一种海洋混合层深度的智能识别方法研究

doi:10.11978/2018137

热带海洋学报 ›› 2019, Vol. 38 ›› Issue (5): 32-41.doi: 10.11978/2018137CSTR: 32234.14.2018137

一种海洋混合层深度的智能识别方法研究

张康^1,²,郭双喜^1,³,黄鹏起^1,²,屈玲^1,³,鲁远征^1,³,岑显荣^1,³,于璐莎^1,²,周伟东^1,³,周生启^1,³()

^1. 热带海洋环境国家重点实验室(中国科学院南海海洋研究所), 广东广州 510301
^2. 中国科学院大学, 北京 100049
^3. 中国科学院南海生态环境工程创新研究院, 广东广州 510301

收稿日期:2018-12-14 修回日期:2019-04-10 出版日期:2019-09-20 发布日期:2019-10-09
通讯作者: 周生启
作者简介:张康(1991—), 男, 安徽省亳州市人, 硕士研究生, 从事物理海洋学研究。E-mail: zhangkang16@mails.ucas.ac.cn
基金资助:
国家自然科学基金项目(91752108);国家自然科学基金项目(41476167);国家自然科学基金项目(41706029);国家自然科学基金项目(41606010);广东省自然科学基金(2016A030311042);广东省自然科学基金(2016A030310114);广州市科技计划重点项目(201804020056);中科院战略性先导专项资助项目(XDA11030302);中国科学院南海生态环境工程创新研究院课题(ISEE2018PY05)

Using artificial intelligence for identifying the depth of upper-ocean mixed layer

Kang ZHANG^1,²,Shuangxi GUO^1,³,Pengqi HUANG^1,²,Ling QU^1,³,Yuanzheng LU^1,³,Xianrong CEN^1,³,Lusha YU^1,²,Weidong ZHOU^1,³,Shengqi ZHOU^1,³()

^1. State Key Laboratory of Tropical Oceanography (South China Sea Institute of Oceanology, Chinese Academy of Sciences), Guangzhou 510301, China
^2. University of Chinese Academy of Sciences, Beijing 100049, China
^3. Institution of South China Sea Ecology and Environmental Engineering, Chinese Academy of Sciences, Guangzhou 510301, China

Received:2018-12-14 Revised:2019-04-10 Online:2019-09-20 Published:2019-10-09
Contact: Shengqi ZHOU
Supported by:
National Natural Science Foundation of China(91752108);National Natural Science Foundation of China(41476167);National Natural Science Foundation of China(41706029);National Natural Science Foundation of China(41606010);Natural Science Foundation of Guangdong Province(2016A030311042);Natural Science Foundation of Guangdong Province(2016A030310114);Guangzhou Science and Technology Program Key Project(201804020056);Strategic Priority Research Program of Chinese Academy of Sciences(XDA11030302);Institution of South China Sea Ecology and Environmental Engineering, Chinese Academy of Sciences(ISEE2018PY05)

摘要/Abstract

摘要：

文章提出了一种识别混合层深度的人工智能方法。该方法在温度(密度)与压强(或深度)间建立线性模型, 并且将其系数和方差做成一组表征廓线特征的统计量。初始时为模型设定一个主观的先验分布, 在一个自海表向下移动的窗口内通过贝叶斯链式法则和最小描述长度原理学习新数据, 得到系数均值的最大后验概率估计。用F-检验识别系数发生突变的位置, 以此确定混合层的存在性及其深度。通过2017年2月太平洋海域的地转海洋学实时观测阵(Array for Real-time Geostrophic Oceanography, ARGO)数据进行测试, 并且以质量因子(Quality Index, QI)值作为判断识别混合层深度结果准确性的依据, 发现该方法相比于梯度法、阈值法、混合法、相对变化法、最大角度法和最优线性插值法在识别结果上具备更大的QI值。表明该方法能够准确识别混合层深度。

关键词: 海洋混合层, 人工智能方法, 贝叶斯链式法则, 最小描述长度原理

Abstract:

