Articles | Volume 17, issue 17
https://doi.org/10.5194/gmd-17-6657-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-17-6657-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Model description paper
| 
10 Sep 2024
Model description paper |
| 10 Sep 2024
| 10 Sep 2024
HyPhAICC v1.0: a hybrid physics–AI approach for probability fields advection shown through an application to cloud cover nowcasting
Rachid El Montassir
CORRESPONDING AUTHOR
CERFACS, Toulouse, France
Olivier Pannekoucke
CORRESPONDING AUTHOR
CERFACS, Toulouse, France
INPT-ENM, Toulouse, France
CNRM, Université de Toulouse, Météo-France, CNRS, Toulouse, France
Corentin Lapeyre
CERFACS, Toulouse, France
Related authors
No articles found.
Théo Defontaine, Sophie Ricci, Corentin J. Lapeyre, Arthur Marchandise, and Etienne Le Pape
EGUsphere, https://doi.org/10.5194/egusphere-2023-2621, https://doi.org/10.5194/egusphere-2023-2621, 2024
Preprint archived
Short summary
Short summary
This work presents how machine learning models predict discharge and outperforms the 6 h lead-time empirical model used operationally in Toulouse. The 40 k points database includes discharge and rainfall data, for 36 flood events. The approach also provides a reliable solution for extended 8 h lead-time. The scarcity and the heterogeneity of the data, especially in presence of outliers, heavily weigh on the learning strategy. Rainfall data processing increases the predictive performances.
Antoine Perrot, Olivier Pannekoucke, and Vincent Guidard
Nonlin. Processes Geophys., 30, 139–166, https://doi.org/10.5194/npg-30-139-2023, https://doi.org/10.5194/npg-30-139-2023, 2023
Short summary
Short summary
This work is a theoretical contribution that provides equations for understanding uncertainty prediction applied in air quality where multiple chemical species can interact. A simplified minimal test bed is introduced that shows the ability of our equations to reproduce the statistics estimated from an ensemble of forecasts. While the latter estimation is the state of the art, solving equations is numerically less costly, depending on the number of chemical species, and motivates this research.
Olivier Pannekoucke and Philippe Arbogast
Geosci. Model Dev., 14, 5957–5976, https://doi.org/10.5194/gmd-14-5957-2021, https://doi.org/10.5194/gmd-14-5957-2021, 2021
Short summary
Short summary
This contributes to research on uncertainty prediction, which is important either for determining the weather today or estimating the risk in prediction. The problem is that uncertainty prediction is numerically very expensive. An alternative has been proposed wherein uncertainty is presented in a simplified form with only the dynamics of certain parameters required. This tool allows for the determination of the symbolic equations of these parameter dynamics and their numerical computation.
Camille Besombes, Olivier Pannekoucke, Corentin Lapeyre, Benjamin Sanderson, and Olivier Thual
Nonlin. Processes Geophys., 28, 347–370, https://doi.org/10.5194/npg-28-347-2021, https://doi.org/10.5194/npg-28-347-2021, 2021
Short summary
Short summary
This paper investigates the potential of a type of deep generative neural network to produce realistic weather situations when trained from the climate of a general circulation model. The generator represents the climate in a compact latent space. It is able to reproduce many aspects of the targeted multivariate distribution. Some properties of our method open new perspectives such as the exploration of the extremes close to a given state or how to connect two realistic weather states.
Olivier Pannekoucke, Richard Ménard, Mohammad El Aabaribaoune, and Matthieu Plu
Nonlin. Processes Geophys., 28, 1–22, https://doi.org/10.5194/npg-28-1-2021, https://doi.org/10.5194/npg-28-1-2021, 2021
Short summary
Short summary
Numerical weather prediction involves numerically solving the mathematical equations, which describe the geophysical flow, by transforming them so that they can be computed. Through this transformation, it appears that the equations actually solved by the machine are then a modified version of the original equations, introducing an error that contributes to the model error. This work helps to characterize the covariance of the model error that is due to this modification of the equations.
Olivier Pannekoucke and Ronan Fablet
Geosci. Model Dev., 13, 3373–3382, https://doi.org/10.5194/gmd-13-3373-2020, https://doi.org/10.5194/gmd-13-3373-2020, 2020
Short summary
Short summary
Learning physics from data using a deep neural network is a challenge that requires an appropriate but unknown network architecture. The package introduced here helps to design an architecture by translating known physical equations into a network, which the experimenter completes to capture unknown physical processes. A test bed is introduced to illustrate how this learning allows us to focus on truly unknown physical processes in the hope of making better use of data and digital resources.
Olivier Pannekoucke, Marc Bocquet, and Richard Ménard
Nonlin. Processes Geophys., 25, 481–495, https://doi.org/10.5194/npg-25-481-2018, https://doi.org/10.5194/npg-25-481-2018, 2018
Short summary
Short summary
The forecast of weather prediction uncertainty is a real challenge and is crucial for risk management. However, uncertainty prediction is beyond the capacity of supercomputers, and improvements of the technology may not solve this issue. A new uncertainty prediction method is introduced which takes advantage of fluid equations to predict simple quantities which approximate real uncertainty but at a low numerical cost. A proof of concept is shown by an academic model derived from fluid dynamics.
E. Emili, B. Barret, S. Massart, E. Le Flochmoen, A. Piacentini, L. El Amraoui, O. Pannekoucke, and D. Cariolle
Atmos. Chem. Phys., 14, 177–198, https://doi.org/10.5194/acp-14-177-2014, https://doi.org/10.5194/acp-14-177-2014, 2014
S. Barthélémy, S. Ricci, O. Pannekoucke, O. Thual, and P. O. Malaterre
Hydrol. Earth Syst. Sci. Discuss., https://doi.org/10.5194/hessd-10-6963-2013, https://doi.org/10.5194/hessd-10-6963-2013, 2013
Preprint withdrawn
Related subject area
Climate and Earth system modeling
Presentation, calibration and testing of the DCESS II Earth system model of intermediate complexity (version 1.0)
Synthesizing global carbon–nitrogen coupling effects – the MAGICC coupled carbon–nitrogen cycle model v1.0
Historical trends and controlling factors of isoprene emissions in CMIP6 Earth system models
Investigating carbon and nitrogen conservation in reported CMIP6 Earth system model data
From weather data to river runoff: using spatiotemporal convolutional networks for discharge forecasting
A Fortran–Python interface for integrating machine learning parameterization into earth system models
A rapid-application emissions-to-impacts tool for scenario assessment: Probabilistic Regional Impacts from Model patterns and Emissions (PRIME)
The DOE E3SM version 2.1: overview and assessment of the impacts of parameterized ocean submesoscales
WRF-ELM v1.0: a regional climate model to study land–atmosphere interactions over heterogeneous land use regions
Modeling commercial-scale CO2 storage in the gas hydrate stability zone with PFLOTRAN v6.0
DiuSST: a conceptual model of diurnal warm layers for idealized atmospheric simulations with interactive sea surface temperature
High-Resolution Model Intercomparison Project phase 2 (HighResMIP2) towards CMIP7
T&C-CROP: representing mechanistic crop growth with a terrestrial biosphere model (T&C, v1.5) – model formulation and validation
An updated non-intrusive, multi-scale, and flexible coupling interface in WRF 4.6.0
Monitoring and benchmarking Earth system model simulations with ESMValTool v2.12.0
The Earth Science Box Modeling Toolkit (ESBMTK 0.14.0.11): a Python library for research and teaching
CropSuite v1.0 – a comprehensive open-source crop suitability model considering climate variability for climate impact assessment
ICON ComIn – the ICON Community Interface (ComIn version 0.1.0, with ICON version 2024.01-01)
Using feature importance as an exploratory data analysis tool on Earth system models
A new metrics framework for quantifying and intercomparing atmospheric rivers in observations, reanalyses, and climate models
The real challenges for climate and weather modelling on its way to sustained exascale performance: a case study using ICON (v2.6.6)
Improving the representation of major Indian crops in the Community Land Model version 5.0 (CLM5) using site-scale crop data
Evaluation of CORDEX ERA5-forced NARCliM2.0 regional climate models over Australia using the Weather Research and Forecasting (WRF) model version 4.1.2
Design, evaluation, and future projections of the NARCliM2.0 CORDEX-CMIP6 Australasia regional climate ensemble
Amending the algorithm of aerosol–radiation interactions in WRF-Chem (v4.4)
