Search

Materials informatics has emerged as a central paradigm in contemporary materials science, leveraging machine learning and data-driven modeling to accelerate materials discovery, optimization, and deployment. Despite substantial advances in predictive accuracy, most existing approaches remain fundamentally correlational, limiting their reliability under distribution shifts, experimental interventions, and real-world deployment scenarios. This reliance on correlation constrains scientific interpretability and undermines the capacity of AI systems to function as genuine instruments of materials reasoning. Causality offers a principled framework for overcoming these limitations by explicitly modeling cause-and-effect relationships among composition, processing, structure, and properties. This narrative review synthesizes conceptual progress in integrating causal inference into materials informatics, examining foundational causal frameworks, advances in causal discovery, and hybrid causal–machine learning approaches, and emerging applications across materials domains such as nanocatalysis, ferroelectrics, and electrochemical energy storage. We critically analyze persistent challenges—including data scarcity, assumption violations, limited external validity, and computational and epistemic constraints—that currently hinder widespread adoption. Drawing exclusively on peer-reviewed literature published, the review emphasizes thematic and epistemic developments rather than algorithmic prescriptions. We argue that causality represents a structural shift in how AI systems contribute to materials science: from correlational predictors to intervention-aware, mechanism-aligned reasoning tools. By articulating future directions centered on hybrid modeling, domain-knowledge integration, and interdisciplinary collaboration, this review positions causality as a necessary foundation for robust, generalizable, and scientifically legitimate materials informatics.

The advent of graph neural networks (GNNs) has revolutionized computational materials engineering by enabling sophisticated representations of atomic structures and interactions for property prediction. This review synthesizes key developments in GNN architectures tailored for materials science, focusing on their application in predicting mechanical, electronic, and thermodynamic properties of diverse materials systems, including polycrystals, metal-organic frameworks, and perovskites. Drawing from high-impact studies, we examine the evolution from basic crystal graph convolutional networks to advanced variants incorporating transfer learning, data augmentation, and force field integration. The synthesis highlights how GNNs address challenges in materials data sparsity and structural complexity through graph-based featurization, leading to improved accuracy in property forecasts compared to traditional machine learning methods. We integrate perspectives on GNNs' role in broader data-driven ecosystems, including their synergy with active learning for autonomous discovery pipelines. Limitations such as interpretability and scalability are critically assessed, alongside advances in benchmark frameworks that standardize evaluations. The review positions GNNs as a cornerstone of next-generation materials informatics, accelerating the design of high-performance materials for energy, catalysis, and structural applications. Future outlooks emphasize hybrid integrations with physics-based simulations to bridge experimental and computational gaps, fostering closed-loop systems for rapid materials innovation. This narrative underscores the transformative potential of GNNs in reshaping materials engineering paradigms.

The integration of machine learning into materials engineering has transformed discovery pipelines by leveraging vast simulation-generated datasets and high-throughput computational workflows. Within this data-driven paradigm, models frequently incorporate simulation priors—implicit assumptions derived from physical approximations, boundary conditions, and discretization choices embedded in first-principles calculations or molecular dynamics trajectories. These priors, often hidden within representation learning and graph-based architectures, introduce epistemic biases that propagate through inference to downstream tasks such as inverse design and closed-loop experimentation. A key conceptual gap lies in the lack of systematic frameworks for articulating and managing these assumptions as integral components of the computational infrastructure rather than incidental data artifacts. This article introduces the Simulation Prior Articulation Framework (SPAF), an original systems-level conceptual structure that delineates layered processing of multimodal materials data, explicit prior extraction from simulation ecosystems, integration into deep learning architectures, and steering of discovery pipelines via feedback mechanisms. SPAF emphasizes representation–inference interactions, computational workflow dynamics, and infrastructure trade-offs to enhance simulation–experiment coupling without empirical benchmarking. By framing hidden physics assumptions as addressable epistemic structures, the framework provides integrative insights for materials informatics, foundation models, and autonomous discovery systems, supporting more transparent and robust data-driven materials engineering pipelines.

