Deep Learning Based Cloud Microphysics Parameterization Scheme for Numerical Weather Prediction with 1DD-CNN

Machine learning methods, represented by deep learning, are rapidly changing and enhancing the process and results of the Numerical Weather Prediction (NWP) model. To better explore the application potential of the machine learning method in the Microphysical Parameterization Schemes (MPS) for NWP model, this study introduces a deep learning based cloud microphysical processes scheme. The scheme includes two steps: data processing and machine learning. The data process step in our scheme is to prepare data for the machine learning method, where the data is extracted and refined from NWP outputs. Subsequent to this process, a one-dimensional dense convolutional neural network (1DD-CNN) is applied to rigorously analyze the data and boost the predictive precision and computational speed of cloud microphysical processes. Empirical results validate the scheme's efficacy in advancing meteorological predictive capabilities.