RAMP 04 El Niño

mardi 16 juin 2015, 09:00 → 18:00 Europe/Paris

Proto204

Balázs Kégl (LAL)

Predict six months ahead the temperature at surface (TAS) in the El Niño 3.4 region from TAS data simulated by the CCSM4 model, brought to you by Claire Monteleoni (GWU), Mahesh Mohan (GWU), Timothy DelSole (COLA), Kathleen Pegion (COLA), Julie Leloup (LOCEAN), and your regular coaches.

The event will take place at Proto204, a 10 minute walk from either the Orsay-Ville or the Bur-sur-Yvette RER B stations.

Supporting material:

• the data, the resampled data.
• The ocean mask.
• an example of a temperature map with the El Niño 3.4 region.
• ipython notebook with the problem description, analysis examples, and submission instructions

Some general guidelines. 

Your primary goal is to have a high score in the "contributivity" column. One way to achieve it is to submit a strong model, high in the "score" column, but we appreciate especially those models which do not have top scores but are sufficiently different from the rest of the models to achieve high score in the "contributivity" column.

A general rule is that you should not resubmit until your previous model has not yet been trained (it shows up in the "New models" table.)

Some strategies you can employ:

1. Take a good regressor and work on the feature extractor or vice verse.
2. Take a good regressor or feature extractor and optimize its hyperparameters using smac or hyperopt. See the course material for help.
3. Take two good submissions and combine the feature extractor and the classifier.

Slides monteleoniParis15.pdf rampIntro15.pdf

Welcome of participants & Coffee

Introduction talk

Session 1

Buffet & presentation of the first results

Session 2

Café

Session 3

Debriefing and closing