| Scope |
This symposium highlights advances in applying Artificial Intelligence (AI) across the full spectrum of Integrated Computational Materials Engineering (ICME), with emphasis on methods that strengthen and accelerate process-structure-property-performance linkages. Contributions are welcome on data-driven, physics-informed, and hybrid approaches spanning multiscale modeling, microstructure characterization, materials and process design, and manufacturing decision support. Relevant themes include machine learning and deep learning surrogates for computationally intensive simulations; generative and optimization methods (including active learning and Bayesian optimization) for accelerated discovery and processing-parameter selection; and uncertainty quantification and design under uncertainty, interpretability, and verification/validation needed for trustworthy deployment. We also encourage emerging foundation-model capabilities, such as multimodal models, large language models (LLMs), and agentic AI, when they enable practical ICME outcomes (e.g., literature-to-data extraction, natural-language interfaces to modeling workflows, knowledge integration with curated databases, or to accelerate materials development). Submissions should address data quality, reproducibility, and pathways to adoption in industrial and certification contexts.
Typical topics include but are not limited to:
• AI/ML methods to strengthen process-structure-property-performance linkages across ICME
• Physics-informed, hybrid, and multi-fidelity models for multiscale ICME integration
• Surrogate modeling and reduced-order models to accelerate FE/CPFEM/phase-field/MD and related simulations
• AI-enabled microstructure characterization and structure-property inference from multimodal data (images, spectra, processing history)
• Generative models for alloy/composition design, microstructure synthesis, and inverse design under constraints
• Active learning, Bayesian optimization, and autonomous/closed-loop experimentation for accelerated discovery and processing optimization
• Uncertainty quantification, calibration, interpretability, and verification/validation of AI models for ICME decision-making
• Data curation, standards, provenance/traceability, and reproducible machine learning operations (MLOps) pipelines for ICME deployment
• Integration of AI with materials databases, ICME toolchains, and digital manufacturing/digital twin frameworks
• Practical applications of foundation models including LLMs for knowledge extraction, workflow assistance, and decision support in ICME |