An artificial intelligence (AI) method for identifying upper-ocean mixed layer depth (MLD) is proposed. In this method, a linear model, whose coefficient and variance are made into a set of statistics to characterize the profile, is established between temperature (density) and pressure (or depth). A subjective priori distribution is set in an initial window. The maximum posterior probability estimate of the mean coefficient value is obtained when the window is moved down from the sea surface, by learning the new data through the Bayesian chain rule and the minimum description length principle. The existence and depth of the mixed layer are determined when the jump of the coefficient is found by using the F-distribution. Using the Argo buoy data measured in the Pacific Ocean in February 2017, and taking the value of the quality index (QI) to estimate the accuracy of the MLD results, we find that this AI method is superior to the gradient method, the threshold method, the Hybrid method, and the relative-variant method.

Key words: upper-ocean mixed layer, artificial intelligence method, Bayesian chain rule, minimum description length principle

中图分类号:

P731.26

张康,郭双喜,黄鹏起,屈玲,鲁远征,岑显荣,于璐莎,周伟东,周生启. 一种海洋混合层深度的智能识别方法研究[J]. 热带海洋学报, 2019, 38(5): 32-41.

Kang ZHANG,Shuangxi GUO,Pengqi HUANG,Ling QU,Yuanzheng LU,Xianrong CEN,Lusha YU,Weidong ZHOU,Shengqi ZHOU. Using artificial intelligence for identifying the depth of upper-ocean mixed layer[J]. Journal of Tropical Oceanography, 2019, 38(5): 32-41.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

