Articles | Volume 15, issue 2
https://doi.org/10.5194/gmd-15-535-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-15-535-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
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
CORRESPONDING AUTHOR
Department of Marine Systems, Tallinn University of Technology, Tallinn, 19086, Estonia
Ilja Maljutenko
Department of Marine Systems, Tallinn University of Technology, Tallinn, 19086, Estonia
Related authors
Urmas Raudsepp, Ilja Maljutenko, Priidik Lagemaa, and Karina von Schuckmann
State Planet, 6-osr9, 6, https://doi.org/10.5194/sp-6-osr9-6-2025, https://doi.org/10.5194/sp-6-osr9-6-2025, 2025
Short summary
Short summary
Over the past 3 decades, the Baltic Sea has warmed and become saltier, reflecting broader atmospheric trends. Heat content changes are mainly driven by subsurface temperature variations in the upper 100 m, influenced by air temperature, evaporation, and wind stress. Freshwater content changes are largely controlled by salinity shifts in the halocline (40–120 m), with key drivers being saline inflows, precipitation, and zonal wind stress.
Urmas Raudsepp, Ulvi Ahmadov, Ilja Maljutenko, Amirhossein Barzandeh, Mariliis Kõuts, and Priidik Lagemaa
State Planet Discuss., https://doi.org/10.5194/sp-2025-7, https://doi.org/10.5194/sp-2025-7, 2025
Preprint under review for SP
Short summary
Short summary
Over the past 30 years, the Baltic Sea’s surface mixed layer has changed unevenly: it is shoaling in the southwest due to warming and increased stratification, while deepening in the northeast as ice loss allows more winter mixing. These shifts affect marine ecosystems—shallower mixing in the south limits oxygen supply to deep waters, worsening hypoxia, while deeper mixing in the north may enhance spring algal blooms. Climate impacts in the Baltic are regionally diverse.
Urmas Raudsepp, Ilja Maljutenko, Jan-Victor Björkqvist, Amirhossein Barzandeh, Sander Rikka, Aarne Männik, Siim Pärt, Priidik Lagemaa, Victor Alari, Kaimo Vahter, and Rivo Uiboupin
State Planet Discuss., https://doi.org/10.5194/sp-2025-8, https://doi.org/10.5194/sp-2025-8, 2025
Preprint under review for SP
Short summary
Short summary
The study identified key extreme metocean conditions relevant for Floating Storage and Regasification Unit design on Estonia’s coast, using statistical approaches like GPD and GEV to estimate return values. These thresholds inform infrastructure safety margins. The analysis was extended across the Baltic Sea using harmonized methods, enabling consistent risk assessment, cross-border planning, and climate-resilient design for major maritime infrastructure sites.
Laura Tuomi, Milla Johansson, Andrew Twelves, Mika Rantanen, Priidik Lagemaa, Hedi Kanarik, Jani Särkkä, Urmas Raudsepp, and Antti Westerlund
State Planet Discuss., https://doi.org/10.5194/sp-2025-12, https://doi.org/10.5194/sp-2025-12, 2025
Preprint under review for SP
Short summary
Short summary
A record low sea level of -153 cm, 34 cm below the previous minimum, was measured in the Bothnian Bay in November 2024. This extreme event was caused by a strong and long-lasting windstorm that followed an unusual track. The BAL MFC NRT physical forecast system was able to accurately predict this sea level event 3–4 days in advance. However, forecasts with longer lead times failed to predict the record low sea level, although they did indicate a significant drop in sea levels during the storm.
Jüri Elken, Ilja Maljutenko, Priidik Lagemaa, Rivo Uiboupin, and Urmas Raudsepp
State Planet, 4-osr8, 9, https://doi.org/10.5194/sp-4-osr8-9-2024, https://doi.org/10.5194/sp-4-osr8-9-2024, 2024
Short summary
Short summary
Baltic deep water is generally warmer than surface water during winter when district heating is required. Depending on the location, depth, and oceanographic situation, bottom water of Tallinn Bay can be used as an energy source for seawater heat pumps until the end of February, covering the major time interval when heating is needed. Episodically, there are colder-water events when seawater heat extraction has to be complemented by other sources of heating energy.
