Code

Implementation of stochastic OnsagerNet in jax

Qianxiao Code

We have just released a Jax implementation of stochastic OnsagerNet, with applications to polymer dynamics.

https://github.com/MLDS-NUS/onsagernet-jax

References

[1] X. Chen et al., “Constructing custom thermodynamics using deep learning,” Nature Computational Science, vol. 4, no. 1, pp. 66–85, 2024. Available: https://www.nature.com/articles/s43588-023-00581-5

[2] K. S. Novoselov and Q. Li, “Learning physical laws from observations of complex dynamics,” Nat Comput Sci, pp. 1–2, Jan. 2024, doi: 10.1038/s43588-023-00590-4.

 

Code Repository

Qianxiao Code, News

We have set up a consolidated code repository where we will share updated implementations of various algorithms we proposed. The goal is to make them easy to use and expand, both by researchers and practitoners.

The repository is found at

https://github.com/MLDS-NUS

Currently, we have a repository released on Koopman decomposition using deep learning, following our original work of Li, Q., Dietrich, F., Bollt, E. M., & Kevrekidis, I. G. (2017). Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator. Chaos: An Interdisciplinary Journal of Nonlinear Science, 27(10), 103111..

More implementations will be added in the future!