Articles | Volume 18, issue 4
https://doi.org/10.5194/gmd-18-921-2025
© Author(s) 2025. 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-18-921-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
19 Feb 2025
Development and technical paper |
| 19 Feb 2025
| 19 Feb 2025
Advances in land surface forecasting: a comparison of LSTM, gradient boosting, and feed-forward neural networks as prognostic state emulators in a case study with ecLand
Marieke Wesselkamp
CORRESPONDING AUTHOR
Department of Biometry, University of Freiburg, Freiburg, Germany
Matthew Chantry
European Centre for Medium-Range Weather Forecasts, Reading, United Kingdom
Ewan Pinnington
European Centre for Medium-Range Weather Forecasts, Reading, United Kingdom
Margarita Choulga
European Centre for Medium-Range Weather Forecasts, Reading, United Kingdom
Souhail Boussetta
European Centre for Medium-Range Weather Forecasts, Reading, United Kingdom
Maria Kalweit
Department of Computer Science, University of Freiburg, Freiburg, Germany
Joschka Bödecker
Department of Computer Science, University of Freiburg, Freiburg, Germany
BrainLinks-BrainTools, University of Freiburg, Freiburg, Germany
Carsten F. Dormann
Department of Biometry, University of Freiburg, Freiburg, Germany
Florian Pappenberger
European Centre for Medium-Range Weather Forecasts, Reading, United Kingdom
Gianpaolo Balsamo
European Centre for Medium-Range Weather Forecasts, Reading, United Kingdom
World Meteorological Organization, Geneva, Switzerland
Related authors
No articles found.
Jasmin Tesch, Kathrin Kühnhammer, Delon Wagner, Andreas Christen, Carsten Dormann, Julian Frey, Rüdiger Grote, Teja Kattenborn, Markus Sulzer, Ulrike Wallrabe, Markus Weiler, Christiane Werner, Samaneh Baghbani, Julian Brzozon, Laura Maria Comella, Lea Dedden, Stefanie Dumberger, Yasmina Frey, Matthias Gassilloud, Timo Gerach, Anna Göritz, Simon Haberstroh, Johannes Klüppel, Luis Kremer, Jürgen Kreuzwieser, Hojin Lee, Joachim Maack, Julian Müller, Oswald Prucker, Sanam K. Rajak, Jürgen Rühe, Stefan J. Rupitsch, Helmer Schack-Kirchner, Christian Scharinger, Uttunga Shinde, Till Steinmann, Clara Stock, and Josef Strack
Geosci. Instrum. Method. Data Syst., 15, 253–272, https://doi.org/10.5194/gi-15-253-2026, https://doi.org/10.5194/gi-15-253-2026, 2026
Short summary
Short summary
In the ECOSENSE forest, we developed a robust infrastructure for distributed forest sensing. Reliable power supply, stable network connection, and smart data collection systems enable the operation of hundreds of sensors under challenging conditions. By detailing the infrastructure design and implementation, we provide a transferable blueprint for building complex monitoring sites that support high-resolution, long-term ecosystem observations.
Cinzia Mazzetti, Hannah Cloke, Dai Yamazaki, Gianpaolo Balsamo, Souhail Boussetta, Jasper Denissen, Michel Wortmann, Gabriele Arduini, Gurpreet Dass, Joe McNorton, Anna Agusti-Panareda, Maliko Tanguy, Ervin Zsoter, Margarita Choulga, Emanuel Dutra, Florian Pappenberger, Christoph Rüdiger, and Christel Prudhomme
EGUsphere, https://doi.org/10.5194/egusphere-2026-4305, https://doi.org/10.5194/egusphere-2026-4305, 2026
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
Rivers are an essential component of the water cycle, yet many Earth system and weather prediction models do not explicitly represent river flow. We integrated a global river model into ECMWF's forecasting system, enabling the simulation of river discharge, water levels, and flooding within a single operational framework. This development lays the foundation for future land–river–atmosphere interactions, paving the way for more complete Earth system models and improved predictions.
Nina Raoult, Ewan Pinnington, Mario Santa Cruz, Florian Pinault, Baudouin Raoult, Natalie Zelenka, Gabriele Arduini, Gianpaolo Balsamo, Souhail Boussetta, Matthew Chantry, Patricia de Rosnay, Peter Dueben, and Christoph Rüdiger
EGUsphere, https://doi.org/10.5194/egusphere-2026-3620, https://doi.org/10.5194/egusphere-2026-3620, 2026
Short summary
Short summary
The land surface shapes our weather and climate by controlling how heat and water move between the ground and the air, so the models representing it matter enormously. But they are costly to run and carry built-in errors. We built a faster artificial-intelligence version of one, then used real measurements from sites worldwide to correct some of these errors. The result stays reliable over years and better captures these heat and water exchanges—a quicker, more accurate tool for forecasting.
Karan Ruparell, Dai Yamazaki, Kieran Hunt, Hannah Cloke, Christel Prudhomme, Florian Pappenberger, and Matthew Chantry
EGUsphere, https://doi.org/10.5194/egusphere-2026-2909, https://doi.org/10.5194/egusphere-2026-2909, 2026
Short summary
Short summary
Reservoirs change how rivers behave, making them harder to predict. We tested whether machine learning models can learn these effects by training on river sites with and without upstream reservoirs across Great Britain. Models without reservoir training overestimated regulated flows, while reservoir-only models performed poorly on natural rivers. Training on both performed well everywhere. All models failed at heavily managed reservoirs where human decisions dominate river flow.
Ather Abbas, Yuan Yang, Ming Pan, Yves Tramblay, Chaopeng Shen, Haoyu Ji, Solomon H. Gebrechorkos, Florian Pappenberger, JongCheol Pyo, Dapeng Feng, George Huffman, Phu Nguyen, Christian Massari, Luca Brocca, Jackson Tan, and Hylke E. Beck
Hydrol. Earth Syst. Sci., 30, 3399–3423, https://doi.org/10.5194/hess-30-3399-2026, https://doi.org/10.5194/hess-30-3399-2026, 2026
Short summary
Short summary
Our study evaluated 24 precipitation datasets using a hydrological model at global scale to assess their suitability and accuracy. We found that MSWEP (Multi-Source Weighted-Ensemble Precipitation) V2.8 excels due to its ability to integrate data from multiple sources, while others, such as IMERG (Integrated Multi-satellitE Retrievals for Global Precipitation Mission) and GDAS (Global Data Assimilation System), demonstrated strong regional performances. This research assists in selecting the appropriate dataset for applications in water resource management, hazard assessment, agriculture, and environmental monitoring.
