DCE is delighted to be partnering with the 662 Colloquium on Physics-enhanced machine learning and data-driven nonlinear dynamics, which takes place in April 2026, in order to produce a special collection of articles. 

Introduction 

Data-inspired and hybrid physics-data techniques are being applied across a wide spectrum of nonlinear systems, enhancing capabilities in modeling, simulation, prediction, and optimization. These methods provide powerful new ways to uncover hidden patterns, develop predictive models, and manage the inherent complexities of dynamical systems. Strategies exploiting neural networks, deep learning, and hybrid physics-data architectures (e.g., physics-inspired symbolic regression, deep symbolic regression methods) which merge physical insights with machine learning to derive interpretable models are particularly welcome. The special collection will provide opportunities for presenting  new research directions in machine learning for nonlinear dynamics.

Topics 

Potential topics of research papers welcome in this collection include but are not limited to:

• Data-driven methods to discover nonlinear dynamics and physical laws
• Deep Learning-based and data-driven model order reduction
• Characterization of nonlinear resonances and dynamic phenomena via machine learning
• Physics-enhanced machine learning to tackle nonlinear dynamics challenges
• Learning and predicting nonlinear dynamics using Neural Networks
• Deep learning-based and data-driven closure models
• Data-driven control & reinforcement learning for dynamical systems

Moreover, other types of articles accepted in the journal, such as data-papers, position papers and translation papers, are also welcome. See below.

Timetable

• Colloquium takes place: 28-30 April 2026 in Como, Italy (see website)
• Submissions to DCE: 1 November 2026

Why Submit to DCE?

✔ A high-quality and efficient peer-review process: papers published as soon as possible after acceptance in the DCE journal. 
✔ Articles presented as part of a collection dedicated to the event, making them more visible to people interested in the area.
✔ Open Access without financial barriers: many authors are covered by transformative (institutional) agreements and those who are not are still able to publish on an OA basis irrespective of funding situation or location. 
✔ No restrictions on the use of preprint repositories like arXiv, if you want to share work prior to the peer-review process.
✔ Well-cited and impactful venue: 2024 Impact Factor: 2.8; 2024 CiteScore: 4.4 and indexed in Web of Science, Scopus and Directory of Open Access Journals.

How to Submit

Key considerations for submitting are below, with full details available in the DCE Instructions for Authors. 

Article types

When they submit to DCE authors are given the following option of article types to select from:

• Research articles using data science methods and models for improving the reliability, resilience, safety, efficiency and usability of engineered systems.
• Translational papers demonstrating the downstream benefits of data-intensive engineering - and the underlying data science principles, techniques and technologies - to wider society, economy, environment, health and way of life. For some more detailed instructions, see this guide to translational papers.
• Data papers that describe in a structured way, with a narrative and accompanying metadata, important and re-usable data sets in open repositories with potential for re-use in engineering research and practice. These papers promote data transparency and data re-use.
• Survey papers providing a detailed, balanced and authoritative current account of the existing literature concerning data-intensive methods in a particular facet of engineering sciences.
• Tutorial reviews providing an introduction and overview of an important topic of relevance to the journal readership. The topic should be of relevance to both students and researchers who are new to the field as well as experts and provide a good introduction to the development of a subject, its current state and indications of future directions the field is expected to take

Templates

Authors have the option but are not required to use the following templates:

• DCE LaTeX template files
• Overleaf (a LaTeX-based collaborative authoring tool; read about benefits of this tool)
• DCE Word template

Note that authors should provide both an abstract that summarizes the paper (250 words or less) and beneath it an impact statement (120 words describing the significance of the findings in language that can be understood by a wide audience). Competing interest, funding and data availability statements should be provided at the end of the main text above the references (see disclosure statements).

Articles should be submitted through the DCE ScholarOne Manuscripts system, but note that if you use the Overleaf tool you can submit directly into the system without having to reupload files. 

You should select the 'Physics-enhanced machine learning and data-driven nonlinear dynamics' option in response to the question about special collections so that we can assign your submission accordingly.

Guest Editors 

• Alice Cicirello, University of Cambridge (DCE Editor-in-Chief)
• Eleni Chatzi, ETH Zurich (DCE Advisory Board)
• Andrea Manzoni, Politecnico di Milano (Guest Editor)
• Pierpaolo Belardinelli, Polytechnic University of Marche (Guest Editor)