Aug 2026· Chemical Reviews· Vol 126, pp. 8644 - 8693· 0 citations· 328 references
Medicine
TL;DR
This review examines emerging AI methodologies for accelerated materials discovery, with particular emphasis on how computational design, data infrastructure, synthesis planning, and autonomous experimentation can be connected into experimentally grounded workflows.
Abstract
Artificial intelligence (AI) is fundamentally transforming materials discovery, shifting the paradigm from labor-intensive trial-and-error approaches to data-driven, automated workflows. This review examines emerging AI methodologies for accelerated materials discovery, with particular emphasis on how computational design, data infrastructure, synthesis planning, and autonomous experimentation can be connected into experimentally grounded workflows. We begin by surveying generative models for inverse materials design, tracing the evolution from early variational autoencoders and generative adversarial networks to recent diffusion models, Bayesian flow networks, flow-based architectures, transformer-based methods, and large language model-driven approaches for the de novo generation of crystalline materials with targeted properties. We then discuss physics-informed and data-efficient AI strategies that incorporate domain knowledge to enhance the model generalizability and robustness in low-data regimes. The emergence of multimodal foundation models, which integrate heterogeneous data modalities including crystal structures, text, and spectroscopic information into unified representations, is examined as a key enabler for cross task generalization. We further review AI-driven synthesis planning algorithms and autonomous self-driving laboratories that bridge the persistent gap between the computational design and experimental realization. Critical infrastructure challenges, including database limitations, FAIR data principles, and knowledge-graph construction, are also addressed. By highlighting both demonstrated capabilities and persistent limitations, this review aims to guide the reliable application of AI toward materials discovery workflows that connect candidate generation, synthesis feasibility, experimental feedback, and data provenance.
The rapid advancement of Artificial intelligence (AI) and machine learning is transforming materials discovery, offering the potential to accelerate the traditionally slow cycle of materials development. This review examines the latest progress through three synergistic axes: (1) acceleration of quantum mechanical simulations via universal machine learning interatomic potentials trained on large-scale density functional theory datasets, (2) materials-aware artificial intelligence leveraging large language models, synthetic narrative datasets, and contrastive multimodal learning for zero-shot materials retrieval, and (3) autonomous laboratories integrating Bayesian optimization and reinforcement learning for closed-loop experimental optimization. We discuss the specific opportunities and remaining challenges for applying these methodologies to ceramic materials and present a vision toward fully autonomous AI-driven materials discovery.
From first-principles calculations to machine learning-driven materials discovery, computational methods enhance our understanding of material behavior under different conditions. Furthermore, these modern computational tools allow scientists to explore vast design spaces more efficiently. Namely, by simulating material properties before synthesis, researchers can rapidly screen potential candidates, optimize structures, and uncover novel materials that might not have been feasible through traditional experimentation alone. As the power of computation continues to grow, the role of computational tools in solving complex materials science challenges will only expand, accelerating innovation and transforming the way materials are understood, discovered, and developed.
I will present examples from our research that illustrate how we integrate high-throughput computing with machine learning (ML) and artificial intelligence (AI) to tackle complex challenges in materials science [1, 2]. I will first discuss recent progress in the development of automated computational workflows that support large-scale screening of materials for targeted properties, such as high electro-conversion or stability against electrochemical dissolution. These frameworks also allow us to develop large databases of relevant materials properties. When combined with modern ML tools, these databases can be used to train surrogate ML-models capable of screening millions of candidate chemistries to identify the ones with optimal reactivity or stability. Furthermore, I will illustrate the use of interpretable ML in materials research that aims to enhance explainability of predictive ML models, enabling understanding of the underlying factors influencing design decisions. Lastly, I will present our current work on inverse material design, where AI methods—particularly generative pretrained transformers—are used to predict new material candidates based on desired properties, pushing the boundaries of materials innovation.
[1] M. Davis, W. Kort-Kamp, E. F. Holby, P. Zelenay, and I. Matanovic, Computational Screening of Transition Metal-Nitrogen-Carbon Materials as Electrocatalysts for CO
2
Reduction.
Electrochimica Acta 510,
145357(2025).
[2] M. Davis, W. Kort-Kamp, I. Matanovic, P. Zelenay and E. F. Holby, Design of Amine-Functionalized Materials for Direct Air Capture Using Integrated High-Throughput Calculations and Machine Learning, accepted in
Communications Chemistry
(2025).
I. Gonzales, R. Ullberg, Andrew H Salij et al.· ECS Meeting Abstracts· 0 citations
Electrochemical energy technologies are central to the net-zero transition, yet their multiscale characteristics ranging from atomic materials to device architectures present critical challenges in research and development (R&D). Although artificial intelligence (AI) has accelerated discovery and design in this field, commonly used predictive AI methods remain limited in enabling disruptive advances. Generative AI has shown transformative potential in disciplines such as biology and medicine, though its impact on electrochemical energy R&D is only beginning to emerge. Here we review recent progress in applying generative AI to molecular and crystal discovery, electrode microstructure design, and system optimization, with particular attention to the role of large language models in electrochemical engineering. We argue for a paradigm shift toward generative electrochemical intelligence (GenE), a physics-informed, multimodal framework that integrates human expertise with automated experimentation. We anticipate that GenE will redefine the R&D paradigm for rapidly deployable electrochemical energy technologies and accelerate their translation into real-world applications.
Zhiqiang Niu, Wanhui Zhao, L. Jackson et al.· Science Bulletin· 0 citations
A materials property hierarchy is introduced, from intrinsic, composition-determined properties to extrinsic, processing-dependent performance, to clarify deployment constraints and distinguish structural, physical and deployment novelty.
Xianyuan Liu, Charles Anjah, Benjamin E. Jolly et al.· Journal of Physics Materials· 0 citations
Generative artificial intelligence is rapidly transforming materials design by enabling de novo exploration of immense chemical spaces. Yet a large proportion of AI-generated compositions remain implausible, violating established chemical principles, which limits the reliability and interpretability of generative materials design. Here, we introduce a chemical validity operator that recasts heuristic chemical rules as a configurable algorithmic prior for evaluating and guiding generative materials discovery. Built on the open-source SMACT package, a data-informed oxidation-state model exposes tunable thresholds, allowing users to interpolate continuously between permissive and conservative chemical constraints, while supporting both exploratory and conservative materials-design workflows. Benchmarking six state-of-the-art generative models for inorganic crystals shows that most reproduce stoichiometry but under-represent realistic oxidation-state combinations, and that filtering removes compositions reliant on rarely observed oxidation states while preserving low-energy compounds near the convex hull. Beyond screening, the same operator can also serve as a reinforcement-learning reward, steering a latent diffusion model towards chemically grounded compositions. By encoding chemical heuristics and observations, this work establishes a foundation for oxidation-state-aware generative models.
Kinga O. Mastej, Panyalak Detrattanawichai, Hyunsoo Park et al.· 0 citations
A reinforcement learning framework that guides latent denoising diffusion models in finding diverse and novel, yet thermodynamically viable, crystalline compounds and demonstrates enhanced property-guided design that preserves chemical validity while targeting desired functional properties.
Hyunsoo Park, Aron Walsh· Nature Machine Intelligence· 27 citations· ⚡3