Journal of Materials Intelligence and Computing (JMIC)

Aims & Scope

JMIC aims to serve as a premier interdisciplinary forum for research integrating materials science with AI, machine learning, and computational modeling. The journal focuses on accelerating materials discovery, optimization, and understanding through data-driven and physics-based approaches.

The journal publishes transformative research addressing grand challenges in materials science, including novel material prediction, process optimization, structure–property relationships, and autonomous experimentation.

1. Materials Informatics & Data Science

• Materials databases, ontologies, and data standards
• High-throughput screening and virtual libraries
• Data mining, feature engineering, and descriptor development
• Transfer learning and multi-fidelity modeling

2. Machine Learning & AI for Materials

• Supervised and unsupervised learning for materials prediction
• Deep learning for molecules, crystals, and microstructures
• Generative models for inverse materials design
• Explainable AI (XAI)

3. Computational Modeling & Simulation

• DFT, molecular dynamics, and Monte Carlo simulations
• Phase-field modeling and finite element analysis
• Multi-scale modeling
• Uncertainty quantification

4. AI Integration

• Physics-informed machine learning
• Hybrid and surrogate modeling
• Model reduction techniques

5. Autonomous Materials Discovery

• Self-driving laboratories
• Active learning and Bayesian optimization
• Closed-loop experimentation

6. Applications

• Energy materials, nanomaterials, and biomaterials
• Functional and structural materials

7. Software & Reproducibility

• Open-source tools and workflows
• FAIR data principles
• Benchmarking and validation