Learn all about

Scientific Machine Learning

Full Day Tutorial on Monday, November 15, 2021
SuperComputing Conference 2021

Thanks for Attending! The videos to this tutorial can be found on RocketML Youtube

Play Video

Scientific Machine Learning is a new frontier

Play Video

What is Scientific Machine Learning

SciML is an approach where scientific based model constraints are introduced into Machine Learning algorithms, allowing prediction of future performance of complex multiscale, multiphysics systems using sparse, high-multi-fidelity, and heterogeneous data

Tutorial Overview

This full day tutorial is a comprehensive overview of building and deploying neural forward and inverse PDE solvers. We will discuss Physics-Informed Neural Networks (PINNs), which are usually dense networks producing point-wise solutions of PDEs, as well as CNN-based networks for producing full-field solutions of parametric PDEs, along with GAN-based networks that solve both forward and inverse ODEs. 

We will work through several cloud scalable approaches including those for simulating across parameters, as well as distributed deep-learning to obtain high-fidelity solutions. This hands-on tutorial will provide the theoretical background, computational training and software tools for practitioners to rapidly deploy cloud scalable solutions for their forward and inverse PDE needs. 

We will provide access to Microsoft Azure HPC clusters, and scripts for attendees to follow all demos at their own pace. We envision this tutorial to be of significant utility for academic and industry practitioners interested in the seamless scale-up of their approaches.


Teaching Team


CTO, RocketML

Data Scientist, ML engineer


GM, Microsoft

Data Scientist


Professor, ISU

Data scientist



CSA, RocketML

Data scientist


Post Doc, ISU

Data scientist

Chih Hsuan

PhD Student, ISU

Data Scientist, ML engineer