An official website of the United States government
Abstract Data-driven design shows the promise of accelerating materials discovery but is challenging due to the prohibitive cost of searching the vast design space of chemistry, structure, and synthesis methods. Bayesian optimization (BO) employs uncertainty-aware machine learning models to select promising designs to evaluate, hence reducing the cost. However, BO with mixed numerical and categorical variables, which is of particular interest in materials design, has not been well studied. In this work, we survey frequentist and Bayesian approaches to uncertainty quantification of machine learning with mixed variables. We then conduct a systematic comparative study of their performances in BO using a popular representative model from each group, the random forest-based Lolo model (frequentist) and the latent variable Gaussian process model (Bayesian). We examine the efficacy of the two models in the optimization of mathematical functions, as well as properties of structural and functional materials, where we observe performance differences as related to problem dimensionality and complexity. By investigating the machine learning models’ predictive and uncertainty estimation capabilities, we provide interpretations of the observed performance differences. Our results provide practical guidance on choosing between frequentist and Bayesian uncertainty-aware machine learning models for mixed-variable BO in materials design.
more »
« less
This content will become publicly available on August 1, 2026
Review of AI-assisted design of low-carbon cost-effective concrete toward carbon neutrality
Abstract Decarbonizing concrete production is a critical step toward achieving carbon neutrality by 2050. This paper highlights the advancements in artificial intelligence-assisted design of low-carbon cost-effective concrete, focusing on integrating machine learning-based property prediction with multi-objective optimization. Data collection and processing techniques, such as automatic data extraction, artificial data generation, and anomaly detection, are first discussed to address the importance of dataset quality. Strategies that capture physicochemical information of ingredients, including by-product supplementary cementitious materials and recycled aggregates, are then examined to enhance model generalizability. Various machine learning models—from individual regression approaches to heterogeneous ensemble methods—are compared for their predictive accuracy and robustness. Methods for hyperparameter tuning, model evaluation, and interpretation to ensure reliable and interpretable predictions are reviewed. Design optimization approaches are then highlighted, ranging from grid/random searches to more sophisticated gradient-based and metaheuristic algorithms, aimed at minimizing carbon footprint, embodied energy, and cost. Future research avenues encompass (1) application-specific design frameworks that integrate critical objectives—mechanical performance, durability, fresh-state behavior, and time-dependent properties such as creep and shrinkage—tailored to specific structural and environmental requirements; (2) holistic design optimization that simultaneously refines mixture design and structural parameters; and (3) probabilistic approaches to systematically manage uncertainties in materials, structural performance, and loading conditions systematically.
more »
« less
- Award ID(s):
- 2046407
- PAR ID:
- 10652475
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- Artificial Intelligence Review
- Volume:
- 58
- Issue:
- 8
- ISSN:
- 1573-7462
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
AbstractComputational methods and machine learning (ML) are reshaping materials science by accelerating their discovery, design, and optimization. Traditional approaches such as density functional theory and molecular dynamics have been instrumental in studying materials at the atomic level. However, their high computational cost and, in certain cases, limited accuracy can restrict the scope ofin silicoexploration. ML promises to accelerate material property prediction and design. However, in many areas, the volume and fidelity of the data are critical barriers. Active learning can reduce the reliance on large data sets, and simulation has emerged as a critical tool for generating data on the fly. Despite these advances, challenges remain, particularly in data quality, model interpretability, and bridging the gap between computational predictions and experimental validation. Future research should develop automated frameworks capable of designing and testing materials for specific applications, and integrating ML with traditional simulations and experiments can contribute to this goal. Graphic abstractmore » « less
-
Abstract Porous carbons are the active materials of choice for supercapacitor applications because of their power capability, long-term cycle stability, and wide operating temperatures. However, the development of carbon active materials with improved physicochemical and electrochemical properties is generally carried out via time-consuming and cost-ineffective experimental processes. In this regard, machine-learning technology provides a data-driven approach to examine previously reported research works to find the critical features for developing ideal carbon materials for supercapacitors. Here, we report the design of a machine-learning-derived activation strategy that uses sodium amide and cross-linked polymer precursors to synthesize highly porous carbons (i.e., with specific surface areas > 4000 m2/g). Tuning the pore size and oxygen content of the carbonaceous materials, we report a highly porous carbon-base electrode with 0.7 mg/cm2of electrode mass loading that exhibits a high specific capacitance of 610 F/g in 1 M H2SO4. This result approaches the specific capacitance of a porous carbon electrode predicted by the machine learning approach. We also investigate the charge storage mechanism and electrolyte transport properties via step potential electrochemical spectroscopy and quasielastic neutron scattering measurements.more » « less
-
Mechanistic data-driven prediction of as-built mechanical properties in metal additive manufacturingAbstract Metal additive manufacturing provides remarkable flexibility in geometry and component design, but localized heating/cooling heterogeneity leads to spatial variations of as-built mechanical properties, significantly complicating the materials design process. To this end, we develop a mechanistic data-driven framework integrating wavelet transforms and convolutional neural networks to predict location-dependent mechanical properties over fabricated parts based on process-induced temperature sequences, i.e., thermal histories. The framework enables multiresolution analysis and importance analysis to reveal dominant mechanistic features underlying the additive manufacturing process, such as critical temperature ranges and fundamental thermal frequencies. We systematically compare the developed approach with other machine learning methods. The results demonstrate that the developed approach achieves reasonably good predictive capability using a small amount of noisy experimental data. It provides a concrete foundation for a revolutionary methodology that predicts spatial and temporal evolution of mechanical properties leveraging domain-specific knowledge and cutting-edge machine and deep learning technologies.more » « less
-
Since the surge of data in materials-science research and the advancement in machine learning methods, an increasing number of researchers are introducing machine learning techniques into the next generation of materials discovery, ranging from neural-network learned potentials to automated characterization techniques for experimental images. In this snapshot review, we first summarize the landscape of techniques for soft materials assembly design that do not employ machine learning or artificial intelligence and then discuss specific machine learning and artificial-intelligence-based methods that enhance the design pipeline, such as high-throughput crystal-structure characterization and the inverse design of building blocks for materials assembly and properties. Additionally, we survey the landscape of current developments of scientific software, especially in the context of their compatibility with traditional molecular-dynamics engines such as LAMMPS and HOOMD-blue.more » « less
