This is a first! Announcing three scholarships for research-based higher degrees in Australia. Seeking Australian or New Zealand candidates who are science and engineering grads and interested in using neural nets to build climate models that work. This really is something new. Skeptical minds encouraged to apply. Please pass this on to people you think might be interested… – Jo
Once in a Life Time Opportunity to be an Honest Climate Modeller
From Jennifer Marohasy
Most critics of anthropogenic global warming, and there are many, never get the opportunity to actually have a go at contributing to climate science in a practical or tangible and constructive way. That is, they never get to pull a lever, press a button, build a model or make a forecast. At best they might throw rotten tomatoes by way of blog posts and comments. This is because the tools of modern climate science are very complex and generally run on super computers with restricted access.
But what if it was possible to build your own climate model on a gaming computer, with some help from artificial neural network (ANN) technology?
Artificial neural networks are a form of artificial intelligence and machine learning, that can be applied were there is an abundance of data with patterns and/or signals embedded in that data. Artificial neural networks have application when there are problems or questions to be answered, but the relationships can’t be easily reduced to simple formula.
Artificial neural networks (ANNs) are a key technology in Big Data already used in many financial, medical, commercial and scientific applications. IBM researchers have so much confidence in the future of the technology that they are designing a chip that’s fundamentally different to the type of computer chip currently used in computing, one that will be more compatible with computers that run ANNs.
John Abbot, a Professor at Central Queensland University, has 10 years experience working with ANNs, initially for share trading. So successful, he once bought himself a Chevrolet corvette on the earnings from a few days of trade.
Unfortunately the Corvette was parked in a garage beside the Brisbane River at the time of the catastrophic 2011 flood.
John could have become depressed about the loss of his little red car, but instead worked with Jennifer Marohasy to see if it might have been possible to forecast that flood event using relevant climate indices and ANNs.
Jennifer and John have since published several peer-reviewed papers on the application of ANN to rainfall forecasting in Queensland Australia. These preliminary investigations suggest that prototype ANNs, mining historical climate data, run on gaming computers, are more skilful at medium-term rainfall forecasts than the most advanced general circulation models run on supercomputers.
The B. Macfie Family Foundation funded this initial research and is now providing money for three scholarships for research higher degree candidates to expand this program of work. Successful applicants will each be provided with a tax-exempt living allowance scholarship for a fixed term of up to 3.5 years, with a commencing stipend of $32,000 per annum. They will also get their own gaming computer and ANN software to play with.
John will be the Principal Supervisor for these projects. He has a BSc from Imperial College, London, a PhD from McGill University, Montreal, and over 110 publications in scientific and law journals. While at the University of Tasmania, John successfully supervised to completion nine PhDs and nine Honours students, resulting in more than 50 co-authored publications.
Applicants must be Australian or New Zealand citizens, or Australian permanent residents, and graduates from a science or engineering discipline. It is expected that applicants will like problem-solving and playing with numbers.
Applicants will not be discriminated against if they already have a lot of life experience, and are sceptical of anthropogenic global warming.
There is more information at the Central Queensland University website.