Articles | Volume 21, issue 12
https://doi.org/10.5194/nhess-21-3679-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Special issue:
https://doi.org/10.5194/nhess-21-3679-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Applying machine learning for drought prediction in a perfect model framework using data from a large ensemble of climate simulations
Center for Digital Technology and Management, Munich, Germany
Department of Geography, Ludwig Maximilian University of Munich, Munich, Germany
Ralf Ludwig
Department of Geography, Ludwig Maximilian University of Munich, Munich, Germany
Related authors
No articles found.
Benjamin Poschlod, Laura Sailer, Alexander Sasse, Anastasia Vogelbacher, and Ralf Ludwig
EGUsphere, https://doi.org/10.5194/egusphere-2025-2483, https://doi.org/10.5194/egusphere-2025-2483, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
Europe was hit by severe droughts in recent years resulting in extreme low flow conditions in rivers. Here, we investigate future climate change effects on river droughts in Bavaria. We find increasing severity for the low peak discharge and low flow duration in a warmer climate. This is caused by hotter and drier summers, where the joint occurrence of heat and drought intensifies. Further, we show that conditions in the year before the drought gain more importance in a warmer climate.
Carolin Boos, Sophie Reinermann, Raul Wood, Ralf Ludwig, Anne Schucknecht, David Kraus, and Ralf Kiese
EGUsphere, https://doi.org/10.5194/egusphere-2024-2864, https://doi.org/10.5194/egusphere-2024-2864, 2024
Preprint archived
Short summary
Short summary
We applied a biogeochemical model on grasslands in the pre-Alpine Ammer region in Germany and analyzed the influence of soil and climate on annual yields. In drought affected years, total yields were decreased by 4 %. Overall, yields decrease with rising elevation, but less so in drier and hotter years, whereas soil organic carbon has a positive impact on yields, especially in drier years. Our findings imply, that adapted management in the region allows to mitigate yield losses from drought.
Florian Willkofer, Raul R. Wood, and Ralf Ludwig
Hydrol. Earth Syst. Sci., 28, 2969–2989, https://doi.org/10.5194/hess-28-2969-2024, https://doi.org/10.5194/hess-28-2969-2024, 2024
Short summary
Short summary
Severe flood events pose a threat to riverine areas, yet robust estimates of the dynamics of these events in the future due to climate change are rarely available. Hence, this study uses data from a regional climate model, SMILE, to drive a high-resolution hydrological model for 98 catchments of hydrological Bavaria and exploits the large database to derive robust values for the 100-year flood events. Results indicate an increase in frequency and intensity for most catchments in the future.
Julia Miller, Andrea Böhnisch, Ralf Ludwig, and Manuela I. Brunner
Nat. Hazards Earth Syst. Sci., 24, 411–428, https://doi.org/10.5194/nhess-24-411-2024, https://doi.org/10.5194/nhess-24-411-2024, 2024
Short summary
Short summary
We assess the impacts of climate change on fire danger for 1980–2099 in different landscapes of central Europe, using the Canadian Forest Fire Weather Index (FWI) as a fire danger indicator. We find that today's 100-year FWI event will occur every 30 years by 2050 and every 10 years by 2099. High fire danger (FWI > 21.3) becomes the mean condition by 2099 under an RCP8.5 scenario. This study highlights the potential for severe fire events in central Europe from a meteorological perspective.
Nicola Maher, Sebastian Milinski, and Ralf Ludwig
Earth Syst. Dynam., 12, 401–418, https://doi.org/10.5194/esd-12-401-2021, https://doi.org/10.5194/esd-12-401-2021, 2021
Benjamin Poschlod, Ralf Ludwig, and Jana Sillmann
Earth Syst. Sci. Data, 13, 983–1003, https://doi.org/10.5194/essd-13-983-2021, https://doi.org/10.5194/essd-13-983-2021, 2021
Short summary
Short summary
This study provides a homogeneous data set of 10-year rainfall return levels based on 50 simulations of the Canadian Regional Climate Model v5 (CRCM5). In order to evaluate its quality, the return levels are compared to those of observation-based rainfall of 16 European countries from 32 different sources. The CRCM5 is able to capture the general spatial pattern of observed extreme precipitation, and also the intensity is reproduced in 77 % of the area for rainfall durations of 3 h and longer.
