KSC - Observational Data Clustering Preprocessorhttps://doi.org/10.26165/JUELICH-DATA/GLTKXZHermanns, AlexanderLange, Anne CarolineFuchs, HendrikKowalski, JuliaFranke. PhilippJülich DATA2025-12-042025-12-04T09:59:36ZPreprocessing routine for ground-based atmospheric monitoring network data. Utilizing a k-means soft constrained clustering algorithm to derive a representative sub-sampling of the availiable data into an assimilation and validation set. This work was partially performed as part of the Helmholtz School for Data Science in Life, Earth and Energy (HDS- LEE) and received funding from the Helmholtz Association of German Research Centres.Earth and Environmental SciencesK-Meanair qualityclusteringData assimilationHermanns, A.: KSC – Observational Data Clustering Preprocessor, Zenodo [code], https://doi.org/10.5281/zenodo.14711881, 2025., doi, https://doi.org/10.5281/zenodo.14711881, https://doi.org/10.5281/zenodo.14711881Hermanns, A., Lange, A. C., Kowalski, J., Fuchs, H., and Franke, P.: Data clustering to optimise the representativity of observational data in air quality data assimilation: a case study with EURAD-IM (version 5.9.1 DA), Geosci. Model Dev., 18, 9417–9432, https://doi.org/10.5194/gmd-18-9417-2025, 2025., doi, https://doi.org/10.5194/gmd-18-9417-2025, https://doi.org/10.5194/gmd-18-9417-2025Franke, Philipp2025-12-03CC0CC0 Waiver