Articles | Volume 29, issue 15
https://doi.org/10.5194/hess-29-3687-2025
© 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/hess-29-3687-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
12 Aug 2025
Research article |
| 12 Aug 2025
| 12 Aug 2025
Infilling of missing rainfall radar data with a memory-assisted deep learning approach
Data Analysis Department, German Climate Computing Center (DKRZ), Hamburg, Germany
Laurens M. Bouwer
Climate Service Center Germany (GERICS), Helmholtz-Zentrum Hereon, Hamburg, Germany
Institute of Geography, University of Hamburg, Hamburg, Germany
Frank Kaspar
Hydrometeorology Department, Deutscher Wetterdienst (DWD), Offenbach, Germany
Roman Lehmann
Institute for Technical Informatics, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
Wolfgang Karl
Institute for Technical Informatics, Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany
Thomas Ludwig
Data Analysis Department, German Climate Computing Center (DKRZ), Hamburg, Germany
Christopher Kadow
Data Analysis Department, German Climate Computing Center (DKRZ), Hamburg, Germany
Related authors
Alexander Dolich, Eduardo Acuña Espinoza, Uwe Ehret, Michael Kraft, Jan Bondy, Johannes Meuer, and Ralf Loritz
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2026-289, https://doi.org/10.5194/essd-2026-289, 2026
Preprint under review for ESSD
Short summary
Short summary
CAMELS-DE-1h provides a unified collection of hourly river flow and weather time series for 1,611 German catchments from 2001 to 2024, alongside operational weather forecasts. Benchmark simulation results serve as a baseline for future model development. This dataset allows researchers to investigate small and medium-sized catchments that react quickly to heavy rainfall and to test models under operational conditions, improving future flood forecasting and early warning systems.
Alexander Dolich, Eduardo Acuña Espinoza, Uwe Ehret, Michael Kraft, Jan Bondy, Johannes Meuer, and Ralf Loritz
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2026-289, https://doi.org/10.5194/essd-2026-289, 2026
Preprint under review for ESSD
Short summary
Short summary
CAMELS-DE-1h provides a unified collection of hourly river flow and weather time series for 1,611 German catchments from 2001 to 2024, alongside operational weather forecasts. Benchmark simulation results serve as a baseline for future model development. This dataset allows researchers to investigate small and medium-sized catchments that react quickly to heavy rainfall and to test models under operational conditions, improving future flood forecasting and early warning systems.
Oakley Wagner, Verena Maleska, and Laurens M. Bouwer
Hydrol. Earth Syst. Sci., 30, 3597–3621, https://doi.org/10.5194/hess-30-3597-2026, https://doi.org/10.5194/hess-30-3597-2026, 2026
Short summary
Short summary
Convection-permitting regional climate models, such as ICON-CLM at 3 km resolution, have great potential for improved hydroclimatic simulations. The studied model run shows lower bias in air temperature and summer global radiation, as well as in the frequency of wind speed over the Weiße Elster catchment in East Central Germany. Due to a pronounced overestimation of the intensity and frequency of heavy rainfall, however the discharge estimates are skewed, with no apparent added value.
Andreas Hense, Christoph Kottmeier, Petra Friederichs, Sebastian Buschow, Svenja Szemkus, Uwe Ulbrich, Jens Grieger, Joaquim G. Pinto, Hendrik Feldmann, Frank Kaspar, Deborah Niermann, Rike Lorenz, Florian Ruff, and Etor E. Lucio Eceiza
EGUsphere, https://doi.org/10.5194/egusphere-2026-2697, https://doi.org/10.5194/egusphere-2026-2697, 2026
This preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).
Short summary
Short summary
The extreme events heatwaves, droughts, heavy precipitation, floods and wind storms affect socio-economic systems and generate strong public attention. They are embedded into atmospheric dynamics and are statistically rare events. Here we compile the contributions of twenty one articles of the inter-journal NHESS/ASCMO/WCD special issue by project ClimXtreme parallel to results from thirty three more publication. The conclusions underline the complexity of the results.
