Metadata Updated: November 12, 2020


Climate models are complex mathematical models designed by meteorologists, geophysicists, and climate scientists to simulate and predict climate. Given temperature predictions from the top 20 climate models worldwide, 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 (HMM), 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 data, our online learning algorithm’s average prediction loss nearly matches that of the best performing climate model in hindsight. Moreover its performance surpasses that of the average model prediction, which was the current state-of-the-art 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 online learning algorithm with respect to the other climate models, and techniques.

Access & Use Information

Public: This dataset is intended for public access and use. License: No license information was provided. If this work was prepared by an officer or employee of the United States government as part of that person's official duties it is considered a U.S. Government Work.

Downloads & Resources


Metadata Created Date November 12, 2020
Metadata Updated Date November 12, 2020
Data Update Frequency irregular

Metadata Source

Harvested from NASA Data.json

Additional Metadata

Resource Type Dataset
Metadata Created Date November 12, 2020
Metadata Updated Date November 12, 2020
Publisher Dashlink
Unique Identifier Unknown
Identifier DASHLINK_223
Data First Published 2010-10-13
Data Last Modified 2020-01-29
Public Access Level public
Data Update Frequency irregular
Bureau Code 026:00
Metadata Context
Metadata Catalog ID
Schema Version
Catalog Describedby
Homepage URL
Program Code 026:029
Source Datajson Identifier True
Source Hash 7110324188220e253f498a375fc0ee587e6b9dea
Source Schema Version 1.1

Didn't find what you're looking for? Suggest a dataset here.