Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate

Machine Learning‐Derived Inference of the Meridional Overturning Circulation From Satellite‐Observable Variables in an Ocean State Estimate
复制标题

机器学习——从卫星推断经向翻转环流——海洋状态估计中的可观测变量

DOI:
10.1029/2022ms003370
复制
发表时间:
2023
影响因子:
6.8
通讯作者:
Manucharyan, Georgy E.
Manucharyan, Georgy E.
中科院分区:
地球科学2区
文献类型:
--
作者:
Solodoch, Aviv;Stewart, Andrew L.;McC. Hogg, Andrew;Manucharyan, Georgy E.

文献摘要

参考文献

相似文献

海洋经向翻转环流(MOC)在气候系统中起着关键作用,监测其演变是科学优先事项。在大西洋的几个纬度建立了监测阵列,但其他纬度和海洋由于后勤原因仍未得到监测。本研究探讨了通过机器学习(ML)技术从全球可用的卫星测量值推断MOC的可能性,使用ECCOV 4状态估计作为测试平台。本方法的方法优势包括纯粹使用可用的卫星数据,其适用于单个ML框架内的多个流域,以及ML模型简单性(具有少量神经元的前馈全连接神经网络(NN))。ML模型在大西洋、印度洋-太平洋和南大洋的MOC重建中表现出很高的技能。该方法在预测南大洋深海MOC模型方面的技能比以前通过基于动力学的方法所实现的技能更高。该模型的技能被量化为在每个海洋盆地的纬度的函数,和MOC变化的时间尺度。我们发现,海底压力一般具有最高的重建技能的潜力,其次是纬向风应力。我们还测试哪些变量组合是最佳的。此外,ML可解释性技术被用来表明,在南大洋的高重建技术主要是由于(NN处理)在几个突出的测深脊的底压变化。最后,重建MOC强度估计从真实的卫星测量的潜力进行了讨论。
The oceanic Meridional Overturning Circulation (MOC) plays a key role in the climate system, and monitoring its evolution is a scientific priority. Monitoring arrays have been established at several latitudes in the Atlantic Ocean, but other latitudes and oceans remain unmonitored for logistical reasons. This study explores the possibility of inferring the MOC from globally‐available satellite measurements via machine learning (ML) techniques, using the ECCOV4 state estimate as a test bed. The methodological advantages of the present approach include the use purely of available satellite data, its applicability to multiple basins within a single ML framework, and the ML model simplicity (a feed‐forward fully connected neural network (NN) with small number of neurons). The ML model exhibits high skill in MOC reconstruction in the Atlantic, Indo‐Pacific, and Southern Oceans. The approach achieves a higher skill in predicting the model Southern Ocean abyssal MOC than has previously been achieved via a dynamically‐based approach. The skill of the model is quantified as a function of latitude in each ocean basin, and of the time scale of MOC variability. We find that ocean bottom pressure generally has the highest reconstruction skill potential, followed by zonal wind stress. We additionally test which combinations of variables are optimal. Furthermore, ML interpretability techniques are used to show that high reconstruction skill in the Southern Ocean is mainly due to (NN processing of) bottom pressure variability at a few prominent bathymetric ridges. Finally, the potential for reconstructing MOC strength estimates from real satellite measurements is discussed.
ECCO Version 4 Release 3 的 ftp 站点概述 ftp://ecco.jpl.nasa.gov/Version4/Release3/
DOI: 10.5194/os-17-1321-2021
发表时间: 2017
期刊: Ocean Science
影响因子: 3.2
作者:
Ou Wang;I. Fukumori;I. Fenty
通讯作者: I. Fenty
用于观测大西洋经向翻转环流的原型系统——科学基础、测量和风险缓解策略以及初步结果
DOI: --
发表时间: 2008
期刊:
影响因子: --
作者:
T. Kanzow;J. Hirschi;C. Meinen;D. Rayner;S. Cunningham;J. Marotzke;W. Johns;H. Bryden;L. Beal;M. Baringer
通讯作者: M. Baringer
本地和远程强迫的副热带 AMOC 变化:时间尺度问题
DOI: 10.1175/jcli-d-19-0844.1
发表时间: 2020
期刊: Journal of Climate
影响因子: 4.9
作者:
Q. Jamet;W. Dewar;N. Wienders;B. Deremble;S. Close;T. Penduff
通讯作者: T. Penduff
DOI: 10.1029/2019ms002002
发表时间: 2019-12
影响因子: 6.8
作者:
B. Toms;E. Barnes;I. Ebert‐Uphoff
通讯作者: B. Toms;E. Barnes;I. Ebert‐Uphoff
DOI: --
发表时间: 2021
期刊: Ocean Science (OS)
影响因子: --
作者:
A. Sanchez‐Franks;E. Frajka‐Williams;B. Moat;D. Smeed
通讯作者: D. Smeed