Piers M. Forster, Tristram Walsh, Chris Smith, William F. Lamb, Robin Lamboll, Christophe Cassou, Mathias Hauser, Zeke Hausfather, June-Yi Lee, Matthew D. Palmer, Karina von Schuckmann, Aimée B. A. Slangen, Sophie Szopa, Blair Trewin, Jeongeun Yun, Nathan P. Gillett, Stuart Jenkins, H. Damon Matthews, Krishnan Raghavan, Aurélien Ribes, Joeri Rogelj, Debbie Rosen, Xuebin Zhang, Myles Allen, Robbie M. Andrew, Chris Atkinson, Richard A. Betts, Antonio Bombelli, Samantha N. Burgess, Lijing Cheng, Helen E. Claxton, Pierre Friedlingstein, Thomas L. Frölicher, Catia M. Domingues, Thomas Gasser, Catherine H. Gregory, Rachel M. Hoesly, Daniel Huppmann, Masayoshi Ishii, Christopher Kadow, Alexia Karwat, John Kennedy, Rachel E. Killick, Mahesh V. M. Kovilakam, Paul B. Krummel, Xin Lan, Jean-François Lamarque, Aurélien Liné, Belén Martín-Míguez, Didier P. Monselesan, Colin Morice, Jens Mühle, Pino Mussak, Glen P. Peters, Anna Pirani, Julia Pongratz, Matthew Rigby, Robert Rohde, Abhishek Savita, Sonia I. Seneviratne, Steven J. Smith, Ghassan Taha, Caterina Tassone, Peter Thorne, Christopher Wells, Luke M. Western, Guido R. van der Werf, Susan E. Wijffels, Marco Zecchetto, Junting Zhong, Xiao-Ye Zhang, Valérie Masson-Delmotte, and Panmao Zhai
Earth Syst. Sci. Data, 18, 3889–3933, https://doi.org/10.5194/essd-18-3889-2026, https://doi.org/10.5194/essd-18-3889-2026, 2026
Short summary
Short summary
We give our annual update of key climate indicators. Our work quantifies the human contribution to global warming and the pace of climate change. This represents a large effort by the international community akin to an Intergovernmental Panel on Climate Change (IPCC) report.
Franziska Bär, Michael Borsche, Frank Kaspar, Thomas Spangehl, Dehong Yuan, David Geiger, and Lukas Pauscher
Adv. Sci. Res., 22, 149–164, https://doi.org/10.5194/asr-22-149-2026, https://doi.org/10.5194/asr-22-149-2026, 2026
Short summary
Short summary
COSMO-REA6 is widely used in energy applications but has known deficits. Its successor, COSMO-R6G2, is evaluated for Germany, focusing on Global Horizontal Irradiance (GHI) as well as wind speed. It shows slightly lower GHI and good wind quality in flat areas, but underestimates night-time wind in mountains. Overall, it is a useful successor, though users should consider remaining limitations.
Daria Paul, Danu Caus, Paul Keil, Christopher Kadow, and Stefanie Arndt
EGUsphere, https://doi.org/10.5194/egusphere-2026-1588, https://doi.org/10.5194/egusphere-2026-1588, 2026
This preprint is open for discussion and under review for The Cryosphere (TC).
Short summary
Short summary
We studied how snow and its properties vary across Antarctic sea ice using detailed field measurements combined with machine learning methods. We found that differences between ice types are mainly due to how snow layers are arranged rather than their basic properties. Snow changes over short distances, meaning single measurements often miss this complexity. Capturing this variability is key to improving climate models and satellite estimates.
Angelika Palarz, Thomas Junghänel, Jennifer Ostermöller, Thomas Deutschländer, and Frank Kaspar
EGUsphere, https://doi.org/10.5194/egusphere-2026-1067, https://doi.org/10.5194/egusphere-2026-1067, 2026
Short summary
Short summary
This study assesses heavy precipitation events (HPEs) across Germany using recently digitised and quality-controlled 5-min precipitation data. The analysis of HPEs with durations ranging from 5 minutes to 7 days reveal a pronounced duration dependence. Short-duration HPEs show predominantly positive tendencies and increasing intensities, whereas long-duration HPEs display more balanced or locally slightly decreasing intensities in recent decades.
