Since model bias and associated initialization shock are serious shortcomings that reduce prediction skills in state-of-the-art decadal climate prediction efforts, we pursue a complementary machine-learning-based approach to climate prediction. The example problem setting we consider consists of predicting natural variability of the North Atlantic sea surface temperature on the interannual timescale in the pre-industrial control simulation of the Community Earth System Model (CESM2). While previous works have considered the use of recurrent networks such as convolutional LSTMs and reservoir computing networks in this and other similar problem settings, we currently focus on the use of feedforward convolutional networks. In particular, we find that a feedforward convolutional network with a Densenet architecture is able to outperform a convolutional LSTM in terms of predictive skill. Next, we go on to consider a probabilistic formulation of the same network based on Stein variational gradient descent and find that in addition to providing useful measures of predictive uncertainty, the probabilistic (Bayesian) version improves on its deterministic counterpart in terms of predictive skill. Finally, we characterize the reliability of the ensemble of ML models obtained in the probabilistic setting by using analysis tools developed in the context of ensemble numerical weather prediction.
Nanjing University（南京大学）；China University of Geosciences (Wuhan)（中国地质大学（武汉））；Nanjing Hydraulic Research Institute（南京水利科学研究院）；Institute of Geodesy and Geophysics, Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences（中国科学院精密测量科学与技术创新研究院大地测量与地球物理研究所）；Sun Yat-Sen University（中山大学）
The Gravity Recovery and Climate Experiment (GRACE) satellite and its successor GRACE Follow-On (GRACE-FO) provide valuable and accurate observations of terrestrial water storage anomalies (TWSAs) at a global scale. However, there is an approximately one-year observation gap of TWSAs between GRACE and GRACE-FO. This poses a challenge for practical applications, as discontinuity in the TWSA observations may introduce significant biases and uncertainties in the hydrological model predictions and consequently mislead decision making. To tackle this challenge, a Bayesian convolutional neural netwo…
Virginia Tech（弗吉尼亚理工大学）；IBM Research Africa（IBM非洲研究院）；IBM Research Europe（IBM欧洲研究院）
As acute climate change impacts weather and climate variability, there is increased demand for robust climate impact model predictions from which forecasts of the impacts can be derived. The quality of those predictions are limited by the climate drivers for the impact models which are nonlinear and highly variable in nature. One way to estimate the uncertainty of the model drivers is to assess the distribution of ensembles of climate forecasts. To capture the uncertainty in the impact model outputs associated with the distribution of the input climate forecasts, each individual forecast ensem…
Over the last few decades, climate scientists have devoted much effort to the development of large numerical models of the atmosphere and the ocean. While there is no question that such models provide important and useful information on complicated aspects of atmosphere and ocean dynamics, skillful prediction also requires a phenomenological approach, particularly for very slow processes, such as glacial-interglacial cycles. Phenomenological models are often represented as low-order dynamical systems. These are tractable, and a rich source of insights about climate dynamics, but they also igno…
Multimodel ensembling has been widely used to improve climate model predictions, and the improvement strongly depends on the ensembling scheme. In this work, we propose a Bayesian neural network (BNN) ensembling method, which combines climate models within a Bayesian model averaging framework, to improve the predictive capability of model ensembles. Our proposed BNN approach calculates spatiotemporally varying model weights and biases by leveraging individual models' simulation skill, calibrates the ensemble prediction against observations by considering observation data uncertainty, and quant…
Climate models are generally calibrated manually by comparing selected climate statistics, such as the global top-of-atmosphere energy balance, to observations. The manual tuning only targets a limited subset of observational data and parameters. Bayesian calibration can estimate climate model parameters and their uncertainty using a larger fraction of the available data and automatically exploring the parameter space more broadly. In Bayesian learning, it is natural to exploit the seasonal cycle, which has large amplitude, compared with anthropogenic climate change, in many climate statistics…
Earth's temperature variability can be partitioned into internal and externally-forced components. Yet, underlying mechanisms and their relative contributions remain insufficiently understood, especially on decadal to centennial timescales. Important reasons for this are difficulties in isolating internal and externally-forced variability. Here, we provide a physically-motivated emulation of global mean surface temperature (GMST) variability, which allows for the separation of internal and external variations. To this end, we introduce the ``ClimBayes'' software package, which infers climate p…
Climate-informed cryospheric reanalysis via hierarchical Bayesian data assimilation
Department of Geosciences, University of Oslo（奥斯陆大学地质科学系）；Instituto Pirenaico de Ecología, Spanish Research Council (IPE-CSIC)（西班牙研究委员会皮耶林生态研究所）；WSL Institute for Snow and Avalanche Research SLF（瑞士联邦雪崩与雪研究所）；Mountain Futures GmbH（山未来有限公司）；Potsdam Institute for Climate Impact Research (PIK)（波茨坦气候影响研究所）；Institute of Geophysics, Polish Academy of Sciences（波兰科学院地球物理研究所）
Correlation Networks (CNs) inherently suffer from redundant information in their network topology. Bayesian Networks (BNs), on the other hand, include only non-redundant information (from a probabilistic perspective) resulting in a sparse topology from which generalizable physical features can be extracted. We advocate the use of BNs to construct data-driven complex networks as they can be regarded as the probabilistic backbone of the underlying complex system. Results are illustrated at the hand of a global climate dataset.
