Presentation of Case Studies: Machine Learning Force Fields for Material Modeling

Added to bookmarks
Bookmarks list

Bookmark has been removed
Bookmarks list

You can't add any more bookmarks

By registering as a member, you can increase the number of bookmarks you can save and organize them with labels.
Free membership registration

last updated：Oct 01, 2025

シュレーディンガー

Introduction of use cases for machine-learned force fields.

Machine-learned force fields (MLFF) are designed to improve traditional force fields by incorporating machine learning models to accurately model interactions between atoms and molecules. This technology is based on neural network potential energy surface (NN-PES) architecture, and the model is trained to reproduce the total electronic energy of the system with chemical accuracy. With the combination of OPLS4 for initial structure generation, fast DFT and MD engines, and key MLFF methods, Schrödinger has become a leading partner in MLFF generation. This application note introduces the application of QRNN technology in modeling across three different areas of materials science: liquid electrolytes, polymers, and ionic liquids.

Inquire About This Product

basic information

【Case Studies】 1. High-dimensional neural network force field for liquid electrolytes 2. Development of a scalable and versatile MLFF for polymers 3. Machine learning-based fitting force field for ionic liquids Schrödinger offers research services focused on the development of advanced machine learning-based force fields to enable accurate molecular dynamics simulations across a wide range of applications, achieving fast and high-precision modeling of complex material systems. *Please feel free to contact us.