Peter W. Thorne, John M. Nicklas, John J. Kennedy, Bruce Calvert, Baylor Fox-Kemper, Mark T. Richardson, Adrian Simmons, Ed Hawkins, Robert Rhode, Kathryn Cowtan, Nerilie J. Abram, Axel Andersson, Simon Noone, Phillipe Marbaix, Nathan Lenssen, Dirk Olonscheck, Tristram Walsh, Stephen Outten, Ingo Bethke, Bjorn H. Samset, Chris Smith, Anna Pirani, Jan Fuglestvedt, Lavanya Rajamani, Richard A. Betts, Elizabeth C. Kent, Blair Trewin, Colin Morice, Tim Osborn, Samantha N. Burgess, Oliver Geden, Andrew Parnell, Piers M. Forster, Chris Hewitt, Zeke Hausfather, Valerie Masson-Delmotte, Jochem Marotzke, Nathan Gillett, Sonia I. Seneviratne, Gavin A. Schmidt, Duo Chan, Stefan Brönnimann, Andy Reisinger, Matthew Menne, Maisa Rojas Corradi, Christopher Kadow, Peter Huybers, David B. Stephenson, Emily Wallis, Joeri Rogelj, Andrew Schurer, Karen McKinnon, Panmao Zhai, Fatima Driouech, Wilfran Moufouma Okia, Saeed Vazifehkhah, Sophie Szopa, Christopher J. Merchant, Shoji Hirahara, Masayoshi Ishii, Francois A. Engelbrecht, Qingxiang Li, June-Yi Lee, Alex J. Cannon, Christophe Cassou, Karina von Schuckmann, Amir H. Delju, and Ellie Murtagh
Earth Syst. Sci. Data Discuss., https://doi.org/10.5194/essd-2025-825, https://doi.org/10.5194/essd-2025-825, 2026
Preprint under review for ESSD
Short summary
Short summary
We reassess the basis for determining the present level of long-term global warming. Unbiased estimates of both realised warming and anthropogenic warming are possible that approximate a 20-year retrospective mean. Our resulting estimates of 1.40 [1.23–1.58] °C (realised) and 1.34 [1.18–1.50] °C (anthropogenic) as at end of 2024 highlight the urgency of immediate, far-reaching and sustained climate mitigation actions if we are to meet the long term temperature goal of the Paris Agreement.
Abhay Devasthale, Sandra Andersson, Erik Engström, Frank Kaspar, Jörg Trentmann, Anke Duguay-Tetzlaff, Jan Fokke Meirink, Erik Kjellström, Tomas Landelius, Manu Anna Thomas, and Karl-Göran Karlsson
Earth Syst. Dynam., 16, 1169–1182, https://doi.org/10.5194/esd-16-1169-2025, https://doi.org/10.5194/esd-16-1169-2025, 2025
Short summary
Short summary
By compositing trends in multiple climate variables, this study presents emerging regimes that are relevant for solar energy applications. It is shown that the favourable conditions for exploiting solar energy are emerging during spring and early summer. The study also underscores the increasingly important role of clouds in regulating surface solar radiation as the aerosol concentrations are decreasing over Europe and the societal value of satellite-based climate monitoring.
Piers M. Forster, Chris Smith, Tristram Walsh, William F. Lamb, Robin Lamboll, Christophe Cassou, Mathias Hauser, Zeke Hausfather, June-Yi Lee, Matthew D. Palmer, Karina von Schuckmann, Aimée B. A. Slangen, Sophie Szopa, Blair Trewin, Jeongeun Yun, Nathan P. Gillett, Stuart Jenkins, H. Damon Matthews, Krishnan Raghavan, Aurélien Ribes, Joeri Rogelj, Debbie Rosen, Xuebin Zhang, Myles Allen, Lara Aleluia Reis, Robbie M. Andrew, Richard A. Betts, Alex Borger, Jiddu A. Broersma, Samantha N. Burgess, Lijing Cheng, Pierre Friedlingstein, Catia M. Domingues, Marco Gambarini, Thomas Gasser, Johannes Gütschow, Masayoshi Ishii, Christopher Kadow, John Kennedy, Rachel E. Killick, Paul B. Krummel, Aurélien Liné, Didier P. Monselesan, Colin Morice, Jens Mühle, Vaishali Naik, Glen P. Peters, Anna Pirani, Julia Pongratz, Jan C. Minx, Matthew Rigby, Robert Rohde, Abhishek Savita, Sonia I. Seneviratne, Peter Thorne, Christopher Wells, Luke M. Western, Guido R. van der Werf, Susan E. Wijffels, Valérie Masson-Delmotte, and Panmao Zhai
Earth Syst. Sci. Data, 17, 2641–2680, https://doi.org/10.5194/essd-17-2641-2025, https://doi.org/10.5194/essd-17-2641-2025, 2025
Short summary
Short summary
In a rapidly changing climate, evidence-based decision-making benefits from up-to-date and timely information. Here we compile monitoring datasets to track real-world changes over time. To make our work relevant to policymakers, we follow methods from the Intergovernmental Panel on Climate Change (IPCC). Human activities are increasing the Earth's energy imbalance and driving faster sea-level rise compared to the IPCC assessment.
