A neural network nonlinear multi-model ensemble for predicting precipitation over ConUS

A novel multi-model ensemble approach based on the neural network (NN) technique is formulated and applied for improving 24-hour precipitation forecasts over the continental US. The developed nonlinear approach allowed us to account for nonlinear correlation between ensemble members and 'optimal' forecast represented by a nonlinear NN ensemble mean. The NN approach is compared with the regular multi-model ensemble, with multiple linear regression ensemble approaches, and with results obtained by human forecasters. The NN multi-model ensemble improves upon regular multi-model and multiple linear regression ensembles: (1) it significantly reduces high bias at low precipitation level; (2) it significantly reduces low bias at high precipitation level, and (3) it sharpens features making them closer to the observed ones. The NN multi-model ensemble performs at least as well as human forecasters supplied with the same information. The developed NN approach is a generic approach that can be applied to other multi-model ensemble fields as well as to single model ensembles. V.M. Krasnopolsky and Y. Lin. "MMAB Contribution No. 296." "January 2012." System requirements: Adobe Acrobat Reader. Includes bibliographical references (pages 25-27).