Gabriel Moldovan, Ewan Pinnington, Ana Prieto Nemesio, Simon Lang, Zied Ben Bouallègue, Jesper Dramsch, Mihai Alexe, Mario Santa Cruz, Sara Hahner, Harrison Cook, Helen Theissen, Mariana Clare, Cathal O'Brien, Jan Polster, Linus Magnusson, Gert Mertes, Florian Pinault, Baudouin Raoult, Patricia de Rosnay, Richard Forbes, and Matthew Chantry
Geosci. Model Dev., 19, 4703–4724, https://doi.org/10.5194/gmd-19-4703-2026, https://doi.org/10.5194/gmd-19-4703-2026, 2026
Short summary
Short summary
We present the latest release of the Artificial Intelligence Forecasting System, AIFS 1.1.0, which shows improved headline forecasting skill through an expanded dataset and enhanced training schedule. The model also incorporates hard physical constraints that facilitate training and improve rainfall prediction. Finally, we extend the set of forecasted variables to include soil conditions and energy-related fields, strengthening the operational value of AIFS.
Hamidreza Mosaffa, Florian Pappenberger, Christel Prudhomme, Matthew Chantry, Christoph Rüdiger, and Hannah Cloke
Hydrol. Earth Syst. Sci., 30, 2079–2092, https://doi.org/10.5194/hess-30-2079-2026, https://doi.org/10.5194/hess-30-2079-2026, 2026
Short summary
Short summary
This study improves river flow prediction by combining two types of artificial intelligence models. One model estimates how rainfall becomes runoff in each part of a river basin, while another represents how water moves through the river network. By linking these processes, the approach better captures how water travels across large basins. The results show more accurate streamflow predictions, which can support water management and flood forecasting.
Fatima M. Pillosu, Mariana Claire, Calum Baugh, Florian Pappenberger, Christel Prudhome, and Hannah L. Cloke
EGUsphere, https://doi.org/10.5194/egusphere-2026-1591, https://doi.org/10.5194/egusphere-2026-1591, 2026
Short summary
Short summary
This paper presents the first global, medium-range probabilistic forecasts of flash flood occurrence. A single XGBoost model trained on coarse impact reports achieves skilful predictions, challenging assumptions that complex architectures and high-resolution data are required. At a time of heightened attention to flash flood risk and early warning, this work demonstrates that skilful global forecasting is achievable in data-sparse regions where flash flood risk is highest.
Gabriele Arduini, Christoph Rüdiger, and Gianpaolo Balsamo
The Cryosphere, 20, 1119–1137, https://doi.org/10.5194/tc-20-1119-2026, https://doi.org/10.5194/tc-20-1119-2026, 2026
Short summary
Short summary
Glaciers and ice sheets are critical components of the climate system. A set of improvements to snow and ice processes, targeting glacier and ice sheet regions, are introduced in a land surface model used to produce Weather Forecasts and climate reanalyses. The results demonstrate that more realistic snow and ice processes can lead to positive impacts on the simulation of various Earth System components, e.g. the surface temperature and the streamflow of rivers contributed by glacier melting.
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.
Gab Abramowitz, Anna Ukkola, Sanaa Hobeichi, Jon Cranko Page, Mathew Lipson, Martin G. De Kauwe, Samuel Green, Claire Brenner, Jonathan Frame, Grey Nearing, Martyn Clark, Martin Best, Peter Anthoni, Gabriele Arduini, Souhail Boussetta, Silvia Caldararu, Kyeungwoo Cho, Matthias Cuntz, David Fairbairn, Craig R. Ferguson, Hyungjun Kim, Yeonjoo Kim, Jürgen Knauer, David Lawrence, Xiangzhong Luo, Sergey Malyshev, Tomoko Nitta, Jerome Ogee, Keith Oleson, Catherine Ottlé, Phillipe Peylin, Patricia de Rosnay, Heather Rumbold, Bob Su, Nicolas Vuichard, Anthony P. Walker, Xiaoni Wang-Faivre, Yunfei Wang, and Yijian Zeng
Biogeosciences, 21, 5517–5538, https://doi.org/10.5194/bg-21-5517-2024, https://doi.org/10.5194/bg-21-5517-2024, 2024
Short summary
Short summary
This paper evaluates land models – computer-based models that simulate ecosystem dynamics; land carbon, water, and energy cycles; and the role of land in the climate system. It uses machine learning and AI approaches to show that, despite the complexity of land models, they do not perform nearly as well as they could given the amount of information they are provided with about the prediction problem.
Sven Armin Westermann, Anke Hildebrandt, Souhail Bousetta, and Stephan Thober
Biogeosciences, 21, 5277–5303, https://doi.org/10.5194/bg-21-5277-2024, https://doi.org/10.5194/bg-21-5277-2024, 2024
Short summary
Short summary
Plants at the land surface mediate between soil and the atmosphere regarding water and carbon transport. Since plant growth is a dynamic process, models need to consider these dynamics. Two models that predict water and carbon fluxes by considering plant temporal evolution were tested against observational data. Currently, dynamizing plants in these models did not enhance their representativeness, which is caused by a mismatch between implemented physical relations and observable connections.
Cecile B. Menard, Sirpa Rasmus, Ioanna Merkouriadi, Gianpaolo Balsamo, Annett Bartsch, Chris Derksen, Florent Domine, Marie Dumont, Dorothee Ehrich, Richard Essery, Bruce C. Forbes, Gerhard Krinner, David Lawrence, Glen Liston, Heidrun Matthes, Nick Rutter, Melody Sandells, Martin Schneebeli, and Sari Stark
The Cryosphere, 18, 4671–4686, https://doi.org/10.5194/tc-18-4671-2024, https://doi.org/10.5194/tc-18-4671-2024, 2024
Short summary
Short summary
Computer models, like those used in climate change studies, are written by modellers who have to decide how best to construct the models in order to satisfy the purpose they serve. Using snow modelling as an example, we examine the process behind the decisions to understand what motivates or limits modellers in their decision-making. We find that the context in which research is undertaken is often more crucial than scientific limitations. We argue for more transparency in our research practice.