The very-high-resolution configuration of the EC-Earth global model for HighResMIP
GOSI9: UK Global Ocean and Sea Ice configurations
Decomposition of skill scores for conditional verification: impact of Atlantic Multidecadal Oscillation phases on the predictability of decadal temperature forecasts
Virtual Integration of Satellite and In-situ Observation Networks (VISION) v1.0: In-Situ Observations Simulator (ISO_simulator)
Climate model downscaling in central Asia: a dynamical and a neural network approach
Advanced climate model evaluation with ESMValTool v2.11.0 using parallel, out-of-core, and distributed computing
Multi-year simulations at kilometre scale with the Integrated Forecasting System coupled to FESOM2.5 and NEMOv3.4
Subsurface hydrological controls on the short-term effects of hurricanes on nitrate–nitrogen runoff loading: a case study of Hurricane Ida using the Energy Exascale Earth System Model (E3SM) Land Model (v2.1)
CARIB12: a regional Community Earth System Model/Modular Ocean Model 6 configuration of the Caribbean Sea
Process-based modeling framework for sustainable irrigation management at the regional scale: Integrating rice production, water use, and greenhouse gas emissions
Architectural insights into and training methodology optimization of Pangu-Weather
Evaluation of global fire simulations in CMIP6 Earth system models
Evaluating downscaled products with expected hydroclimatic co-variances
Software sustainability of global impact models
fair-calibrate v1.4.1: calibration, constraining, and validation of the FaIR simple climate model for reliable future climate projections
ISOM 1.0: a fully mesoscale-resolving idealized Southern Ocean model and the diversity of multiscale eddy interactions
A computationally lightweight model for ensemble forecasting of environmental hazards: General TAMSAT-ALERT v1.2.1
Introducing the MESMER-M-TPv0.1.0 module: spatially explicit Earth system model emulation for monthly precipitation and temperature
The need for carbon-emissions-driven climate projections in CMIP7
Robust handling of extremes in quantile mapping – “Murder your darlings”
A protocol for model intercomparison of impacts of marine cloud brightening climate intervention
An extensible perturbed parameter ensemble for the Community Atmosphere Model version 6
Coupling the regional climate model ICON-CLM v2.6.6 to the Earth system model GCOAST-AHOI v2.0 using OASIS3-MCT v4.0
A fully coupled solid-particle microphysics scheme for stratospheric aerosol injections within the aerosol–chemistry–climate model SOCOL-AERv2
The Tropical Basin Interaction Model Intercomparison Project (TBIMIP)
Esteban Fernández Villanueva and Gary Shaffer
Geosci. Model Dev., 18, 2161–2192, https://doi.org/10.5194/gmd-18-2161-2025, https://doi.org/10.5194/gmd-18-2161-2025, 2025
Short summary
Short summary
We describe, calibrate and test the Danish Center for Earth System Science (DCESS) II model, a new, broad, adaptable and fast Earth system model. DCESS II is designed for global simulations over timescales of years to millions of years using limited computer resources like a personal computer. With its flexibility and comprehensive treatment of the global carbon cycle, DCESS II is a useful, computationally friendly tool for simulations of past climates as well as for future Earth system projections.
Gang Tang, Zebedee Nicholls, Alexander Norton, Sönke Zaehle, and Malte Meinshausen
Geosci. Model Dev., 18, 2193–2230, https://doi.org/10.5194/gmd-18-2193-2025, https://doi.org/10.5194/gmd-18-2193-2025, 2025
Short summary
Short summary
We studied carbon–nitrogen coupling in Earth system models by developing a global carbon–nitrogen cycle model (CNit v1.0) within the widely used emulator MAGICC. CNit effectively reproduced the global carbon–nitrogen cycle dynamics observed in complex models. Our results show persistent nitrogen limitations on plant growth (net primary production) from 1850 to 2100, suggesting that nitrogen deficiency may constrain future land carbon sequestration.
Ngoc Thi Nhu Do, Kengo Sudo, Akihiko Ito, Louisa K. Emmons, Vaishali Naik, Kostas Tsigaridis, Øyvind Seland, Gerd A. Folberth, and Douglas I. Kelley
Geosci. Model Dev., 18, 2079–2109, https://doi.org/10.5194/gmd-18-2079-2025, https://doi.org/10.5194/gmd-18-2079-2025, 2025
Short summary
Short summary
Understanding historical isoprene emission changes is important for predicting future climate, but trends and their controlling factors remain uncertain. This study shows that long-term isoprene trends vary among Earth system models mainly due to partially incorporating CO2 effects and land cover changes rather than to climate. Future models that refine these factors’ effects on isoprene emissions, along with long-term observations, are essential for better understanding plant–climate interactions.
Gang Tang, Zebedee Nicholls, Chris Jones, Thomas Gasser, Alexander Norton, Tilo Ziehn, Alejandro Romero-Prieto, and Malte Meinshausen
Geosci. Model Dev., 18, 2111–2136, https://doi.org/10.5194/gmd-18-2111-2025, https://doi.org/10.5194/gmd-18-2111-2025, 2025
Short summary
Short summary
We analyzed carbon and nitrogen mass conservation in data from various Earth system models. Our findings reveal significant discrepancies between flux and pool size data, where cumulative imbalances can reach hundreds of gigatons of carbon or nitrogen. These imbalances appear primarily due to missing or inconsistently reported fluxes – especially for land-use and fire emissions. To enhance data quality, we recommend that future climate data protocols address this issue at the reporting stage.
Florian Börgel, Sven Karsten, Karoline Rummel, and Ulf Gräwe
Geosci. Model Dev., 18, 2005–2019, https://doi.org/10.5194/gmd-18-2005-2025, https://doi.org/10.5194/gmd-18-2005-2025, 2025
Short summary
Short summary
Forecasting river runoff, which is crucial for managing water resources and understanding climate impacts, can be challenging. This study introduces a new method using convolutional long short-term memory (ConvLSTM) networks, a machine learning model that processes spatial and temporal data. Focusing on the Baltic Sea region, our model uses weather data as input to predict daily river runoff for 97 rivers.
Tao Zhang, Cyril Morcrette, Meng Zhang, Wuyin Lin, Shaocheng Xie, Ye Liu, Kwinten Van Weverberg, and Joana Rodrigues
Geosci. Model Dev., 18, 1917–1928, https://doi.org/10.5194/gmd-18-1917-2025, https://doi.org/10.5194/gmd-18-1917-2025, 2025
Short summary
Short summary
Earth system models (ESMs) struggle with the uncertainties associated with parameterizing subgrid physics. Machine learning (ML) algorithms offer a solution by learning the important relationships and features from high-resolution models. To incorporate ML parameterizations into ESMs, we develop a Fortran–Python interface that allows for calling Python functions within Fortran-based ESMs. Through two case studies, this interface demonstrates its feasibility, modularity, and effectiveness.
Camilla Mathison, Eleanor J. Burke, Gregory Munday, Chris D. Jones, Chris J. Smith, Norman J. Steinert, Andy J. Wiltshire, Chris Huntingford, Eszter Kovacs, Laila K. Gohar, Rebecca M. Varney, and Douglas McNeall
Geosci. Model Dev., 18, 1785–1808, https://doi.org/10.5194/gmd-18-1785-2025, https://doi.org/10.5194/gmd-18-1785-2025, 2025
Short summary
Short summary
We present PRIME (Probabilistic Regional Impacts from Model patterns and Emissions), which is designed to take new emissions scenarios and rapidly provide regional impact information. PRIME allows large ensembles to be run on multi-centennial timescales, including the analysis of many important variables for impact assessments. Our evaluation shows that PRIME reproduces the climate response for known scenarios, providing confidence in using PRIME for novel scenarios.
Katherine M. Smith, Alice M. Barthel, LeAnn M. Conlon, Luke P. Van Roekel, Anthony Bartoletti, Jean-Christophe Golaz, Chengzhu Zhang, Carolyn Branecky Begeman, James J. Benedict, Gautam Bisht, Yan Feng, Walter Hannah, Bryce E. Harrop, Nicole Jeffery, Wuyin Lin, Po-Lun Ma, Mathew E. Maltrud, Mark R. Petersen, Balwinder Singh, Qi Tang, Teklu Tesfa, Jonathan D. Wolfe, Shaocheng Xie, Xue Zheng, Karthik Balaguru, Oluwayemi Garuba, Peter Gleckler, Aixue Hu, Jiwoo Lee, Ben Moore-Maley, and Ana C. Ordoñez
Geosci. Model Dev., 18, 1613–1633, https://doi.org/10.5194/gmd-18-1613-2025, https://doi.org/10.5194/gmd-18-1613-2025, 2025
Short summary
Short summary
Version 2.1 of the U.S. Department of Energy's Energy Exascale Earth System Model (E3SM) adds the Fox-Kemper et al. (2011) mixed-layer eddy parameterization, which restratifies the ocean surface layer through an overturning streamfunction. Results include surface layer bias reduction in temperature, salinity, and sea ice extent in the North Atlantic; a small strengthening of the Atlantic meridional overturning circulation; and improvements to many atmospheric climatological variables.