Fabian von Trentini, Emma E. Aalbers, Erich M. Fischer, and Ralf Ludwig
Earth Syst. Dynam., 11, 1013–1031, https://doi.org/10.5194/esd-11-1013-2020, https://doi.org/10.5194/esd-11-1013-2020, 2020
Short summary
Short summary
We compare the inter-annual variability of three single-model initial-condition large ensembles (SMILEs), downscaled with three regional climate models over Europe for seasonal temperature and precipitation, the number of heatwaves, and maximum length of dry periods. They all show good consistency with observational data. The magnitude of variability and the future development are similar in many cases. In general, variability increases for summer indicators and decreases for winter indicators.
Fabian Willibald, Sven Kotlarski, Adrienne Grêt-Regamey, and Ralf Ludwig
The Cryosphere, 14, 2909–2924, https://doi.org/10.5194/tc-14-2909-2020, https://doi.org/10.5194/tc-14-2909-2020, 2020
Short summary
Short summary
Climate change will significantly reduce snow cover, but the extent remains disputed. We use regional climate model data as a driver for a snow model to investigate the impacts of climate change and climate variability on snow. We show that natural climate variability is a dominant source of uncertainty in future snow trends. We show that anthropogenic climate change will change the interannual variability of snow. Those factors will increase the vulnerabilities of snow-dependent economies.
Cited articles
Barnston, A. G. and Livezey, R. E.: Classification, Seasonality and
Persistence of Low-Frequency Atmospheric Circulation Patterns, Mon. Weather
Rev., 115, 1083–1126, https://doi.org/10.1175/1520-0493(1987)115<1083:CSAPOL>2.0.CO;2, 1987. a
Belayneh, A., Adamowski, J., Khalil, B., and Quilty, J.: Coupling machine learning methods with wavelet transforms and the bootstrap and boosting ensemble approaches for drought prediction, Atmos. Res., 172–173, 37–47, https://doi.org/10.1016/j.atmosres.2015.12.017, 2016. a, b
Biesiada, J. and Duch, W.: Feature Selection for High-Dimensional Data – A Pearson Redundancy Based Filter, in: Computer Recognition Systems 2, edited by: Kurzynski, M., Puchala, E., Wozniak, M., and Zolnierek, A., Springer, Berlin, Heidelberg, 242–249, 2007. a
Bishop, C. M.: Pattern Recognition and Machine Learning (Information Science and Statistics), 1st edn., Springer, Berlin, Heidelberg, 2007. a
Bonaccorso, B., Cancelliere, A., and Rossi, G.: Probabilistic forecasting of drought class transitions in Sicily (Italy) using Standardized Precipitation Index and North Atlantic Oscillation Index, J. Hydrol., 526, 136–150, https://doi.org/10.1016/j.jhydrol.2015.01.070, 2015. a, b, c, d
Bueh, C. and Nakamura, H.: Scandinavian pattern and its climatic impact, Q. J. Roy. Meteor. Soc., 133, 2117–2131, https://doi.org/10.1002/qj.173, 2007. a
Ceglar, A., Zampieri, M., Toreti, A., and Dentener, F.: Observed Northward Migration of Agro-Climate Zones in Europe Will Further Accelerate Under Climate Change, Earths Future, 7, 1088–1101, https://doi.org/10.1029/2019EF001178, 2019. a
Clevert, D. A., Unterthiner, T., and Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs), arXiv [preprint], arXiv:1511.07289, 23 November 2015. a, b
ClimEx project: CRCM5-LE, available at: https://climex-data.srv.lrz.de/Public/ (last access: 30 November 2021), 2020. a
Dawson, A.: eofs: A Library for EOF Analysis of Meteorological, Oceanographic, and Climate Data, Journal of Open Research Software, 4, e14, https://doi.org/10.5334/jors.122, 2016. a, b
Deo, R. C., Kisi, O., and Singh, V. P.: Drought forecasting in eastern Australia using multivariate adaptive regression spline, least square support vector machine and M5Tree model, Atmos. Res., 184, 149–175, https://doi.org/10.1016/j.atmosres.2016.10.004, 2017. a
Enfield, D. B., Mestas-Nuñez, A. M., and Trimble, P. J.: The Atlantic Multidecadal Oscillation and its relation to rainfall and river flows in the continental U.S., Geophys. Res. Lett., 28, 2077–2080, https://doi.org/10.1029/2000GL012745, 2001. a
Environment and Climate Change Canada: The Canadian Earth System Model Large Ensembles, available at: https://open.canada.ca/data/en/dataset/aa7b6823-fd1e-49ff-a6fb-68076a4a477c (last access: 29 November 2021), 2020. a
European Centre for Medium-Range Weather Forecasts: ERA Interim, Daily, available at: https://apps.ecmwf.int/datasets/data/interim-full-daily/levtype=sfc/ (last access: 29 November 2021), 2020.
