Articles | Volume 15, issue 2
Geosci. Model Dev., 15, 535–551, 2022
https://doi.org/10.5194/gmd-15-535-2022
Geosci. Model Dev., 15, 535–551, 2022
https://doi.org/10.5194/gmd-15-535-2022
Methods for assessment of models
25 Jan 2022
Methods for assessment of models | 25 Jan 2022

A method for assessment of the general circulation model quality using the K-means clustering algorithm: a case study with GETM v2.5

Urmas Raudsepp and Ilja Maljutenko

Related authors

Baltic Sea freshwater content
Urmas Raudsepp, Ilja Maljutenko, Amirhossein Barzandeh, Rivo Uiboupin, and Priidik Lagemaa
State Planet Discuss., https://doi.org/10.5194/sp-2022-14,https://doi.org/10.5194/sp-2022-14, 2022
Preprint under review for SP
Short summary
Modelling of discharges from Baltic Sea shipping
Jukka-Pekka Jalkanen, Lasse Johansson, Magda Wilewska-Bien, Lena Granhag, Erik Ytreberg, K. Martin Eriksson, Daniel Yngsell, Ida-Maja Hassellöv, Kerstin Magnusson, Urmas Raudsepp, Ilja Maljutenko, Hulda Winnes, and Jana Moldanova
Ocean Sci., 17, 699–728, https://doi.org/10.5194/os-17-699-2021,https://doi.org/10.5194/os-17-699-2021, 2021
Short summary
Model for leisure boat activities and emissions – implementation for the Baltic Sea
Lasse Johansson, Erik Ytreberg, Jukka-Pekka Jalkanen, Erik Fridell, K. Martin Eriksson, Maria Lagerström, Ilja Maljutenko, Urmas Raudsepp, Vivian Fischer, and Eva Roth
Ocean Sci., 16, 1143–1163, https://doi.org/10.5194/os-16-1143-2020,https://doi.org/10.5194/os-16-1143-2020, 2020
Short summary

Related subject area

Numerical methods
The Intelligent Prospector v1.0: geoscientific model development and prediction by sequential data acquisition planning with application to mineral exploration
John Mern and Jef Caers
Geosci. Model Dev., 16, 289–313, https://doi.org/10.5194/gmd-16-289-2023,https://doi.org/10.5194/gmd-16-289-2023, 2023
Short summary
Predicting peak daily maximum 8 h ozone and linkages to emissions and meteorology in Southern California using machine learning methods (SoCAB-8HR V1.0)
Ziqi Gao, Yifeng Wang, Petros Vasilakos, Cesunica E. Ivey, Khanh Do, and Armistead G. Russell
Geosci. Model Dev., 15, 9015–9029, https://doi.org/10.5194/gmd-15-9015-2022,https://doi.org/10.5194/gmd-15-9015-2022, 2022
Short summary
Transfer learning for landslide susceptibility modeling using domain adaptation and case-based reasoning
Zhihao Wang, Jason Goetz, and Alexander Brenning
Geosci. Model Dev., 15, 8765–8784, https://doi.org/10.5194/gmd-15-8765-2022,https://doi.org/10.5194/gmd-15-8765-2022, 2022
Short summary
ISMIP-HOM benchmark experiments using Underworld
Till Sachau, Haibin Yang, Justin Lang, Paul D. Bons, and Louis Moresi
Geosci. Model Dev., 15, 8749–8764, https://doi.org/10.5194/gmd-15-8749-2022,https://doi.org/10.5194/gmd-15-8749-2022, 2022
Short summary
spyro: a Firedrake-based wave propagation and full-waveform-inversion finite-element solver
Keith J. Roberts, Alexandre Olender, Lucas Franceschini, Robert C. Kirby, Rafael S. Gioria, and Bruno S. Carmo
Geosci. Model Dev., 15, 8639–8667, https://doi.org/10.5194/gmd-15-8639-2022,https://doi.org/10.5194/gmd-15-8639-2022, 2022
Short summary

Cited articles

Argo: Argo float data and metadata from Global Data Assembly Centre (Argo GDAC) – Snapshot of Argo GDAC of August 10st 2020, SEANOE [data set], https://doi.org/10.17882/42182#76230, 2020. 
Bholowalia, P. and Kumar, A.: EBK-means: A clustering technique based on elbow method and K-means in WSN, International Journal of Computer Applications, 105, 17–24, 2014. 
Burchard, H. and Bolding, K.: GETM – a general estuarine transport model, scientific documentation, Tech. Rep. EUR 20253 EN, European Commission (220), 2002. 
Celebi, M. E., Kingravi, H. A., and Vela, P. A.: A comparative study of efficient initialization methods for the K-means clustering algorithm, Expert Syst. Appl., 40, 200–210, https://doi.org/10.1016/j.eswa.2012.07.021, 2013. 
CMEMS: CMEMS-PQ-StrategicPlan, available at: https://marine.copernicus.eu/sites/default/files/wp-content/uploads/2017/03/CMEMS-PQ-StrategicPlan-v1.6-1.pdf (last acess: 18 February 2021), 2016. 
Download
Short summary
A model's ability to reproduce the state of a simulated object is always a subject of discussion. A new method for the multivariate assessment of numerical model skills uses the K-means algorithm for clustering model errors. All available data that fall into the model domain and simulation period are incorporated into the skill assessment. The clustered errors are used for spatial and temporal analysis of the model accuracy. The method can be applied to different types of geoscientific models.