Huilin Huang, Yun Qian, Gautam Bisht, Jiali Wang, Tirthankar Chakraborty, Dalei Hao, Jianfeng Li, Travis Thurber, Balwinder Singh, Zhao Yang, Ye Liu, Pengfei Xue, William J. Sacks, Ethan Coon, and Robert Hetland
Geosci. Model Dev., 18, 1427–1443, https://doi.org/10.5194/gmd-18-1427-2025, https://doi.org/10.5194/gmd-18-1427-2025, 2025
Short summary
Short summary
We integrate the E3SM Land Model (ELM) with the WRF model through the Lightweight Infrastructure for Land Atmosphere Coupling (LILAC) Earth System Modeling Framework (ESMF). This framework includes a top-level driver, LILAC, for variable communication between WRF and ELM and ESMF caps for ELM initialization, execution, and finalization. The LILAC–ESMF framework maintains the integrity of the ELM's source code structure and facilitates the transfer of future ELM model developments to WRF-ELM.
Michael Nole, Jonah Bartrand, Fawz Naim, and Glenn Hammond
Geosci. Model Dev., 18, 1413–1425, https://doi.org/10.5194/gmd-18-1413-2025, https://doi.org/10.5194/gmd-18-1413-2025, 2025
Short summary
Short summary
Safe carbon dioxide (CO2) storage is likely to be critical for mitigating some of the most severe effects of climate change. We present a simulation framework for modeling CO2 storage beneath the seafloor, where CO2 can form a solid. This can aid in permanent CO2 storage for long periods of time. Our models show what a commercial-scale CO2 injection would look like in a marine environment. We discuss what would need to be considered when designing a subsea CO2 injection.
Reyk Börner, Jan O. Haerter, and Romain Fiévet
Geosci. Model Dev., 18, 1333–1356, https://doi.org/10.5194/gmd-18-1333-2025, https://doi.org/10.5194/gmd-18-1333-2025, 2025
Short summary
Short summary
The daily cycle of sea surface temperature (SST) impacts clouds above the ocean and could influence the clustering of thunderstorms linked to extreme rainfall and hurricanes. However, daily SST variability is often poorly represented in modeling studies of how clouds cluster. We present a simple, wind-responsive model of upper-ocean temperature for use in atmospheric simulations. Evaluating the model against observations, we show that it performs significantly better than common slab models.
Malcolm J. Roberts, Kevin A. Reed, Qing Bao, Joseph J. Barsugli, Suzana J. Camargo, Louis-Philippe Caron, Ping Chang, Cheng-Ta Chen, Hannah M. Christensen, Gokhan Danabasoglu, Ivy Frenger, Neven S. Fučkar, Shabeh ul Hasson, Helene T. Hewitt, Huanping Huang, Daehyun Kim, Chihiro Kodama, Michael Lai, Lai-Yung Ruby Leung, Ryo Mizuta, Paulo Nobre, Pablo Ortega, Dominique Paquin, Christopher D. Roberts, Enrico Scoccimarro, Jon Seddon, Anne Marie Treguier, Chia-Ying Tu, Paul A. Ullrich, Pier Luigi Vidale, Michael F. Wehner, Colin M. Zarzycki, Bosong Zhang, Wei Zhang, and Ming Zhao
Geosci. Model Dev., 18, 1307–1332, https://doi.org/10.5194/gmd-18-1307-2025, https://doi.org/10.5194/gmd-18-1307-2025, 2025
Short summary
Short summary
HighResMIP2 is a model intercomparison project focusing on high-resolution global climate models, that is, those with grid spacings of 25 km or less in the atmosphere and ocean, using simulations of decades to a century in length. We are proposing an update of our simulation protocol to make the models more applicable to key questions for climate variability and hazard in present-day and future projections and to build links with other communities to provide more robust climate information.
Jordi Buckley Paules, Simone Fatichi, Bonnie Warring, and Athanasios Paschalis
Geosci. Model Dev., 18, 1287–1305, https://doi.org/10.5194/gmd-18-1287-2025, https://doi.org/10.5194/gmd-18-1287-2025, 2025
Short summary
Short summary
We present and validate enhancements to the process-based T&C model aimed at improving its representation of crop growth and management practices. The updated model, T&C-CROP, enables applications such as analysing the hydrological and carbon storage impacts of land use transitions (e.g. conversions between crops, forests, and pastures) and optimizing irrigation and fertilization strategies in response to climate change.
Sébastien Masson, Swen Jullien, Eric Maisonnave, David Gill, Guillaume Samson, Mathieu Le Corre, and Lionel Renault
Geosci. Model Dev., 18, 1241–1263, https://doi.org/10.5194/gmd-18-1241-2025, https://doi.org/10.5194/gmd-18-1241-2025, 2025
Short summary
Short summary
This article details a new feature we implemented in the popular regional atmospheric model WRF. This feature allows for data exchange between WRF and any other model (e.g. an ocean model) using the coupling library Ocean–Atmosphere–Sea–Ice–Soil Model Coupling Toolkit (OASIS3-MCT). This coupling interface is designed to be non-intrusive, flexible and modular. It also offers the possibility of taking into account the nested zooms used in WRF or in the models with which it is coupled.
Axel Lauer, Lisa Bock, Birgit Hassler, Patrick Jöckel, Lukas Ruhe, and Manuel Schlund
Geosci. Model Dev., 18, 1169–1188, https://doi.org/10.5194/gmd-18-1169-2025, https://doi.org/10.5194/gmd-18-1169-2025, 2025
Short summary
Short summary
Earth system models are important tools to improve our understanding of current climate and to project climate change. Thus, it is crucial to understand possible shortcomings in the models. New features of the ESMValTool software package allow one to compare and visualize a model's performance with respect to reproducing observations in the context of other climate models in an easy and user-friendly way. We aim to help model developers assess and monitor climate simulations more efficiently.
Ulrich G. Wortmann, Tina Tsan, Mahrukh Niazi, Irene A. Ma, Ruben Navasardyan, Magnus-Roland Marun, Bernardo S. Chede, Jingwen Zhong, and Morgan Wolfe
Geosci. Model Dev., 18, 1155–1167, https://doi.org/10.5194/gmd-18-1155-2025, https://doi.org/10.5194/gmd-18-1155-2025, 2025
Short summary
Short summary
The Earth Science Box Modeling Toolkit (ESBMTK) is a user-friendly Python library that simplifies the creation of models to study earth system processes, such as the carbon cycle and ocean chemistry. It enhances learning by emphasizing concepts over programming and is accessible to students and researchers alike. By automating complex calculations and promoting code clarity, ESBMTK accelerates model development while improving reproducibility and the usability of scientific research.
Florian Zabel, Matthias Knüttel, and Benjamin Poschlod
Geosci. Model Dev., 18, 1067–1087, https://doi.org/10.5194/gmd-18-1067-2025, https://doi.org/10.5194/gmd-18-1067-2025, 2025
Short summary
Short summary
CropSuite is a new open-source crop suitability model. It provides a GUI and a wide range of options, including a spatial downscaling of climate data. We apply CropSuite to 48 staple and opportunity crops at a 1 km spatial resolution in Africa. We find that climate variability significantly impacts suitable areas but also affects optimal sowing dates and multiple cropping potential. The results provide valuable information for climate impact assessments, adaptation, and land-use planning.
Kerstin Hartung, Bastian Kern, Nils-Arne Dreier, Jörn Geisbüsch, Mahnoosh Haghighatnasab, Patrick Jöckel, Astrid Kerkweg, Wilton Jaciel Loch, Florian Prill, and Daniel Rieger
Geosci. Model Dev., 18, 1001–1015, https://doi.org/10.5194/gmd-18-1001-2025, https://doi.org/10.5194/gmd-18-1001-2025, 2025
Short summary
Short summary
The ICOsahedral Non-hydrostatic (ICON) model system Community Interface (ComIn) library supports connecting third-party modules to the ICON model. Third-party modules can range from simple diagnostic Python scripts to full chemistry models. ComIn offers a low barrier for code extensions to ICON, provides multi-language support (Fortran, C/C++, and Python), and reduces the migration effort in response to new ICON releases. This paper presents the ComIn design principles and a range of use cases.
