DKRZ Project

1083: Climate Informatics: New machine learning methods for climate data and climate model evaluation

active project

Principal investigator: Jakob Runge

DLR, Institut für Datenwissenschaften (Community project)

Report 7/2018 to 6/2019
Report 7/2019 to 6/2020
Report 7/2021 to 6/2022
Report 7/2022 to 6/2023
Report 7/2023 to 6/2024
Report 7/2024 to 6/2025

Publications

DOI: https://media.suub.uni-bremen.de/handle/ elib/8016, G. Behrens. Understanding and Modelling Convection with Machine Learning. PhD thesis, 2024. URL https://media.suub.uni-bremen.de/handle/elib/8016.
DOI: 10.5194/egusphere-egu25-10947, A. Lanson and J. Runge. Causal effect estimation for robust detection of critical slowing down, 2025. URL https://doi.org/10.5194/egusphere-egu25-10947
DOI: http://dx.doi.org/10.5194/esd-16-607-2025, K. Debeire, L. Bock, P. Nowack, J. Runge, and V. Eyring. Constraining uncertainty in projected precipitation over land with causal discovery. Earth System Dynamics, 16(2):607–630, Apr. 2025. ISSN 2190-4987. doi: 10.5194/esd-16-607-2025. URL http://dx.doi.org/10.5194/esd-16-607-2025.
DOI: https://arxiv.org/abs/2502.20099, J. L. Gamella, S. Bing, and J. Runge. Sanity checking causal representation learning on a simple real-world system. arXiv preprint arXiv:2502.20099, 2025
DOI: http://dx.doi.org/10.5194/esd-15-689-2024, S. Karmouche, E. Galytska, G. A. Meehl, J. Runge, K. Weigel, and V. Eyring. Changing effects of external forcing on atlantic–pacific interactions. Earth System Dynamics, 15(3):689–715, June 2024. ISSN 2190-4987. doi: 10.5194/esd-15-689-2024. URL http://dx.doi.org/10.5194/esd-15-689-2024
DOI: http://dx.doi.org/10.1029/2024EF004901, R. Swaminathan, J. Schewe, J. Walton, K. Zimmermann, C. Jones, R. A. Betts, C. Burton, C. D. Jones, M. Mengel, C. P. O. Reyer, A. G. Turner, and K. Weigel. Regional impacts poorly constrained by climate sensitivity. Earth’s Future, 12(12), Dec. 2024. ISSN 2328-4277. doi: 10.1029/2024ef004901. URL http://dx.doi.org/10.1029/2024EF004901
DOI: http://dx.doi.org/10.1029/2024MS004272, G. Behrens, T. Beucler, F. Iglesias-Suarez, S. Yu, P. Gentine, M. Pritchard, M. Schwabe, and V. Eyring. Simulating atmospheric processes in earth system models and quantifying uncertainties with deep learning multi-member and stochastic parameterizations. Journal of Advances in Modeling Earth Systems, 17(4), Apr. 2025. ISSN 1942-2466. doi: 10.1029/2024ms004272. URL http://dx.doi.org/10.1029/2024MS004272.
DOI: https://ui.adsabs.harvard.edu/link_gateway/2024EGUGA..2622158H/doi:10.5194/egusphere-egu24-22158, R. Herman and J. Runge. Spatiotemporal causal effect estimation. In EGU General Assembly Conference Abstracts, page 22158, 2024
DOI: http://dx.doi.org/10.5194/ egusphere-egu25-4127, D. Atmojo, K. Weigel, A. Grundner, M. Holland, and V. Eyring. Data-driven equation discovery of a sea ice albedo parametrisation. Mar. 2025. doi: 10.5194/egusphere-egu25-4127. URL http://dx.doi.org/10.5194/egusphere-egu25-4127
DOI: http://dx.doi.org/10.5194/egusphere-egu25-12753, L. Lindenlaub, K. Weigel, B. Hassler, C. Jones, and V. Eyring. Characteristics of agricultural droughts under projected atmospheric changes. Mar. 2025b. doi: 10.5194/egusphere-egu25-12753. URL http://dx.doi.org/10.5194/egusphere-egu25-12753
DOI: http://dx.doi.org/10.5194/egusphere-2025-1517, L. Lindenlaub, K. Weigel, B. Hassler, C. Jones, and V. Eyring. Characteristics of agricultural droughts in cmip6 historical simulations and future projections. EGUsphere [preprint], Apr. 2025a. doi: 10.5194/egusphere-2025-1517. URL http://dx.doi.org/10.5194/egusphere-2025-1517
