Options

Networks in climate science

I was invited to give a talk at NIPS (the Neural Information Processing Seminar, a big annual conference on neural networks, machine learning and other things), in early December 2014. I've decided to take a chance and give a talk on climate networks and El Niño prediction

I am hoping some of you - especially you programmers - can help me by developing our El Niño project to the point where I have something interesting and new to show them! If not, I will just review other people's work.

Either way, I will label this as a talk "by the Azimuth Project" and cite by name those who have helped. The conversations here have already helped a lot.

It's a bit crazy to do this, but the worst that can happen is that a few hundred people will decide I'm an idiot. I will show all of you drafts of the talk to reduce the chance of this.

I am now motivated to work quite hard on our El Niño project - that's the point.

Here's the title and abstract:

Networks in climate science

The El Niño is a powerful but irregular climate cycle that has huge consequences for agriculture and perhaps global warming. Predicting its arrival more than 6 months ahead of time has been difficult. A recent paper by Ludescher et al caused a stir by using ideas from network theory to predict the start of an El Niño toward the end of 2014 with a 3-in-4 likelihood. We critically analyze their technique, related applications of network theory, and also attempts to use neural networks to help model the Earth's climate.

Sign In or Register to comment.