Daniel Ries, Katherine Goode, Kellie McClernon, and Benjamin Hillman
Geosci. Model Dev., 18, 1041–1065, https://doi.org/10.5194/gmd-18-1041-2025, https://doi.org/10.5194/gmd-18-1041-2025, 2025
Short summary
Short summary
Machine learning has advanced research in the climate science domain, but its models are difficult to understand. In order to understand the impacts and consequences of climate interventions such as stratospheric aerosol injection, complex models are often necessary. We use a case study to illustrate how we can understand the inner workings of a complex model. We present this technique as an exploratory tool that can be used to quickly discover and assess relationships in complex climate data.
Bo Dong, Paul Ullrich, Jiwoo Lee, Peter Gleckler, Kristin Chang, and Travis A. O'Brien
Geosci. Model Dev., 18, 961–976, https://doi.org/10.5194/gmd-18-961-2025, https://doi.org/10.5194/gmd-18-961-2025, 2025
Short summary
Short summary
A metrics package designed for easy analysis of atmospheric river (AR) characteristics and statistics is presented. The tool is efficient for diagnosing systematic AR bias in climate models and useful for evaluating new AR characteristics in model simulations. In climate models, landfalling AR precipitation shows dry biases globally, and AR tracks are farther poleward (equatorward) in the North and South Atlantic (South Pacific and Indian Ocean).
Panagiotis Adamidis, Erik Pfister, Hendryk Bockelmann, Dominik Zobel, Jens-Olaf Beismann, and Marek Jacob
Geosci. Model Dev., 18, 905–919, https://doi.org/10.5194/gmd-18-905-2025, https://doi.org/10.5194/gmd-18-905-2025, 2025
Short summary
Short summary
In this paper, we investigated performance indicators of the climate model ICON (ICOsahedral Nonhydrostatic) on different compute architectures to answer the question of how to generate high-resolution climate simulations. Evidently, it is not enough to use more computing units of the conventionally used architectures; higher memory throughput is the most promising approach. More potential can be gained from single-node optimization rather than simply increasing the number of compute nodes.
Kangari Narender Reddy, Somnath Baidya Roy, Sam S. Rabin, Danica L. Lombardozzi, Gudimetla Venkateswara Varma, Ruchira Biswas, and Devavat Chiru Naik
Geosci. Model Dev., 18, 763–785, https://doi.org/10.5194/gmd-18-763-2025, https://doi.org/10.5194/gmd-18-763-2025, 2025
Short summary
Short summary
The study aimed to improve the representation of wheat and rice in a land model for the Indian region. The modified model performed significantly better than the default model in simulating crop phenology, yield, and carbon, water, and energy fluxes compared to observations. The study highlights the need for global land models to use region-specific crop parameters for accurately simulating vegetation processes and land surface processes.
Giovanni Di Virgilio, Fei Ji, Eugene Tam, Jason P. Evans, Jatin Kala, Julia Andrys, Christopher Thomas, Dipayan Choudhury, Carlos Rocha, Yue Li, and Matthew L. Riley
Geosci. Model Dev., 18, 703–724, https://doi.org/10.5194/gmd-18-703-2025, https://doi.org/10.5194/gmd-18-703-2025, 2025
Short summary
Short summary
We evaluate the skill in simulating the Australian climate of some of the latest generation of regional climate models. We show when and where the models simulate this climate with high skill versus model limitations. We show how new models perform relative to the previous-generation models, assessing how model design features may underlie key performance improvements. This work is of national and international relevance as it can help guide the use and interpretation of climate projections.
Giovanni Di Virgilio, Jason P. Evans, Fei Ji, Eugene Tam, Jatin Kala, Julia Andrys, Christopher Thomas, Dipayan Choudhury, Carlos Rocha, Stephen White, Yue Li, Moutassem El Rafei, Rishav Goyal, Matthew L. Riley, and Jyothi Lingala
Geosci. Model Dev., 18, 671–702, https://doi.org/10.5194/gmd-18-671-2025, https://doi.org/10.5194/gmd-18-671-2025, 2025
Short summary
Short summary
We introduce new climate models that simulate Australia’s future climate at regional scales, including at an unprecedented resolution of 4 km for 1950–2100. We describe the model design process used to create these new climate models. We show how the new models perform relative to previous-generation models and compare their climate projections. This work is of national and international relevance as it can help guide climate model design and the use and interpretation of climate projections.
Jiawang Feng, Chun Zhao, Qiuyan Du, Zining Yang, and Chen Jin
Geosci. Model Dev., 18, 585–603, https://doi.org/10.5194/gmd-18-585-2025, https://doi.org/10.5194/gmd-18-585-2025, 2025
Short summary
Short summary
In this study, we improved the calculation of how aerosols in the air interact with radiation in WRF-Chem. The original model used a simplified method, but we developed a more accurate approach. We found that this method significantly changes the properties of the estimated aerosols and their effects on radiation, especially for dust aerosols. It also impacts the simulated weather conditions. Our work highlights the importance of correctly representing aerosol–radiation interactions in models.
Eduardo Moreno-Chamarro, Thomas Arsouze, Mario Acosta, Pierre-Antoine Bretonnière, Miguel Castrillo, Eric Ferrer, Amanda Frigola, Daria Kuznetsova, Eneko Martin-Martinez, Pablo Ortega, and Sergi Palomas
Geosci. Model Dev., 18, 461–482, https://doi.org/10.5194/gmd-18-461-2025, https://doi.org/10.5194/gmd-18-461-2025, 2025
Short summary
Short summary
We present the high-resolution model version of the EC-Earth global climate model to contribute to HighResMIP. The combined model resolution is about 10–15 km in both the ocean and atmosphere, which makes it one of the finest ever used to complete historical and scenario simulations. This model is compared with two lower-resolution versions, with a 100 km and a 25 km grid. The three models are compared with observations to study the improvements thanks to the increased resolution.
Catherine Guiavarc'h, David Storkey, Adam T. Blaker, Ed Blockley, Alex Megann, Helene Hewitt, Michael J. Bell, Daley Calvert, Dan Copsey, Bablu Sinha, Sophia Moreton, Pierre Mathiot, and Bo An
Geosci. Model Dev., 18, 377–403, https://doi.org/10.5194/gmd-18-377-2025, https://doi.org/10.5194/gmd-18-377-2025, 2025
Short summary
Short summary
The Global Ocean and Sea Ice configuration version 9 (GOSI9) is the new UK hierarchy of model configurations based on the Nucleus for European Modelling of the Ocean (NEMO) and available at three resolutions. It will be used for various applications, e.g. weather forecasting and climate prediction. It improves upon the previous version by reducing global temperature and salinity biases and enhancing the representation of Arctic sea ice and the Antarctic Circumpolar Current.
Andy Richling, Jens Grieger, and Henning W. Rust
Geosci. Model Dev., 18, 361–375, https://doi.org/10.5194/gmd-18-361-2025, https://doi.org/10.5194/gmd-18-361-2025, 2025
Short summary
Short summary
The performance of weather and climate prediction systems is variable in time and space. It is of interest how this performance varies in different situations. We provide a decomposition of a skill score (a measure of forecast performance) as a tool for detailed assessment of performance variability to support model development or forecast improvement. The framework is exemplified with decadal forecasts to assess the impact of different ocean states in the North Atlantic on temperature forecast.
Maria R. Russo, Sadie L. Bartholomew, David Hassell, Alex M. Mason, Erica Neininger, A. James Perman, David A. J. Sproson, Duncan Watson-Parris, and Nathan Luke Abraham
Geosci. Model Dev., 18, 181–191, https://doi.org/10.5194/gmd-18-181-2025, https://doi.org/10.5194/gmd-18-181-2025, 2025
Short summary
Short summary
Observational data and modelling capabilities have expanded in recent years, but there are still barriers preventing these two data sources from being used in synergy. Proper comparison requires generating, storing, and handling a large amount of data. This work describes the first step in the development of a new set of software tools, the VISION toolkit, which can enable the easy and efficient integration of observational and model data required for model evaluation.