Florian Knutzen, Paul Averbeck, Caterina Barrasso, Laurens M. Bouwer, Barry Gardiner, José M. Grünzweig, Sabine Hänel, Karsten Haustein, Marius Rohde Johannessen, Stefan Kollet, Mortimer M. Müller, Joni-Pekka Pietikäinen, Karolina Pietras-Couffignal, Joaquim G. Pinto, Diana Rechid, Efi Rousi, Ana Russo, Laura Suarez-Gutierrez, Sarah Veit, Julian Wendler, Elena Xoplaki, and Daniel Gliksman
Nat. Hazards Earth Syst. Sci., 25, 77–117, https://doi.org/10.5194/nhess-25-77-2025, https://doi.org/10.5194/nhess-25-77-2025, 2025
Short summary
Short summary
Our research, involving 22 European scientists, investigated drought and heat impacts on forests in 2018–2022. Findings reveal that climate extremes are intensifying, with central Europe being most severely impacted. The southern region showed resilience due to historical drought exposure, while northern and Alpine areas experienced emerging or minimal impacts. The study highlights the need for region-specific strategies, improved data collection, and sustainable practices to safeguard forests.
Piers M. Forster, Chris Smith, Tristram Walsh, William F. Lamb, Robin Lamboll, Bradley Hall, Mathias Hauser, Aurélien Ribes, Debbie Rosen, Nathan P. Gillett, Matthew D. Palmer, Joeri Rogelj, Karina von Schuckmann, Blair Trewin, Myles Allen, Robbie Andrew, Richard A. Betts, Alex Borger, Tim Boyer, Jiddu A. Broersma, Carlo Buontempo, Samantha Burgess, Chiara Cagnazzo, Lijing Cheng, Pierre Friedlingstein, Andrew Gettelman, Johannes Gütschow, Masayoshi Ishii, Stuart Jenkins, Xin Lan, Colin Morice, Jens Mühle, Christopher Kadow, John Kennedy, Rachel E. Killick, Paul B. Krummel, Jan C. Minx, Gunnar Myhre, Vaishali Naik, Glen P. Peters, Anna Pirani, Julia Pongratz, Carl-Friedrich Schleussner, Sonia I. Seneviratne, Sophie Szopa, Peter Thorne, Mahesh V. M. Kovilakam, Elisa Majamäki, Jukka-Pekka Jalkanen, Margreet van Marle, Rachel M. Hoesly, Robert Rohde, Dominik Schumacher, Guido van der Werf, Russell Vose, Kirsten Zickfeld, Xuebin Zhang, Valérie Masson-Delmotte, and Panmao Zhai
Earth Syst. Sci. Data, 16, 2625–2658, https://doi.org/10.5194/essd-16-2625-2024, https://doi.org/10.5194/essd-16-2625-2024, 2024
Short summary
Short summary
This paper tracks some key indicators of global warming through time, from 1850 through to the end of 2023. It is designed to give an authoritative estimate of global warming to date and its causes. We find that in 2023, global warming reached 1.3 °C and is increasing at over 0.2 °C per decade. This is caused by all-time-high greenhouse gas emissions.