Anja Lindenthal, Claudia Hinrichs, Simon Jandt-Scheelke, Tim Kruschke, Priidik Lagemaa, Eefke M. van der Lee, Ilja Maljutenko, Helen E. Morrison, Tabea R. Panteleit, and Urmas Raudsepp
State Planet, 4-osr8, 16, https://doi.org/10.5194/sp-4-osr8-16-2024, https://doi.org/10.5194/sp-4-osr8-16-2024, 2024
Short summary
Short summary
In 2022, large parts of the Baltic Sea experienced the third-warmest to warmest summer and autumn temperatures since 1997 and several marine heatwaves (MHWs). Using remote sensing, reanalysis, and in situ data, this study characterizes regional differences in MHW properties in the Baltic Sea in 2022. Furthermore, it presents an analysis of long-term trends and the relationship between atmospheric warming and MHW occurrences, including their propagation into deeper layers.
Karina von Schuckmann, Lorena Moreira, Mathilde Cancet, Flora Gues, Emmanuelle Autret, Ali Aydogdu, Lluis Castrillo, Daniele Ciani, Andrea Cipollone, Emanuela Clementi, Gianpiero Cossarini, Alvaro de Pascual-Collar, Vincenzo De Toma, Marion Gehlen, Rianne Giesen, Marie Drevillon, Claudia Fanelli, Kevin Hodges, Simon Jandt-Scheelke, Eric Jansen, Melanie Juza, Ioanna Karagali, Priidik Lagemaa, Vidar Lien, Leonardo Lima, Vladyslav Lyubartsev, Ilja Maljutenko, Simona Masina, Ronan McAdam, Pietro Miraglio, Helen Morrison, Tabea Rebekka Panteleit, Andrea Pisano, Marie-Isabelle Pujol, Urmas Raudsepp, Roshin Raj, Ad Stoffelen, Simon Van Gennip, Pierre Veillard, and Chunxue Yang
State Planet, 4-osr8, 2, https://doi.org/10.5194/sp-4-osr8-2-2024, https://doi.org/10.5194/sp-4-osr8-2-2024, 2024
Urmas Raudsepp, Ilja Maljutenko, Amirhossein Barzandeh, Rivo Uiboupin, and Priidik Lagemaa
State Planet, 1-osr7, 7, https://doi.org/10.5194/sp-1-osr7-7-2023, https://doi.org/10.5194/sp-1-osr7-7-2023, 2023
Short summary
Short summary
The freshwater content in the Baltic Sea has wide sub-regional variability characterized by the local climate dynamics. The total freshwater content trend is negative due to the recent increased inflows of saltwater, but there are also regions where the increase in runoff and decrease in ice content have led to an increase in the freshwater content.
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
Short summary
This modelling study describes a methodology for describing pollutant discharges from ships to the sea. The pilot area used is the Baltic Sea area and discharges of bilge, ballast, sewage, wash water as well as stern tube oil are reported for the year 2012. This work also reports the release of SOx scrubber effluents. This technique may be used by ships to comply with tight sulfur limits inside Emission Control Areas, but it also introduces a new pollutant stream from ships to the 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
Short summary
Very little is currently known about the activities and emissions of private leisure boats. To change this, a new model was created (BEAM). The model was used for the Baltic Sea to estimate leisure boat emissions, also considering antifouling paint leach. When compared to commercial shipping, the modeled leisure boat emissions were seen to be surprisingly large for some pollutant species, and these emissions were heavily concentrated on coastal inhabited areas during summer and early autumn.
Urmas Raudsepp, Ilja Maljutenko, Priidik Lagemaa, and Karina von Schuckmann
State Planet, 6-osr9, 6, https://doi.org/10.5194/sp-6-osr9-6-2025, https://doi.org/10.5194/sp-6-osr9-6-2025, 2025
Short summary
Short summary
Over the past 3 decades, the Baltic Sea has warmed and become saltier, reflecting broader atmospheric trends. Heat content changes are mainly driven by subsurface temperature variations in the upper 100 m, influenced by air temperature, evaporation, and wind stress. Freshwater content changes are largely controlled by salinity shifts in the halocline (40–120 m), with key drivers being saline inflows, precipitation, and zonal wind stress.