Margarita Choulga, Francesca Moschini, Cinzia Mazzetti, Stefania Grimaldi, Juliana Disperati, Hylke Beck, Peter Salamon, and Christel Prudhomme
Hydrol. Earth Syst. Sci., 28, 2991–3036, https://doi.org/10.5194/hess-28-2991-2024, https://doi.org/10.5194/hess-28-2991-2024, 2024
Short summary
Short summary
CEMS_SurfaceFields_2022 dataset is a new set of high-resolution maps for land type (e.g. lake, forest), soil properties and population water needs at approximately 2 and 6 km at the Equator, covering Europe and the globe (excluding Antarctica). We describe what and how new high-resolution information can be used to create the dataset. The paper suggests that the dataset can be used as input for river, weather or other models, as well as for statistical descriptions of the region of interest.
Jasper M. C. Denissen, Adriaan J. Teuling, Sujan Koirala, Markus Reichstein, Gianpaolo Balsamo, Martha M. Vogel, Xin Yu, and René Orth
Earth Syst. Dynam., 15, 717–734, https://doi.org/10.5194/esd-15-717-2024, https://doi.org/10.5194/esd-15-717-2024, 2024
Short summary
Short summary
Heat extremes have severe implications for human health and ecosystems. Heat extremes are mostly introduced by large-scale atmospheric circulation but can be modulated by vegetation. Vegetation with access to water uses solar energy to evaporate water into the atmosphere. Under dry conditions, water may not be available, suppressing evaporation and heating the atmosphere. Using climate projections, we show that regionally less water is available for vegetation, intensifying future heat extremes.
Dominik L. Schumacher, Mariam Zachariah, Friederike Otto, Clair Barnes, Sjoukje Philip, Sarah Kew, Maja Vahlberg, Roop Singh, Dorothy Heinrich, Julie Arrighi, Maarten van Aalst, Mathias Hauser, Martin Hirschi, Verena Bessenbacher, Lukas Gudmundsson, Hiroko K. Beaudoing, Matthew Rodell, Sihan Li, Wenchang Yang, Gabriel A. Vecchi, Luke J. Harrington, Flavio Lehner, Gianpaolo Balsamo, and Sonia I. Seneviratne
Earth Syst. Dynam., 15, 131–154, https://doi.org/10.5194/esd-15-131-2024, https://doi.org/10.5194/esd-15-131-2024, 2024
Short summary
Short summary
The 2022 summer was accompanied by widespread soil moisture deficits, including an unprecedented drought in Europe. Combining several observation-based estimates and models, we find that such an event has become at least 5 and 20 times more likely due to human-induced climate change in western Europe and the northern extratropics, respectively. Strong regional warming fuels soil desiccation; hence, projections indicate even more potent future droughts as we progress towards a 2 °C warmer world.
Tom Kimpson, Margarita Choulga, Matthew Chantry, Gianpaolo Balsamo, Souhail Boussetta, Peter Dueben, and Tim Palmer
Hydrol. Earth Syst. Sci., 27, 4661–4685, https://doi.org/10.5194/hess-27-4661-2023, https://doi.org/10.5194/hess-27-4661-2023, 2023
Short summary
Short summary
Lakes play an important role when we try to explain and predict the weather. More accurate and up-to-date description of lakes all around the world for numerical models is a continuous task. However, it is difficult to assess the impact of updated lake description within a weather prediction system. In this work, we develop a method to quickly and automatically define how, where, and when updated lake description affects weather prediction.
Gregory Duveiller, Mark Pickering, Joaquin Muñoz-Sabater, Luca Caporaso, Souhail Boussetta, Gianpaolo Balsamo, and Alessandro Cescatti
Geosci. Model Dev., 16, 7357–7373, https://doi.org/10.5194/gmd-16-7357-2023, https://doi.org/10.5194/gmd-16-7357-2023, 2023
Short summary
Short summary
Some of our best tools to describe the state of the land system, including the intensity of heat waves, have a problem. The model currently assumes that the number of leaves in ecosystems always follows the same cycle. By using satellite observations of when leaves are present, we show that capturing the yearly changes in this cycle is important to avoid errors in estimating surface temperature. We show that this has strong implications for our capacity to describe heat waves across Europe.
Fransje van Oorschot, Ruud J. van der Ent, Markus Hrachowitz, Emanuele Di Carlo, Franco Catalano, Souhail Boussetta, Gianpaolo Balsamo, and Andrea Alessandri
Earth Syst. Dynam., 14, 1239–1259, https://doi.org/10.5194/esd-14-1239-2023, https://doi.org/10.5194/esd-14-1239-2023, 2023
Short summary
Short summary
Vegetation largely controls land hydrology by transporting water from the subsurface to the atmosphere through roots and is highly variable in space and time. However, current land surface models have limitations in capturing this variability at a global scale, limiting accurate modeling of land hydrology. We found that satellite-based vegetation variability considerably improved modeled land hydrology and therefore has potential to improve climate predictions of, for example, droughts.
