«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《地球科学与环境学报》[ISSN:1672-6561/CN:61-1423/P]

卷:

第46卷

期数:

2024年第03期

页码:

285-297

栏目:

环境与可持续发展

出版日期:

2024-05-15

文章信息/Info

Title:

MEPM: MultivariateENSOPredictionModel Based on Deep Learning

文章编号:

1672-6561(2024)03-0285-13

作者:

方巍¹; 2; 3; 4; 5*; 张霄智¹; 2; 齐媚涵¹; 2

(1. 南京信息工程大学 计算机学院,江苏 南京 210044; 2. 南京信息工程大学 数字取证教育部工程研究中心,江苏 南京 210044; 3. 南京气象科技创新研究院 中国气象局交通气象重点开放实验室,江苏 南京210041; 4. 中国气象局武汉暴雨研究所 中国气象局流域强降水重点开放实验室/暴雨监测预警湖北省重点实验室,湖北 武汉 430205; 5. 苏州大学江苏省计算机信息处理技术重点实验室,江苏 苏州 215006)

Author(s):

FANG Wei¹; 2; 3; 4; 5*;  ZHANG Xiao-zhi¹; 2;  QI Mei-han¹; 2

(1. School of ComputerScience, Nanjing University of Information Science & Technology, Nanjing210044, Jiangsu, China; 2. Engineering Research Center of Digital Forensics of Ministry ofEducation, Nanjing University of Information Science & Technology, Nanjing 210044,Jiangsu,China; 3. Key Laboratory of Transportation Meteorology of ChinaMeteorologicalAdministration, NanjingJoint Institutefor AtmosphericSciences, Nanjing 210041, Jiangsu, China; 4. ChinaMeteorologicalAdministration Basin Heavy Rainfall Key Laboratory/Hubei KeyLaboratory forHeavy Rain Monitoringand Warning Research,Institute of HeavyRain,China Meteorological Administration,Wuhan 430205,Hubei,China; 5. Jiangsu Provincial KeyLaboratory for ComputerInformation Processing Technology,SoochowUniversity, Suzhou 215006, Jiangsu, China)

关键词:

气候变化;  厄尔尼诺-南方涛动;  多气候变量;  深度学习;  时空序列预测;  卷积神经网络

Keywords:

climate change;  ENSO;  multi-climate variables;  deep learning;  spatio-temporal sequence prediction;  convolutional neural network

分类号:

P467; TP18

DOI:

10.19814/j.jese.2023.08029

文献标志码:

A

摘要:

厄尔尼诺-南方涛动(ENSO)是发生在热带太平洋年际时间尺度的海-气相互作用的异常现象,并由Niño3.4指数表征其发生情况; 除此之外,ENSO与众多极端气候事件密切相关。因此,有效的ENSO预测对于预防极端气候事件和深入研究全球气候变化具有重要意义。然而,目前基于深度学习的ENSO预测大多数是预测一个指数或者单一变量,对于模拟多气候要素下的ENSO预测研究较少。通过提出一种利用多气候变量的ENSO预测模型——MEPM模型,其中包括多变量信息提取模块(MIEM)和时空融合模块(STFM),捕获不同气候变量在时空上的相互依赖性,进而提高ENSO预测的准确性。选取了纬向风应力异常(τ_x)、经向风应力异常(τ_y)、海表温度异常(SSTA)和海表下150 m温度异常(SSTA150)4个变量的距平值进行ENSO预测。结果表明:MEPM模型在提前11个月的Niño3.4指数相关技巧上分别比北美多模型集合中的动力预报系统CanCM4、CCSM3和GFDL-aer04高10%、20%和14%。此外,MEPM模型在中期Niño3.4指数相关技巧上显著优于其他深度学习模型,并可提供长达17个月的有效预测。

Abstract:

The El Niño-Southern Oscillation(ENSO)is an anomaly of air-sea interaction on an interannual time scale in the tropical Pacific Ocean, and its occurrence is characterized by the Niño3.4 index. In addition, ENSO is closely related to many extreme climatic events. Therefore, effective ENSO prediction is of great significance for preventing extreme climate events andin-depth study of global climate change. However, most ENSO predictions based on deep learning predict an index or a single variable, and there are few research on the space-time evolution of ENSO under the simulation of multi-climate factors.MEPM, a multivariate ENSO prediction model, was presented. These include multivariate information extraction module(MIEM)and spatial-temporal fusion module(STFM), to capture the interdependencies of different climate elements in time and space, thereby improving the accuracy of ENSO prediction. The anomalies oflatitudewind stress anomaly(τ_x),longitudewind stress anomaly(τ_y),sea surface temperature anomaly(SSTA)and 150 m below sea surface temperature anomaly(SSTA150)were selected, and sufficient experiments were carried out. The results show that MEPM is 10%, 20%and 14% higher, respectively, than dynamic forecasting systemsCanCM4, CCSM3, and GFDL-aer04 in North American multi-model ensemble on the average of Niño3.4 index-related techniques 11 months in advance. In addition, MEPM significantly outperforms other deep learning models on Niño3.4 index-related techniques over the medium term and provides valid predictions up to 17 months.