Urmas Raudsepp, Ulvi Ahmadov, Ilja Maljutenko, Amirhossein Barzandeh, Mariliis Kõuts, and Priidik Lagemaa
State Planet Discuss., https://doi.org/10.5194/sp-2025-7, https://doi.org/10.5194/sp-2025-7, 2025
Preprint under review for SP
Short summary
Short summary
Over the past 30 years, the Baltic Sea’s surface mixed layer has changed unevenly: it is shoaling in the southwest due to warming and increased stratification, while deepening in the northeast as ice loss allows more winter mixing. These shifts affect marine ecosystems—shallower mixing in the south limits oxygen supply to deep waters, worsening hypoxia, while deeper mixing in the north may enhance spring algal blooms. Climate impacts in the Baltic are regionally diverse.
Urmas Raudsepp, Ilja Maljutenko, Jan-Victor Björkqvist, Amirhossein Barzandeh, Sander Rikka, Aarne Männik, Siim Pärt, Priidik Lagemaa, Victor Alari, Kaimo Vahter, and Rivo Uiboupin
State Planet Discuss., https://doi.org/10.5194/sp-2025-8, https://doi.org/10.5194/sp-2025-8, 2025
Preprint under review for SP
Short summary
Short summary
The study identified key extreme metocean conditions relevant for Floating Storage and Regasification Unit design on Estonia’s coast, using statistical approaches like GPD and GEV to estimate return values. These thresholds inform infrastructure safety margins. The analysis was extended across the Baltic Sea using harmonized methods, enabling consistent risk assessment, cross-border planning, and climate-resilient design for major maritime infrastructure sites.
Laura Tuomi, Milla Johansson, Andrew Twelves, Mika Rantanen, Priidik Lagemaa, Hedi Kanarik, Jani Särkkä, Urmas Raudsepp, and Antti Westerlund
State Planet Discuss., https://doi.org/10.5194/sp-2025-12, https://doi.org/10.5194/sp-2025-12, 2025
Preprint under review for SP
Short summary
Short summary
A record low sea level of -153 cm, 34 cm below the previous minimum, was measured in the Bothnian Bay in November 2024. This extreme event was caused by a strong and long-lasting windstorm that followed an unusual track. The BAL MFC NRT physical forecast system was able to accurately predict this sea level event 3–4 days in advance. However, forecasts with longer lead times failed to predict the record low sea level, although they did indicate a significant drop in sea levels during the storm.
Amirhossein Barzandeh, Matjaž Ličer, Marko Rus, Matej Kristan, Ilja Maljutenko, Jüri Elken, Priidik Lagemaa, and Rivo Uiboupin
Ocean Sci., 21, 1315–1327, https://doi.org/10.5194/os-21-1315-2025, https://doi.org/10.5194/os-21-1315-2025, 2025
Short summary
Short summary
We evaluated a deep-learning model, HIDRA2, for predicting sea levels along the Estonian coast and compared it to traditional numerical models. HIDRA2 performed better overall, offering faster forecasts and valuable uncertainty estimates using ensemble predictions.
Jüri Elken, Ilja Maljutenko, Priidik Lagemaa, Rivo Uiboupin, and Urmas Raudsepp
State Planet, 4-osr8, 9, https://doi.org/10.5194/sp-4-osr8-9-2024, https://doi.org/10.5194/sp-4-osr8-9-2024, 2024
Short summary
Short summary
Baltic deep water is generally warmer than surface water during winter when district heating is required. Depending on the location, depth, and oceanographic situation, bottom water of Tallinn Bay can be used as an energy source for seawater heat pumps until the end of February, covering the major time interval when heating is needed. Episodically, there are colder-water events when seawater heat extraction has to be complemented by other sources of heating energy.
Anja Lindenthal, Claudia Hinrichs, Simon Jandt-Scheelke, Tim Kruschke, Priidik Lagemaa, Eefke M. van der Lee, Ilja Maljutenko, Helen E. Morrison, Tabea R. Panteleit, and Urmas Raudsepp
State Planet, 4-osr8, 16, https://doi.org/10.5194/sp-4-osr8-16-2024, https://doi.org/10.5194/sp-4-osr8-16-2024, 2024
Short summary
Short summary
In 2022, large parts of the Baltic Sea experienced the third-warmest to warmest summer and autumn temperatures since 1997 and several marine heatwaves (MHWs). Using remote sensing, reanalysis, and in situ data, this study characterizes regional differences in MHW properties in the Baltic Sea in 2022. Furthermore, it presents an analysis of long-term trends and the relationship between atmospheric warming and MHW occurrences, including their propagation into deeper layers.