Matthew J. McGrath, Ana Maria Roxana Petrescu, Philippe Peylin, Robbie M. Andrew, Bradley Matthews, Frank Dentener, Juraj Balkovič, Vladislav Bastrikov, Meike Becker, Gregoire Broquet, Philippe Ciais, Audrey Fortems-Cheiney, Raphael Ganzenmüller, Giacomo Grassi, Ian Harris, Matthew Jones, Jürgen Knauer, Matthias Kuhnert, Guillaume Monteil, Saqr Munassar, Paul I. Palmer, Glen P. Peters, Chunjing Qiu, Mart-Jan Schelhaas, Oksana Tarasova, Matteo Vizzarri, Karina Winkler, Gianpaolo Balsamo, Antoine Berchet, Peter Briggs, Patrick Brockmann, Frédéric Chevallier, Giulia Conchedda, Monica Crippa, Stijn N. C. Dellaert, Hugo A. C. Denier van der Gon, Sara Filipek, Pierre Friedlingstein, Richard Fuchs, Michael Gauss, Christoph Gerbig, Diego Guizzardi, Dirk Günther, Richard A. Houghton, Greet Janssens-Maenhout, Ronny Lauerwald, Bas Lerink, Ingrid T. Luijkx, Géraud Moulas, Marilena Muntean, Gert-Jan Nabuurs, Aurélie Paquirissamy, Lucia Perugini, Wouter Peters, Roberto Pilli, Julia Pongratz, Pierre Regnier, Marko Scholze, Yusuf Serengil, Pete Smith, Efisio Solazzo, Rona L. Thompson, Francesco N. Tubiello, Timo Vesala, and Sophia Walther
Earth Syst. Sci. Data, 15, 4295–4370, https://doi.org/10.5194/essd-15-4295-2023, https://doi.org/10.5194/essd-15-4295-2023, 2023
Short summary
Short summary
Accurate estimation of fluxes of carbon dioxide from the land surface is essential for understanding future impacts of greenhouse gas emissions on the climate system. A wide variety of methods currently exist to estimate these sources and sinks. We are continuing work to develop annual comparisons of these diverse methods in order to clarify what they all actually calculate and to resolve apparent disagreement, in addition to highlighting opportunities for increased understanding.
Anna Agustí-Panareda, Jérôme Barré, Sébastien Massart, Antje Inness, Ilse Aben, Melanie Ades, Bianca C. Baier, Gianpaolo Balsamo, Tobias Borsdorff, Nicolas Bousserez, Souhail Boussetta, Michael Buchwitz, Luca Cantarello, Cyril Crevoisier, Richard Engelen, Henk Eskes, Johannes Flemming, Sébastien Garrigues, Otto Hasekamp, Vincent Huijnen, Luke Jones, Zak Kipling, Bavo Langerock, Joe McNorton, Nicolas Meilhac, Stefan Noël, Mark Parrington, Vincent-Henri Peuch, Michel Ramonet, Miha Razinger, Maximilian Reuter, Roberto Ribas, Martin Suttie, Colm Sweeney, Jérôme Tarniewicz, and Lianghai Wu
Atmos. Chem. Phys., 23, 3829–3859, https://doi.org/10.5194/acp-23-3829-2023, https://doi.org/10.5194/acp-23-3829-2023, 2023
Short summary
Short summary
We present a global dataset of atmospheric CO2 and CH4, the two most important human-made greenhouse gases, which covers almost 2 decades (2003–2020). It is produced by combining satellite data of CO2 and CH4 with a weather and air composition prediction model, and it has been carefully evaluated against independent observations to ensure validity and point out deficiencies to the user. This dataset can be used for scientific studies in the field of climate change and the global carbon cycle.
Ana Maria Roxana Petrescu, Chunjing Qiu, Matthew J. McGrath, Philippe Peylin, Glen P. Peters, Philippe Ciais, Rona L. Thompson, Aki Tsuruta, Dominik Brunner, Matthias Kuhnert, Bradley Matthews, Paul I. Palmer, Oksana Tarasova, Pierre Regnier, Ronny Lauerwald, David Bastviken, Lena Höglund-Isaksson, Wilfried Winiwarter, Giuseppe Etiope, Tuula Aalto, Gianpaolo Balsamo, Vladislav Bastrikov, Antoine Berchet, Patrick Brockmann, Giancarlo Ciotoli, Giulia Conchedda, Monica Crippa, Frank Dentener, Christine D. Groot Zwaaftink, Diego Guizzardi, Dirk Günther, Jean-Matthieu Haussaire, Sander Houweling, Greet Janssens-Maenhout, Massaer Kouyate, Adrian Leip, Antti Leppänen, Emanuele Lugato, Manon Maisonnier, Alistair J. Manning, Tiina Markkanen, Joe McNorton, Marilena Muntean, Gabriel D. Oreggioni, Prabir K. Patra, Lucia Perugini, Isabelle Pison, Maarit T. Raivonen, Marielle Saunois, Arjo J. Segers, Pete Smith, Efisio Solazzo, Hanqin Tian, Francesco N. Tubiello, Timo Vesala, Guido R. van der Werf, Chris Wilson, and Sönke Zaehle
Earth Syst. Sci. Data, 15, 1197–1268, https://doi.org/10.5194/essd-15-1197-2023, https://doi.org/10.5194/essd-15-1197-2023, 2023
Short summary
Short summary
This study updates the state-of-the-art scientific overview of CH4 and N2O emissions in the EU27 and UK in Petrescu et al. (2021a). Yearly updates are needed to improve the different respective approaches and to inform on the development of formal verification systems. It integrates the most recent emission inventories, process-based model and regional/global inversions, comparing them with UNFCCC national GHG inventories, in support to policy to facilitate real-time verification procedures.
Kieran M. R. Hunt, Gwyneth R. Matthews, Florian Pappenberger, and Christel Prudhomme
Hydrol. Earth Syst. Sci., 26, 5449–5472, https://doi.org/10.5194/hess-26-5449-2022, https://doi.org/10.5194/hess-26-5449-2022, 2022
Short summary
Short summary
In this study, we use three models to forecast river streamflow operationally for 13 months (September 2020 to October 2021) at 10 gauges in the western US. The first model is a state-of-the-art physics-based streamflow model (GloFAS). The second applies a bias-correction technique to GloFAS. The third is a type of neural network (an LSTM). We find that all three are capable of producing skilful forecasts but that the LSTM performs the best, with skilful 5 d forecasts at nine stations.
Melissa Ruiz-Vásquez, Sungmin O, Alexander Brenning, Randal D. Koster, Gianpaolo Balsamo, Ulrich Weber, Gabriele Arduini, Ana Bastos, Markus Reichstein, and René Orth
Earth Syst. Dynam., 13, 1451–1471, https://doi.org/10.5194/esd-13-1451-2022, https://doi.org/10.5194/esd-13-1451-2022, 2022
Short summary
Short summary
Subseasonal forecasts facilitate early warning of extreme events; however their predictability sources are not fully explored. We find that global temperature forecast errors in many regions are related to climate variables such as solar radiation and precipitation, as well as land surface variables such as soil moisture and evaporative fraction. A better representation of these variables in the forecasting and data assimilation systems can support the accuracy of temperature forecasts.