参考文献/References:

[1] 石世玮,智 海,林鹏飞,等.热带太平洋盐度年际变化对海表温度异常作用比较:1997/1998、2014/2015和2015/2016年El Niño事件[J].大气科学,2020,44(5):1057-1075.
SHI Shi-wei,ZHI Hai,LIN Peng-fei,et al.Contrasting Salinity Interannual Variations in the Tropical Pacific and Their Effects on Recent El Niño Events:1997/1998,2014/2015,and 2015/2016[J].Chinese Journal of Atmospheric Sciences,2020,44(5):1057-1075.
[2]祁 莉,毛 欣,张文君.北太平洋海温Victoria模态与ENSO年际关系的非对称特征[J].大气科学学报,2022,45(2):280-291.
QI Li,MAO Xin,ZHANG Wen-jun.Asymmetric Characteristics of Interannual Relationship Between Victoria Mode of North Pacific SST and ENSO[J].Transactions of Atmospheric Sciences,2022,45(2):280-291.
[3]万云霞,晏红明,金 燕,等.两次不同ENSO背景下云南冬季极端冷事件的成因分析[J].大气科学学报,2023,46(4):575-586.
WAN Yun-xia,YAN Hong-ming,JIN Yan,et al.Causes of Two Extremely Cold Events in Yunnan During Different ENSO Events[J].Transactions of Atmospheric Sciences,2023,46(4):575-586.
[4]CAI W J,SANTOSO A,COLLINS M,et al.Changing El Niño-Southern Oscillation in a Warming Climate[J].Nature Reviews Earth & Environment,2021,2:628-644.
[5]CORDERO R R,FERON S,DAMIANI A,et al.Extreme Fire Weather in Chile Driven by Climate Change and El Niño-Southern Oscillation(ENSO)[J].Scientific Reports,2024,14(1):1974.
[6]CAI W J,NG B,GENG T,et al.Anthropogenic Impacts on Twentieth-century ENSO Variability Changes[J].Nature Reviews Earth & Environment,2023,4:407-418.
[7]FEKADU K.Ethiopian Seasonal Rainfall Variability and Prediction Using Canonical Correlation Analysis(CCA)[J].Earth Sciences,2015,4(3):112-119.
[8]BIABANAKI M,ESLAMIAN S S,KOUPAI J A,et al.A Principal Components/Singular Spectrum Analysis Approach to ENSO and PDO Influences on Rainfall in Western Iran[J].Hydrology Research,2014,45(2):250-262.
[9]ZHOU L,ZHANG R H.A Hybrid Neural Network Model for ENSO Prediction in Combination with Principal Oscillation Pattern Analyses[J].Advances in Atmospheric Sciences,2022,39(6):889-902.
[10]KIDO S,RICHTER I,TOZUKA T,et al.Understanding the Interplay Between ENSO and Related Tropical SST Variability Using Linear Inverse Models[J].Climate Dynamics,2023,61(3):1029-1048.
[11]唐 韬.CMIP5/6系统性偏差对热带太平洋SST变化模拟和预估的影响[D].南京:南京信息工程大学,2023.
TANG Tao.Impact of Systematical Biases in CMIP5/6 on Tropical Pacific SST Change Simulation and Projection[D].Nanjing:Nanjing University of Information Science & Technology,2023.
[12]杨淑贤,零丰华,应武杉,等.人工智能技术气候预测应用简介[J].大气科学学报,2022,45(5):641-659.
YANG Shu-xian,LING Feng-hua,YING Wu-shan,et al.A Brief Overview of the Application of Artificial Intelligence to Climate Prediction[J].Transactions of Atmospheric Sciences,2022,45(5):641-659.
[13]FANG W,SHA Y,SHENG V S.Survey on the Application of Artificial Intelligence in ENSO Forecasting[J].Mathematics,2022,10(20):3793.
[14]任宏利,郑 飞,罗京佳,等.中国热带海-气相互作用与ENSO动力学及预测研究进展[J].气象学报,2020,78(3):351-369.
REN Hong-li,ZHENG Fei,LUO Jing-jia,et al.A Review of Research on Tropical Air-sea Interaction,ENSO Dynamics,and ENSO Prediction in China[J].Acta Meteorologica Sinica,2020,78(3):351-369.
[15]DONG C M,XU G J,HAN G Q,et al.Recent Developments in Artificial Intelligence in Oceanography[J].Ocean-land-atmosphere Research,2022,2022:9870950.
[16]ZHU Y C,ZHANG R H,MOUM J N,et al.Physics-informed Deep-learning Parameterization of Ocean Vertical Mixing Improves Climate Simulations[J].National Science Review,2022,9(8):nwac044.