Federal Ministry of Food and Agriculture: Trockenheit und Dürre
2018 – Überblick über Maßnahmen, available at: https://www.bmel.de/DE/Landwirtschaft/Nachhaltige-Landnutzung/Klimawandel/_Texte/Extremwetterlagen-Zustaendigkeiten.html (last access: 25 July 2019), 2018. a
Folland, C. K., Knight, J., Linderholm, H. W., Fereday, D., Ineson, S., and Hurrell, J. W.: The Summer North Atlantic Oscillation: Past, Present, and Future, J. Climate, 22, 1082–1103, https://doi.org/10.1175/2008JCLI2459.1, 2009. a, b
Hao, K.: We analyzed 16,625 papers to figure out where AI is headed next,
available at:
https://www.technologyreview.com/2019/01/25/1436/we-analyzed-16625-papers-to-figure-out-where-ai-is-headed-next/
(last access: 21 March 2021), 2019. a
Hao, Z., Singh, V. P., and Xia, Y.: Seasonal Drought Prediction: Advances, Challenges, and Future Prospects, Rev. Geophys., 56, 108–141, https://doi.org/10.1002/2016RG000549, 2018. a, b
Hurrell, J. W., Kushnir, Y., Ottersen, G., and Visbeck, M. (Eds.): The North
Atlantic Oscillation: Climatic Significance and Environmental Impact, American
Geophysical Union, Washington, D.C., 2003. a
IPCC: Climate Change 2013 – The Physical Science Basis: Working Group I Contribution to the Fifth Assessment Report of the IPCC, Assessment report (Intergovernmental Panel on Climate Change), Working Group, Cambridge University Press, Cambridge, England, 2013. a
Janocha, K. and Czarnecki W. M. Wojciech: On Loss Functions for Deep Neural Networks in Classification, Schedae Informaticae, 25, 49–59, https://doi.org/10.4467/20838476SI.16.004.6185, 2016. a
Keyantash, J. and National Center for Atmospheric Research Staff: The Climate Data
Guide: Standardized Precipitation Index (SPI), available at:
https://climatedataguide.ucar.edu/climate-data/standardized-precipitation-index-spi
(last access: 21 March 2021), 2018. a
Kington, J. A.: Daily weather mapping from 1781, Climatic Change, 3, 7–36, https://doi.org/10.1007/bf02423166, 1980. a
Kirchmeier-Young, M., Zwiers, F., and Gillett, N.: Attribution of Extreme Events in Arctic Sea Ice Extent, J. Climate, 30, 553–571, https://doi.org/10.1175/JCLI-D-16-0412.1, 2016. a
Kumar, V. and Minz, S.: Feature selection: a literature review, SmartCR, 4, 211–229, 2014. a
Kushner, P. J., Mudryk, L. R., Merryfield, W., Ambadan, J. T., Berg, A., Bichet, A., Brown, R., Derksen, C., Déry, S. J., Dirkson, A., Flato, G., Fletcher, C. G., Fyfe, J. C., Gillett, N., Haas, C., Howell, S., Laliberté, F., McCusker, K., Sigmond, M., Sospedra-Alfonso, R., Tandon, N. F., Thackeray, C., Tremblay, B., and Zwiers, F. W.: Canadian snow and sea ice: assessment of snow, sea ice, and related climate processes in Canada's Earth system model and climate-prediction system, The Cryosphere, 12, 1137–1156, https://doi.org/10.5194/tc-12-1137-2018, 2018. a
Leduc, M., Mailhot, A., Frigon, A., Martel, J.-L., Ludwig, R., Brietzke, G. B., Giguère, M., Brissette, F., Turcotte, R., Braun, M., and Scinocca, J.: The ClimEx Project: A 50-Member Ensemble of Climate Change Projections at 12-km Resolution over Europe and Northeastern North America with the Canadian Regional Climate Model (CRCM5), J. Appl. Meteorol. Clim., 58, 663–693, https://doi.org/10.1175/JAMC-D-18-0021.1, 2019. a
Lim, Y.-K.: The East Atlantic/West Russia (EA/WR) teleconnection in the North
Atlantic: climate impact and relation to Rossby wave propagation,
Clim. Dynam., 44, 3211–3222, https://doi.org/10.1007/s00382-014-2381-4, 2015. a
Lundberg, S. and Lee, S.: A unified approach to interpreting model
predictions, CoRR, arXiv [preprint], arXiv:1705.07874, 25 November 2017. a
