Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step

Chang Hoo Jeong,Dongmin Jang,Wonkyun Joo,Mun Yong Yi,Wonsu Kim

doi:10.3390/atmos12020261

Abstract

Nowcasting is an important technique for weather forecasting because sudden weather changes significantly affect human life. The encoding-forecasting model, which is a state-of-the-art architecture in the field of data-driven radar extrapolation, does not particularly focus on the latest data when forecasting natural phenomena. This paper proposes a weighted broadcasting method that emphasizes the latest data of the time step to improve the nowcasting performance. This weighted broadcasting method allows the most recent rainfall patterns to have a greater impact on the forecasting network by extending the architecture of the existing encoding-forecasting model. Experimental results show that the proposed model is 1.74% and 2.20% better than the existing encoding-forecasting model in terms of mean absolute error and critical success index, respectively. In the case of heavy rainfall with an intensity of 30 mm/h or higher, the proposed model was more than 30% superior to the existing encoding-forecasting model. Therefore, applying the weighted broadcasting method, which explicitly places a high emphasis on the latest information, to the encoding-forecasting model is considered as an improvement that is applicable to the state-of-the-art implementation of data-driven radar-based precipitation nowcasting.

Highlights

With the increase in the number of successful cases of application of deep learning in real life, such as in autonomous driving, healthcare, and smart cities [1,2,3,4,5,6,7,8,9], various attempts have been made to apply deep learning to weather-related fields using numerical models [10] to improve the performance of weather forecasting [11,12,13,14,15]
The extant nowcasting methods can be classified into traditional methods based on numerical models or optical flows and machine learning methods based on statistical methods [19]
In recent years, deep learning using statistical methods is being actively studied because it surpasses traditional methods in performance [19,20,21]

Summary

Introduction

With the increase in the number of successful cases of application of deep learning in real life, such as in autonomous driving, healthcare, and smart cities [1,2,3,4,5,6,7,8,9], various attempts have been made to apply deep learning to weather-related fields using numerical models [10] to improve the performance of weather forecasting [11,12,13,14,15]. Because models using only CNN do not explicitly model temporal phenomena, unlike RNN, the following two methods are used to predict future time steps. Tran and Song [18] combined the structural similarity index used to measure the image quality and distance-based loss functions such as mean absolute error (MAE) and mean square error (MSE) to improve the existing model They decreased the number of channels in high abstract recurrent layers, unlike the usual methods. This study seeks to overcome the shortcomings of the encoding-forecasting model, which is a state-of-the-art architecture in the field of radar echo extrapolation and nowcasting [21] To achieve this goal, we propose an improved deep learning model incorporating a weighted broadcasting block that explicitly reflects the latest phenomena. The superior performance indices, such as distance and confusion metrics, of the weighted broadcasting-based encoding-forecasting model were confirmed by comparing them with those of the existing encoding-forecasting model

Dataset

Model Description

Evaluation Metrics

Results