Bjorn Stevens, Stefan Adami, Tariq Ali, Hartwig Anzt, Zafer Aslan, Sabine Attinger, Jaana Bäck, Johanna Baehr, Peter Bauer, Natacha Bernier, Bob Bishop, Hendryk Bockelmann, Sandrine Bony, Guy Brasseur, David N. Bresch, Sean Breyer, Gilbert Brunet, Pier Luigi Buttigieg, Junji Cao, Christelle Castet, Yafang Cheng, Ayantika Dey Choudhury, Deborah Coen, Susanne Crewell, Atish Dabholkar, Qing Dai, Francisco Doblas-Reyes, Dale Durran, Ayoub El Gaidi, Charlie Ewen, Eleftheria Exarchou, Veronika Eyring, Florencia Falkinhoff, David Farrell, Piers M. Forster, Ariane Frassoni, Claudia Frauen, Oliver Fuhrer, Shahzad Gani, Edwin Gerber, Debra Goldfarb, Jens Grieger, Nicolas Gruber, Wilco Hazeleger, Rolf Herken, Chris Hewitt, Torsten Hoefler, Huang-Hsiung Hsu, Daniela Jacob, Alexandra Jahn, Christian Jakob, Thomas Jung, Christopher Kadow, In-Sik Kang, Sarah Kang, Karthik Kashinath, Katharina Kleinen-von Königslöw, Daniel Klocke, Uta Kloenne, Milan Klöwer, Chihiro Kodama, Stefan Kollet, Tobias Kölling, Jenni Kontkanen, Steve Kopp, Michal Koran, Markku Kulmala, Hanna Lappalainen, Fakhria Latifi, Bryan Lawrence, June Yi Lee, Quentin Lejeun, Christian Lessig, Chao Li, Thomas Lippert, Jürg Luterbacher, Pekka Manninen, Jochem Marotzke, Satoshi Matsouoka, Charlotte Merchant, Peter Messmer, Gero Michel, Kristel Michielsen, Tomoki Miyakawa, Jens Müller, Ramsha Munir, Sandeep Narayanasetti, Ousmane Ndiaye, Carlos Nobre, Achim Oberg, Riko Oki, Tuba Özkan-Haller, Tim Palmer, Stan Posey, Andreas Prein, Odessa Primus, Mike Pritchard, Julie Pullen, Dian Putrasahan, Johannes Quaas, Krishnan Raghavan, Venkatachalam Ramaswamy, Markus Rapp, Florian Rauser, Markus Reichstein, Aromar Revi, Sonakshi Saluja, Masaki Satoh, Vera Schemann, Sebastian Schemm, Christina Schnadt Poberaj, Thomas Schulthess, Cath Senior, Jagadish Shukla, Manmeet Singh, Julia Slingo, Adam Sobel, Silvina Solman, Jenna Spitzer, Philip Stier, Thomas Stocker, Sarah Strock, Hang Su, Petteri Taalas, John Taylor, Susann Tegtmeier, Georg Teutsch, Adrian Tompkins, Uwe Ulbrich, Pier-Luigi Vidale, Chien-Ming Wu, Hao Xu, Najibullah Zaki, Laure Zanna, Tianjun Zhou, and Florian Ziemen
Earth Syst. Sci. Data, 16, 2113–2122, https://doi.org/10.5194/essd-16-2113-2024, https://doi.org/10.5194/essd-16-2113-2024, 2024
Short summary
Short summary
To manage Earth in the Anthropocene, new tools, new institutions, and new forms of international cooperation will be required. Earth Virtualization Engines is proposed as an international federation of centers of excellence to empower all people to respond to the immense and urgent challenges posed by climate change.
Thomas Spangehl, Michael Borsche, Deborah Niermann, Frank Kaspar, Semjon Schimanke, Susanne Brienen, Thomas Möller, and Maren Brast
Adv. Sci. Res., 20, 109–128, https://doi.org/10.5194/asr-20-109-2023, https://doi.org/10.5194/asr-20-109-2023, 2023
Short summary
Short summary
The quality of the global reanalysis ERA5, the regional reanalysis COSMO-REA6 and a successor version (R6G2), the new Copernicus European Regional Re-Analysis (CERRA) and a regional downscaling simulation with COSMO-CLM (HoKliSim-De) is assessed for offshore wind farm planning in the German Exclusive Economic Zone (EEZ) of the North Sea. The quality is assessed using in-situ wind measurements at the research platform FINO1 and satellite-based data of the near-surface wind speed as reference.
