The complex network framework has been successfully applied to the analysis of climatological data, providing, for example, a better understanding of the mechanisms underlying reduced predictability during El Niño or La Niña years. Despite the large interest that climate networks have attracted, several issues remain to be investigated. Here we focus in the influence of the periodic solar forcing in climate networks constructed via similarities of monthly averaged surface air temperature (SAT) anomalies. We shift the time series in each pair of nodes such as to superpose their seasonal cycles. In this way, when two nodes are located in different hemispheres we are able to quantify the similarity of SAT anomalies during the winters and during the summers. We find that data time-shifting does not significantly modify the network area weighted connectivity (AWC), which is the fraction of the total area of the Earth to which each node is con- nected. This unexpected network property can be understood in terms of how data time-shifting modifies the strength of the links connecting geographical regions in different hemispheres, and how these modifications are washed out by averaging the AWC.
A Deep Learning Model for Forecasting Global Monthly Mean Sea Surface Temperature Anomalies
CSIRO Data61(澳大利亚联邦科学与工业研究组织Data61);The Australian National University(澳大利亚国立大学);Defence Science and Technology Group, Department of Defence(国防部国防科学与技术集团);CSIRO(澳大利亚联邦科学与工业研究组织)
海表温度(SST)变率在全球天气和气候系统中起着关键作用,厄尔尼诺-南方涛动等现象被认为是全球尺度年际气候变率的主要来源。能够对海面温度异常,特别是与极端海洋热浪事件有关的海面温度异常进行长期预报,具有潜在的重大经济和社会效益。我们基于70多年(1950-2021)ECMWF ERA 5月平均平均海面水温和2米气温数据开发了一个深度学习时间序列预测模型(Unet-LSTM)。Unet-LSTM模型能够学习驱动二维全球海面温度时间演变的基础物理学。该模型准确地预测海面温度超过24个月的时间内,均方根误差保持在0.75 $^\circ$ C以下的所有预测的月份。我们还研究了该模型预测Niño3.4区域海表温度异常的能力,以及过去十年中的一些海洋热浪热点。对Niño3.4指数的模型预测使我们能够提前24个月捕捉到2010-11年强烈的拉尼娜现象,2009-10年厄尔尼诺现象和2015-16年极端厄尔尼诺现象。它还显示了对东北太平洋海洋热浪Blob的长期预测技能。然而,对东南部印度洋的海洋热浪--宁格鲁厄尔尼诺现象--的预测显示出有限的技能。这些结果表明,显着的潜力,数据驱动的方法,以产生长期的海表温度异常的预测。
DiffESM: Conditional Emulation of Temperature and Precipitation in Earth System Models with 3D Diffusion Models
Utah State University(犹他州立大学);Joint Global Change Research Institute(全球变化联合研究所);Pacific Northwest National Laboratory(西北太平洋国家实验室);Western Washington University(西华盛顿大学);Indiana University(印第安纳大学)
Bridging Gaps in the Climate Observation Network: A Physics-based Nonlinear Dynamical Interpolation of Lagrangian Ice Floe Measurements via Data-Driven Stochastic Models
VARENN: Graphical representation of spatiotemporal data and application to climate studies
Field Science Education and Research Center (FSERC), Kyoto University(京都大学 田野科学教育研究中心(FSERC));Center for the Promotion of Interdisciplinary Education and Research, Kyoto University(京都大学 跨学科教育研究推进中心)
Accelerating exploration of Marine Cloud Brightening impacts on tipping points Using an AI Implementation of Fluctuation-Dissipation Theorem
University of Victoria(维多利亚大学);Palo Alto Research Center(帕洛阿尔托研究中心);Excarta;University of California San Diego(加利福尼亚大学圣迭戈分校);University of Washington(华盛顿大学)
Learning Climate Variability from Scarce Data with Diffusion Models: A Test Case for ENSO
Barcelona Supercomputing Center(巴塞罗那超级计算中心);Facultat de Física, Universitat de Barcelona(巴塞罗那大学物理学院);Institució Catalana de Recerca i Estudis Avançats (ICREA)(加泰罗尼亚高级研究学院)
Projection Of Temperature And Precipitation For 2020-2100 For Tehran Region Using Post-processing Of General Circulation Models Output And Artificial Neural Network Approach
Disentangling Internal and Forced Climate Variability with Convolutional Neural Networks using Multivariate Fields
UMR LOCEAN, IPSL, Sorbonne Université, IRD, CNRS, MNHN(洛桑海洋与气候联合研究实验室,巴黎地球物理研究所,索邦大学,法国国家科研中心,国家自然历史博物馆);Institute for Atmospheric and Climate Science, ETH Zurich(苏黎世联邦理工学院大气与气候科学研究所)
Global Climate Model Bias Correction Using Deep Learning
Department of Computational;Data Sciences, Indian Institute of Science, Bengaluru 560012, India. Divecha Center for Climate Change, Indian Institute of Science, Bengaluru 560012, India.