The Journal of Physical Chemistry A, B, and C will publish a Virtual Special Issue (VSI) on machine learning in physical chemistry in 2020.
The Guest Editors for the Virtual Special Issue Will Be:
- JPC A: Professor Thomas F. Miller III, California Institute of Technology
- JPC B: Associate Professor Andrew L. Ferguson, University of Chicago, and Associate Professor Jim Pfaendtner, University of Washington
- JPC C: Assistant Professor Johannes Hachmann, University at Buffalo
Together they welcome researchers to submit their new and unpublished work by June 30, 2020.
If you are unsure if your research is within scope or have other questions about submitting a manuscript to this VSI, please email Editor-in-Chief Joan-Emma Shea’s office at email@example.com.
What is a Virtual Special Issue?
Why Submit to a Virtual Special Issue?:
- Timely publication: Each manuscript will first be published in a regular issue shortly after it is accepted for publication.
- Additional exposure for your work: Once all papers in the VSI have been accepted they will be collected together on a single web page and announced in another regular issue, including a preface written by the guest editors.
Articles Published as part of the VSI So Far Include:
Accelerating Variational Transition State Theory via Artificial Neural Networks
J. Phys. Chem. A 2020, 124, 5, 1038-1046
Gaussian Process Regression for Minimum Energy Path Optimization and Transition State Search
J. Phys. Chem. A 2019, 123, 44, 9600-9611
Analysis of Self-Assembly Pathways with Unsupervised Machine Learning Algorithms
J. Phys. Chem. B 2020, 124, 1, 69-78
Efficient Phase Diagram Sampling by Active Learning
J. Phys. Chem. B ASAP
Ensemble Learning of Partition Functions for the Prediction of Thermodynamic Properties of Adsorption in Metal–Organic and Covalent Organic Frameworks
J. Phys. Chem. C 2020, 124, 3, 1907-1917
Symmetry-Adapted High Dimensional Neural Network Representation of Electronic Friction Tensor of Adsorbates on Metals
J. Phys. Chem. C 2020, 124, 1, 186-195
What to Submit—Deadline: June 30, 2020:
- New representations for quantum machine learning
- Accelerating and improving the accuracy of quantum chemistry and quantum dynamics through machine learning
- Discovery of materials for novel reactivity via machine learning
“Machine learning offers completely new avenues to address the quantum chemical problems of electronic structure and chemical dynamics, as well as novel strategies for refining and accelerating conventional quantum chemistry calculations,” Professor Miller says.
- New molecular featurizations for machine learning
- New algorithms for materials or molecular design
- Production of new materials or synthesis routes enabled by AI
- Machine learning for a new understanding of protein folding and assembly
- AI in the chemical industry
- AI in microscopy and characterization
- Prediction of new materials or molecules with bespoke properties from ML algorithms
“The integration of artificial intelligence with soft materials simulation, synthesis, and characterization is poised to do nothing short of revolutionize molecular and soft materials discovery,” Professor Ferguson says.
- New methods and techniques for machine learning in the chemical and materials domain (including featurization)
- Case studies for rational design and inverse engineering enabled by machine learning
- Examples of closed design-synthesis-characterization loops
- Discovery of new structure-property relationships that could be used as design guidelines
- Examples of AI-driven decision making in chemical research/industry
- Examples of the democratization of machine learning approaches in the chemistry community
- Advances of software for machine learning in chemistry and materials
“Machine learning offers a path to accelerated discovery, rational design, and inverse engineering that transcends traditional research approaches in the chemistry and materials domain,” Professor Hachmann says. “Today, we witness transformative advances in the corresponding tools and techniques, and at the same time, a push towards democratizing them so that machine learning becomes an accessible and viable proposition for the community at large.”
Important Submission Instructions
- Hua Guo for JPC A
- Gang-yu Liu and Arun Yethiraj for JPC B
- William F. Schneider for JPC C
To ensure an unbiased peer-review process, they ask that you don’t indicate within your manuscript that the submission is intended for the “Machine Learning in Physical Chemistry” VSI. If you do, your manuscript will be returned for correction. Instead, when you submit your manuscript, please indicate this on your cover letter and note what part and section you feel will be the best fit. You can find a complete list of sections and other important information for authors in the JPC Author Guidelines.
As with all submissions to JPC, your manuscript should represent a rigorous scientific report of original research, and that it will be peer-reviewed as a regular Article. Manuscripts are expected to provide new physical insight and/or present new theoretical or computational methods of broad interest.