Page 153 - 《高原气象》2025年第6期

6 期 谭淇昌等：基于深度学习方法改进CMIP6模式对中国东部沿海复合极端风雨事件的模拟能力 1561

Improving the Capability of CMIP6 Simulations for Compound

Extreme Wind and Precipitation Events in the Eastern Coastal
Region of China Using Deep Learning Methods

1
1
TAN Qichang ， ZHANG Yu ， GE Fei ， JIAN Yifei ， WU Yuyan ， WANG Kangning 1
1
2
1
（1. School of Atmospheric Sciences， Plateau Atmosphere and Environment Key Laboratory of Sichuan Province， Chengdu Plain Urban
Me-teorology and Environment Observation and Research Station of Sichuan Province， Sichuan Meteorological Disaster Prediction
and Early Warning Engineering Laboratory， Chengdu University of Information Technology， Chengdu 610225， Sichuan， China；
2. College of Ocean and Meteorology， Guangdong Ocean University， Zhanjiang 524088， Guangdong， China）
Abstract： Relative to individual extreme weather and climate events， Compound Wind and Precipitation Ex‐
tremes （CWPE）， which result from extreme winds and extreme precipitation， have a profound impact on the
economy and daily life in coastal areas. In this study， we utilized the simulations from 17 models within the Cou‐
pled Model Intercomparison Project Phase 6 （CMIP6） for the period 1961-2000 of CWPE in the eastern coastal
region of China as a training set， and established a Deep Learning （DL） model employing a multi-layer percep‐
tron neural network. By constructing a loss function suitable for CWPE and optimizing the model accordingly，
we have developed a DL model aimed at reducing the simulation bias and uncertainty of CMIP6 models for
CWPE. The research results indicate that the majority of CMIP6 models possess a relatively good simulation ca‐
pability for CWPE in the eastern coastal region of China， with the Multi-Model Ensemble Mean （MME-Mean）
and the Multi-Model Ensemble Median （MME-Median） demonstrating better performance in assessments com‐
pared to individual models. The DL model constructed with the Mean Squared Error （MSE） function as the loss
function performs worse in terms of Taylor Skill Score （TS） and Root Mean Squared Error （RMSE） compared
to the statistical results of the Multi-Model Ensemble. Incorporating the Ratio of the Standard Deviation （RSD）
from climate evaluation metrics and an underestimation constraint function into the MSE loss function can signifi‐
cantly enhance the performance of the DL model in terms of TS and RMSE. Therefore， the DL model trained
with a weighted loss function constructed from MSE， RSD， and underestimation constraint function is defined
as DL-MRM， while the DL model trained solely with MSE as the loss function is defined as DL-MSE. By com‐
paring and analyzing the performance of the two DL models in simulating CWPE over the eastern coastal region
of China from 2001 to 2014， as well as the performance of DL-MRM relative to multi-model ensemble methods，
we conclude： （1） Both DL models exhibit underestimation in their simulation results， but the bias of the DL-
MRM is lower than that of the DL-MSE， being closer to the observations. Specifically， in the study area， the rel‐
ative bias of the DL-MRM is lower than that of the DL-MSE by about 63%， and the average relative bias is re‐
duced by approximately 20%.（2） The DL-MRM has a lower overall bias compared to the MME-Mean and
MME-Median， with simulation results that are closer to the observations. In the study area， the DL-MRM has a
lower relative bias in 67% and 62% of the area compared to the MME-Mean and MME-Median， respectively，
and the average relative bias is reduced by approximately 10% and 20%， respectively. Overall， by integrating the
RSD and underestimation constraint functions to construct a weighted loss function for model optimization， a DL
model suitable for improving the simulation of CWPE by CMIP6 models was established. This indicates that the
combination of deep learning methods can more effectively reduce the biases in CMIP6 model simulations of
CWPE compared to traditional multi-model ensemble methods.
Key words： deep learning； compound wind and precipitation extremes； CMIP6； eastern coastal region of China