insight into the underlying uncertainties of the three-element HLS architecture.

Stephanie Y. Zhu↗

A Gaussian process autoregressive model capturing microstructure evolution paths in a Ni–Mo–Nb alloy

Additive manufacturing is increasingly being employed to produce components of complex geometries in structural alloys because of the expected energy savings associated with the near-net-shape capability and the ability to build in novel internal features that are not possible with many conventional manufacturing approaches. However, because of the extreme thermal conditions encountered, the non-equilibrium microstructures produced during powder bed-based additive manufacturing processes must be subjected to custom post-heat treatment processes to recover the target mechanical properties. Phase-field models and simulation techniques have matured to a state where the microstructure evolution paths, and the morphologies of the resulting precipitate phases can be predicted reasonably accurately, considering alloy-specific thermodynamic and kinetic aspects of the nucleation and growth processes. However, phase-field simulations are computationally intensive, which precludes the ability to apply the simulations directly to the length scale of the entire component. Therefore, it is highly desirable to develop low-computational-cost surrogate models that effectively capture the physics at the microstructural length scale, while facilitating the design of optimized processing conditions resulting in location-specific targeted microstructures at the component scale. The work presented here demonstrates the application of the materials knowledge system framework to develop a surrogate model that effectively captures the microstructural path during annealing of a Ni–Mo–Nb alloy containing different Mo and Nb compositions known to segregate during solidification under additive manufacturing conditions. Specifically, the surrogate model built in this work is based on a Gaussian process autoregressive model informed by statistical representation of simulated microstructures using two-point correlations and dimensionality reduction through principal component analysis. In conclusion, this surrogate model is shown to capture the bifurcation of the microstructural path during precipitation, which yields a microstructure dominated by the $\gamma^{\prime\prime}$ phase at high Nb concentrations and the $\delta$ phase at low Nb concentrations.

36 MATERIALS SCIENCE↗

Review of multi-fidelity models

Multi-fidelity models provide a framework for integrating computational models of varying complexity, allowing for accurate predictions while optimizing computational resources. These models are especially beneficial when acquiring high-accuracy data is costly or computationally intensive. This review offers a comprehensive analysis of multi-fidelity models, focusing on their applications in scientific and engineering fields, particularly in optimization and uncertainty quantification. It classifies publications on multi-fidelity modeling according to several criteria, including application area, surrogate model selection, types of fidelity, combination methods and year of publication. The study investigates techniques for combining different fidelity levels, with an emphasis on multi-fidelity surrogate models. Here this work discusses reproducibility, open-sourcing methodologies and benchmarking procedures to promote transparency. The manuscript also includes educational toy problems to enhance understanding. Additionally, this paper outlines best practices for presenting multi-fidelity-related savings in a standardized, succinct and yet thorough manner. The review concludes by examining current trends in multi-fidelity modeling, including emerging techniques, recent advancements, and promising research directions.

42 ENGINEERING↗

Emerging materials intelligence ecosystems propelled by machine learning

We report that the age of cognitive computing and artificial intelligence (AI) is just dawning. Inspired by its successes and promises, several AI ecosystems are blossoming, many of them within the domain of materials science and engineering. These materials intelligence ecosystems are being shaped by several independent developments. Machine learning (ML) algorithms and extant materials data are utilized to create surrogate models of materials properties and performance predictions. Materials data repositories, which fuel such surrogate model development, are mushrooming. Automated data and knowledge capture from the literature (to populate data repositories) using natural language processing approaches is being explored. The design of materials that meet target property requirements and of synthesis steps to create target materials appear to be within reach, either by closed-loop active-learning strategies or by inverting the prediction pipeline using advanced generative algorithms. AI and ML concepts are also transforming the computational and physical laboratory infrastructural landscapes used to create materials data in the first place. Surrogate models that can outstrip physics-based simulations (on which they are trained) by several orders of magnitude in speed while preserving accuracy are being actively developed. Automation, autonomy and guided high-throughput techniques are imparting enormous efficiencies and eliminating redundancies in materials synthesis and characterization. The integration of the various parts of the burgeoning ML landscape may lead to materials-savvy digital assistants and to a human-machine partnership that could enable dramatic efficiencies, accelerated discoveries and increased productivity. Here, we review these emergent materials intelligence ecosystems and discuss the imminent challenges and opportunities. The materials research landscape is being transformed by the infusion of approaches based on machine learning. This Review discusses the emerging materials intelligence ecosystems and the potential of human-machine partnerships for fast and efficient virtual materials screening, development and discovery.

36 MATERIALS SCIENCE↗