Home
😨 This Wiki is depreciated 😨 Visit the new Wiki at sapsan-wiki.github.io
Depreciated Home
Sapsan is a pipeline for Machine Learning (ML) based turbulence modeling. While turbulence is important in a wide range of mediums, the pipeline primarily focuses on astrophysical application. With Sapsan, one can create their own custom models or use either conventional or physics-informed ML approaches for turbulence modeling included with the pipeline (estimators). For example, Sapsan features ML models in its set of tools to accurately capture the turbulent nature applicable to Core-Collapse Supernovae.
Sapsan takes out all the hard work from data preparation and analysis in turbulence and astrophysical applications, leaving you focused on ML model design, layer by layer.
Feel free to check out a website version with a few examples at sapsan.app. The interface is identical to the GUI of the local version of Sapsan, except lacking the ability to edit the model code on the fly and to use mlflow for tracking.
Note: currently Sapsan is in beta, but we are actively working on it and introduce new features on a daily basis.
Physics-Informed Machine Learning for Modeling Turbulence in Supernovae
Astrophysical Journal (ApJ) - 2022
Sapsan: Framework for Supernovae Turbulence Modeling with Machine Learning
Journal of Open Source Software (JOSS) - November 26, 2021
Provectus Brings Machine Learning to Numerical Astrophysics, Helping Simulate Turbulence in Supernovae Models
Provectus IT Press Release - March 9, 2021
Machine Learning for Supernova Turbulence
Society for Industrial and Applied Mathematics (SIAM) News (CSE21) - March 4, 2021