In the evolving landscape of computational and data-driven materials engineering, transfer learning has emerged as a pivotal strategy to address data scarcity and enhance predictive capabilities across diverse materials systems. This approach leverages pre-trained models from one materials class to inform modeling in another, capitalizing on shared representational structures within high-dimensional chemical and physical spaces. However, the conceptual boundaries of reusability remain underexplored, particularly in terms of how representational invariances and domain shifts influence cross-class applicability. This manuscript introduces a novel conceptual framework, termed the Reusability Boundary Architecture (RBA), which delineates the systemic interactions between data representations, model architectures, and discovery workflows in transfer learning paradigms. By integrating insights from materials informatics, graph neural networks, and uncertainty quantification, the RBA elucidates the epistemic trade-offs inherent in transferring knowledge across materials classes, such as from inorganic crystals to organic polymers or metallic alloys to ceramics. The framework emphasizes computational steering logics that dynamically adjust for feature misalignment and contextual divergences, fostering more robust integration of simulation and experimental pipelines. Implications for the field include enhanced design of multimodal datasets, refined autonomous discovery systems, and improved inverse materials engineering, ultimately accelerating innovation in sustainable materials development without relying on empirical validations. This work provides a theoretical foundation for navigating the reusability frontiers in computational materials science, promoting interdisciplinary synergies between machine learning and domain-specific knowledge.

Self-driving laboratories have emerged as a cornerstone of computational and data-driven materials engineering, fusing automated high-throughput experimentation with machine-learning-driven decision engines to compress discovery timelines from years to weeks. This paradigm shift reconfigures the materials pipeline into a closed-loop system in which data generation, model inference, and experimental steering operate with minimal human intervention. Yet the very autonomy that accelerates discovery simultaneously obscures the epistemic foundations of the knowledge it produces. Failures—whether arising from underrepresented chemical spaces, model extrapolation beyond training distributions, or unacknowledged aleatoric–epistemic uncertainty boundaries—often remain latent until downstream validation, eroding trust in autonomous outputs. Current uncertainty quantification and explainability techniques, while technically sophisticated, are typically deployed in isolation and rarely propagate failure signals across the full discovery stack. We articulate a conceptual architecture, the Epistemic Visibility and Accountability Framework (EVAF), that treats failure not as an anomaly to be minimized but as a structured signal to be surfaced and attributed at every layer of the self-driving pipeline. By integrating multi-scale representation tracking, inference-trace logging, and risk-propagation mapping, EVAF establishes a computational substrate for epistemic accountability: the systematic assignment of responsibility for knowledge claims to specific data, model, or orchestration components. The framework reframes self-driving systems from opaque optimizers into transparent epistemic engines, enabling materials engineers to maintain intellectual oversight without sacrificing autonomy. Its implications extend to infrastructure design, regulatory readiness for autonomous discovery platforms, and the long-term reliability of data-intensive materials science.

In the evolving landscape of computational and data-driven materials engineering, autonomous experimentation platforms are transforming discovery pipelines by integrating machine learning algorithms with robotic systems to accelerate material synthesis and characterization. These self-driving laboratories operate through closed-loop cycles where data acquisition, model inference, and experimental steering occur without continuous human oversight, raising critical questions about resource allocation mechanisms that ensure efficient, unbiased, and scalable operations. This manuscript addresses a conceptual gap in the governance of such systems: the need for structures that allocate decision rights—encompassing experimental priorities, parameter spaces, and computational resources—absent deliberate intervention. We introduce the Implicit Allocation Governance (IAG) framework, which conceptualizes resource distribution as emergent from layered interactions between data representations, inference engines, and discovery logics, emphasizing epistemic trade-offs and feedback dynamics. By synthesizing recent advancements in Bayesian active learning, reinforcement learning-guided workflows, and multi-agent robotic systems, the framework highlights how governance can arise implicitly through system architectures that balance exploration-exploitation tensions and mitigate representational biases. Implications extend to enhancing the robustness of autonomous materials discovery, fostering interoperability across distributed labs, and informing the design of next-generation computational infrastructures. This work underscores the shift from human-centric deliberation to algorithmically embedded governance, paving the way for more resilient and adaptive materials engineering paradigms.