Artificial Intelligence for Composite Materials: Modeling, Prediction, and Design

Dear Colleagues,

Composite materials underpin critical technologies in aerospace, energy, and civil infrastructure due to their high specific performance and tunable architectures. However, their macroscopic behavior emerges from complex, multiscale interactions among constituents, microstructures, and processing histories, making property prediction and materials optimization a longstanding scientific challenge. Conventional experiments and high-fidelity simulations are often prohibitively expensive when exploring such high-dimensional design spaces. Recent advances in machine learning, particularly physics-informed and hybrid data–mechanics approaches, are reshaping composite materials research by enabling efficient discovery of nonlinear structure–property relationships. These methods offer unprecedented opportunities to accelerate materials development, enhance predictive fidelity, and advance the rational design of next-generation composite systems.

This Special Issue aims to consolidate state-of-the-art methodologies and emerging applications of machine learning for the modeling, prediction, and design of composite materials. It seeks contributions demonstrating how advanced ML frameworks—such as convolutional neural networks, graph neural networks, physics-informed neural networks, and large language models, etc.—can enhance the efficiency and accuracy of composite property prediction and performance evaluation. Emphasis is placed on approaches that bridge microstructural characteristics with macroscopic mechanical responses, directly aligning with the journal’s focus on the analysis, mechanics, and design of composite structures and materials.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

1. Data-driven prediction of physical properties: Focusing on effective thermal conductivity, electrical conductivity, and mechanical modulus of composites,
2. ML for mechanical performance: Prediction of stiffness, strength, fatigue life, and fracture toughness using deep learning architectures.
3. Inverse design and optimization: Generative models (g., GANs, VAEs) for designing composite microstructures with targeted thermal or mechanical properties.
4. Large language model–powered modeling: Automation of composite design, simulation, and computational analysis.

We look forward to receiving your contributions.

Prof. Dr. Haifeng Zhao
Dr. Gongye Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Composites Science is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• machine learning
• composite materials
• data-driven modeling
• physics-informed neural networks
• multiscale modeling
• structure–property relationships
• performance prediction
• large language model
• homogenization
• effective properties
• microstructure characterization