Advances in AI and Multiphysics Modelling

Dear Colleagues,

Recent advances in artificial intelligence (AI) are transforming the landscape of multiphysics modelling by enhancing the predictive capabilities, efficiency, and interpretability of traditional physics-based simulations. This Special Issue aims to bring together contributions that integrate AI methodologies—ranging from machine learning to deep neural networks—with multiphysics simulation approaches. We invite authors to submit high-quality manuscripts, including original research, methodological advances, and comprehensive reviews that bridge the gap between these exciting fields.

1. Scope and Rationale

The merging of AI techniques with multiphysics modelling promises to address longstanding challenges in simulation accuracy, computational efficiency, and data integration. Key areas include:

• Hybrid Modelling Approaches: Combining data-driven methods with classical physics-based models to enhance simulation fidelity and adaptivity.
• Surrogate and Reduced-Order Modelling: Employing AI to develop fast surrogate models and reduced-order representations of complex multiphysics systems.
• Physics-Informed Machine Learning: Integrating known physical laws directly into the learning process (e.g., Physics-Informed Neural Networks, or PINNs) to better solve partial differential equations and inverse problems.
• Uncertainty Quantification and Sensitivity Analysis: Applying AI-based frameworks to assess and reduce uncertainties inherent in multiphysics simulations.
• Optimisation and Control: Using AI for enhanced design optimisation and real-time control in systems governed by coupled multiphysics phenomena.
• These research foci have been validated by recent the literature and conference proceedings in both computational science and AI communities.

2. Topics of Interest

Submissions may explore, but are not limited to, the following topics:

• AI-Driven Simulation and Modelling:
  • Development and application of Physics-Informed Neural Networks (PINNs) for solving multiphysics problems.
  • Deep learning architectures (including convolutional, recurrent, and transformer-based approaches) tailored for spatio-temporal multiphysics data.
• Hybrid Modelling Techniques:
  • Integration of traditional numerical simulations with data-driven models.
  • Hybrid models that combine mechanistic insights with learned patterns for enhanced prediction.
• Surrogate and Reduced-Order Modelling:
  • Development of surrogate models and reduced-order models using machine learning techniques to accelerate multiphysics computations.
  • Approaches for model order reduction that retain key system dynamics while cutting computational costs.
• Uncertainty Quantification and Sensitivity Analysis:
  • AI methods for quantifying model uncertainty in multiphysics scenarios.
  • Sensitivity analysis and robust optimisation using data-driven methods.
• Inverse Problems and Model Discovery:
  • Data-driven approaches for discovering governing equations from experimental or simulation data.
  • AI methodologies to solve inverse problems in complex physical systems.
• High-Performance Computing Integration:
  • Leveraging AI to enhance computational efficiency in large-scale multiphysics simulations.
  • Parallel and distributed AI approaches to handle vast datasets and complex model calculations.
• Applications across Domains:
  • Case studies in aerospace, biomedical engineering, energy systems, and materials science where AI-enhanced multiphysics modelling is driving innovation.
  • Implementation of AI to facilitate design optimisation, predictive maintenance, and real-time system monitoring.

These topics reflect the most current research areas in the field identified in recent reviews and conference sessions on AI in computational modelling.

3. Submission Guidelines

Manuscripts should be prepared following the journal’s guidelines and submitted via the online system under the “Special Issue” category. We welcome submissions in the following formats:

• Original Research Articles
• Review Papers
• Short Communications
• Methodological Notes/Case Studies

Each submission will be rigorously peer-reviewed to ensure high scientific standards. Manuscripts should provide sufficient detail on methodologies, experiments, and potential applications of the proposed AI and multiphysics approaches.

4. Important Dates

Manuscript Submission Deadline: 31 October 2025

First Decision Notification: Based on notification

Revised Manuscript Submission Deadline: 31 October 2025

Final Decision: Based on notification

Publication Date (Online): Based on notification

Note: The timeline may be subject to change. Please refer to the journal’s website or contact the editorial office for the most current information.

5. Concluding Remarks

This Special Issue on Advances in AI and Multiphysics Modelling aims to serve as a platform for disseminating innovative research that leverages AI to overcome the challenges faced in traditional multiphysics simulations. We look forward to receiving your submissions and to advancing the state-of-the-art in both theoretical and practical applications.

Dr. Gasser Abdelal
Guest Editor

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 100 words) can be sent to the Editorial Office for announcement on this website.

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. Applied Sciences is an international peer-reviewed open access semimonthly 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 2400 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.

• artificial intelligence
• machine learning
• deep learning
• physics-informed neural networks (PINNs)
• hybrid modelling
• surrogate modelling