DOI: https://proceedings.mlr.press/v236/bing24a.html, S. Bing, U. Ninad, J. Wahl, and J. Runge. Identifying linearly-mixed causal representations from multi-node inter- ventions. In Proceedings of the Third Conference on Causal Learning and Reasoning, volume 236 of Proceedings of Machine Learning Research, pages 843–867. PMLR, 01–03 Apr 2024.
DOI: http://dx.doi.org/10.5194/egusphere-2023-1861, S. Karmouche, E. Galytska, G. A. Meehl, J. Runge, K. Weigel, and V. Eyring. Changing effects of external forcing on atlantic-pacific interactions. 2023a.
DOI: https://proceedings.mlr.press/v216/gunther23a.html, W. Günther, U. Ninad, and J. Runge. Causal discovery for time series from multiple datasets with latent contexts. In Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, volume 216 of Proceedings of Machine Learning Research, pages 766–776. PMLR, 2023
DOI: 10.5194/esd-14-309-2023, S. Karmouche, E. Galytska, J. Runge, G. A. Meehl, A. S. Phillips, K. Weigel, and V. Eyring. Regime-oriented causal model evaluation of atlantic–pacific teleconnections in cmip6. Earth System Dynamics, 14 (2):309–344, 2023.
DOI: http://dx.doi.org/10.1029/2023JD038906, A. Pa ̧cal, B. Hassler, K. Weigel, M. L. Kurnaz, M. F. Wehner, and V. Eyring. Detecting extreme temperature events using gaussian mixture models. Journal of Geophysical Research: Atmospheres, 128(18), Sept. 2023. ISSN 2169-8996. doi: 10.1029/2023jd038906. URL http://dx.doi.org/10.1029/2023JD038906.
DOI: https://proceedings.mlr.press/v236/debeire24a.html, K. Debeire, J. Runge, A. Gerhardus, and V. Eyring. Bootstrap aggregation and confidence measures to improve time series causal discovery, 2024. URL https://arxiv.org/abs/2306.08946. to be published in Proceedings of CLeaR 2024.
DOI: 10.1038/s41612-023-00452-w, Fons, E., Runge, J., Neubauer, D. et al. Stratocumulus adjustments to aerosol perturbations disentangled with a causal approach. npj Clim Atmos Sci 6, 130 (2023).
DOI: 10.1017/eds.2023.17, W. Günther, P. Miersch, U. Ninad, and J. Runge. Clustering of causal graphs to explore drivers of river discharge. Environmental Data Science, 2:e25, 2023. doi: 10.1017/eds.2023.17
DOI: https://papers.nips.cc/paper_files/paper/2023/hash/44a6769fe6c695f8dfb347c649f7c9f0-Abstract-Datasets_and_Benchmarks.html, J. Kaltenborn, C. Lange, V. Ramesh, P. Brouillard, Y. Gurwicz, C. Nagda, J. Runge, P. Nowack, and D. Rol- nick. Climateset: A large-scale climate model dataset for machine learning. In Advances in Neural Information Processing Systems, volume 36, pages 21757–21792. Curran Associates, Inc., 2023.
DOI: https://arxiv.org/abs/2310. 11132., O.-I. Popescu, A. Gerhardus, and J. Runge. Non-parametric conditional independence testing for mixed continuous- categorical variables: A novel method and numerical evaluation, 2023. URL https://arxiv.org/abs/2310. 11132.
DOI: https://arxiv.org/abs/2404.11939., R. Swaminathan, J. Schewe, J. Walton, K. Zimmermann, C. Jones, R. A. Betts, C. Burton, C. D. Jones, M. Mengel, C. P. O. Reyer, A. G. Turner, and K. Weigel. Regional impacts poorly constrained by climate sensitivity, 2024. URL https://arxiv.org/abs/2404.11939. submitted to PNAS.
DOI: https://arxiv.org/abs/2306.07047, J. Wahl, U. Ninad, and J. Runge. Foundations of Causal Discovery on Groups of Variables, June 2023. arXiv:2306.07047 [math, stat]
J. Wahl∗, U. Ninad∗, and J. Runge. Vector causal inference between two groups of variables. arXiv preprint arXiv:2209.14283, accepted at AAAI 2023.
DOI: 10.5194/esd-14-309-2023, S. Karmouche, E. Galytska, J. Runge, G. A. Meehl, A. S. Phillips, K. Weigel, and V. Eyring. Regime-oriented causal model evaluation of atlantic–pacific teleconnections in cmip6. Earth System Dynamics, 14 (2):309–344, 2023.
