Call for papers: Data-driven Mechanics

Artificial intelligence (AI) and machine learning (ML) are having a tremendous impact across a range of subject areas including engineering and computational mechanics, which is the focus of this journal. Novel AI/ML-based methods for generating data-driven models such as Gaussian processes and convolutional neural networks offer much promise for enhancing our capability to simulate complex mechanics more accurately, to characterise fundamentally new underpinning science, and to tackle challenging mechanics problems previously deemed computationally hard. These methods are also allowing for a re-think of the way we approach computational modelling. For example, novel hybrid approaches that integrate AI/ML-based surrogates and conventional numerical models (e.g., finite element) are increasingly explored for both minimising simulation time and capturing the physics at high spatial and temporal resolutions. Another example could be the recent interest in physics-informed machine learning approaches that support creating data-driven models that satisfy the underlying physics of the system. This themed issue aims to capture such recent research developments involving the development and application of AI/ML concepts for solving applied mechanics challenges across the broad civil engineering discipline. Papers must have a significant mechanics component, i.e., have a scientific focus on subjects such as solid mechanics and fluid mechanics. Applications can include, but are not limited to, the following areas:

• Structural design and analysis
• Structural dynamics
• Digital twins
• Building performance modelling
• Fluid/structure interaction
• Soil/structure interaction.

Submit your abstract by 15 November 2023

Full submissions: 15 February 2024