GLORIA

GEOMAR Library Ocean Research Information Access

feed icon rss

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
  • 1
    Publication Date: 2022-12-06
    Description: Deep learning can accurately represent sub‐grid‐scale convective processes in climate models, learning from high resolution simulations. However, deep learning methods usually lack interpretability due to large internal dimensionality, resulting in reduced trustworthiness in these methods. Here, we use Variational Encoder Decoder structures (VED), a non‐linear dimensionality reduction technique, to learn and understand convective processes in an aquaplanet superparameterized climate model simulation, where deep convective processes are simulated explicitly. We show that similar to previous deep learning studies based on feed‐forward neural nets, the VED is capable of learning and accurately reproducing convective processes. In contrast to past work, we show this can be achieved by compressing the original information into only five latent nodes. As a result, the VED can be used to understand convective processes and delineate modes of convection through the exploration of its latent dimensions. A close investigation of the latent space enables the identification of different convective regimes: (a) stable conditions are clearly distinguished from deep convection with low outgoing longwave radiation and strong precipitation; (b) high optically thin cirrus‐like clouds are separated from low optically thick cumulus clouds; and (c) shallow convective processes are associated with large‐scale moisture content and surface diabatic heating. Our results demonstrate that VEDs can accurately represent convective processes in climate models, while enabling interpretability and better understanding of sub‐grid‐scale physical processes, paving the way to increasingly interpretable machine learning parameterizations with promising generative properties.
    Description: Plain Language Summary: Deep neural nets are hard to interpret due to their hundred thousand or million trainable parameters without further postprocessing. We demonstrate in this paper the usefulness of a network type that is designed to drastically reduce this high dimensional information in a lower‐dimensional space to enhance the interpretability of predictions compared to regular deep neural nets. Our approach is, on the one hand, able to reproduce small‐scale cloud related processes in the atmosphere learned from a physical model that simulates these processes skillfully. On the other hand, our network allows us to identify key features of different cloud types in the lower‐dimensional space. Additionally, the lower‐order manifold separates tropical samples from polar ones with a remarkable skill. Overall, our approach has the potential to boost our understanding of various complex processes in Earth System science.
    Description: Key Points: A Variational Encoder Decoder (VED) can predict sub‐grid‐scale thermodynamics from the coarse‐scale climate state. The VED's latent space can distinguish convective regimes, including shallow/deep/no convection. The VED's latent space reveals the main sources of convective predictability at different latitudes.
    Description: EC ERC HORIZON EUROPE European Research Council http://dx.doi.org/10.13039/100019180
    Description: Columbia sub‐award 1
    Description: Advanced Research Projects Agency - Energy http://dx.doi.org/10.13039/100006133
    Description: Deutsches Klimarechenzentrum http://dx.doi.org/10.13039/100018730
    Description: National Science Foundation Science and Technology Center Learning the Earth with Artificial intelligence and Physics
    Keywords: ddc:551.5 ; machine learning ; generative deep learning ; convection ; parameterization ; explainable artificial intelligence ; dimensionality reduction
    Language: English
    Type: doc-type:article
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 2
    Publication Date: 2023-12-05
    Description: A promising approach to improve cloud parameterizations within climate models and thus climate projections is to use deep learning in combination with training data from storm‐resolving model (SRM) simulations. The ICOsahedral Non‐hydrostatic (ICON) modeling framework permits simulations ranging from numerical weather prediction to climate projections, making it an ideal target to develop neural network (NN) based parameterizations for sub‐grid scale processes. Within the ICON framework, we train NN based cloud cover parameterizations with coarse‐grained data based on realistic regional and global ICON SRM simulations. We set up three different types of NNs that differ in the degree of vertical locality they assume for diagnosing cloud cover from coarse‐grained atmospheric state variables. The NNs accurately estimate sub‐grid scale cloud cover from coarse‐grained data that has similar geographical characteristics as their training data. Additionally, globally trained NNs can reproduce sub‐grid scale cloud cover of the regional SRM simulation. Using the game‐theory based interpretability library SHapley Additive exPlanations, we identify an overemphasis on specific humidity and cloud ice as the reason why our column‐based NN cannot perfectly generalize from the global to the regional coarse‐grained SRM data. The interpretability tool also helps visualize similarities and differences in feature importance between regionally and globally trained column‐based NNs, and reveals a local relationship between their cloud cover predictions and the thermodynamic environment. Our results show the potential of deep learning to derive accurate yet interpretable cloud cover parameterizations from global SRMs, and suggest that neighborhood‐based models may be a good compromise between accuracy and generalizability.