Martynov, A., Laprise, R., Sushama, L., Winger, K., Šeparović, L., and Dugas, B.: Reanalysis-driven climate simulation over CORDEX North America domain using the Canadian Regional Climate Model, version 5: model performance evaluation, Clim. Dynam., 41, 2973–3005, https://doi.org/10.1007/s00382-013-1778-9, 2013. a
McGovern, A., Elmore, K. L., Gagne, D. J., Haupt, S. E., Karstens, C. D., Lagerquist, R., Smith, T., and Williams, J. K.: Using Artificial Intelligence to Improve Real-Time Decision-Making for High-Impact Weather, B. Am. Meteorol. Soc., 98, 2073–2090, https://doi.org/10.1175/BAMS-D-16-0123.1, 2017. a, b
McKee, T., Doesken, N., and Kleist, J.: The relationship of drought frequency
and duration to time scales, in: Proceedings of the 8th Conference on Applied
Climatology, American Meteorological Society Boston, 17–22 January 1993, Anaheim, CA, USA,
1993. a
Mikhailova, N. and Yurovsky, A.: The East Atlantic Oscillation: Mechanism and Impact on the European Climate in Winter, Phys. Oceanogr., 4, 27–36, https://doi.org/10.22449/1573-160X-2016-4-25-33, 2016. a
Morid, S., Smakhtin, V., and Bagherzadeh, K.: Drought forecasting using artificial neural networks and time series of drought indices, Int. J. Climatol., 27, 2103–2111, https://doi.org/10.1002/joc.1498, 2007. a, b
Saito, T. and Rehmsmeier, M.: The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets, PLoS One, 10, 1–21, https://doi.org/10.1371/journal.pone.0118432, 2015. a, b
Santos, J. F., Portela, M. M., and Pulido-Calvo, I.: Spring drought prediction based on winter NAO and global SST in Portugal, Hydrol. Process., 28, 1009–1024, https://doi.org/10.1002/hyp.9641, 2014. a, b, c
Sasaki, Y.: The truth about of the F-measure, available at: https://www.cs.odu.edu/~mukka/cs795sum09dm/Lecturenotes/Day3/F-measure-YS-26Oct07.pdf (last access: 30 November 2021), 2007. a
Sheffield, J., Andreadis, K. M., Wood, E. F., and Lettenmaier, D. P.: Global and Continental Drought in the Second Half of the Twentieth Century: Severity–Area–Duration Analysis and Temporal Variability of Large-Scale Events, J. Climate, 22, 1962–1981, https://doi.org/10.1175/2008JCLI2722.1, 2009. a, b
Spinoni, J., Naumann, G., Vogt, J., and Barbosa, P.: Meteorological Drought in Europe: Events and Impacts: Past Trends and Future Projections, Publications Office of the European Union, Luxembourg, 2016. a
Spinoni, J., Naumann, G., and Vogt, J. V.: Pan-European seasonal trends and recent changes of drought frequency and severity, Global Planet. Change, 148, 113–130, https://doi.org/10.1016/j.gloplacha.2016.11.013, 2017. a
Trenberth, K.: Changes in Precipitation with Climate Change, Clim. Res., 47, 123–138, https://doi.org/10.3354/cr00953, 2011. a
von Trentini, F., Aalbers, E. E., Fischer, E. M., and Ludwig, R.: Comparing interannual variability in three regional single-model initial-condition large ensembles (SMILEs) over Europe, Earth Syst. Dynam., 11, 1013–1031, https://doi.org/10.5194/esd-11-1013-2020, 2020. a
World Meteorological Organization: Standardized Precipitation Index User
Guide, WMO, Geneva, Switzerland, 2012. a
Zargar, A., Sadiq, R., Naser, B., and Khan, F. I.: A review of drought indices, Environ. Rev., 19, 333–349, https://doi.org/10.1139/a11-013, 2011. a
Short summary
This study applies artificial neural networks to predict drought occurrence in Munich and Lisbon, with a lead time of 1 month. An analysis of the variables that have the highest impact on the prediction is performed. The study shows that the North Atlantic Oscillation index and air pressure 1 month before the event have the highest importance for the prediction. Moreover, it shows that seasonality strongly influences the goodness of prediction for the Lisbon domain.
This study applies artificial neural networks to predict drought occurrence in Munich and...
Altmetrics
Final-revised paper
Preprint