表2

图11

参考文献 38

[1]	范聪慧 , 2007. 多因素对海洋上混合层深度影响的数值模拟[D]. 北京: 中国科学院研究生院( 海洋研究所):1-65.
	FAN CONGHUI , 2007. Numerical simulation of the ocean surface mixed layer depth influenced by the multi-factors[D]. Beijing: The Institute of Oceanology, Chinese Academy of Sciences (in Chinese with English abstract).
[2]	BAYES T , 1763. An essay towards solving a problem in the doctrine of chances[J]. Philosophical Transactions of the Royal Society of London, 53:370-418.
[3]	BERNARDO J M, SMITH A F M , 1994. Bayesian theory[M]. New York: Wiley:265-268.
[4]	BRAINERD K E, GREGG M C , 1995. Surface mixed and mixing layer depths[J]. Deep Sea Research Part I: Oceanographic Research Papers, 42(9):1521-1543.
[5]	CARTON J A, GRODSKY S A, LIU HAILONG , 2008. Variability of the oceanic mixed layer, 1960-2004[J]. Journal of Climate, 21(5):1029-1047.
[6]	CHU P C, FAN CHENWU , 2010. Optimal linear fitting for objective determination of ocean mixed layer depth from glider profiles[J]. Journal of Atmospheric and Oceanic Technology, 27(11):1893-1898.
[7]	CHU P C, FAN CHENWU , 2011. Maximum angle method for determining mixed layer depth from seaglider data[J]. Journal of Oceanography, 67(2):219-230.
[8]	DE BOYER MONTÉGUT C, MADEC G, FISCHER A S , et al, 2004. Mixed layer depth over the global ocean: an examination of proﬁle data and a proﬁle-based climatology[J]. Journal of Geophysical Research: Oceans, 109(C12):C12003.
[9]	DEGROOT M H , 1970. Optimal statistical decisions[M]. New York: McGraw- Hill:159-172.
[10]	DESER C, ALEXANDER M A, TIMLIN M S , 1996. Upper-ocean thermal variations in the north paciﬁc during 1970-1991[J]. Journal of Climate, 9(8):1840-1855.
[11]	DONG SHENFU, SPRINTALL J, GILLE S T , et al, 2008. Southern ocean mixed-layer depth from Argo ﬂoat proﬁles[J]. Journal of Geophysical Research: Oceans, 113(C6):C06013.
[12]	HANAWA K, TALLEY L D , 2001. Chapter 5.4 Mode waters[J]. International Geophysics, 77:373-386.
[13]	HANSEN M H, YU BIN , 2003. Minimum description length model selection criteria for generalized linear models[M] //GOLDSTEIN D R. Statistics and science: a festschrift for terry speed. U.S.: Institute of Mathematical Statistics: 145-163.
[14]	HOLTE J, TALLEY L , 2009. A new algorithm for ﬁnding mixed layer depths with applications to Argo data and subantarctic mode water formation[J]. Journal of Atmospheric and Oceanic Technology, 26(9):1920-1939.
[15]	HOLTE J, TALLEY L D, GILSON J , et al, 2017. An Argo mixed layer climatology and database[J]. Geophysical Research Letters, 44(11):5618-5626.
[16]	HUANG PENGQI, LU YUANZHENG, ZHOU SHENGQI , 2018. An objective method for determining ocean mixed layer depth with applications to WOCE data[J]. Journal of Atmospheric and Oceanic Technology, 35(3):441-458.
[17]	KANTHA L, CLAYSON C A , 1999. Surface density changes and the ocean mixed layer[M] //CURRY J A, WEBSTER P J. Thermodynamics of atmospheres and oceans. San Diego, U.S: Academic Press: 291-298.
[18]	KARA A B, ROCHFORD P A, HURLBURT H E , 2000. An optimal deﬁnition for ocean mixed layer depth[J]. Journal of Geophysical Research: Oceans, 105(C7):16803-16821.
[19]	KOCH K R , 2007. Introduction to Bayesian statistics[M]. New York: Springer:85-121.
[20]	LAVENDER K L, DAVIS R E, OWENS W B , 2002. Observations of open-ocean deep convection in the Labrador Sea from subsurface ﬂoats[J]. Journal of Physical Oceanography, 32(2):511-526.
[21]	LIANG FENG, PAULO R, MOLINA G , et al, 2008. Mixtures of g priors for Bayesian variable Selection[J]. Journal of the American Statistical Association, 103(481):410-423.
[22]	LORBACHER K, DOMMENGET D, NIILER P P , et al, 2006. Ocean mixed layer depth: a subsurface proxy of ocean- atmosphere variability[J]. Journal of Geophysical Research: Oceans, 111(C7):C07010.
[23]	LUKAS R, LINDSTROM E , 1991. The mixed layer of the western equatorial paciﬁc ocean[J]. Journal of Geophysical Research: Oceans, 96(S01):3343-3357.
[24]	OBATA A, ISHIZAKA J, ENDOH M , 1996. Global verification of critical depth theory for phytoplankton bloom with climatological in situ temperature and satellite ocean color data[J]. Journal of Geophysical Research: Oceans, 101(C9):20657-20667.
[25]	OHNO Y, IWASAKA N, KOBASHI F , et al, 2009. Mixed layer depth climatology of the north paciﬁc based on Argo observations[J]. Journal of Oceanography, 65(1):1-16.
[26]	OKA E, QIU BO, TAKATANI Y , et al, 2015. Decadal variability of subtropical mode water subduction and its impact on biogeochemistry[J]. Journal of Oceanography, 71(4):389-400.
[27]	QIU CHUNHUA, CUI YONGSHENG, REN JIE , et al, 2016. Characteristics of the surface mixed layer depths in the northern South China Sea in spring[J]. Journal of Oceanography, 72(4):567-576.
[28]	QIU CHUNHUA, HUO DAN, LIU CHANGJIAN , et al, 2019. Upper vertical structures and mixed layer depth in the shelf of the northern South China Sea[J]. Continental Shelf Research, 174:26-34.
[29]	QIU CHUNHUA, KAWAMURA H, MAO HUABIN , et al, 2014. Mechanisms of the disappearance of sea surface temperature fronts in the subtropical North Pacific Ocean[J]. Journal of Geophysical Research: Oceans, 119(7):4389-4398.
[30]	RISSANEN J , 1978. Modeling by shortest data description[J]. Automatica, 14(5):465-471.
[31]	RISSANEN J , 1989. Stochastic complexity in statistical inquiry[M]. London: World Scientific: 122-130.
[32]	RISSANEN J , 2009. Model selection and testing by the MDL principle[M] //EMMERT-STREIB F, DEHMER M. Information theory and statistical learning. New York, U.S.: Springer:25-43.
[33]	TALLEY L D, PICKARD G L, EMERY W J , et al, 2011. Descriptive physical oceanography: an introduction[M]. 6th ed. London: Academic Press: 194-195.
[34]	THOMSON R E, FINE I V , 2003. Estimating mixed layer depth from oceanic proﬁle data[J]. Journal of Atmospheric and Oceanic Technology, 20(2):319-329.
[35]	VANIN N S, KHEN G V , 2009. Vertical structure of water masses and silicon-phosphorus ratios in the west Bering Sea and in the Sea of Okhotsk[J]. Oceanology, 49(3):350-360.
[36]	WUNSCH C, FERRARI R , 2004. Vertical mixing, energy, and the general circulation of the oceans[J]. Annual Review of Fluid Mechanics, 36:281-314.
[37]	YU LISAN, WELLER R A , 2007. Objectively analyzed air-sea heat ﬂuxes for the global ice-free oceans (1981-2005)[J]. Bulletin of the American Meteorological Society, 88(4):527-540.
[38]	ZELLNER A , 1986. On assessing prior distributions and Bayesian regression analysis with G-prior distributions[M] //GOEL P K, ZELLNER A. Bayesian inference and decision techniques. New York, U.S.: Elsevier Science Publishers: 233-243.

