 |
Center for Nonlinear Studies |
Climate models are complex mathematical models designed by meteorologists, geophysicists, and climate scientists, and run as computer simulations, to predict climate. There is currently high variance among the predictions of 20 global climate models that inform the Intergovernmental Panel on Climate Change (IPCC). Given temperature predictions from 20 IPCC global climate models, and over 100 years of historical temperature data, we track the changing sequence of which model currently predicts best. We use an algorithm due to Monteleoni and Jaakkola, that models the sequence of observations using a hierarchical learner, based on a set of generalized Hidden Markov Models (HMMs), where the identity of the current best climate model is the hidden variable. The transition probabilities between climate models are learned online, simultaneous to tracking the temperature predictions. On historical global mean temperature data, our algorithm's average prediction loss nearly matches that of the best performing climate model in hindsight. Moreover its performance surpasses that of the average over climate model predictions, which is the default practice in climate science, the median prediction, and least squares linear regression. We also experimented on climate model predictions through the year 2098. Simulating labels with the predictions of any one climate model, we found significantly improved performance using our algorithm with respect to the other climate models, and techniques. Drilling down on Africa, Europe, and North America, on historical data, at both annual and monthly time-scales, and in future simulations, our algorithm typically outperforms both the best climate model per geographical region, and linear regression, and consistently outperforms the average climate model prediction, the benchmark. This talk is based on joint work with Gavin Schmidt (NASA Goddard Institute for Space Studies and Columbia University Earth Institute), Shailesh Saroha, and Eva Asplund (Computer Science, Columbia University).
Host: Frank Alexander, fja@lanl.gov, 665-4518. Information Science and Technology Center (ISTC)