Applied Mathematical Modelling focuses on significant and novel scientific developments for mathematical modelling and computational methods and tools for engineering, industrial and environmental systems and processes leading to future innovations and novel technologies.

The topics considered are: heat transfer, fluid mechanics, computational fluid dynamics and electromagnetics, and transport phenomena; solid mechanics and mechanics of metals; electromagnets and magnetohydrodynamics; reliability modelling and system optimization; modelling of inventory, industrial, manufacturing and logistics systems with managerial insights; engineering systems and structures; mineral and energy resources; software engineering developments; digital twins; materials; unmanned vehicles; robotics; network traffic control; energy sustainability models; optimization; population dynamics with realistic scenarios; high-performance methods for data-driven engineering applications; numerical procedures; computational intelligence in complex engineering problems.

Applied Mathematical Modelling is primarily interested in:

    Papers developing increased insights into real-world problems through novel analytical or semi-analytical mathematical and computational modelling.
    Papers with multi- and interdisciplinary topics, including linking with data driven models and applications.
    Papers on novel applications or a combination with the above.

Papers employing existing methods must demonstrate significant novelty in the solution of practical problems. Model validation, verification and reproducibility is a fundamental principle for published papers.

Papers based on fuzzy logic in decision-making, financial mathematics, heuristic algorithms, neural networks, data modelling, game-theoretical, fractional differential equations, bifurcation and numerical methods papers are not considered unless they solve practical problems, supported by reasonable empirical evidence. Submissions with no real-world application will not be considered.

Special Issue on Advances in AI-Enhanced Computational Mechanics: Bridging Data-Driven and Physics-Aware Paradigms
截稿日期: 2025-12-31

Artificial Intelligence (AI) is revolutionizing Computational Mechanics, providing groundbreaking solutions to complex engineering and scientific challenges. Data-driven AI and Physics-aware AI represent two transformative paradigms that offer distinct and complementary advantages, paving the way for unprecedented advancements in computational methods. Data-driven AI leverages large-scale datasets to model intricate systems and uncover hidden patterns, while Physics-aware AI integrates domain knowledge into AI frameworks to ensure physical consistency and prediction reliability. This special issue invites high-quality contributions exploring the latest innovations in both Data-driven AI and Physics-aware AI. The focus will be on how these computing paradigms, either individually or synergistically, address critical challenges in Computational Mechanics, unlocking new frontiers in research and application across diverse domains.

Guest editors:

Dr. Jinlong Fu (Queen Mary University of London, UK); 
Prof. Dunhui Xiao (Tongji University, China); 
Prof. Wei Tan (Queen Mary University of London, UK); 
Prof. Min Luo (Zhejiang University, China); 
Prof. Lu Lu (Yale University, USA); 
Prof. Xiaoying Zhuang (Leibniz University Hannover, Germany)

Manuscript submission information:

We invite original research articles addressing theoretical developments, methodological innovations, and engineering applications of AI in computational mechanics. Topics of interest include, but are not limited to:

• Data-driven computing paradigm:
- Data-driven constitutive modeling for advanced materials
- Data-driven homogenization techniques for multiscale modeling
- AI-driven topology optimization and materials design
- Reduced-order modeling and real-time simulations of high-dimensional systems
- Data-driven modeling with incomplete, noisy or heterogenous datasets

• Physics-aware computing paradigm:
- Physics-Informed Neural Networks (PINNs) for solving partial differential equations
- Novel methodology for incorporating domain-specific knowledge into AI models
- Hybrid models combining physics-based constraints with data-driven flexibility
- AI-physics hybrid methods for multi-physics modelling, including fluid dynamics, solid mechanics, and heat transfer
- Applications of physics-aware AI to large-scale computational problems

• Theoretical and methodological advances:
- Novel AI architectures tailored for computational mechanics problems
- Transparent AI techniques for improving interpretability and trust in results
- Advances in training strategies for physics-aware and data-driven AI models

• Applications across engineering disciplines:
- AI-enhanced simulations in aerospace, mechanical, civil, ocean, and biological engineering
- AI-driven advancements in energy systems, including wind and solar applications
- AI methods for uncertainty quantification and failure analysis in structural systems

Submission Deadline: 31st December 2025

Submission Guidelines: Authors are encouraged to submit original, high-quality, unpublished work in accordance with the guidelines of Applied Mathematical Modelling. To submit your manuscript, please use the journal's online submission platform and select the article type “VSI: AI-Mechanics”during the submission  process. All manuscripts will undergo a rigorous peer-review process by at least three independent experts. Papers will be evaluated based on novelty, methodological rigor, relevance, and clarity.

