This new PROTECT article addresses an urgent problem: the proper quantification and attribution of uncertainties relating to sea-level rise. The authors show how a machine-learning approach may show the way towards a more rigorous treatment of these uncertainties, and how this might be used for policy making.
Example of machine-learning-based diagnostic for a particular sea level result (blue horizontal bar) extracted from the MIROC5 RCP8.5-forced Multi-Model Ensemble of future sea level contribution of the Greenland ice sheet for year 2100. Each row shows how the positive (green bar) or negative (red bar) contribution of each modelling assumption (vertical axis) moves the prediction from the mean ensemble (denoted µ0). The grey color indicates that the contribution cannot be considered with confidence.
Leave a Reply