Joe McNorton, Nicolas Bousserez, Anna Agustí-Panareda, Gianpaolo Balsamo, Luca Cantarello, Richard Engelen, Vincent Huijnen, Antje Inness, Zak Kipling, Mark Parrington, and Roberto Ribas
Atmos. Chem. Phys., 22, 5961–5981, https://doi.org/10.5194/acp-22-5961-2022, https://doi.org/10.5194/acp-22-5961-2022, 2022
Short summary
Short summary
Concentrations of atmospheric methane continue to grow, in recent years at an increasing rate, for unknown reasons. Using newly available satellite observations and a state-of-the-art weather prediction model we perform global estimates of emissions from hotspots at high resolution. Results show that the system can accurately report on biases in national inventories and is used to conclude that the early COVID-19 slowdown period (March–June 2020) had little impact on global methane emissions.
Ralf Döscher, Mario Acosta, Andrea Alessandri, Peter Anthoni, Thomas Arsouze, Tommi Bergman, Raffaele Bernardello, Souhail Boussetta, Louis-Philippe Caron, Glenn Carver, Miguel Castrillo, Franco Catalano, Ivana Cvijanovic, Paolo Davini, Evelien Dekker, Francisco J. Doblas-Reyes, David Docquier, Pablo Echevarria, Uwe Fladrich, Ramon Fuentes-Franco, Matthias Gröger, Jost v. Hardenberg, Jenny Hieronymus, M. Pasha Karami, Jukka-Pekka Keskinen, Torben Koenigk, Risto Makkonen, François Massonnet, Martin Ménégoz, Paul A. Miller, Eduardo Moreno-Chamarro, Lars Nieradzik, Twan van Noije, Paul Nolan, Declan O'Donnell, Pirkka Ollinaho, Gijs van den Oord, Pablo Ortega, Oriol Tintó Prims, Arthur Ramos, Thomas Reerink, Clement Rousset, Yohan Ruprich-Robert, Philippe Le Sager, Torben Schmith, Roland Schrödner, Federico Serva, Valentina Sicardi, Marianne Sloth Madsen, Benjamin Smith, Tian Tian, Etienne Tourigny, Petteri Uotila, Martin Vancoppenolle, Shiyu Wang, David Wårlind, Ulrika Willén, Klaus Wyser, Shuting Yang, Xavier Yepes-Arbós, and Qiong Zhang
Geosci. Model Dev., 15, 2973–3020, https://doi.org/10.5194/gmd-15-2973-2022, https://doi.org/10.5194/gmd-15-2973-2022, 2022
Short summary
Short summary
The Earth system model EC-Earth3 is documented here. Key performance metrics show physical behavior and biases well within the frame known from recent models. With improved physical and dynamic features, new ESM components, community tools, and largely improved physical performance compared to the CMIP5 version, EC-Earth3 represents a clear step forward for the only European community ESM. We demonstrate here that EC-Earth3 is suited for a range of tasks in CMIP6 and beyond.
Margarita Choulga, Greet Janssens-Maenhout, Ingrid Super, Efisio Solazzo, Anna Agusti-Panareda, Gianpaolo Balsamo, Nicolas Bousserez, Monica Crippa, Hugo Denier van der Gon, Richard Engelen, Diego Guizzardi, Jeroen Kuenen, Joe McNorton, Gabriel Oreggioni, and Antoon Visschedijk
Earth Syst. Sci. Data, 13, 5311–5335, https://doi.org/10.5194/essd-13-5311-2021, https://doi.org/10.5194/essd-13-5311-2021, 2021
Short summary
Short summary
People worry that growing man-made carbon dioxide (CO2) concentrations lead to climate change. Global models, use of observations, and datasets can help us better understand behaviour of CO2. Here a tool to compute uncertainty in man-made CO2 sources per country per year and month is presented. An example of all sources separated into seven groups (intensive and average energy, industry, humans, ground and air transport, others) is presented. Results will be used to predict CO2 concentrations.
Cited articles
Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M.: Optuna: A Next-generation Hyperparameter Optimization Framework, in: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD '19: The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 4–8 August 2019, Anchorage AK, USA, 2623–2631, https://doi.org/10.1145/3292500.3330701, 2019.
Baker, E., Harper, A. B., Williamson, D., and Challenor, P.: Emulation of high-resolution land surface models using sparse Gaussian processes with application to JULES, Geosci. Model Dev., 15, 1913–1929, https://doi.org/10.5194/gmd-15-1913-2022, 2022.
Balsamo, G., Bousseea, S., Dutra, E., Beljaars, A., Viterbo, P., and Van den Hurk, B.: ECMWF Newsleeer No 127, Meteorology, Spring 2011, 17–22, https://doi.org/10.21957/x1j3i7bz, 2011.
Bassi, A., Höge, M., Mira, A., Fenicia, F., and Albert, C.: Learning landscape features from streamflow with autoencoders, Hydrol. Earth Syst. Sci., 28, 4971–4988, https://doi.org/10.5194/hess-28-4971-2024, 2024.
Bengtsson, L. K., Magnusson, L., and Källén, E.: Independent Estimations of the Asymptotic Variability in an Ensemble Forecast System, Mon. Weather Rev., 136, 4105–4112, https://doi.org/10.1175/2008MWR2526.1, 2008.
Beucler, T., Pritchard, M., Rasp, S., Ott, J., Baldi, P., and Gentine, P.: Enforcing Analytic Constraints in Neural Networks Emulating Physical Systems, Phys. Rev. Lett., 126, 098302, https://doi.org/10.1103/PhysRevLett.126.098302, 2021.
Bi, K., Xie, L., Zhang, H., Chen, X., Gu, X., and Tian, Q.: Accurate medium-range global weather forecasting with 3D neural networks, Nature, 619, 533–538, https://doi.org/10.1038/s41586-023-06185-3, 2023.
