MULTI-MODEL BLENDING VIA A NEURAL NETWORK FOR PROBABILISTIC WEATHER FORECASTS
卷宗概要
发明人
Samuel James Levang; Fran Bartolic
IPC 分类
CPC 分类
Multi-model blending via a neural network for probabilistic weather forecasts is described. A system segments a first training data set into a plurality of second training data sets each including subsets of a first output of a first probabilistic model and a second output of a second probabilistic model. The system modifies, for each of the subsets, weights of a neural network model according to first points of each of the plurality of second training data sets, second points of each of the plurality of second training data sets, and a tuning parameter of the neural network corresponding to the weather condition. The system generates a control parameter indicative of alignment of the neural network model with one or more of the plurality of second training data sets. The system provides the neural network model to generate a weighted output of the first probabilistic model and the second probabilistic model.
原文（中文）
Multi-model blending via a neural network for probabilistic weather forecasts is described. A system segments a first training data set into a plurality of second training data sets each including subsets of a first output of a first probabilistic model and a second output of a second probabilistic model. The system modifies, for each of the subsets, weights of a neural network model according to first points of each of the plurality of second training data sets, second points of each of the plurality of second training data sets, and a tuning parameter of the neural network corresponding to the weather condition. The system generates a control parameter indicative of alignment of the neural network model with one or more of the plurality of second training data sets. The system provides the neural network model to generate a weighted output of the first probabilistic model and the second probabilistic model.