Radar Quantitative Precipitation Estimation Based on the Gated Recurrent Unit Neural Network and Echo-Top Data

Abstract

The Gated Recurrent Unit (GRU) neural network has great potential in estimating and predicting a variable. In addition to radar reflectivity (Z), radar echo-top height (ET) is also a good indicator of rainfall rate (R). In this study, we propose a new method, GRU_Z-ET, by introducing Z and ET as two independent variables into the GRU neural network to conduct the quantitative single-polarization radar precipitation estimation. The performance of GRU_Z-ET is compared with that of the other three methods in three heavy rainfall cases in China during 2018, namely, the traditional Z-R relationship (Z=300R^1.4), the optimal Z-R relationship (Z=79R^1.68) and the GRU neural network with only Z as the independent input variable (GRU_Z). The results indicate that the GRU_Z-ET performs the best, while the traditional Z-R relationship performs the worst. The performances of the rest two methods are similar.

To further evaluate the performance of the GRU_Z-ET, 200 rainfall events with 21882 total samples during May–July of 2018 are used for statistical analysis. Results demonstrate that the spatial correlation coefficients, threat scores and probability of detection between the observed and estimated precipitation are the largest for the GRU_Z-ET and the smallest for the traditional Z-R relationship, and the root mean square error is just the opposite. In addition, these statistics of GRU_Z are similar to those of optimal Z-R relationship. Thus, it can be concluded that the performance of the GRU_Z-ET is the best in the four methods for the quantitative precipitation estimation.

摘要

门控循环神经网络在估测和预测变量方面具有巨大潜能. 除了雷达反射率外, 雷达回波顶高也能很好地反映降水. 利用门控循环神经网络, 本文发展了一种新的单偏振雷达的定量降水估测方法 GRU_Z-ET, 该方法是将雷达反射率和雷达回波顶高同时作为自变量引入门控循环神经网络来估测降水. 随后, 基于 2018 年江西省北部的三次强降雨过程, 对比分析了新方法 GRU_Z-ET 与其他三种方法的表现. 其他三种方法分别是传统的 Z-R 关系 (Z=300R^1.4)、 最优法拟合的 Z-R 关系 (Z=79R^1.68) 和仅有雷达反射率一个自变量的门控循环神经网络(GRU_Z). 结果表明, 在这四种方法中, GRU_Z-ET方法估测的降水精度最高, 而传统的Z-R关系精度最低, 最优法拟合的Z-R关系和GRU_Z方法的精度相当. 为了进一步评估GRU_Z-ET方法对降水的估测性能, 利用这四种方法对2018年5-7月江西北部的200个降水过程(21882个样本)的降水量进行了定量估测和统计分析. 结果表明, 在这四种方法中, GRU_Z-ET方法估测的降水与观测降水的空间相关系数、 威胁分数和探测概率最高, 均方根误差最低; 传统Z-R关系的空间相关系数、 威胁分数和探测概率最低, 均方根误差最高; GRU_Z 方法和最优法拟合Z-R关系的空间相关系数、 威胁分数和探测概率和均方根误差相似. 这进一步验证了在这些雷达降水估测的方法中, 本文发展的 GRU_Z-ET 方法的精度最高, 传统的 Z-R 关系精度最低, GRU_Z 方法和最优法拟合的 Z-R 关系的精度相当.