Estimating Climate Feedbacks Using a Neural Network

被引:11
作者
Zhu, Tingting [1 ,2 ]
Huang, Yi [2 ]
Wei, Haikun [1 ]
机构
[1] Southeast Univ, Sch Automat, Key Lab Measurement & Control CSE, Minist Educ, Nanjing, Jiangsu, Peoples R China
[2] McGill Univ, Dept Atmospher & Ocean Sci, Montreal, PQ, Canada
基金
中国国家自然科学基金; 加拿大自然科学与工程研究理事会;
关键词
climate feedback; neural network; nonlinearity; cloud feedback; CLOUD FEEDBACK; WATER-VAPOR;
D O I
10.1029/2018JD029223
中图分类号
P4 [大气科学(气象学)];
学科分类号
0706 ; 070601 ;
摘要
A nonlinear method has been developed to estimate climate feedbacks based on the Neural Network (NN) taking advantage of its self-learning skills. The NN model developed here is trained using a reanalysis data set and predicts radiation flux globally from atmospheric and surface variables. The radiative feedbacks of temperature, water vapor, surface albedo, and cloud in the interannual climate variations estimated from the NN method are in agreement with those from a broadly used kernel method. However, the NN method demonstrates significant advantages: (1) it withdraws the linearity assumption of the kernel method and accounts for the nonlinear effects of the feedbacks. In the case of large climate perturbations, such as that in the Arctic caused by sea ice melt, the NN method achieves better radiation closure. (2) The method can directly calculate the radiative feedback of cloud and its components. We find that the high, middle, and low cloud feedback components analyzed from the NN method are linearly additive in the interannual climate variations, although there is a considerable nonlinear effect arising from the interactions between cloud and noncloud variables.
引用
收藏
页码:3246 / 3258
页数:13
相关论文
共 30 条
[21]   Global cooling after the eruption of Mount Pinatubo: A test of climate feedback by water vapor [J].
Soden, BJ ;
Wetherald, RT ;
Stenchikov, GL ;
Robock, A .
SCIENCE, 2002, 296 (5568) :727-730
[22]   Quantifying climate feedbacks using radiative kernels [J].
Soden, Brian J. ;
Held, Isaac M. ;
Colman, Robert ;
Shell, Karen M. ;
Kiehl, Jeffrey T. ;
Shields, Christine A. .
JOURNAL OF CLIMATE, 2008, 21 (14) :3504-3520
[23]  
Soden BJ, 2006, J CLIMATE, V19, P3354, DOI [10.1175/JCLI3799.1, 10.1175/JCLI3990.1]
[24]   Radiative and dynamical feedbacks over the equatorial cold tongue: Results from nine atmospheric GCMs [J].
Sun, D. -Z. ;
Zhang, T. ;
Covey, C. ;
Klein, S. A. ;
Collins, W. D. ;
Hack, J. J. ;
Kiehl, J. T. ;
Meehl, G. A. ;
Held, I. M. ;
Suarez, M. .
JOURNAL OF CLIMATE, 2006, 19 (16) :4059-4074
[25]   On the interpretation of inter-model spread in CMIP5 climate sensitivity estimates [J].
Vial, Jessica ;
Dufresne, Jean-Louis ;
Bony, Sandrine .
CLIMATE DYNAMICS, 2013, 41 (11-12) :3339-3362
[26]  
WETHERALD RT, 1988, J ATMOS SCI, V45, P1397, DOI 10.1175/1520-0469(1988)045<1397:CFPIAG>2.0.CO
[27]  
2
[28]   Observation-Based Longwave Cloud Radiative Kernels Derived from the A-Train [J].
Yue, Qing ;
Kahn, Brian H. ;
Fetzer, Eric J. ;
Schreier, Mathias ;
Wong, Sun ;
Chen, Xiuhong ;
Huang, Xianglei .
JOURNAL OF CLIMATE, 2016, 29 (06) :2023-2040
[29]   Computing and Partitioning Cloud Feedbacks Using Cloud Property Histograms. Part I: Cloud Radiative Kernels [J].
Zelinka, Mark D. ;
Klein, Stephen A. ;
Hartmann, Dennis L. .
JOURNAL OF CLIMATE, 2012, 25 (11) :3715-3735
[30]   Uncertainty in the 2°C Warming Threshold Related to Climate Sensitivity and Climate Feedback [J].
Zhou Tianjun ;
Chen Xiaolong .
JOURNAL OF METEOROLOGICAL RESEARCH, 2015, 29 (06) :884-895