Bijan Fallah, Masoud Rostami, Emmanuele Russo, Paula Harder, Christoph Menz, Peter Hoffmann, Iulii Didovets, and Fred F. Hattermann
Geosci. Model Dev., 18, 161–180, https://doi.org/10.5194/gmd-18-161-2025, https://doi.org/10.5194/gmd-18-161-2025, 2025
Short summary
Short summary
We tried to contribute to a local climate change impact study in central Asia, a region that is water-scarce and vulnerable to global climate change. We use regional models and machine learning to produce reliable local data from global climate models. We find that regional models show more realistic and detailed changes in heavy precipitation than global climate models. Our work can help assess the future risks of extreme events and plan adaptation strategies in central Asia.
Manuel Schlund, Bouwe Andela, Jörg Benke, Ruth Comer, Birgit Hassler, Emma Hogan, Peter Kalverla, Axel Lauer, Bill Little, Saskia Loosveldt Tomas, Francesco Nattino, Patrick Peglar, Valeriu Predoi, Stef Smeets, Stephen Worsley, Martin Yeo, and Klaus Zimmermann
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2024-236, https://doi.org/10.5194/gmd-2024-236, 2025
Revised manuscript accepted for GMD
Short summary
Short summary
The Earth System Model Evaluation Tool (ESMValTool) is a community diagnostics and performance metrics tool for the evaluation of Earth system models. Here, we describe recent significant improvements of ESMValTool’s computational efficiency including parallel, out-of-core, and distributed computing. Evaluations with the enhanced version of ESMValTool are faster, use less computational resources, and can handle input data larger than the available memory.
Thomas Rackow, Xabier Pedruzo-Bagazgoitia, Tobias Becker, Sebastian Milinski, Irina Sandu, Razvan Aguridan, Peter Bechtold, Sebastian Beyer, Jean Bidlot, Souhail Boussetta, Willem Deconinck, Michail Diamantakis, Peter Dueben, Emanuel Dutra, Richard Forbes, Rohit Ghosh, Helge F. Goessling, Ioan Hadade, Jan Hegewald, Thomas Jung, Sarah Keeley, Lukas Kluft, Nikolay Koldunov, Aleksei Koldunov, Tobias Kölling, Josh Kousal, Christian Kühnlein, Pedro Maciel, Kristian Mogensen, Tiago Quintino, Inna Polichtchouk, Balthasar Reuter, Domokos Sármány, Patrick Scholz, Dmitry Sidorenko, Jan Streffing, Birgit Sützl, Daisuke Takasuka, Steffen Tietsche, Mirco Valentini, Benoît Vannière, Nils Wedi, Lorenzo Zampieri, and Florian Ziemen
Geosci. Model Dev., 18, 33–69, https://doi.org/10.5194/gmd-18-33-2025, https://doi.org/10.5194/gmd-18-33-2025, 2025
Short summary
Short summary
Detailed global climate model simulations have been created based on a numerical weather prediction model, offering more accurate spatial detail down to the scale of individual cities ("kilometre-scale") and a better understanding of climate phenomena such as atmospheric storms, whirls in the ocean, and cracks in sea ice. The new model aims to provide globally consistent information on local climate change with greater precision, benefiting environmental planning and local impact modelling.
Yilin Fang, Hoang Viet Tran, and L. Ruby Leung
Geosci. Model Dev., 18, 19–32, https://doi.org/10.5194/gmd-18-19-2025, https://doi.org/10.5194/gmd-18-19-2025, 2025
Short summary
Short summary
Hurricanes may worsen water quality in the lower Mississippi River basin (LMRB) by increasing nutrient runoff. We found that runoff parameterizations greatly affect nitrate–nitrogen runoff simulated using an Earth system land model. Our simulations predicted increased nitrogen runoff in the LMRB during Hurricane Ida in 2021, albeit less pronounced than the observations, indicating areas for model improvement to better understand and manage nutrient runoff loss during hurricanes in the region.
Giovanni Seijo-Ellis, Donata Giglio, Gustavo Marques, and Frank Bryan
Geosci. Model Dev., 17, 8989–9021, https://doi.org/10.5194/gmd-17-8989-2024, https://doi.org/10.5194/gmd-17-8989-2024, 2024
Short summary
Short summary
A CESM–MOM6 regional configuration of the Caribbean Sea was developed in response to the rising need for high-resolution models for climate impact studies. The configuration is validated for the period 2000–2020 and improves significant errors in a low-resolution model. Oceanic properties are well represented. Patterns of freshwater associated with the Amazon River are well captured, and the mean flows of ocean waters across multiple passages in the Caribbean Sea agree with observations.
Yan Bo, Hao Liang, Tao Li, and Feng Zhou
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2024-212, https://doi.org/10.5194/gmd-2024-212, 2024
Revised manuscript accepted for GMD
Short summary
Short summary
This study proposed an advancing framework for modeling regional rice production, water use, and greenhouse gas emissions. The framework integrated a process-based soil-crop model with key physiological effects, a novel model upscaling method, and the NSGA-II multi-objective optimization algorithm at a parallel computing platform. The framework provides a valuable tool for irrigation optimization to deliver co-benefits of ensuring food production, reducing water use and greenhouse gas emissions.
Deifilia To, Julian Quinting, Gholam Ali Hoshyaripour, Markus Götz, Achim Streit, and Charlotte Debus
Geosci. Model Dev., 17, 8873–8884, https://doi.org/10.5194/gmd-17-8873-2024, https://doi.org/10.5194/gmd-17-8873-2024, 2024
Short summary
Short summary
Pangu-Weather is a breakthrough machine learning model in medium-range weather forecasting that considers 3D atmospheric information. We show that using a simpler 2D framework improves robustness, speeds up training, and reduces computational needs by 20 %–30 %. We introduce a training procedure that varies the importance of atmospheric variables over time to speed up training convergence. Decreasing computational demand increases the accessibility of training and working with the model.
Fang Li, Xiang Song, Sandy P. Harrison, Jennifer R. Marlon, Zhongda Lin, L. Ruby Leung, Jörg Schwinger, Virginie Marécal, Shiyu Wang, Daniel S. Ward, Xiao Dong, Hanna Lee, Lars Nieradzik, Sam S. Rabin, and Roland Séférian
Geosci. Model Dev., 17, 8751–8771, https://doi.org/10.5194/gmd-17-8751-2024, https://doi.org/10.5194/gmd-17-8751-2024, 2024
Short summary
Short summary
This study provides the first comprehensive assessment of historical fire simulations from 19 Earth system models in phase 6 of the Coupled Model Intercomparison Project (CMIP6). Most models reproduce global totals, spatial patterns, seasonality, and regional historical changes well but fail to simulate the recent decline in global burned area and underestimate the fire response to climate variability. CMIP6 simulations address three critical issues of phase-5 models.
Seung H. Baek, Paul A. Ullrich, Bo Dong, and Jiwoo Lee
Geosci. Model Dev., 17, 8665–8681, https://doi.org/10.5194/gmd-17-8665-2024, https://doi.org/10.5194/gmd-17-8665-2024, 2024
Short summary
Short summary
We evaluate downscaled products by examining locally relevant co-variances during precipitation events. Common statistical downscaling techniques preserve expected co-variances during convective precipitation (a stationary phenomenon). However, they dampen future intensification of frontal precipitation (a non-stationary phenomenon) captured in global climate models and dynamical downscaling. Our study quantifies a ramification of the stationarity assumption underlying statistical downscaling.
Emmanuel Nyenah, Petra Döll, Daniel S. Katz, and Robert Reinecke
Geosci. Model Dev., 17, 8593–8611, https://doi.org/10.5194/gmd-17-8593-2024, https://doi.org/10.5194/gmd-17-8593-2024, 2024
Short summary
Short summary
Research software is vital for scientific progress but is often developed by scientists with limited skills, time, and funding, leading to challenges in usability and maintenance. Our study across 10 sectors shows strengths in version control, open-source licensing, and documentation while emphasizing the need for containerization and code quality. We recommend workshops; code quality metrics; funding; and following the findable, accessible, interoperable, and reusable (FAIR) standards.
Chris Smith, Donald P. Cummins, Hege-Beate Fredriksen, Zebedee Nicholls, Malte Meinshausen, Myles Allen, Stuart Jenkins, Nicholas Leach, Camilla Mathison, and Antti-Ilari Partanen
Geosci. Model Dev., 17, 8569–8592, https://doi.org/10.5194/gmd-17-8569-2024, https://doi.org/10.5194/gmd-17-8569-2024, 2024
Short summary
Short summary
Climate projections are only useful if the underlying models that produce them are well calibrated and can reproduce observed climate change. We formalise a software package that calibrates the open-source FaIR simple climate model to full-complexity Earth system models. Observations, including historical warming, and assessments of key climate variables such as that of climate sensitivity are used to constrain the model output.
