Acuña Espinoza, EduardoLoritz, RalfKratzert, FrederikKlotz, DanielGauch, MartinÁlvarez Chaves, ManuelEhret, Uwe2025-03-1920251607-79381027-5606192348799Xhttp://nbn-resolving.de/urn:nbn:de:bsz:93-opus-ds-157650https://elib.uni-stuttgart.de/handle/11682/15765https://doi.org/10.18419/opus-15746Data-driven techniques have shown the potential to outperform process-based models in rainfall–runoff simulation. Recently, hybrid models, which combine data-driven methods with process-based approaches, have been proposed to leverage the strengths of both methodologies, aiming to enhance simulation accuracy while maintaining a certain interpretability. Expanding the set of test cases to evaluate hybrid models under different conditions, we test their generalization capabilities for extreme hydrological events, comparing their performance against long short-term memory (LSTM) networks and process-based models. Our results indicate that hybrid models show performance similar to that of the LSTM network for most cases. However, hybrid models reported slightly lower errors in the most extreme cases and were able to produce higher peak discharges.enCC BYinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/4.0/550article2025-03-13