Machine Learning, particularly 'Deep Learning', has been a big player in the data-driven world of methods recently, thanks to the vast amount of available data stored and collected from billions of sensors and actuators. Since such data usually comes from multiscale physics problems and applications, data-driven approaches can produce physically inconsistent or implausible predictions while providing excellent accuracy.
In this scenario, a question arises: Can physics-informed machine learning be the new essential tool for solving challenging physics problems and applications?
Nowadays, a new frontier in Machine Learning is represented by combining physics laws and domain knowledge into the models (i.e. neural networks); in this way, such models can benefit from theoretical constraints on top of the observational data. The main goal is to improve the performance of the learning algorithms and introduce a new way of explaining and interpreting the obtained solutions.
The main research topics of this topical collection include, but are not limited to:
- Theory for Physics-Informed Neural Networks (PINNs)
- Neural Network architectures for PINNs
- Hybrid approaches for Physics-Informed Machine Learning
- Application of physical sciences to model and improve ML performance
- Scientific Machine Learning approaches for ODE and PDE
Lead Guest Editor:
Francesco Piccialli, University of Naples Federico II, Department of Mathematics and Applications “R. Caccioppoli”, Italy
David Camacho, Universidad Politecnica de Madrid, Spain
Gang Mei, University of Geosciences, Beijing, China
Initial Paper Submission: February 28, 2022
Initial Paper Decision: April 31, 2022
Revised Paper Submission: July 30, 2022
Final Paper Decision: August 30, 2022
Peer Review Process:
Advanced Modeling and Simulation in Engineering Sciences operates a single-blind peer-review system, where the reviewers are aware of the names and affiliations of the authors, but the reviewer reports provided to authors are anonymous.
Submitted manuscripts will generally be reviewed by two to three experts who will be asked to evaluate whether the manuscript is scientifically sound and coherent, whether it duplicates already published work, and whether or not the manuscript is sufficiently clear for publication. The Editors will reach a decision based on these reports and, where necessary, they will consult with members of the Editorial Board.
Please refer to the complete journal peer review policy here: https://amses-journal.springeropen.com/submission-guidelines/peer-review-policy.
Before submitting your manuscript, please ensure you have carefully read the submission guidelines for Advanced Modeling and Simulation in Engineering Sciences. Your complete manuscript should be submitted through the Advanced Modeling and Simulation in Engineering Sciences submission system, selecting inclusion with the thematic series, “Physics Informed Machine Learning” when prompted. All submissions will undergo rigorous peer review and accepted articles will be published within the journal as a collection.
Open Access Publication
Submissions will also benefit from the usual advantages of open access publication:Rapid publication: Online submission, electronic peer review and production make the process of publishing your article simple and efficient.
High visibility and international readership in your field: Open access publication ensures high visibility and maximum exposure for your work - anyone with online access can read your article.
No space constraints: Publishing online means unlimited space for figures, extensive data and video footage.
Authors retain copyright, licensing the article under a Creative Commons license: articles can be freely redistributed and reused as long as the article is correctly attributed.
Sign up for article alerts to keep updated on articles published in Advanced Modeling and Simulation in Engineering Sciences - including articles published in this thematic series.