Boussetta, S., Balsamo, G., Arduini, G., Dutra, E., McNorton, J., Choulga, M., Agustí-Panareda, A., Beljaars, A., Wedi, N., Munõz-Sabater, J., De Rosnay, P., Sandu, I., Hadade, I., Carver, G., Mazzetti, C., Prudhomme, C., Yamazaki, D., and Zsoter, E.: ECLand: the ECMWF land surface modelling system, Atmosphere, 12, 723, https://doi.org/10.3390/atmos12060723, 2021.
Bouthillier, X., Delaunay, P., Bronzi, M., Trofimov, A., Nichyporuk, B., Szeto, J., Sepah, N., Raff, E., Madan, K., Voleti, V., Kahou, S. E., Michalski, V., Serdyuk, D., Arbel, T., Pal, C., Varoquaux, G., and Vincent, P.: Accounting for Variance in Machine Learning Benchmarks, arXiv [preprint], https://doi.org/10.48550/arXiv.2103.03098, 1 March 2021.
Brenowitz, N. D., Henn, B., McGibbon, J., Clark, S. K., Kwa, A., Perkins, W. A., Watt-Meyer, O., and Bretherton, C. S.: Machine Learning Climate Model Dynamics: Offline versus Online Performance, arXiv [preprint], https://doi.org/10.48550/arXiv.2011.03081, 5 November 2020.
Chantry, M., Halield, S., Dueben, P., Polichtchouk, I., and Palmer, T.: Machine learning emulation of gravity wave drag in numerical weather forecasting, J. Adv. Model. Earth Sy., 13, e2021MS002477, https://doi.org/10.1029/2021MS002477, 2021.
Chen, T. and Guestrin, C.: XGBoost: A Scalable Tree Boosting System, arXiv [preprint], https://doi.org/10.48550/arXiv.1603.02754, 10 June 2016.
Chen, X., Huang, J., Han, Z., Gao, H., Liu, M., Li, Z., Liu, X., Li, Q., Qi, H., and Huang, Y.: The importance of short lag-time in the runoff forecasting model based on long short-term memory, J. Hydrol., 589, 125359, https://doi.org/10.1016/j.jhydrol.2020.125359, 2020.
Chen, Z., Badrinarayanan, V., Lee, C.-Y., and Rabinovich, A.: GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks, arXiv [preprint], https://doi.org/10.48550/arXiv.1711.02257, 19 December 2017.
Choulga, M., Kourzeneva, E., Balsamo, G., Boussetta, S., and Wedi, N.: Upgraded global mapping information for earth system modelling: an application to surface water depth at the ECMWF, Hydrol. Earth Syst. Sci., 23, 4051–4076, https://doi.org/10.5194/hess-23-4051-2019, 2019.
Cui, Z., Qing, X., Chai, H., Yang, S., Zhu, Y., and Wang, F.: Real-time rainfall-runoff prediction using light gradient boosting machine coupled with singular spectrum analysis, J. Hydrol., 603, 127124, https://doi.org/10.1016/j.jhydrol.2021.127124, 2021.
Datta, P. and Faroughi, S. A.: A multihead LSTM technique for prognostic prediction of soil moisture, Geoderma, 433, 116452, https://doi.org/10.1016/j.geoderma.2023.116452, 2023.
De Rosnay, P., Balsamo, G., Albergel, C., Muñoz-Sabater, J., and Isaksen, L.: Initialisation of Land Surface Variables for Numerical Weather Prediction, Surv. Geophys., 35, 607–621, https://doi.org/10.1007/s10712-012-9207-x, 2014.
Dunkl, I., Spring, A., Friedlingstein, P., and Brovkin, V.: Process-based analysis of terrestrial carbon flux predictability, Earth Syst. Dynam., 12, 1413–1426, https://doi.org/10.5194/esd-12-1413-2021, 2021.
ECMWF: IFS Documentation CY43R3 – Part IV: Physical processes, ECMWF, https://doi.org/10.21957/EFYK72KL, 2017.
ECMWF: IFS Documentation CY48R1 – Part IV: Physical Processes, ECMWF, https://doi.org/10.21957/02054F0FBF, 2023.
Fer, I., Kelly, R., Moorcroft, P. R., Richardson, A. D., Cowdery, E. M., and Dietze, M. C.: Linking big models to big data: efficient ecosystem model calibration through Bayesian model emulation, Biogeosciences, 15, 5801–5830, https://doi.org/10.5194/bg-15-5801-2018, 2018.
Gelbrecht, M., White, A., Bathiany, S., and Boers, N.: Differentiable programming for Earth system modeling, Geosci. Model Dev., 16, 3123–3135, https://doi.org/10.5194/gmd-16-3123-2023, 2023.
Girshick, R.: Fast R-CNN, arXiv [preprint], https://doi.org/10.48550/arXiv.1504.08083, 27 September 2015.
Goodfellow, I., Bengio, Y., and Courville, A.: Deep learning, The MIT Press, Cambridge, Massachusetts, 775 pp., ISBN 9780262035613, 2016.
Grinsztajn, L., Oyallon, E., and Varoquaux, G.: Why do tree-based models still outperform deep learning on tabular data?, arXiv [preprint], https://doi.org/10.48550/arXiv.2207.08815, 18 July 2022.
Gu, M., Wang, X., and Berger, J. O.: Robust Gaussian stochastic process emulation, Ann. Stat., 46, 3038–3066, 2018.
Guo, Y., Yu, X., Xu, Y.-P., Chen, H., Gu, H., and Xie, J.: AI-based techniques for multi-step streamflow forecasts: application for multi-objective reservoir operation optimization and performance assessment, Hydrol. Earth Syst. Sci., 25, 5951–5979, https://doi.org/10.5194/hess-25-5951-2021, 2021.
Guo, Z., Dirmeyer, P. A., and DelSole, T.: Land surface impacts on subseasonal and seasonal predictability: land impacts subseasonal predictability, Geophys. Res. Lett., 38, L24812, https://doi.org/10.1029/2011GL049945, 2011.
Hatfield, S., Chantry, M., Dueben, P., Lopez, P., Geer, A., and Palmer, T.: Building Tangent-Linear and Adjoint Models for Data Assimilation With Neural Networks, J. Adv. Model. Earth Sy., 13, e2021MS002521, https://doi.org/10.1029/2021MS002521, 2021.
