H-HIGNN Toolkit: A Software for Efficient and Scalable Simulation of Large-Scale Particulate Suspensions Using GNNs and H-Matrices
Abstract
H-HIGNN is a framework designed for efficient and scalable simulation of large-scale particulate suspensions. It effectively captures both short- and long-range HIs and their many-body effects and enables substantial computational acceleration by harvesting the power of machine learning and hierarchical matrix.
Fields of Study & Subjects
Particle Dynamics in Fluid Flows
Model Reduction and Neural Networks
Machine Learning in Materials Science
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 19 January 2026