Jingwei Xie, Xi Wang, Hailong Liu, Pengfei Lin, Jiangfeng Yu, Zipeng Yu, Junlin Wei, and Xiang Han
Geosci. Model Dev., 17, 8469–8493, https://doi.org/10.5194/gmd-17-8469-2024, https://doi.org/10.5194/gmd-17-8469-2024, 2024
Short summary
Short summary
We propose the concept of mesoscale ocean direct numerical simulation (MODNS), which should resolve the first baroclinic deformation radius and ensure the numerical dissipative effects do not directly contaminate the mesoscale motions. It can be a benchmark for testing mesoscale ocean large eddy simulation (MOLES) methods in ocean models. We build an idealized Southern Ocean model using MITgcm to generate a type of MODNS. We also illustrate the diversity of multiscale eddy interactions.
Emily Black, John Ellis, and Ross I. Maidment
Geosci. Model Dev., 17, 8353–8372, https://doi.org/10.5194/gmd-17-8353-2024, https://doi.org/10.5194/gmd-17-8353-2024, 2024
Short summary
Short summary
We present General TAMSAT-ALERT, a computationally lightweight and versatile tool for generating ensemble forecasts from time series data. General TAMSAT-ALERT is capable of combining multiple streams of monitoring and meteorological forecasting data into probabilistic hazard assessments. In this way, it complements existing systems and enhances their utility for actionable hazard assessment.
Sarah Schöngart, Lukas Gudmundsson, Mathias Hauser, Peter Pfleiderer, Quentin Lejeune, Shruti Nath, Sonia Isabelle Seneviratne, and Carl-Friedrich Schleussner
Geosci. Model Dev., 17, 8283–8320, https://doi.org/10.5194/gmd-17-8283-2024, https://doi.org/10.5194/gmd-17-8283-2024, 2024
Short summary
Short summary
Precipitation and temperature are two of the most impact-relevant climatic variables. Yet, projecting future precipitation and temperature data under different emission scenarios relies on complex models that are computationally expensive. In this study, we propose a method that allows us to generate monthly means of local precipitation and temperature at low computational costs. Our modelling framework is particularly useful for all downstream applications of climate model data.
Benjamin M. Sanderson, Ben B. B. Booth, John Dunne, Veronika Eyring, Rosie A. Fisher, Pierre Friedlingstein, Matthew J. Gidden, Tomohiro Hajima, Chris D. Jones, Colin G. Jones, Andrew King, Charles D. Koven, David M. Lawrence, Jason Lowe, Nadine Mengis, Glen P. Peters, Joeri Rogelj, Chris Smith, Abigail C. Snyder, Isla R. Simpson, Abigail L. S. Swann, Claudia Tebaldi, Tatiana Ilyina, Carl-Friedrich Schleussner, Roland Séférian, Bjørn H. Samset, Detlef van Vuuren, and Sönke Zaehle
Geosci. Model Dev., 17, 8141–8172, https://doi.org/10.5194/gmd-17-8141-2024, https://doi.org/10.5194/gmd-17-8141-2024, 2024
Short summary
Short summary
We discuss how, in order to provide more relevant guidance for climate policy, coordinated climate experiments should adopt a greater focus on simulations where Earth system models are provided with carbon emissions from fossil fuels together with land use change instructions, rather than past approaches that have largely focused on experiments with prescribed atmospheric carbon dioxide concentrations. We discuss how these goals might be achieved in coordinated climate modeling experiments.
Peter Berg, Thomas Bosshard, Denica Bozhinova, Lars Bärring, Joakim Löw, Carolina Nilsson, Gustav Strandberg, Johan Södling, Johan Thuresson, Renate Wilcke, and Wei Yang
Geosci. Model Dev., 17, 8173–8179, https://doi.org/10.5194/gmd-17-8173-2024, https://doi.org/10.5194/gmd-17-8173-2024, 2024
Short summary
Short summary
When bias adjusting climate model data using quantile mapping, one needs to prescribe what to do at the tails of the distribution, where a larger data range is likely encountered outside of the calibration period. The end result is highly dependent on the method used. We show that, to avoid discontinuities in the time series, one needs to exclude data in the calibration range to also activate the extrapolation functionality in that time period.
Philip J. Rasch, Haruki Hirasawa, Mingxuan Wu, Sarah J. Doherty, Robert Wood, Hailong Wang, Andy Jones, James Haywood, and Hansi Singh
Geosci. Model Dev., 17, 7963–7994, https://doi.org/10.5194/gmd-17-7963-2024, https://doi.org/10.5194/gmd-17-7963-2024, 2024
Short summary
Short summary
We introduce a protocol to compare computer climate simulations to better understand a proposed strategy intended to counter warming and climate impacts from greenhouse gas increases. This slightly changes clouds in six ocean regions to reflect more sunlight and cool the Earth. Example changes in clouds and climate are shown for three climate models. Cloud changes differ between the models, but precipitation and surface temperature changes are similar when their cooling effects are made similar.
Trude Eidhammer, Andrew Gettelman, Katherine Thayer-Calder, Duncan Watson-Parris, Gregory Elsaesser, Hugh Morrison, Marcus van Lier-Walqui, Ci Song, and Daniel McCoy
Geosci. Model Dev., 17, 7835–7853, https://doi.org/10.5194/gmd-17-7835-2024, https://doi.org/10.5194/gmd-17-7835-2024, 2024
Short summary
Short summary
We describe a dataset where 45 parameters related to cloud processes in the Community Earth System Model version 2 (CESM2) Community Atmosphere Model version 6 (CAM6) are perturbed. Three sets of perturbed parameter ensembles (263 members) were created: current climate, preindustrial aerosol loading and future climate with sea surface temperature increased by 4 K.
Ha Thi Minh Ho-Hagemann, Vera Maurer, Stefan Poll, and Irina Fast
Geosci. Model Dev., 17, 7815–7834, https://doi.org/10.5194/gmd-17-7815-2024, https://doi.org/10.5194/gmd-17-7815-2024, 2024
Short summary
Short summary
The regional Earth system model GCOAST-AHOI v2.0 that includes the regional climate model ICON-CLM coupled to the ocean model NEMO and the hydrological discharge model HD via the OASIS3-MCT coupler can be a useful tool for conducting long-term regional climate simulations over the EURO-CORDEX domain. The new OASIS3-MCT coupling interface implemented in ICON-CLM makes it more flexible for coupling to an external ocean model and an external hydrological discharge model.
Sandro Vattioni, Rahel Weber, Aryeh Feinberg, Andrea Stenke, John A. Dykema, Beiping Luo, Georgios A. Kelesidis, Christian A. Bruun, Timofei Sukhodolov, Frank N. Keutsch, Thomas Peter, and Gabriel Chiodo
Geosci. Model Dev., 17, 7767–7793, https://doi.org/10.5194/gmd-17-7767-2024, https://doi.org/10.5194/gmd-17-7767-2024, 2024
Short summary
Short summary
We quantified impacts and efficiency of stratospheric solar climate intervention via solid particle injection. Microphysical interactions of solid particles with the sulfur cycle were interactively coupled to the heterogeneous chemistry scheme and the radiative transfer code of an aerosol–chemistry–climate model. Compared to injection of SO2 we only find a stronger cooling efficiency for solid particles when normalizing to the aerosol load but not when normalizing to the injection rate.
Ingo Richter, Ping Chang, Gokhan Danabasoglu, Dietmar Dommenget, Guillaume Gastineau, Aixue Hu, Takahito Kataoka, Noel Keenlyside, Fred Kucharski, Yuko Okumura, Wonsun Park, Malte Stuecker, Andrea Taschetto, Chunzai Wang, Stephen Yeager, and Sang-Wook Yeh
EGUsphere, https://doi.org/10.5194/egusphere-2024-3110, https://doi.org/10.5194/egusphere-2024-3110, 2024
Short summary
Short summary
The tropical ocean basins influence each other through multiple pathways and mechanisms, here referred to as tropical basin interaction (TBI). Many researchers have examined TBI using comprehensive climate models, but have obtained conflicting results. This may be partly due to differences in experiment protocols, and partly due to systematic model errors. TBIMIP aims to address this problem by designing a set of TBI experiments that will be performed by multiple models.
