The Journal of Artificial Intelligence for Materials Science (JAIMS), ISSN: 3149-8957, published by Institute for Advanced Materials Research Press, is an international, peer-reviewed, open-access journal dedicated to research at the intersection of artificial intelligence, data science, computational methods, and materials science and engineering.
The journal provides a multidisciplinary platform for materials scientists, engineers, chemists, physicists, data scientists, computer scientists, experimental researchers, and industry professionals to publish original and evidence-based contributions concerning the development, evaluation, implementation, and responsible use of intelligent computational methods in materials research.
JAIMS publishes Original Research Articles, Review Articles, Systematic Reviews, Materials or Engineering Case Studies.
The journal’s scope includes:
Materials Informatics, including materials databases, knowledge representation, data integration, materials ontologies, structure-property relationships, and informatics-supported research workflows
Data-Driven Materials Design, including inverse design, data-guided candidate selection, generative approaches, and the identification of scientifically defensible materials design rules
Computational Materials Science, including computational methods for investigating material structures, properties, processes, performance, and behavior
Materials Modeling and Simulation, including atomistic simulation, molecular dynamics, phase-field modeling, finite-element analysis, multiscale simulation, and physics-informed computational models
Predictive Modeling of Material Properties, including the prediction of mechanical, thermal, electrical, chemical, optical, magnetic, and functional properties
High-Throughput Materials Screening, including automated candidate evaluation, virtual screening, active learning, combinatorial experiments, and accelerated materials discovery
Digital Materials Engineering, including digital representations of materials, integrated computational workflows, digital manufacturing, process monitoring, and intelligent engineering systems
Artificial Intelligence in Materials Science, including generative artificial intelligence, knowledge-based systems, autonomous experimentation, intelligent optimization, and AI-supported scientific reasoning
Machine Learning for Materials Discovery, including supervised, unsupervised, semi-supervised, self-supervised, reinforcement, transfer, and active-learning methods
Materials Characterization and Analysis, including AI-assisted microscopy, spectroscopy, diffraction, imaging, signal processing, microstructure analysis, defect detection, and multimodal characterization
AI-Assisted Materials Synthesis, including synthesis prediction, reaction and process optimization, robotic experimentation, closed-loop laboratories, and autonomous synthesis systems
Smart Materials, including data-driven design, modeling, characterization, control, and optimization of responsive and adaptive materials
Nanomaterials, including AI-enabled discovery, synthesis, characterization, modeling, property prediction, and performance optimization at the nanoscale
Advanced Functional Materials, including intelligent approaches to electronic, optical, magnetic, energy, catalytic, sensing, and multifunctional materials
Sustainable Materials Development, including AI-supported sustainable design, resource-efficient processing, lifecycle analysis, circular materials systems, recyclability, and environmentally responsible materials development
The journal also welcomes research on the experimental validation, reproducibility, scalability, reliability, safety, economic feasibility, and industrial implementation of AI-based materials technologies. Studies addressing human-AI collaboration, autonomous laboratories, data quality, algorithmic bias, model uncertainty, interpretability, explainability, scientific robustness, and responsible artificial intelligence are within scope.
Research involving materials datasets, computational workflows, and machine-learning models should clearly describe data provenance, preprocessing procedures, validation methods, evaluation metrics, uncertainty, limitations, and the physical or scientific relevance of the results. Studies combining artificial intelligence with experimental synthesis, characterization, manufacturing, or performance testing are particularly encouraged.
JAIMS welcomes interdisciplinary studies connecting artificial intelligence and materials science with fields such as physics, chemistry, chemical engineering, mechanical engineering, manufacturing engineering, nanotechnology, energy systems, electronics, robotics, automation, and environmental engineering.
Submissions must demonstrate a clear and substantial connection between artificial intelligence, machine learning, materials informatics, data-driven methods, or computational intelligence and a meaningful materials-science or materials-engineering problem.
Manuscripts focused solely on general computer science, standalone algorithm development, generic optimization, or non-materials datasets without a relevant materials application or scientific evaluation are outside the journal’s scope. Conventional materials synthesis, characterization, or engineering studies that do not include a meaningful artificial-intelligence, data-driven, informatics, or advanced computational contribution may also be considered outside scope.
Institute for Advanced Materials Research Press