MSEAS ATL

Overview

MIT's MSEAS (Multidisciplinary Simulation, Estimation, and Assimilation Systems) project is performing ongoing research in Active Transfer Learning (ATL) for Ocean Modeling. ATL is an experimental outgrowth of both active learning and transfer learning (ie, inductive transfer).

The MSEAS Ocean Test Cases provide a common framework for researchers, helping them to evaluate ATL approaches and technology. ISLE's response to these test cases will be based on Inductive Process Modeling (IPM) in general and IPM Lab in particular.

MSEAS Test Cases

MSEAS has provided several test cases, including equations, simulated data, and suggested problems. After performing some of the simpler problems in this case, to demonstrate that we have the basics right, we plan to select and/or generate more challenging problems that take advantage of our approach (IPM) and technology (IPM Lab).

We are currently concentrating on Test Case 2 (Learning for 2-D Biogeochemical Dynamical Systems). Test Case 2 concentrates on the following general areas:

Dynamics Classification

  • Discover unknown biomass, biomass (time)

  • Discover dynamical regimes, etc.

Inductive Model Learning

  • Learn specific terms (e.g., unknown functionals, functionals (time), etc.

  • Discover parameters and structures of the 0D biological reaction terms.

  • Determine when/where certain terms matter: e.g. when do the physical terms matter?

Resources


This wiki page is maintained by Rich Morin, an independent consultant specializing in software design, development, and documentation. Please feel free to email comments, inquiries, suggestions, etc!

Topic revision: r47 - 30 Jul 2014, RichMorin
This site is powered by FoswikiCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding CFCL Wiki? Send feedback