Piers M. Forster, Christopher J. Smith, Tristram Walsh, William F. Lamb, Robin Lamboll, Mathias Hauser, Aurélien Ribes, Debbie Rosen, Nathan Gillett, Matthew D. Palmer, Joeri Rogelj, Karina von Schuckmann, Sonia I. Seneviratne, Blair Trewin, Xuebin Zhang, Myles Allen, Robbie Andrew, Arlene Birt, Alex Borger, Tim Boyer, Jiddu A. Broersma, Lijing Cheng, Frank Dentener, Pierre Friedlingstein, José M. Gutiérrez, Johannes Gütschow, Bradley Hall, Masayoshi Ishii, Stuart Jenkins, Xin Lan, June-Yi Lee, Colin Morice, Christopher Kadow, John Kennedy, Rachel Killick, Jan C. Minx, Vaishali Naik, Glen P. Peters, Anna Pirani, Julia Pongratz, Carl-Friedrich Schleussner, Sophie Szopa, Peter Thorne, Robert Rohde, Maisa Rojas Corradi, Dominik Schumacher, Russell Vose, Kirsten Zickfeld, Valérie Masson-Delmotte, and Panmao Zhai
Earth Syst. Sci. Data, 15, 2295–2327, https://doi.org/10.5194/essd-15-2295-2023, https://doi.org/10.5194/essd-15-2295-2023, 2023
Short summary
Short summary
This is a critical decade for climate action, but there is no annual tracking of the level of human-induced warming. We build on the Intergovernmental Panel on Climate Change assessment reports that are authoritative but published infrequently to create a set of key global climate indicators that can be tracked through time. Our hope is that this becomes an important annual publication that policymakers, media, scientists and the public can refer to.
Katharina Lengfeld, Paul Voit, Frank Kaspar, and Maik Heistermann
Nat. Hazards Earth Syst. Sci., 23, 1227–1232, https://doi.org/10.5194/nhess-23-1227-2023, https://doi.org/10.5194/nhess-23-1227-2023, 2023
Short summary
Short summary
Estimating the severity of a rainfall event based on the damage caused is easy but highly depends on the affected region. A less biased measure for the extremeness of an event is its rarity combined with its spatial extent. In this brief communication, we investigate the sensitivity of such measures to the underlying dataset and highlight the importance of considering multiple spatial and temporal scales using the devastating rainfall event in July 2021 in central Europe as an example.
Alberto Caldas-Alvarez, Markus Augenstein, Georgy Ayzel, Klemens Barfus, Ribu Cherian, Lisa Dillenardt, Felix Fauer, Hendrik Feldmann, Maik Heistermann, Alexia Karwat, Frank Kaspar, Heidi Kreibich, Etor Emanuel Lucio-Eceiza, Edmund P. Meredith, Susanna Mohr, Deborah Niermann, Stephan Pfahl, Florian Ruff, Henning W. Rust, Lukas Schoppa, Thomas Schwitalla, Stella Steidl, Annegret H. Thieken, Jordis S. Tradowsky, Volker Wulfmeyer, and Johannes Quaas
Nat. Hazards Earth Syst. Sci., 22, 3701–3724, https://doi.org/10.5194/nhess-22-3701-2022, https://doi.org/10.5194/nhess-22-3701-2022, 2022
Short summary
Short summary
In a warming climate, extreme precipitation events are becoming more frequent. To advance our knowledge on such phenomena, we present a multidisciplinary analysis of a selected case study that took place on 29 June 2017 in the Berlin metropolitan area. Our analysis provides evidence of the extremeness of the case from the atmospheric and the impacts perspectives as well as new insights on the physical mechanisms of the event at the meteorological and climate scales.
Lennart Marien, Mahyar Valizadeh, Wolfgang zu Castell, Christine Nam, Diana Rechid, Alexandra Schneider, Christine Meisinger, Jakob Linseisen, Kathrin Wolf, and Laurens M. Bouwer
Nat. Hazards Earth Syst. Sci., 22, 3015–3039, https://doi.org/10.5194/nhess-22-3015-2022, https://doi.org/10.5194/nhess-22-3015-2022, 2022
Short summary
Short summary
Myocardial infarctions (MIs; heart attacks) are influenced by temperature extremes, air pollution, lack of green spaces and ageing population. Here, we apply machine learning (ML) models in order to estimate the influence of various environmental and demographic risk factors. The resulting ML models can accurately reproduce observed annual variability in MI and inter-annual trends. The models allow quantification of the importance of individual factors and can be used to project future risk.