Objective probabilistic forecasts of future climate that include parameter uncertainty can be made by using the Bayesian prediction integral with the prior set to Jeffreys' Prior. The calculations involved in determining the prior can then be simplified by making parametric assumptions about the distribution of the output from the climate model. The most obvious assumption to make is that the climate model output is normally distributed, in which case evaluating the prior becomes a question of evaluating gradients in the parameters of the normal distribution. In previous work we have considere…
The Sun becomes brighter with time, but Earth's climate is roughly temperate for life during its long-term history; for early Earth, this is known as the Faint Young Sun Problem (FYSP). Besides the carbonate-silicate feedback, recent researches suggest that a long-term cloud feedback may partially solve the FYSP. However, the general circulation models they used cannot resolve convection and clouds explicitly. This study re-investigates the clouds using a near-global cloud-permitting model without cumulus convection parameterization. Our results confirm that a stabilizing shortwave cloud feedb…
We apply an empirical, data-driven approach for describing crop yield as a function of monthly temperature and precipitation by employing generative probabilistic models with parameters determined through Bayesian inference. Our approach is applied to state-scale maize yield and meteorological data for the US Corn Belt from 1981 to 2014 as an exemplar, but would be readily transferable to other crops, locations and spatial scales. Experimentation with a number of models shows that maize growth rates can be characterised by a two-dimensional Gaussian function of temperature and precipitation wi…
We build a conceptual coupled model of the climate and tidal evolution of the Earth-Moon system to find the influence of the former on the latter. An energy balance model is applied to calculate steady-state temperature field from the mean annual insolation as a function of varying astronomical parameters. A harmonic oscillator model is applied to integrate the lunar orbit and Earth's rotation with the tidal torque dependent on the dominant natural frequency of ocean. An ocean geometry acts as a bridge between temperature and oceanic frequency. On assumptions of a fixed hemispherical continent…
Tongji University（同济大学）；College of Civil Engineering, Tongji University（同济大学土木工程学院）
An extreme wind speed estimation method that considers wind hazard climate types is critical for design wind load calculation for building structures affected by mixed climates. However, it is very difficult to obtain wind hazard climate types from meteorological data records, because they restrict the application of extreme wind speed estimation in mixed climates. This paper first proposes a wind hazard type identification algorithm based on a numerical pattern recognition method that utilizes feature extraction and generalization. Next, it compares six commonly used machine learning models u…
Building on recent research for prediction of hurricane trajectories using recurrent neural networks (RNNs), we have developed improved methods and generalized the approach to predict Bayesian intervals in addition to simple point estimates. Tropical storms are capable of causing severe damage, so accurately predicting their trajectories can bring significant benefits to cities and lives, especially as they grow more intense due to climate change effects. By implementing the Bayesian interval using dropout in an RNN, we improve the actionability of the predictions, for example by estimating th…
It is shown in this comment that considering the Mauna Loa observation of the atmospheric carbon dioxide concentration and the mean near surface temperature anomalies for the period from the beginning of the seventies to recent years only is, clearly, a source of misinterpretation. If we consider the whole period of available data (1958 - 2004), we obtain results which differ from those presented by Rahmstorf et al. It is also shown that in 1988 when the Intergovernmental Panel of Climate Change (IPCC) of the United Nations and the World Meteorological Organization (WMO) was established there …
Assessing the consistency between short-term global temperature trends in observations and climate model projections is a challenging problem. While climate models capture many processes governing short-term climate fluctuations, they are not expected to simulate the specific timing of these somewhat random phenomena - the occurrence of which may impact the realized trend. Therefore, to assess model performance, we develop distributions of projected temperature trends from a collection of climate models running the IPCC A1B emissions scenario. We evaluate where observed trends of length 5 to 1…
High obliquity planets represent potentially extreme limits of terrestrial climate, as they exhibit large seasonality, a reversed annual-mean pole-to-equator gradient of stellar heating, and novel cryospheres. A suite of 3-D global climate model simulations with a dynamic ocean is performed with Earthlike atmospheres for low and high obliquity planets with various stellar fluxes, CO2 concentrations, and initial conditions to explore the propensity for high obliquity climates approaching the outer edge of the Habitable Zone to undergo global glaciation. We also simulate planets with thick CO2 o…
In this study we used HadCRUT4 temperature anomalies for 1950-2013 years in order to investigate properties of recent warming. Our aim was to separate changes produced by short-term ENSO variations and to look on temporal and spatial dynamics of residual temperature anomalies. For this we subtract linear influence of ENSO index from each HadCRUT4 grid box. We found that residual global temperature dynamics looks like staircase function: linear trends for three quasi-stable periods 1950-1987, 1988-1997 and 1998-2013 are near zero and near all warming occurred during two shifts of 1987/1988 and …
Allen Institute for Artificial Intelligence (Ai2)（人工智能艾伦研究所）；Department of Electrical and Computer Engineering, University of Washington（华盛顿大学电气与计算机工程系）
We construct directed and weighted climate networks based on near surface air temperature to investigate the global impacts of El Nino and La Nina. We find that regions which are characterized by higher positive or negative network in weighted links, are exhibiting stronger correlations with the El Nino basin and are warmer or cooler during El Nino or La Nina periods. These stronger in-weighted activities are found to be concentrated in localized areas, as compared to non-El Nino periods, whereas a large fraction of the globe is not influenced by the events. The regions of localized activity v…