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz-Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., Simmons, A., Soci, C., Abdalla, S., Abellan, X., Balsamo, G., Bechtold, P., Biavati, G., Bidlot, J., Bonavita, M., De Chiara, G., Dahlgren, P., Dee, D., Diamantakis, M., Dragani, R., Flemming, J., Forbes, R., Fuentes, M., Geer, A., Haimberger, L., Healy, S., Hogan, R. J., Hólm, E., Janisková, M., Keeley, S., Laloyaux, P., Lopez, P., Lupu, C., Radnoti, G., De Rosnay, P., Rozum, I., Vamborg, F., Villaume, S., and Thépaut, J.: The ERA5 global reanalysis, Q. J. Roy. Meteor. Soc., 146, 1999–2049, https://doi.org/10.1002/qj.3803, 2020.
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997.
Irrgang, C., Boers, N., Sonnewald, M., Barnes, E. A., Kadow, C., Staneva, J., and Saynisch-Wagner, J.: Towards neural Earth system modelling by integrating artificial intelligence in Earth system science, Nature Machine Intelligence, 3, 667–674, https://doi.org/10.1038/s42256-021-00374-3, 2021.
James, W. and Stein, C.: Estimation with Quadratic Loss, in: Breakthroughs in Statistics, edited by: Kotz, S. and Johnson, N. L., Springer New York, New York, NY, 443–460, https://doi.org/10.1007/978-1-4612-0919-5_30, 1992.
Kadra, A., Lindauer, M., Hutter, F., and Grabocka, J.: Well-tuned Simple Nets Excel on Tabular Datasets, arXiv [preprint], https://doi.org/10.48550/arXiv.2106.11189, 5 November 2021.
Keisler, R.: Forecasting Global Weather with Graph Neural Networks, arXiv [preprint], https://doi.org/10.48550/arXiv.2202.07575, 15 February 2022.
Kimpson, T., Choulga, M., Chantry, M., Balsamo, G., Boussetta, S., Dueben, P., and Palmer, T.: Deep learning for quality control of surface physiographic fields using satellite Earth observations, Hydrol. Earth Syst. Sci., 27, 4661–4685, https://doi.org/10.5194/hess-27-4661-2023, 2023.
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, arXiv [preprint], https://doi.org/10.48550/arXiv.1412.6980, 30 January 2017.
Kratzert, F., Herrnegger, M., Klotz, D., Hochreiter, S., and Klambauer, G.: NeuralHydrology – Interpreting LSTMs in Hydrology, arXiv [preprint], https://doi.org/10.48550/arXiv.1903.07903, 12 November 2019a.
Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., and Nearing, G.: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets, Hydrol. Earth Syst. Sci., 23, 5089–5110, https://doi.org/10.5194/hess-23-5089-2019, 2019b.
Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., Hu, W., Merose, A., Hoyer, S., Holland, G., Vinyals, O., Stott, J., Pritzel, A., Mohamed, S., and Battaglia, P.: Learning skillful medium-range global weather forecasting, Science, 382, 1416–1421, https://doi.org/10.1126/science.adi2336, 2023.
Lang, S., Alexe, M., Chantry, M., Dramsch, J., Pinault, F., Raoult, B., Clare, M. C. A., Lessig, C., Maier-Gerber, M., Magnusson, L., Bouallègue, Z. B., Nemesio, A. P., Dueben, P. D., Brown, A., Pappenberger, F., and Rabier, F.: AIFS – ECMWF's data-driven forecasting system, arXiv [preprint], https://doi.org/10.48550/arXiv.2406.01465, 7 August 2024.
Lees, T., Reece, S., Kratzert, F., Klotz, D., Gauch, M., De Bruijn, J., Kumar Sahu, R., Greve, P., Slater, L., and Dadson, S. J.: Hydrological concept formation inside long short-term memory (LSTM) networks, Hydrol. Earth Syst. Sci., 26, 3079–3101, https://doi.org/10.5194/hess-26-3079-2022, 2022.
Li, L., Carver, R., Lopez-Gomez, I., Sha, F., and Anderson, J.: Generative emulation of weather forecast ensembles with diffusion models, Sci. Adv., 10, eadk4489, https://doi.org/10.1126/sciadv.adk4489, 2024.
Machac, D., Reichert, P., and Albert, C.: Emulation of dynamic simulators with application to hydrology, J. Comput. Phys., 313, 352–366, https://doi.org/10.1016/j.jcp.2016.02.046, 2016.
Meyer, D., Grimmond, S., Dueben, P., Hogan, R., and Van Reeuwijk, M.: Machine Learning Emulation of Urban Land Surface Processes, J. Adv. Model. Earth Sy., 14, e2021MS002744, https://doi.org/10.1029/2021MS002744, 2022.
Mironov, D. V.: Parameterization of lakes in numerical weather prediction: Description of a lake model, COSMO Technical Report, No. 11, Deutscher Weeerdienst, Offenbach am Main, Germany, 41 pp., 2008.
Muñoz-Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., Boussetta, S., Choulga, M., Harrigan, S., Hersbach, H., Martens, B., Miralles, D. G., Piles, M., Rodríguez-Fernández, N. J., Zsoter, E., Buontempo, C., and Thépaut, J.-N.: ERA5-Land: a state-of-the-art global reanalysis dataset for land applications, Earth Syst. Sci. Data, 13, 4349–4383, https://doi.org/10.5194/essd-13-4349-2021, 2021.
Nath, S., Lejeune, Q., Beusch, L., Seneviratne, S. I., and Schleussner, C.-F.: MESMER-M: an Earth system model emulator for spatially resolved monthly temperature, Earth Syst. Dynam., 13, 851–877, https://doi.org/10.5194/esd-13-851-2022, 2022.
Nearing, G., Cohen, D., Dube, V., Gauch, M., Gilon, O., Harrigan, S., Hassidim, A., Klotz, D., Kratzert, F., Metzger, A., Nevo, S., Pappenberger, F., Prudhomme, C., Shalev, G., Shenzis, S., Tekalign, T. Y., Weitzner, D., and Matias, Y.: Global prediction of extreme floods in ungauged watersheds, Nature, 627, 559–563, https://doi.org/10.1038/s41586-024-07145-1, 2024.