[17]ZHENG G,LI X F,ZHANG R H,et al.Purely Satellite Data-driven Deep Learning Forecast of Complicated Tropical Instability Waves[J].Science Advances,2020,6(29):eaba1482.
[18]HAM J Y G,KIM J H,LUO J J.Deep Learning for Multi-year ENSO Forecasts[J].Nature,2019,573:568-572.
[19]周 佩,黄颖婕,胡冰逸,等.基于LSTM深度学习的ENSO预测及其春季预报障碍研究[J].北京大学学报(自然科学版),2021,57(6):1071-1078.
ZHOU Pei,HUANG Ying-jie,HU Bing-yi,et al.Spring Predictability Barrier Phenomenon in ENSO Prediction Model Based on LSTM Deep Learning Algorithm[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2021,57(6):1071-1078.
[20]KIM J,KWON M,KIM S D,et al.Spatiotemporal Neural Network with Attention Mechanism for El Niño Forecasts[J].Scientific Reports,2022,12:7204.
[21]RUI C,SUN Z Y,ZHANG W S,et al.Enhancing ENSO Predictions with Self-attention ConvLSTM and Temporal Embeddings[J].Frontiers in Marine Science,2024,11:1334210.
[22]PATIL K R,DOI T,JAYANTHI V R,et al.Deep Learning for Skillful Long-lead ENSO Forecasts[J].Frontiers in Climate,2023,4:1058677.
[23]ZHOU L,ZHANG R H.A Self-attention-based Neural Network for Three-dimensional Multivariate Modeling and Its Skillful ENSO Predictions[J].Science Advances,2023,9(10):eadf2827.
[24]WOO S,PARK J,LEE J Y,et al.CBAM:Convolutional Block Attention Module[C]∥FERRARI V,HEBERT M,SMINCHISESCU C,et al.Computer Vision-ECcV 2018.Munich:Spriner,2018:3-19.
[25]HU J,SHEN L,SUN G.Squeeze-and-excitation Networks[C]∥IEEE.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE,2018:7132-7141.
[26]TAN C,GAO Z Y,WU L R,et al.Temporal Attention Unit:Towards Efficient Spatiotemporal Predictive Learning[C]∥IEEE.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Vancouver:IEEE,2023:18770-18782.
[27]HUANG F H,YI P Y,WANG J C,et al.A Dynamical Spatial-temporal Graph Neural Network for Traffic Demand Prediction[J].Information Sciences,2022,594:286-304.
[28]方 巍,齐媚涵.基于深度学习的高时空分辨率降水临近预报方法[J].地球科学与环境学报,2023,45(3):706-718.
FANG Wei,QI Mei-han.Precipitation Nowcasting Method with High Spatio-temporal Resolution Based on Deep Learning[J].Journal of Earth Sciences and Environment,2023,45(3):706-718.
[29]CHANDRA R,JAIN A,CHAUHAN D S.Deep Learning via LSTM Models for COVID-19 Infection Forecasting in India[J].PLoS One,2022,17(1):e0262708.
[30]YE F,HU J,HUANG T Q,et al.Transformer for EI Niño-Southern Oscillation Prediction[J].IEEE Geoscience and Remote Sensing Letters,2021,19:1003305.
[31]GAO Z Y,TAN C,WU L R,et al.SimVP:Simpler yet Better Video Prediction[C]∥IEEE.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans:IEEE,2022:3170-3180.
[32]KIRTMAN B P,MIN D,INFANTI J M,et al.The North American Multimodel Ensemble:Phase-1 Seasonal-to-interannual Prediction; Phase-2 Toward Developing Intraseasonal Prediction[J].Bulletin of the American Meteorological Society,2014,95(4):585-601.
[33]MISRA D,NALAMADA T,ARASANIPALAI A U,et al.Rotate to Attend:Convolutional Triplet Attention Module[C]∥IEEE.Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.Nashville:IEEE,2021:3139-3148.
[34]HOU Q B,ZHOU D B,FENG J S.Coordinate Attention for Efficient Mobile Network Design[C]∥IEEE.Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Nashville:IEEE,2021:13713-13722.