    Description: Plain Language Summary: Climate models, such as the ICOsahedral Non‐hydrostatic climate model, operate on low‐resolution grids, making it computationally feasible to use them for climate projections. However, physical processes –especially those associated with clouds– that happen on a sub‐grid scale (inside a grid box) cannot be resolved, yet they are critical for the climate. In this study, we train neural networks that return the cloudy fraction of a grid box knowing only low‐resolution grid‐box averaged variables (such as temperature, pressure, etc.) as the climate model sees them. We find that the neural networks can reproduce the sub‐grid scale cloud fraction on data sets similar to the one they were trained on. The networks trained on global data also prove to be applicable on regional data coming from a model simulation with an entirely different setup. Since neural networks are often described as black boxes that are therefore difficult to trust, we peek inside the black box to reveal what input features the neural networks have learned to focus on and in what respect the networks differ. Overall, the neural networks prove to be accurate methods of reproducing sub‐grid scale cloudiness and could improve climate model projections when implemented in a climate model.
    Description: Key Points: Neural networks can accurately learn sub‐grid scale cloud cover from realistic regional and global storm‐resolving simulations. Three neural network types account for different degrees of vertical locality and differentiate between cloud volume and cloud area fraction. Using a game theory based library we find that the neural networks tend to learn local mappings and are able to explain model errors.
    Description: EC ERC HORIZON EUROPE European Research Council
    Description: Partnership for Advanced Computing in Europe (PRACE)
    Description: NSF Science and Technology Center, Center for Learning the Earth with Artificial Intelligence and Physics (LEAP)
    Description: Deutsches Klimarechenzentrum
    Description: Columbia sub‐award 1
    Description: https://github.com/agrundner24/iconml_clc
    Description: https://doi.org/10.5281/zenodo.5788873
    Description: https://code.mpimet.mpg.de/projects/iconpublic
    Keywords: ddc:551.5 ; cloud cover ; parameterization ; machine learning ; neural network ; explainable AI ; SHAP
    Language: English
    Type: doc-type:article
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 3
    Publication Date: 2021-07-03
    Description: The terrestrial biosphere is currently slowing down global warming by absorbing about 30% of human emissions of carbon dioxide (CO2). The largest flux of the terrestrial carbon uptake is gross primary production (GPP) defined as the production of carbohydrates by photosynthesis. Elevated atmospheric CO2 concentration is expected to increase GPP (“CO2 fertilization effect”). However, Earth system models (ESMs) exhibit a large range in simulated GPP projections. In this study, we combine an existing emergent constraint on CO2 fertilization with a machine learning approach to constrain the spatial variations of multimodel GPP projections. In a first step, we use observed changes in the CO2 seasonal cycle at Cape Kumukahi to constrain the global mean GPP at the end of the 21st century (2091–2100) in Representative Concentration Pathway 8.5 simulations with ESMs participating in the Coupled Model Intercomparison Project Phase 5 (CMIP5) to 171 ± 12 Gt C yr−1, compared to the unconstrained model range of 156–247 Gt C yr−1. In a second step, we use a machine learning model to constrain gridded future absolute GPP and gridded fractional GPP change in two independent approaches. For this, observational data are fed into the machine learning algorithm that has been trained on CMIP5 data to learn relationships between present‐day physically relevant diagnostics and the target variable. In a leave‐one‐model‐out cross‐validation approach, the machine learning model shows superior performance to the CMIP5 ensemble mean. Our approach predicts an increased GPP change in northern high latitudes compared to regions closer to the equator.
    Description: Plain Language Summary: About a quarter of human emissions of carbon dioxide (CO2) is absorbed by vegetation and soil on the Earth's surface and hence does not contribute to global warming caused by CO2 in the atmosphere. Thus, in order to better define the remaining carbon budgets left to meet particular warming targets like the 1.5°C of the Paris Agreement, it is important to accurately quantify the carbon uptake by plants in the future. Currently, this is modeled by Earth system models yet with great uncertainties. In this work, we present an alternative machine learning approach to reduce spatial uncertainties of vegetation carbon uptake in future climate projections using observations of today's conditions.
    Description: Key Points: An emergent constraint on CO2 seasonal cycle amplitude changes reduces uncertainties in global mean gross primary production projections. A machine learning model with multiple predictors can further constrain the spatial distribution of gross primary production. High‐latitude ecosystems show higher gross primary production increase over the 21st century compared to regions closer to the equator.