Owens, R. G. and Hewson, T. D.: ECMWF Forecast User Guide, ECMWF, Reading, https://doi.org/10.21957/m1cs7h, last access: 4 July 2024, 2018.
Ozaki, Y., Tanigaki, Y., Watanabe, S., Nomura, M., and Onishi, M.: Multiobjective Tree-Structured Parzen Estimator, J. Artif. Intell. Res., 73, 1209–1250, https://doi.org/10.1613/jair.1.13188, 2022.
Pappenberger, F., Ramos, M. H., Cloke, H. L., Wetterhall, F., Alfieri, L., Bogner, K., Mueller, A., and Salamon, P.: How do I know if my forecasts are better? Using benchmarks in hydrological ensemble prediction, J. Hydrol., 522, 697–713, https://doi.org/10.1016/j.jhydrol.2015.01.024, 2015.
Popov, S., Morozov, S., and Babenko, A.: Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data, arXiv [preprint], https://doi.org/10.48550/arXiv.1909.06312, 19 September 2019.
Reichstein, M., Camps-Valls, G., Stevens, B., Jung, M., Denzler, J., Carvalhais, N., and Prabhat: Deep learning and process understanding for data-driven Earth system science, Nature, 566, 195–204, https://doi.org/10.1038/s41586-019-0912-1, 2019.
Sener, O. and Koltun, V.: Multi-Task Learning as Multi-Objective Optimization, arXiv [preprint], https://doi.org/10.48550/arXiv.1810.04650, 10 October 2018.
Shukla, J.: Dynamical Predictability of Monthly Means, J. Atmos. Sci., 38, 2547–2572, https://doi.org/10.1175/1520-0469(1981)038<2547:DPOMM>2.0.CO;2, 1981.
Shwartz-Ziv, R. and Armon, A.: Tabular Data: Deep Learning is Not All You Need. Information Fusion, 81, 84–90, https://doi.org/10.1016/j.inffus.2021.11.011, 2022.
Slater, L. J., Arnal, L., Boucher, M.-A., Chang, A. Y.-Y., Moulds, S., Murphy, C., Nearing, G., Shalev, G., Shen, C., Speight, L., Villarini, G., Wilby, R. L., Wood, A., and Zappa, M.: Hybrid forecasting: blending climate predictions with AI models, Hydrol. Earth Syst. Sci., 27, 1865–1889, https://doi.org/10.5194/hess-27-1865-2023, 2023.
Thorpe, A., Bauer, P., Magnusson, L., and Richardson, D.: An evaluation of recent performance of ECMWF's forecasts, ECMWF, https://doi.org/10.21957/HI1EEKTR, 2013.
Van Katwyk, P., Fox-Kemper, B., Seroussi, H., Nowicki, S., and Bergen, K. J.: A Variational LSTM Emulator of Sea Level Contribution From the Antarctic Ice Sheet, J. Adv. Model. Earth Sy., 15, e2023MS003899, https://doi.org/10.1029/2023MS003899, 2023.
Viterbo, P.: Land_surface_processes [education material], Meteorological Training Course Lecture Series, ECMWF, 2002.
Wesselkamp, M., Chantry, M., Pinnington, E., Choulga, M., Boussetta, S., Kalweit, M., Boedecker, J., Dormann, C. F., Pappenberger, F., and Balsamo, G.: Advances in Land Surface Model-based Forecasting: A Comparison of LSTM, Gradient Boosting, and Feedforward Neural Networks as Prognostic State Emulators in a Case Study with ECLand, OSF [model code] https://doi.org/10.17605/OSF.IO/8567D, 2024a.
Wesselkamp, M., Chantry, M., Pinnington, E., Choulga, M., Boussetta, S., Kalweit, M., Boedecker, J., Dormann, C. F., Pappenberger, F., and Balsamo, G.: Advances in Land Surface Model-based Forecasting: A Comparison of LSTM, Gradient Boosting, and Feedforward Neural Networks as Prognostic State Emulators in a Case Study with ECLand. European and Global training and test data, ECMWF [data set], https://doi.org/10.21957/n17n-6a68, 2024b.
Wesselkamp, M., Chantry, M., Pinnington, E., Choulga, M., Boussetta, S., Kalweit, M., Boedecker, J., Dormann, C. F., Pappenberger, F., and Balsamo, G.: Advances in Land Surface Model-based Forecasting: A Comparison of LSTM, Gradient Boosting, and Feedforward Neural Networks as Prognostic State Emulators in a Case Study with ECLand. European and Global training and test data, ECMWF [data set], https://doi.org/10.21957/pcf3-ah06, 2024c.
Wesselkamp, M., Moser, N., Kalweit, M., Boedecker, J., and Dormann, C. F.: Process-Informed Neural Networks: A Hybrid Modelling Approach to Improve Predictive Performance and Inference of Neural Networks in Ecology and Beyond, Ecology Leeers, 27, e70012, https://doi.org/10.1111/ele.70012, 2024d.
Zwart, J. A., Oliver, S. K., Watkins, W. D., Sadler, J. M., Appling, A. P., Corson-Dosch, H. R., Jia, X., Kumar, V., and Read, J. S.: Near-term forecasts of stream temperature using deep learning and data assimilation in support of management decisions, J. Am. Water Resour. As., 59, 317–337, https://doi.org/10.1111/1752-1688.13093, 2023.
Short summary
We compared spatiotemporal forecasts of three machine learning models that learned water and energy
states on the land surface from a physical model scheme. The forecasting models were developed with reanalysis data and simulations on a European scale and transferred to the globe. We found that all approaches deliver highly accurate approximations of the physical dynamic at long time horizons, implying their usefulness to advance land surface forecasting with synthetic data.
states on the land surface from a physical model scheme. The forecasting models were developed with reanalysis data and simulations on a European scale and transferred to the globe. We found that all approaches deliver highly accurate approximations of the physical dynamic at long time horizons, implying their usefulness to advance land surface forecasting with synthetic data.
We compared spatiotemporal forecasts of three machine learning models that learned water and...
Altmetrics
Final-revised paper
Preprint