相似文献/References:

[1]张继效,王伟铭,高峰.云南剑川地区象鼻洞遗址孢粉组合和古环境[J].地球科学与环境学报,2014,36(04):134.
　ZHANG Ji-xiao,WANG Wei-ming,GAO Feng.Palynological Assemblages and Palaeoenvironment of Xiangbidong Site in Jianchuan Area of Yunnan[J].Journal of Earth Sciences and Environment,2014,36(03):134.
[2]曹军骥,占长林.黑碳在全球气候和环境系统中的作用及其在相关研究中的意义[J].地球科学与环境学报,2011,33(02):177.
　CAO Jun-ji,ZHAN Chang-lin.Research Significance and Role of Black Carbon in the Global Climate and Environmental Systems[J].Journal of Earth Sciences and Environment,2011,33(03):177.
[3]沈华东,于革.青藏高原兹格塘错流域50年来湖泊水量对气候变化响应的模拟研究[J].地球科学与环境学报,2011,33(03):282.
　SHEN Hua-dong,YU Ge.Simulation Study on Hydrological Response of Water Quantity to Climate Change in Zigetang Lake of Tibetan Plateau During the Past 50 Years[J].Journal of Earth Sciences and Environment,2011,33(03):282.
[4]李久乐,徐柏青,林树标,等.青藏高原南部枪勇错冰前湖泊沉积记录的近千年来冰川与气候变化[J].地球科学与环境学报,2011,33(04):402.
　LI Jiu-le,XU Bai-qing,LIN Shu-biao,et al.Glacier and Climate Changes over the Past Millennium Recorded by Proglacial Sediment Sequence from Qiangyong Lake, Southern Tibetan Plateau[J].Journal of Earth Sciences and Environment,2011,33(03):402.
[5]李佩成.关于气候变化的哲学思考[J].地球科学与环境学报,2008,30(04):331.
　LI Pei-cheng.Considerations on Climate Change Based on Philosophic Principle[J].Journal of Earth Sciences and Environment,2008,30(03):331.
[6]任朝霞,杨达源.西北干旱区近50年气候变化特征与趋势[J].地球科学与环境学报,2007,29(01):99.
　REN Zhao-xia,YANG Da-y uan.Trend and Characteristics of Climatic Change in Arid Region of Northwest China in Resent 50 Years[J].Journal of Earth Sciences and Environment,2007,29(03):99.
[7]郑国璋,岳乐平.中国北方第四纪磁性地层记录的 古地磁极倒转与气候变化耦合关系[J].地球科学与环境学报,2005,27(03):91.
　ZHENG Guo-zhang,YUE Le-ping.Coupling of paleomagnetic polarity reverse with climatic change recoded by magnetostratigraphy in Northern China during Quaternary[J].Journal of Earth Sciences and Environment,2005,27(03):91.
[8]William A. Gough.北美地区大湖水位的变化研究[J].地球科学与环境学报,2005,27(04):8.
　William A. Gough.Water Levels of the Great Lakes of North America[J].Journal of Earth Sciences and Environment,2005,27(03):8.
[9]景民昌,杨革联,孙乃达.末次间冰期 —末次冰期柴达木盆地东部气候演化形式[J].地球科学与环境学报,2004,26(03):83.
　JING Min-chang,YANG Ge-lian,SUN Nai-da.Study on the climatic changes between the last interglacial age and the last glacial age recorded by ostracoda in eastern Qaidam Basin[J].Journal of Earth Sciences and Environment,2004,26(03):83.

备注/Memo

备注/Memo:

收稿日期:2023-08-19; 修回日期:2024-03-05
基金项目:国家自然科学基金项目(42075007); 江苏省计算机信息处理技术重点实验室开放研究基金项目(KJS2275); 中国气象局交通气象重点开放实验室开放研究基金项目(BJG202306); 中国气象局流域强降水重点开放实验室开放研究基金项目(2023BHR-Y14); 江苏省研究生科研与实践创新计划项目(KYCX23_1388)
*通信作者:方 巍(1975-),男,安徽黄山人,南京信息工程大学教授,博士研究生导师,工学博士,博士后,E-mail:hsfangwei@sina.com。

常用功能

更新日期/Last Update: 2024-05-30