Cited articles
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: a system for large-scale machine learning, in: Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation, OSDI'16, pp. 265–283, USENIX Association, USA, ISBN 978-1-931971-33-1, 2016. a
Aydin, O. U., Taha, A. A., Hilbert, A., Khalil, A. A., Galinovic, I., Fiebach, J. B., Frey, D., and Madai, V. I.: On the usage of average Hausdorff distance for segmentation performance assessment: hidden error when used for ranking, European Radiology Experimental, 5, 4, https://doi.org/10.1186/s41747-020-00200-2, 2021. a
Ayzel, G., Scheffer, T., and Heistermann, M.: RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting, Geosci. Model Dev., 13, 2631–2644, https://doi.org/10.5194/gmd-13-2631-2020, 2020. a, b, c
Ballard, S. P., Li, Z., Simonin, D., and Caron, J.-F.: Performance of 4D-Var NWP-based nowcasting of precipitation at the Met Office for summer 2012, Q. J. Roy. Meteor. Soc., 142, 472–487, https://doi.org/10.1002/qj.2665, 2016. a
Bechini, R. and Chandrasekar, V.: An Enhanced Optical Flow Technique for Radar Nowcasting of Precipitation and Winds, J. Atmos. Ocean. Tech., 34, 2637–2658, https://doi.org/10.1175/JTECH-D-17-0110.1, 2017. a
Berthomier, L., Pradel, B., and Perez, L.: Cloud Cover Nowcasting with Deep Learning, in: 2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA), 1–6, https://doi.org/10.1109/IPTA50016.2020.9286606, 2020. a, b, c, d
Chen, R. T. Q., Rubanova, Y., Bettencourt, J., and Duvenaud, D. K.: Neural Ordinary Differential Equations, in: Advances in Neural Information Processing Systems, vol. 31, Curran Associates, Inc., https://doi.org/10.48550/arXiv.1806.07366, 2018. a
Cheng, S., Quilodrán-Casas, C., Ouala, S., Farchi, A., Liu, C., Tandeo, P., Fablet, R., Lucor, D., Iooss, B., Brajard, J., Xiao, D., Janjic, T., Ding, W., Guo, Y., Carrassi, A., Bocquet, M., and Arcucci, R.: Machine Learning With Data Assimilation and Uncertainty Quantification for Dynamical Systems: A Review, IEEE/CAA Journal of Automatica Sinica, 10, 1361–1387, https://doi.org/10.1109/JAS.2023.123537, 2023. a, b
Chollet, F.: Xception: Deep Learning with Depthwise Separable Convolutions, IEEE Computer Society, ISBN 978-1-5386-0457-1, https://doi.org/10.1109/CVPR.2017.195, 2017. a
Courant, R., Friedrichs, K., and Lewy, H.: Über die partiellen Differenzengleichungen der mathematischen Physik, Mathematische Annalen, 100, 32–74, https://doi.org/10.1007/BF01448839, 1928. a
Daw, A., Karpatne, A., Watkins, W., Read, J., and Kumar, V.: Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling, in: Knowledge Guided Machine Learning, Chapman and Hall/CRC, https://doi.org/10.1201/9781003143376-15, 2021. a, b
de Bezenac, E., Pajot, A., and Gallinari, P.: Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge, J. Stat, Mech., 2019, 124009, https://doi.org/10.1088/1742-5468/ab3195, 2018. a, b
Efron, B.: Bootstrap Methods: Another Look at the Jackknife, Ann. Stat., 7, 1–26, https://doi.org/10.1214/aos/1176344552, 1979. a
El Montassir, R.: relmonta/hyphai: Update paper information (v1.1.1), Zenodo [code], https://doi.org/10.5281/zenodo.11518540, 2024. a, b
El Montassir, R., Pannekoucke, O., and Lapeyre, C.: Pre-trained HyPhAICCast-1, HyPhAICCast-2 and U-Net's weights, Zenodo [code], https://doi.org/10.5281/zenodo.10393415, 2023a. a
El Montassir, R., Pannekoucke, O., and Lapeyre, C.: HyPhAICCast-1 2-hour forecast on 01/01/2021 at 12:00 p.m., Zenodo [video], https://doi.org/10.5281/zenodo.10375284, 2023b. a, b
Espeholt, L., Agrawal, S., Sønderby, C., Kumar, M., Heek, J., Bromberg, C., Gazen, C., Carver, R., Andrychowicz, M., Hickey, J., Bell, A., and Kalchbrenner, N.: Deep learning for twelve hour precipitation forecasts, Nat. Commun., 13, 5145, https://doi.org/10.1038/s41467-022-32483-x, 2022. a
European Organisation for the Exploitation of Meteorological Satellites: A sample of the training data used in the paper “A Hybrid Physics-AI (HyPhAI) approach for probability fields advection: Application to cloud cover nowcasting”, Zenodo [data set], https://doi.org/10.5281/zenodo.10642094, 2024. a
Fablet, R., Ouala, S., and Herzet, C.: Bilinear residual Neural Network for the identification and forecasting of dynamical systems, 26th European Signal Processing Conference (EUSIPCO), Rome, Italy, 2018, pp. 1477–1481, https://doi.org/10.23919/EUSIPCO.2018.8553492, 2017. a
Fernandes, B., González-Briones, A., Novais, P., Calafate, M., Analide, C., and Neves, J.: An Adjective Selection Personality Assessment Method Using Gradient Boosting Machine Learning, Processes, 8, 618, https://doi.org/10.3390/pr8050618, 2020. a
Fokker, A. D.: Die mittlere Energie rotierender elektrischer Dipole im Strahlungsfeld, Annalen der Physik, 348, 810–820, https://doi.org/10.1002/andp.19143480507, 1914. a
Forssell, U. and Lindskog, P.: Combining Semi-Physical and Neural Network Modeling: An Example ofIts Usefulness, IFAC Proceedings Volumes, 30, 767–770, https://doi.org/10.1016/S1474-6670(17)42938-7, 1997. a, b
García-Pereda, J., Fernandez-Serdan, J. M., Alonso, O., Sanz, A., Guerra, R., Ariza, C., Santos, I., and Fernández, L.: NWCSAF High Resolution Winds (NWC/GEO-HRW) Stand-Alone Software for Calculation of Atmospheric Motion Vectors and Trajectories, Remote Sens., 11, 2032, https://doi.org/10.3390/rs11172032, 2019. a, b, c, d, e
Gilbert, G. K.: Finley's tornado predictions, Am. Meteorol. J., 1, 166–172, 1884. a
He, K., Zhang, X., Ren, S., and Sun, J.: Deep Residual Learning for Image Recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778, https://doi.org/10.1109/CVPR.2016.90, iSSN: 1063-6919, 2016. a
Hochreiter, S. and Schmidhuber, J.: Long Short-term Memory, Neural computation, 9, 1735–80, https://doi.org/10.1162/neco.1997.9.8.1735, 1997. a
Jia, X., Willard, J., Karpatne, A., Read, J., Zwart, J., Steinbach, M., and Kumar, V.: Physics Guided RNNs for Modeling Dynamical Systems: A Case Study in Simulating Lake Temperature Profiles, in: Proceedings of the 2019 SIAM International Conference on Data Mining (SDM), Proceedings, 558–566, Society for Industrial and Applied Mathematics, https://doi.org/10.1137/1.9781611975673.63, 2019. a, b
Jia, X., Willard, J., Karpatne, A., Read, J. S., Zwart, J. A., Steinbach, M., and Kumar, V.: Physics-Guided Machine Learning for Scientific Discovery: An Application in Simulating Lake Temperature Profiles, ACM/IMS Transactions on Data Science, 2, 20:1–20:26, https://doi.org/10.1145/3447814, 2021. a
Joe, P., Sun, J., Yussouf, N., Goodman, S., Riemer, M., Gouda, K. C., Golding, B., Rogers, R., Isaac, G., Wilson, J., Li, P. W. P., Wulfmeyer, V., Elmore, K., Onvlee, J., Chong, P., and Ladue, J.: Predicting the Weather: A Partnership of Observation Scientists and Forecasters, in: Towards the “Perfect” Weather Warning: Bridging Disciplinary Gaps through Partnership and Communication, edited by: Golding, B., 201–254, Springer International Publishing, Cham, ISBN 978-3-030-98989-7, https://doi.org/10.1007/978-3-030-98989-7_7, 2022. a
Karimi, D. and Salcudean, S. E.: Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networks, in: IEEE Transactions on Medical Imaging, 39, 499–513, https://doi.org/10.1109/TMI.2019.2930068, 2019. a
Karpatne, A., Atluri, G., Faghmous, J., Steinbach, M., Banerjee, A., Ganguly, A., Shekhar, S., Samatova, N., and Kumar, V.: Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data, IEEE T. Knowl. Data En., 29, 2318–2331, https://doi.org/10.1109/TKDE.2017.2720168, 2017. a, b