    Description: EC | Horizon 2020 Framework Programme 4C
    Description: EC | Horizon 2020 Framework Programme CRESCENDO
    Description: ERC Consolidator Grant SEDAL
    Description: ERC Synergy Grant USMILE
    Keywords: 551.6 ; future climate projections ; modeling
    Type: article
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 4
    Publication Date: 2022-05-26
    Description: © The Author(s), 2020. This article is distributed under the terms of the Creative Commons Attribution License. The definitive version was published in von Schuckmann, K., Cheng, L., Palmer, M. D., Hansen, J., Tassone, C., Aich, V., Adusumilli, S., Beltrami, H., Boyer, T., Cuesta-Valero, F. J., Desbruyeres, D., Domingues, C., Garcia-Garcia, A., Gentine, P., Gilson, J., Gorfer, M., Haimberger, L., Ishii, M., Johnson, G. C., Killick, R., King, B. A., Kirchengast, G., Kolodziejczyk, N., Lyman, J., Marzeion, B., Mayer, M., Monier, M., Monselesan, D. P., Purkey, S., Roemmich, D., Schweiger, A., Seneviratne, S., I., Shepherd, A., Slater, D. A., Steiner, A. K., Straneo, F., Timmermans, M., & Wijffels, S. E. Heat stored in the Earth system: where does the energy go? Earth System Science Data, 12(3), (2020): 2013-2041, doi:10.5194/essd-12-2013-2020.
    Description: Human-induced atmospheric composition changes cause a radiative imbalance at the top of the atmosphere which is driving global warming. This Earth energy imbalance (EEI) is the most critical number defining the prospects for continued global warming and climate change. Understanding the heat gain of the Earth system – and particularly how much and where the heat is distributed – is fundamental to understanding how this affects warming ocean, atmosphere and land; rising surface temperature; sea level; and loss of grounded and floating ice, which are fundamental concerns for society. This study is a Global Climate Observing System (GCOS) concerted international effort to update the Earth heat inventory and presents an updated assessment of ocean warming estimates as well as new and updated estimates of heat gain in the atmosphere, cryosphere and land over the period 1960–2018. The study obtains a consistent long-term Earth system heat gain over the period 1971–2018, with a total heat gain of 358±37 ZJ, which is equivalent to a global heating rate of 0.47±0.1 W m−2. Over the period 1971–2018 (2010–2018), the majority of heat gain is reported for the global ocean with 89 % (90 %), with 52 % for both periods in the upper 700 m depth, 28 % (30 %) for the 700–2000 m depth layer and 9 % (8 %) below 2000 m depth. Heat gain over land amounts to 6 % (5 %) over these periods, 4 % (3 %) is available for the melting of grounded and floating ice, and 1 % (2 %) is available for atmospheric warming. Our results also show that EEI is not only continuing, but also increasing: the EEI amounts to 0.87±0.12 W m−2 during 2010–2018. Stabilization of climate, the goal of the universally agreed United Nations Framework Convention on Climate Change (UNFCCC) in 1992 and the Paris Agreement in 2015, requires that EEI be reduced to approximately zero to achieve Earth's system quasi-equilibrium. The amount of CO2 in the atmosphere would need to be reduced from 410 to 353 ppm to increase heat radiation to space by 0.87 W m−2, bringing Earth back towards energy balance. This simple number, EEI, is the most fundamental metric that the scientific community and public must be aware of as the measure of how well the world is doing in the task of bringing climate change under control, and we call for an implementation of the EEI into the global stocktake based on best available science. Continued quantification and reduced uncertainties in the Earth heat inventory can be best achieved through the maintenance of the current global climate observing system, its extension into areas of gaps in the sampling, and the establishment of an international framework for concerted multidisciplinary research of the Earth heat inventory as presented in this study. This Earth heat inventory is published at the German Climate Computing Centre (DKRZ, https://www.dkrz.de/, last access: 7 August 2020) under the DOI https://doi.org/10.26050/WDCC/GCOS_EHI_EXP_v2 (von Schuckmann et al., 2020).
    Description: Matthew D. Palmer and Rachel E. Killick were supported by the Met Office Hadley Centre Climate Programme funded by the BEIS and Defra. PML authors were supported by contribution number 5053. Catia M. Domingues was supported by an ARC Future Fellowship (FT130101532). Lijing Cheng is supported by the Key Deployment Project of Centre for Ocean Mega-Research of Science, CAS (COMS2019Q01). Maximilian Gorfer was supported by WEGC atmospheric remote sensing and climate system research group young scientist funds. Michael Mayer was supported by Austrian Science Fund project P33177. This work was supported by grants from the National Sciences and Engineering Research Council of Canada Discovery Grant (NSERC DG 140576948) and the Canada Research Chairs Program (CRC 230687) to Hugo Beltrami. Almudena García-García and Francisco José Cuesta-Valero are funded by Beltrami's CRC program, the School of Graduate Studies at Memorial University of Newfoundland and the Research Office at St. Francis Xavier University. Fiamma Straneo was supported by NSF OCE 1657601. Susheel Adusumilli was supported by NASA grant 80NSSC18K1424.
    Repository Name: Woods Hole Open Access Server
    Type: Article
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...