Keywords:

Computational Mechanics; Physics-aware AI; Data-driven AI; Mathematical Modelling; Numerical Simulation; Multiscale and Multiphysics Analysis

Special Issue on New Trends in Machine Learning Mathematical Models for Structural Analysis and Design
截稿日期: 2026-01-31

Machine learning has seen rapid advancements and widespread applications across various fields in thepast two decades, revolutionizing problem-solving in complex real-world scenarios. In structural engineering, machine learning is increasingly transforming traditional analysis and design processes,
enhancing efficiency, accuracy, and automation. This special issue, Machine Learning in Structural Analysis and Design, focuses on the latest developments and innovative applications of machine learning in structural engineering. It aims to highlight cutting-edge research that leverages machine
learning techniques to improve structural analysis, optimize design processes, and address emerging challenges in the field.

Guest editors:

Professor Wei Gao, University of New South Wales, w.gao@unsw.edu.au;
Professor Zhenyu Liu, Zhejiang University;
Professor Alba Sofi, University Mediterranea of Reggio Calabria;
Dr Yuan Feng, University of Technology Sydney

Manuscript submission information:

Topics of interest include (but are not limited to) machine learningassisted/
related:

    Machine learning-assisted structural static, dynamic, and stability analysis
    Data-driven structural health monitoring, fault detection, and damage assessment
    Reliability-based structural optimization and uncertainty-aware design strategies
    Risk assessment, safety evaluation, and resilient structural design
    Predictive modelling for structural aging, deterioration, and life-cycle assessment
    Machine learning applications in topology optimization and performance-based design
    Experimental investigations integrated with machine learning techniques
    Surrogate modelling and reduced-order methods for structural simulations
    Enhancing structural resilience against natural (e.g., earthquakes, wind) and human-induced
    hazards
    Theoretical advancements in data-driven structural mechanics and computational methods
    Deployment of advanced machine learning algorithms in structural engineering applications
    Uncertainty quantification and reliability assessment in structural systems

The Guest Editors invite submissions that explore theoretical, computational, and experimental studies on
machine learning-assisted structural analysis, safety assessment, and structural design. Contributions
focusing on health monitoring, predictive maintenance, and cost-effective management of aging structures
are also encouraged. These studies may involve the development of novel machine learning methodologies
and their application across various domains of structural engineering, advancing both fundamental
research and practical implementations.

The prospective authors are encouraged to submit their manuscripts online to the journal Applied
Mathematical Modelling through link:
https://www.sciencedirect.com/journal/applied-mathematical-modelling 

When submitting your manuscript please choose the special issue “Machine learning in SAD” from the
choice of submission types. The manuscripts will go through the regular peer review process before being
accepted. Please visit the journal website for additional notes for the authors. The deadline for submission
of manuscripts is 1 December 2025.

Applied Mathematical Modelling is publishing special issues in the new format where special issue articles
are published in regular issues as soon as they are available, and simultaneously being grouped online
under a specific special issue link, which is easily accessible and navigable on ScienceDirect. Please note
that papers solicited through this call will undergo standard journal peer review process and will be
indexed for citations like other regular journal papers. All interested authors can submit papers to the
special issue through the online journal submission system at www.editorialmanager.com/ammod.

The first submission date: 1 May 2025
(Elsevier System open for submissions)
The final submission deadline: 1 December 2025
(The last date until which Elsevier System will be open for new submissions)
The final acceptance deadline (for guest editors): 15 May 2026