风云四号卫星东南沿海热带气旋强度深度学习估算  

Deep learning estimation of tropical cyclone intensity along the southeast coast of China using FY-4A satellite

作　　者：崔林丽[1] 陈昭 于兴兴 陈光琛 王晓峰[1] 陆一闻 郭巍 CUI Linli;CHEN Zhao;YU Xingxing;CHEN Guangchen;WANG Xiaofeng;LU Yiwen;GUO Wei(Shanghai Ecological Forecasting and Remote Sensing Center,Shanghai Meteorological Service,Shanghai 200030,China;College of Computer Science and Technology,Donghua University,Shanghai 201620,China)

机构地区：[1]上海市气象局上海市生态气象和卫星遥感中心,上海200030 [2]东华大学计算机科学与技术学院,上海201620

出　　处：《遥感学报》2020年第7期842-851,共10页NATIONAL REMOTE SENSING BULLETIN

基　　金：上海市自然科学基金(编号:18ZR1434100);上海气象科技联合中心合作基金(编号:LHZX201601)。

摘　　要：热带气旋TC (Tropical Cyclone)是影响中国的一个重要天气系统。TC强度准确估测对台风灾害防御具有至关重要的意义。本文基于第二代静止气象卫星风云四号(FY-4A)多通道扫描成像辐射计AGRI(Advanced Geosynchronous Radiation Imager)资料,建立了台风强度识别的深度卷积神经网络模型CNN(Convolutional Neural Network),对台风强度不同等级和台风中心最大风速进行了试验。结果表明,CNN模型具有良好的高维非线性处理能力和算法稳定性,能对TC强度进行有效估计,不同TC强度等级识别精度均在97%以上,近中心最大风速平均绝对误差MAE (Mean Absolute Error)为1.75 m/s,均方根误差RMSE (Root Mean Square Error)为2.04 m/s。CNN可有效挖掘卫星TC形态的深层信息,对台风强度的定量化估测具有较高的应用前景。A Tropical Cyclone(TC) is one of the most destructive meteorological disasters. The strong winds and heavy precipitation have significant effect on people’slives, property, and social and economic development. Therefore, the accuracy of thepath and intensity prediction of TCs is always an important consideration in meteorological research. However, considering the complexity and variability of typhoon cloud patterns, the existing objective methods are usually based on statistical linear regression.Moreover,they still have deficiencies in expressing the dynamic changes of the complex characteristics of TC cloud patterns. The deep learning algorithm performs well in highdimensional nonlinear modelingandaccurately identifies the input mode with displacement and slight deformation. This algorithm finds significance in Tropical Cyclone(TC) monitoring with dynamic changes over time. To develop TC intensity estimation technology further in the field of satellite remote sensing, this studyapplied a new machine-learning technology to analyze and to study the TC intensity of FY-4A/AGRI data from China’s second-generation stationary meteorological satellite.First, a deep Convolution Neural Network(CNN) model was used to distinguish effectively and estimate quantitatively the TC intensity level and center wind speed. The images of day and night were placed into the convolution sampling channel of the CNN to obtain and combinesame-size spectral features. Then, multilayer convolution, pooling, nonlinear mapping, and other operations were used to mine the input characteristicsdeeply.Finally, the TC intensity was estimated. The experiment was divided into the TC intensity classification test and the quantitative estimation test of the TC center maximum wind speed. The CNN model was used to convert the recognition of the TC intensity into the pattern recognition of satellite cloud images, which could classify and identify the TC level.The experiment found that the recognition accuracy of the TC intensity was all above 95%rega

关 键 词：遥感 热带气旋 FY-4A/AGRI卫星云图 深度卷积神经网络 强度估测 

分 类 号：P414.4[天文地球—大气科学及气象学] P444