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings, ArXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 2017. a
Kutta, W.: Beitrag zur näherungsweisen Integration totaler Differentialgleichungen, Zeitschrift für Mathematik und Physik, 46, 435–453, 1901. a
Lin, C., Vasić, S., Kilambi, A., Turner, B., and Zawadzki, I.: Precipitation forecast skill of numerical weather prediction models and radar nowcasts, Geophys. Res. Lett., 32, 14, https://doi.org/10.1029/2005GL023451, 2005. a, b
Matte, D., Christensen, J. H., Feddersen, H., Vedel, H., Nielsen, N. W., Pedersen, R. A., and Zeitzen, R. M. K.: On the Potentials and Limitations of Attributing a Small-Scale Climate Event, Geophys. Res. Lett., 49, e2022GL099481, https://doi.org/10.1029/2022GL099481, 2022. a
Nakahara, M.: Geometry, Topology and Physics (Second Edition), Taylor & Francis, ISBN 0-7503-0606-8, 2003. a
Pannekoucke, O. and Fablet, R.: PDE-NetGen 1.0: from symbolic partial differential equation (PDE) representations of physical processes to trainable neural network representations, Geosci. Model Dev., 13, 3373–3382, https://doi.org/10.5194/gmd-13-3373-2020, 2020. a
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Köpf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., and Chintala, S.: PyTorch: an imperative style, high-performance deep learning library, in: Proceedings of the 33rd International Conference on Neural Information Processing Systems, pp. 8026–8037, Curran Associates Inc., Red Hook, NY, USA, 2019. a
Pavliotis, G. and Stuart, A.: Multiscale Methods: Averaging and Homogenization, vol. 53, Springer, New York, NY, ISBN 978-0-387-73828-4, https://doi.org/10.1007/978-0-387-73829-1, 2008. a, b
Raissi, M., Wang, Z., Triantafyllou, M. S., and Karniadakis, G. E.: Deep Learning of Vortex Induced Vibrations, J. Fluid Mech., 861, 119–137, https://doi.org/10.1017/jfm.2018.872, 2019. a
Ravuri, S., Lenc, K., Willson, M., Kangin, D., Lam, R., Mirowski, P., Fitzsimons, M., Athanassiadou, M., Kashem, S., Madge, S., Prudden, R., Mandhane, A., Clark, A., Brock, A., Simonyan, K., Hadsell, R., Robinson, N., Clancy, E., Arribas, A., and Mohamed, S.: Skilful precipitation nowcasting using deep generative models of radar, Nature, 597, 672–677, https://doi.org/10.1038/s41586-021-03854-z, 2021. a
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, in: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science, edited by: Navab, N., Hornegger, J., Wells, W. M., and Frangi, A. F., vol. 9351, 234–241, Springer International Publishing, Cham, ISBN 978-3-319-24573-7 978-3-319-24574-4, https://doi.org/10.1007/978-3-319-24574-4_28, 2015. a, b
Runge, C.: Ueber die numerische Auflösung von Differentialgleichungen, Mathematische Annalen, 46, 167–178, https://doi.org/10.1007/BF01446807, 1895. a
Ruthotto, L. and Haber, E.: Deep Neural Networks Motivated by Partial Differential Equations, J. Math. Imaging Vis., 62, 352–364, https://doi.org/10.1007/s10851-019-00903-1, 2020. a
Schultz, M. G., Betancourt, C., Gong, B., Kleinert, F., Langguth, M., Leufen, L. H., Mozaffari, A., and Stadtler, S.: Can deep learning beat numerical weather prediction?, Philos. T. A, 379, 20200097, https://doi.org/10.1098/rsta.2020.0097, 2021. a
Schweidtmann, A. M., Zhang, D., and von Stosch, M.: A review and perspective on hybrid modeling methodologies, Digital Chemical Engineering, 10, 100 136, https://doi.org/10.1016/j.dche.2023.100136, 2024. a
Shah, S., Dey, D., Lovett, C., and Kapoor, A.: AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles, in: Field and Service Robotics. Springer Proceedings in Advanced Robotics, edited by: Hutter, M. and Siegwart, R., vol 5, Springer, Cham, https://doi.org/10.1007/978-3-319-67361-5_40, 2017. a
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-k., and Woo, W.-c.: Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting, in: Advances in Neural Information Processing Systems, vol. 28, Curran Associates, Inc., https://proceedings.neurips.cc/paper/2015/hash/07563a3fe3bbe7e3ba84431ad9d055af-Abstract.html (last access: 7 June 2024), 2015. a, b
Sokolova, M. and Lapalme, G.: A systematic analysis of performance measures for classification tasks, Inform. Process. Manage., 45, 427–437, https://doi.org/10.1016/j.ipm.2009.03.002, 2009. a
Sultan, M. M., Wayment-Steele, H. K., and Pande, V. S.: Transferable Neural Networks for Enhanced Sampling of Protein Dynamics, J. Chem. Theor. Comput., 14, 1887–1894, https://doi.org/10.1021/acs.jctc.8b00025, 2018. a
Sun, J., Xue, M., Wilson, J. W., Zawadzki, I., Ballard, S. P., Onvlee-Hooimeyer, J., Joe, P., Barker, D. M., Li, P.-W., Golding, B., Xu, M., and Pinto, J.: Use of NWP for Nowcasting Convective Precipitation: Recent Progress and Challenges, B. Am. Meteorol. Soc., 95, 409–426, https://doi.org/10.1175/BAMS-D-11-00263.1, 2014. a, b
Takahashi, K., Yamamoto, K., Kuchiba, A., and Koyama, T.: Confidence interval for micro-averaged F1 and macro-averaged F1 scores, Applied Intelligence, 52, 4961–4972, https://doi.org/10.1007/s10489-021-02635-5, 2022. a
Tamvakis, P. N., Kiourt, C., Solomou, A. D., Ioannakis, G., and Tsirliganis, N. C.: Semantic Image Segmentation with Deep Learning for Vine Leaf Phenotyping, IFAC-PapersOnLine, 55, 83–88, https://doi.org/10.1016/j.ifacol.2022.11.119, 2022. a
Trebing, K., Stanczyk, T., and Mehrkanoon, S.: SmaAt-UNet: Precipitation nowcasting using a small attention-UNet architecture, Pattern Recogn. Lett., 145, 178–186, https://doi.org/10.1016/j.patrec.2021.01.036, 2021. a, b, c
Wang, S.-H., Nayak, D. R., Guttery, D. S., Zhang, X., and Zhang, Y.-D.: COVID-19 classification by CCSHNet with deep fusion using transfer learning and discriminant correlation analysis, Information Fusion, 68, 131–148, https://doi.org/10.1016/j.inffus.2020.11.005, 2021. a
Wang, Y., Gao, Z., Long, M., Jianmin Wang, Wang, J., Yu, P. S., and Philip S. Yu: PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning, ICML, pp. 5110–5119, aRXIV_ID: 1804.06300 MAG ID: 2963326684 S2ID: d718941506d2adabc4792cb13d49e6336957e52e, 2018. a
Wang, Y., Zhang, J., Zhu, H., Long, M., Wang, J., and Yu, P. S.: Memory in Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamics, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 9146–9154, https://doi.org/10.1109/CVPR.2019.00937, 2019. a
Willard, J., Jia, X., Xu, S., Steinbach, M., and Kumar, V.: Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems, ACM Computing Surveys, 55, 1–37, https://doi.org/10.1145/3514228, 2022. a
Wood-Bradley, P., Zapata, J., and Pye, J.: Cloud tracking with optical flow for short-term solar forecasting, in: Proceedings of 50th Annual AuSES Conference (Solar 2012), Australian Solar Energy Society, https://openresearch-repository.anu.edu.au/handle/1885/28800 (last access: 17 November 2022), 2012. a
Short summary
This study introduces a novel approach that combines physics and artificial intelligence (AI) for improved cloud cover forecasting. This approach outperforms traditional deep learning (DL) methods in producing realistic and physically consistent results while requiring less training data. This architecture provides a promising solution to overcome the limitations of classical AI methods and contributes to open up new possibilities for combining physical knowledge with deep learning models.
This study introduces a novel approach that combines physics and artificial intelligence (AI)...
