Materials Data Science and artificial intelligence are introduced as a new paradigm in materials science. Materials scientists routine produce big and complex datasets through a variety of experimental and computational approaches, and analyze them to discover new materials or predict and improve the properties of materials. Increasingly, these tasks are becoming too complex to achieve with human reasoning alone, and the assistance of artificial intelligence in analyzing these datasets can unlock new possibilities. Machine learning and data mining as an application of data science are becoming one of the key technologies for assisting scientists in this area. Data science and artificial intelligence can also accelerate the development of materials science. In addition, metadata frameworks, as material classification schemes and the materials ontology as a knowledge representation of materials data, are critical to succeed in material data science and artificial intelligence. The Materials Data Science and AI section in Materials Today Communication covers all aspects of this topic, including:
- Machine learning in materials science
- Deep learning in materials science
- Neural networks in materials science
- Convolutional Neural Networks in material science
- Metadata in materials science
- Ontology and knowledge graph in materials science
- Materials informatics
- Artificial intelligence in material science
- AI software in materials science
- FAIR Data Principles (findable, accessible, interoperable, and reusable) in material science
The section editor Dr. Mehrdad Jalali welcomes submissions dealing with the topics listed above. Please ensure that during your submission you select the section ‘Materials Data Science & AI’. The publisher and section editor looking forward to your contributions.