Universal Differential Equations for Scientific Machine Learning

by   Christopher Rackauckas, et al.

In the context of science, the well-known adage "a picture is worth a thousand words" might well be "a model is worth a thousand datasets." Scientific models, such as Newtonian physics or biological gene regulatory networks, are human-driven simplifications of complex phenomena that serve as surrogates for the countless experiments that validated the models. Recently, machine learning has been able to overcome the inaccuracies of approximate modeling by directly learning the entire set of nonlinear interactions from data. However, without any predetermined structure from the scientific basis behind the problem, machine learning approaches are flexible but data-expensive, requiring large databases of homogeneous labeled training data. A central challenge is reconciling data that is at odds with simplified models without requiring "big data". In this work we develop a new methodology, universal differential equations (UDEs), which augments scientific models with machine-learnable structures for scientifically-based learning. We show how UDEs can be utilized to discover previously unknown governing equations, accurately extrapolate beyond the original data, and accelerate model simulation, all in a time and data-efficient manner. This advance is coupled with open-source software that allows for training UDEs which incorporate physical constraints, delayed interactions, implicitly-defined events, and intrinsic stochasticity in the model. Our examples show how a diverse set of computationally-difficult modeling issues across scientific disciplines, from automatically discovering biological mechanisms to accelerating climate simulations by 15,000x, can be handled by training UDEs.




This is amazing and important and I am beside myself over how easily an amateur like me can understand and appreciate it.  Wow!


This is amazing!  Crisp and understandable for an amateur.  I have been keeping an eye out for this kind of solution for 30 years.  When you you attack Schrodinger with it?


page 1

page 4


Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations

While there is currently a lot of enthusiasm about "big data", useful da...

Deep-learning PDEs with unlabeled data and hardwiring physics laws

Providing fast and accurate solutions to partial differential equations ...

Integrating Machine Learning with Physics-Based Modeling

Machine learning is poised as a very powerful tool that can drastically ...

Accelerating Physics Simulations with TPUs: An Inundation Modeling Example

Recent advancements in hardware accelerators such as Tensor Processing U...

Predicting Real-time Scientific Experiments Using Transformer models and Reinforcement Learning

Life and physical sciences have always been quick to adopt the latest ad...

Simflowny 2: An upgraded platform for scientific modeling and simulation

Simflowny is an open platform which automatically generates parallel cod...

Learning Discrepancy Models From Experimental Data

First principles modeling of physical systems has led to significant tec...

Code Repositories


Repository for the Universal Differential Equations for Scientific Machine Learning paper, describing a computational basis for high performance SciML

view repo


Helicopter Scientific Machine Learning (SciML) Challenge Problem

view repo


Scientific Machine Learning team information directory

view repo


study on UDEs for Scientific Machine Learning

view repo


A compendium of examples utilizing "Scientific Machine Learning" for the harmonic oscillator.

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.