Short-term Precipitation Correction Based on GRU Deep Learning
To improve the accuracy of short-term precipitation forecasts,a deep learning method is proposed to correct numerical model precipitation forecast products.This method extracts spatiotemporal features from numerical model forecasts and observations using a neural network and performs corrections based on a gated recurrent unit(GRU)framework.Additionally,an atmospheric physics adaptor module is meticu-lously designed to address systematic errors in the intensity and displacement of numerical model forecast by leveraging physical condition mechanisms.The module plays a crucial role within the overarching model framework,which consists of three integrated components:Feature network,recurrent-revising network,and physical adaptor.The feature network extracts precipitation intensity,distribution,motion character-istics and other related atmospheric physical features from precipitation in situ and numerical model fore-cast data,serving as input to the recurrent-revising network.Recurrent-revising network utilizes a recur-rent neural network structure to adjust grid point forecast results on a time-step basis.Deep neural net-works are used to extract spatiotemporal variation features from numerical model forecast data and histori-cal observations,learning systematic errors in the evolution processes to correct the precipitation magni-tude and distribution.The physical adaptor is an atmospheric physics adaptation module,which prepro-cesses numerical model forecast data using frequency distribution fitting and distribution deviation correc-tion methods.In Guangxi convective-scale model precipitation forecast data,when there are significant differences between numerous samples and the precipitation in situ,the feature correlation is low,making it a challenge to capture systematic error characteristics during neural network training.By preprocessing the samples with the physical adaptor,differences between forecasts and observations are reduced,enhan-cing feature correlation between training input datasets and observations,thus facilitating better neural network training and achieving superior correction skills.This method not only adheres to but also in-tegrates fundamental atmospheric physical laws governing precipitation evolution,thereby offering a ro-bust and innovative approach for post-processing numerical model short-term precipitation forecasts.By incorporating these physical principles into the model framework,corrected forecasts not only reflect sta-tistical patterns but also adhere closely to the underlying physical processes driving precipitation dynamics.Experimental results in Guangxi indicate that the model demonstrates positive threat score skills across va-rious forecast times and precipitation intensitis.Specifically,for different precipitation intensities(average of all times),threat score skills for 0.1 mm·h-1,2 mm·h-1,7 mm·h-1,15 mm·h-1,25 mm·h-1,and 40 mm·h-1 are 5.67％,3.59％,2.18％,1.46％,1.01％,and 0.46％,respectively;for different lead times,threat score skills for 0-2 h,2-4 h,and 4-6 h are 4.77％,1.28％,and 0.91％,respective-ly;and the overall average threat score skill across all precipitation intensitis and times is 2.21％.
万方数据
维普