方法	QI_mean	QI_0.25	QI_0.5	QI_0.75	QI_std
阈值法	0.795	0.708	0.899	0.962	0.239
梯度法	0.683	0.488	0.800	0.948	0.316
混合法	0.713	0.549	0.865	0.963	0.329
相对变化法	0.900	0.870	0.945	0.982	0.129
最大角度法	0.710	0.556	0.820	0.956	0.307
最优线性拟合	0.782	0.725	0.927	0.985	0.314
AI法	0.936	0.922	0.969	0.990	0.104

方法	QI_mean	QI_0.25	QI_0.5	QI_0.75	QI_std
阈值法	0.783	0.672	0.915	0.974	0.267
梯度法	0.727	0.596	0.808	0.926	0.251
混合法	0.734	0.594	0.872	0.962	0.306
相对变化法	0.893	0.862	0.945	0.983	0.144
最大角度法	0.740	0.621	0.850	0.965	0.299
最优线性拟合	0.797	0.752	0.930	0.985	0.297
AI法	0.921	0.902	0.959	0.988	0.117

一种海洋混合层深度的智能识别方法研究

Using artificial intelligence for identifying the depth of upper-ocean mixed layer

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 38

相关文章 5

Metrics

本文评价

推荐阅读 0

[1]	李杨, 黄鹏起, 鲁远征, 屈玲, 郭双喜, 岑显荣, 周生启, 张佳政, 丘学林. 基于精细温度观测的南海东北部陆坡-深海盆底层湍流混合^*[J]. 热带海洋学报, 2022, 41(1): 62-74.
[2]	林姚坤, 包芸, 陈起程, 吴加学. 夏季长江河口层化与湍流混合特征分析[J]. 热带海洋学报, 2018, 37(5): 33-39.
[3]	齐鹏, 李莎莎, 曹蕾. 影响吕宋海峡水体输运量年代际变化的局地因子[J]. 热带海洋学报, 2016, 35(4): 1-10.
[4]	宣莉莉，邱云，许金电，李自强. 孟加拉湾与赤道东印度洋水交换的季节变化特征^*[J]. 热带海洋学报, 2015, 34(6): 26-34.
[5]	裴木凤, 李适宇, 胡嘉镗, 胡希声. 丰、枯水期珠江河口水体交换的数值模拟[J]. 热带海洋学报, 2013, 32(6): 28-35.