AI & Materials is an online multidisciplinary open access journal committed to the deep integration and common enhancement in materials science and artificial intelligence (AI) technology. The journal aims to build an open and fair platform to attract peer-reviewed research articles that report newest achievements with innovation related to joint developments of AI theory and technology and materials design, prediction and production. Moreover, the journal also welcomes the novel research papers that potentially motivate the Interdisciplinary progresses of materials science and AI. The scope of the journal includes but is not limited to:

    Novel AI algorithms that have potential applications to materials
    Computer-aided design of novel materials
    AI for science technique, especially for materials science
    Digital twin technology with AI for materials industry
    Modelling techniques for manufacturing processes and systems boosted with AI
    Materials theory assisted by AI technology
    High-Performance Computing (HPC) for modeling, simulation, and analysis applicable to materials and AI

Special Issue on AI-Bridged New Materials for Batteries and Fuel Cells
Submission Date: 2025-12-18

The rapid development of artificial intelligence (AI) and machine learning (ML) is revolutionizing the discovery and design of advanced materials for energy storage and conversion technologies. This special issue focuses on bridging AI-driven methodologies with experimental and computational approaches to accelerate the development of next-generation catalytic and electrode materials for batteries and fuel cells. By integrating data-driven screening, multiscale modeling, and atomic-level insights, AI serves as a critical tool to overcome traditional bottlenecks in material design, such as balancing catalytic activity, stability, and cost.

The Journal AI & Materials invites submissions for a special issue dedicated to the AI-Bridged new materials for batteries and fuel cells. We invite original research papers, review articles, and case studies addressing a broad range of topics, including but not limited to:

    Machine learning models for predicting catalytic activity, stability, and electronic properties.
    Deep learning approaches to map structure-property relationships (e.g., volcano plots for ORR/OER).
    Active learning and Bayesian optimization for accelerated screening of materials.
    Explainable AI (XAI) to interpret complex electrochemical mechanisms.
    Fuel cell catalysts: ORR/HOR catalysts (Pt-free alloys, M-N-C materials), PEMFC/SOFC electrodes.
    Battery materials: High-energy-density cathodes/anodes, solid-state electrolytes, and interface stabilizers.
    Nanostructured systems: Subnanometer clusters, single-atom catalysts, 2D materials, and bimetallic composites.
    AI-guided strategies to enhance durability, mass activity, and cost efficiency.
    Mitigating degradation pathways (e.g., carbon corrosion, metal dissolution) through computational design.
    Trade-off analysis between catalytic activity and stability via ML-aided descriptors.
    Hybrid workflows integrating density functional theory (DFT) and ML for large-scale screening.
    Bridging atomic-scale simulations (e.g., DFT, molecular dynamics) with macroscale device performance.
    Experimental synthesis and characterization of AI-predicted materials (e.g., in-situ TEM, XAS).
    AI-powered automation in material synthesis (e.g., robotic labs) and characterization.
    Case studies on AI-driven breakthroughs in industrial-scale energy devices (e.g., fuel cell stacks, EV batteries).
    Open datasets and benchmarks for energy material informatics.
    Design of low-cost, non-toxic, and recyclable materials through AI.
    Addressing biases in ML models for equitable energy technology development.

Special Issue on Intelligent Additive Manufacturing
Submission Date: 2026-03-01

Additive manufacturing (AM) is revolutionising how components are fabricated by enabling complex geometry and lightweight, topology‑optimised structures. Yet intrinsic process-induced defects—porosity, microcracks, residual stresses and mechanical anisotropy—can severely limit component performance and service life. Therefore, over the past few years, artificial intelligence and machine‑learning methods have been widely adopted to tackle these challenges:

    In‑situ defect detection via computer vision, infrared thermography, acoustic emission and other sensor readings, enabling real‑time identification of defects.
    Data‑driven parameter optimization uses supervised and reinforcement learning to tune layer height, scan speed, laser power and bead overlap, achieving target density, mechanical properties and surface finish.
    Closed‑loop feedback control—often implemented through digital‑twin frameworks and real‑time sensor fusion—allows adaptive adjustment of extrusion rates, melt‑pool dynamics or scan strategies to suppress defect nucleation and propagation.
    Al-powered process design, implementation and optimization greatly improve the intelligence level of high-end manufacturing systems via the support of Internet of Things, Big Data, Cloud Computing, etc.

This special issue welcomes original research articles, review papers and case studies addressing AI‑empowered solutions across diverse materials (polymers, metals, ceramics, composites) and AM processes (FFF, SLM, DED, SLA). The main goal is to extend fundamental knowledge, foster open data exchange, and highlight successful deployments of intelligent monitoring and control strategies that enhance structural integrity, reproducibility and sustainability in additive manufacturing for academia and industry.

Special Issue on AI-Enhanced Multifunctional Dielectric Materials — From Design to Application
Submission Date: 2026-06-30

This Special Issue of AI & Materials (AIMAT) is launched in conjunction with the newly established ICAIM Workshop “AI-Enhanced Multifunctional Dielectric Materials: From Design to Application.” Both the workshop and the Special Issue aim to build a synergistic platform for advancing the integration of artificial intelligence with multifunctional dielectric materials research.

Multifunctional dielectric materials exhibiting coupled mechanical, electrical, magnetic, thermal, and optical responses are at the core of innovation in electronics, energy storage, and energy conversion. However, their complex structure–property relationships under multiphysics coupling remain difficult to model and optimize. Artificial intelligence offers transformative capabilities to accelerate design, characterization, and performance prediction in this field.

This Special Issue welcomes original research papers, reviews, and perspectives that address AI-driven methodologies for the design, characterization, and optimization of multifunctional dielectric materials. Topics of interest include, but are not limited to:

    AI-based modeling and prediction of dielectric material performance under multiphysics constraints
    Machine learning–assisted optimization of ferroelectric capacitors for memory and energy storage
    AI-guided design of ferroelectric materials for high-efficiency photovoltaic applications
    Intelligent design of electromagnetic wave–absorbing materials
    Data-driven discovery of novel dielectric systems with multifunctional responses
    Integration of computational and experimental AI frameworks for material innovation

The goal of this Special Issue is to promote interdisciplinary collaboration among materials scientists, physicists, chemists, electrical engineers, and computer scientists, and to accelerate the development of next-generation smart dielectric materials empowered by artificial intelligence.