Cited articles
Barrios, A., Trincado, G., and Garreaud, R.: Alternative approaches for estimating missing climate data: application to monthly precipitation records in South-Central Chile, Forest Ecosystems, 5, 1–10, 2018. a
Charlton-Perez, A. J., Dacre, H. F., Driscoll, S., Gray, S. L., Harvey, B., Harvey, N. J., Hunt, K. M., Lee, R. W., Swaminathan, R., Vandaele, R., and Volonté, A.: Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán, npj Climate and Atmospheric Science, 7, 93, https://doi.org/10.1038/s41612-024-00638-w, 2024. a
Elharrouss, O., Almaadeed, N., Al-Maadeed, S., and Akbari, Y.: Image inpainting: A review, Neural Process. Lett., 51, 2007–2028, 2020. a
Facebook: Pytorch, https://pytorch.org/ (last access: 10 April 2025), 2025. a
Geiss, A. and Hardin, J. C.: Inpainting radar missing data regions with deep learning, Atmos. Meas. Tech., 14, 7729–7747, https://doi.org/10.5194/amt-14-7729-2021, 2021. a, b, c
Hochreiter, S. and Schmidhuber, J.: Long short-term memory, Neural Comput., 9, 1735–1780, 1997. a
James, P. M., Reichert, B. K., and Heizenreder, D.: NowCastMIX: Automatic integrated warnings for severe convection on nowcasting time scales at the German Weather Service, Weather Forecast., 33, 1413–1433, 2018. a
Kaspar, F. and Mächel, H.: Beobachtung von Klima und Klimawandel in Mitteleuropa und Deutschland, edited by: Brasseur, G. P., Jacob, D., and Schuck-Zöller, S., Klimawandel in Deutschland, https://doi.org/10.1007/978-3-662-66696-8_3, 2023. a
Landot, T., Sgellari, S., Lima, C., and Lall, U.: In-filling missing historical daily rainfall data study, Final Report, South Florida Water Management District, Columbia University, New York, NY, https://scholar.google.com/scholar?hl=en&q=Landot+T,+Sgellari+S,+Lima+C,+Lall+U.+2008.+In% E2% 80% 90filling+missing+historical+daily+rainfall+data+study.+Final+Report,+South+Florida+Water+Management+District,+Columbia+University,+New+York,+NY (last access: 20 January 2024), 2008. a
Lang, P.: Konrad, Umweltwissenschaften und Schadstoff-Forschung, 14, 212, https://doi.org/10.1007/BF03038827, 2002. a
Lengfeld, K., Winterrath, T., Junghänel, T., Hafer, M., and Becker, A.: Characteristic spatial extent of hourly and daily precipitation events in Germany derived from 16 years of radar data, Characteristic spatial extent of hourly and daily precipitation events in Germany derived from 16 years of radar data, Meteorol. Z., 28, 363–378, 2019. a, b
Meuer, J., Plésiat, É., Inoue, N., Witte, M., Seitz, S., and Kadow, C.: FREVA-CLINT/climatereconstructionAI: Guacamole (v1.0.4), Zenodo [code], https://doi.org/10.5281/zenodo.13767317, 2024. a
Mohr, S., Ehret, U., Kunz, M., Ludwig, P., Caldas-Alvarez, A., Daniell, J. E., Ehmele, F., Feldmann, H., Franca, M. J., Gattke, C., Hundhausen, M., Knippertz, P., Küpfer, K., Mühr, B., Pinto, J. G., Quinting, J., Schäfer, A. M., Scheibel, M., Seidel, F., and Wisotzky, C.: A multi-disciplinary analysis of the exceptional flood event of July 2021 in central Europe – Part 1: Event description and analysis, Nat. Hazards Earth Syst. Sci., 23, 525–551, https://doi.org/10.5194/nhess-23-525-2023, 2023. a
Panziera, L., Germann, U., Gabella, M., and Mandapaka, P.: NORA–Nowcasting of Orographic Rainfall by means of Analogues, Q. J. Roy. Meteor. Soc., 137, 2106–2123, 2011. a
Ronneberger, O., Fischer, P., and Brox, T.: U-net: Convolutional networks for biomedical image segmentation, in: International Conference on Medical image computing and computer-assisted intervention, Springer, 234–241, https://doi.org/10.1007/978-3-319-24574-4_28, 2015. a
Shibata, S., Iiyama, M., Hashimoto, A., and Minoh, M.: Restoration of sea surface temperature satellite images using a partially occluded training set, in: 2018 24th International Conference on Pattern Recognition (ICPR), ICPR 2018, Beijing, China, 20–24 August 2018, 2771–2776, https://doi.org/10.1109/ICPR.2018.8546261, 2018. a
