Skip to main content
Skip to main menu Skip to spotlight region Skip to secondary region Skip to UGA region Skip to Tertiary region Skip to Quaternary region Skip to unit footer


Comparison of Multifidelity Machine Learning Models for Potential Energy Surfaces

Portrait of Stephen Goodlett, speaker
Stephen Goodlett
Graduate Student, Department of Chemistry
University of Georgia
iSTEM Building 2, Room 1218
Physical Seminar

Multifidelity modeling is a technique for fusing the information from two or more datasets into one model. It is particularly advantageous when one dataset contains few accurate results and the other contains many less accurate results. Within the context of modeling potential energy surfaces, the low fidelity dataset can be made up of a large number of inexpensive energy computations that provide adequate coverage of the N-dimensional space spanned by the molecular internal coordinates. The high fidelity dataset can provide fewer but more accurate electronic energies for the molecule in question. Here we compare the performance of several neural network based approaches to multifidelity modeling. We show that the four methods (dual, ∆- learning, weight transfer, and Meng–Karniadakis neural networks) outperform a traditional implementation of a neural network, given the same amount of training data. We also show that the ∆-learning approach is the most practical and tends to provide the most accurate model.

Support Us

We appreciate your financial support. Your gift is important to us and helps support critical opportunities for students and faculty alike, including lectures, travel support, and any number of educational events that augment the classroom experience. Click here to learn more about giving.

Every dollar given has a direct impact upon our students and faculty.

Got More Questions?

Undergraduate inquiries: 

Registration and credit

AP Credit, Section Changes, Overrides,

Graduate inquiries:

Contact Us!

Assistant to the Department Head: Donna Spotts, 706-542-1919 

Main office phone: 706-542-1919 

Main Email:

Head of Chemistry: Prof. Jason Locklin