DOI: 10.1017/eds.2022.11, X.-A. Tibau, C. Reimers, A. Gerhardus, J. Denzler, V. Eyring, and J. Runge. A spatiotemporal stochastic climate model for benchmarking causal discovery methods for teleconnections. Environmental Data Science, 1:e12, 2022.
J. Gottfriedsen, M. Berrendorf, P. Gentine, M. Reichstein, K. Weigel, B. Hassler, and V. Eyring. On the generalization of agricultural drought classification from climate data, 2021. NeurIPS 2021 Workshop: Tackling Climate Change with Machine Learning. URL: https://arxiv.org/abs/ 2111.15452.
J. Gottfriedsen, M. Berrendorf, P. Gentine, M. Reichstein, K. Weigel, B. Hassler, and V. Eyring. On the generalization of agricultural drought classification from climate data, 2021. NeurIPS 2021 Workshop: Tackling Climate Change with Machine Learning. URL: https://arxiv.org/abs/ 2111.15452.
DOI: 10.5194/gmd-14-3159-2021, Weigel, K., Bock, L., Gier, B. K., Lauer, A., Righi, M., Schlund, M., Adeniyi, K., Andela, B., Arnone, E., Berg, P., Caron, L.-P., Cionni, I., Corti, S., Drost, N., Hunter, A., Lledó, L., Mohr, W. C., Paçal, A., Pérez-Zanón, N., Predoi, V., Sandstad, M., Sillmann, J., Sterl, A., Vegas-Regidor, J., von Hardenberg, J., and Eyring, V.: Earth System Model Evaluation Tool (ESMValTool) v2.0 - diagnostics for extreme events, regional and impact evaluation, and analysis of Earth system models in CMIP, Geosci. Model Dev., 14, 3159-3184, doi: 10.5194/gmd-14-3159-2021, 2021.
W. Günther, U. Ninad∗, J. Wahl∗, and J. Runge. Conditional inde- pendence testing with heteroskedastic data and applications to causal discovery. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems, volume 35, pages 16191–16202. Curran Associates, Inc., 2022. URL https://proceedings.neurips.cc/paper_files/paper/2022/file/ 6739d8df16b5bce3587ca5f18662a6aa-Paper-Conference.pdf.
J. Gottfriedsen, M. Berrendorf, P. Gentine, M. Reichstein, K. Weigel, B. Hassler, and V. Eyring. On the generaliza- tion of agricultural drought classification from climate data, 2021.
C. Käding , J. Runge. Distinguishing cause and effect in bivariate structural causal models: A systematic investigation, 2022. Under review at Journal of Machine Learning Research.
X.-A. Tibau, C. Reimers, A. Gerhardus, J. Denzler, V. Eyring, and J. Runge. A spatio-temporal stochastic climate model for benchmarking causal discovery methods for teleconnections, 2021. Under review at the Journal of Environmental Data Science.
DOI: 10.5194/ gmd-14-3159-2021, K. Weigel, L. Bock, B. K. Gier, A. Lauer, M. Righi, M. Schlund, K. Adeniyi, B. Andela, E. Arnone, P. Berg, L.-P. Caron, I. Cionni, S. Corti, N. Drost, A. Hunter, L. Lled ́o, C. W. Mohr, A. Pa ̧cal, N. P ́erez-Zan ́on, V. Predoi, M. Sandstad, J. Sillmann, A. Sterl, J. Vegas-Regidor, J. von Hardenberg, and V. Eyring. Earth system model evaluation tool (ESMValTool) v2.0 – diagnostics for extreme events, regional and impact evaluation, and analysis of earth system models in CMIP. Geoscientific Model Development, 14(6):3159–3184, June 202
DOI: 10.1038/s41467-020-15195-y, Nowack, P., Runge, J., Eyring, V., and Haigh, J. D. (2020). Causal networks for climate model evaluation and constrained projections. Nature communications, 11(1):1–11.
Zitzmann, S. F. (2020). Detecting Activity of Tropical Cyclones with the Unsupervised Maximally Divergent Interval Algorithm. Master’s Thesis. Ludwig Maximilian University of Munich, Germany.
DOI: 10.1126/sciadv.aau4996, Runge, J., Nowack, P., Kretschmer, M., Flaxman, S., and Sejdinovic, D. (2019). Detecting and quantifying causal associations in large nonlinear time series datasets. Science Advances, 5(11):eaau4996.