AutoEmulate: An emulator platform for Digital Twins#
AutoEmulate is designed to automate the complex process of emulating simulations with machine learning models. We often need emulators as drop-in replacements for complex physical simulations, which can be very slow and computationally expensive. The goal of Autoemulate is to make it easy to replace simulations with fast, accurate emulators. To do this, the package automatically compares, optimises, and evaluates a range of models, like Radial Basis Functions, Gaussian Processes or Neural Networks to find the best emulator for a simulation.
Useful links: Code repository | Issues |