Smith, T. M., Reynolds, R. W., Livezey, R. E., and Stokes, D. C.: Reconstruction of historical sea surface temperatures using empirical orthogonal functions, J. Climate, 9, 1403–1420, 1996. a
Srivastava, N., Mansimov, E., and Salakhudinov, R.: Unsupervised learning of video representations using lstms, in: International conference on machine learning, ICML 2015, Lille, France, 6–11 July 2015, https://dl.acm.org/doi/10.5555/3045118.3045209, 843–852, 2015. a, b, c
Teegavarapu, R. S. and Chandramouli, V.: Improved weighting methods, deterministic and stochastic data-driven models for estimation of missing precipitation records, J. Hydrol., 312, 191–206, 2005. a
Teegavarapu, R. S., Aly, A., Pathak, C. S., Ahlquist, J., Fuelberg, H., and Hood, J.: Infilling missing precipitation records using variants of spatial interpolation and data-driven methods: use of optimal weighting parameters and nearest neighbour-based corrections, Int. J. Climatol., 38, 776–793, 2018. a, b, c, d
Tian, L., Li, X., Ye, Y., Xie, P., and Li, Y.: A generative adversarial gated recurrent unit model for precipitation nowcasting, IEEE Geosci. Remote S., 17, 601–605, 2019. a
Verworn, A. and Haberlandt, U.: Spatial interpolation of hourly rainfall – effect of additional information, variogram inference and storm properties, Hydrol. Earth Syst. Sci., 15, 569–584, https://doi.org/10.5194/hess-15-569-2011, 2011. a, b
Vislocky, R. L. and Fritsch, J. M.: Generalized additive models versus linear regression in generating probabilistic MOS forecasts of aviation weather parameters, Weather Forecast., 10, 669–680, 1995. a
Wapler, K., Goeber, M., and Trepte, S.: Comparative verification of different nowcasting systems to support optimisation of thunderstorm warnings, Adv. Sci. Res., 8, 121–127, 2012. a
Winterrath, T., Brendel, C., Hafer, M., Junghänel, T., Klameth, A., Lengfeld, K., Walawender, E., Weigl, E., and Becker, A.: RADKLIM Version 2017.002: Reprocessed gauge-adjusted radar data, one-hour precipitation sums (RW), Deutscher Wetterdienst (DWD) [data set], https://doi.org/10.5676/DWD/RADKLIM_RW_V2017.002, 2018a. a, b, c, d
Winterrath, T., Brendel, C., Hafer, M., Junghänel, T., Klameth, A., Lengfeld, K., Walawender, E., Weigl, E., and Becker, A.: Radar-based gauge-adjusted one-hour precipitation sum climatology Version 2017.002 Gridded Precipitation Data for Germany version v2017.02, Deutscher Wetterdienst (DWD) [data set], https://doi.org/10.5676/DWD/RADKLIM_RW_V2017.002, 2018b. a
Xingjian, S., 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, Adv. Neur. In., 28, 802–810, https://proceedings.neurips.cc/paper/2015/file/07563a3fe3bbe7e3ba84431ad9d055af-Paper.pdf (last access: 25 June 2023), 2015. a, b, c
Xu, W., Chen, K., Han, T., Chen, H., Ouyang, W., and Bai, L.: Extremecast: Boosting extreme value prediction for global weather forecast, arXiv [preprint], https://doi.org/10.48550/arXiv.2402.01295, 2 February 2024. a
Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., and Huang, T. S.: Generative image inpainting with contextual attention, arXiv [preprint], https://doi.org/10.48550/arXiv.1801.07892, 2018. a
Zhong, X., Chen, L., Liu, J., Lin, C., Qi, Y., and Li, H.: FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion model, Science China Earth Sciences, 67, 3696–3708, https://doi.org/10.1007/s11430-023-1427-x, 2024. a
Short summary
Our study focuses on filling in missing precipitation data using an advanced neural network model. Traditional methods for estimating missing climate information often struggle in large regions where data are scarce. Our solution, which incorporates recent advances in machine learning, captures the intricate patterns of precipitation over time, especially during extreme weather events. Our model shows good performance in reconstructing large regions of missing rainfall radar data.
Our study focuses on filling in missing precipitation data using an advanced neural network...