Karina von Schuckmann, Lorena Moreira, Mathilde Cancet, Flora Gues, Emmanuelle Autret, Ali Aydogdu, Lluis Castrillo, Daniele Ciani, Andrea Cipollone, Emanuela Clementi, Gianpiero Cossarini, Alvaro de Pascual-Collar, Vincenzo De Toma, Marion Gehlen, Rianne Giesen, Marie Drevillon, Claudia Fanelli, Kevin Hodges, Simon Jandt-Scheelke, Eric Jansen, Melanie Juza, Ioanna Karagali, Priidik Lagemaa, Vidar Lien, Leonardo Lima, Vladyslav Lyubartsev, Ilja Maljutenko, Simona Masina, Ronan McAdam, Pietro Miraglio, Helen Morrison, Tabea Rebekka Panteleit, Andrea Pisano, Marie-Isabelle Pujol, Urmas Raudsepp, Roshin Raj, Ad Stoffelen, Simon Van Gennip, Pierre Veillard, and Chunxue Yang
State Planet, 4-osr8, 2, https://doi.org/10.5194/sp-4-osr8-2-2024, https://doi.org/10.5194/sp-4-osr8-2-2024, 2024
Shakti Singh, Ilja Maljutenko, and Rivo Uiboupin
EGUsphere, https://doi.org/10.5194/egusphere-2024-1701, https://doi.org/10.5194/egusphere-2024-1701, 2024
Short summary
Short summary
The sea ice statistics study highlights the bias in model estimations compared to satellite data and provides a simple approach to minimise that. During the study period, the model estimates sea ice forming slightly earlier but aligns well with the satellite data for ice season's end. Rapid decrease in the sea ice parameters is observed across the Baltic Sea, especially the ice thickness in the Bothnian Bay sub-basin. These statistics could be crucial for regional adaptation strategies.
Jan Åström, Fredrik Robertsen, Jari Haapala, Arttu Polojärvi, Rivo Uiboupin, and Ilja Maljutenko
The Cryosphere, 18, 2429–2442, https://doi.org/10.5194/tc-18-2429-2024, https://doi.org/10.5194/tc-18-2429-2024, 2024
Short summary
Short summary
The HiDEM code has been developed for analyzing the fracture and fragmentation of brittle materials and has been extensively applied to glacier calving. Here, we report on the adaptation of the code to sea-ice dynamics and breakup. The code demonstrates the capability to simulate sea-ice dynamics on a 100 km scale with an unprecedented resolution. We argue that codes of this type may become useful for improving forecasts of sea-ice dynamics.
Urmas Raudsepp, Ilja Maljutenko, Amirhossein Barzandeh, Rivo Uiboupin, and Priidik Lagemaa
State Planet, 1-osr7, 7, https://doi.org/10.5194/sp-1-osr7-7-2023, https://doi.org/10.5194/sp-1-osr7-7-2023, 2023
Short summary
Short summary
The freshwater content in the Baltic Sea has wide sub-regional variability characterized by the local climate dynamics. The total freshwater content trend is negative due to the recent increased inflows of saltwater, but there are also regions where the increase in runoff and decrease in ice content have led to an increase in the freshwater content.
Tuomas Kärnä, Patrik Ljungemyr, Saeed Falahat, Ida Ringgaard, Lars Axell, Vasily Korabel, Jens Murawski, Ilja Maljutenko, Anja Lindenthal, Simon Jandt-Scheelke, Svetlana Verjovkina, Ina Lorkowski, Priidik Lagemaa, Jun She, Laura Tuomi, Adam Nord, and Vibeke Huess
Geosci. Model Dev., 14, 5731–5749, https://doi.org/10.5194/gmd-14-5731-2021, https://doi.org/10.5194/gmd-14-5731-2021, 2021
Short summary
Short summary
We present Nemo-Nordic 2.0, a novel operational marine model for the Baltic Sea. The model covers the Baltic Sea and the North Sea with approximately 1 nmi resolution. We validate the model's performance against sea level, water temperature, and salinity observations, as well as sea ice charts. The skill analysis demonstrates that Nemo-Nordic 2.0 can reproduce the hydrographic features of the Baltic Sea.
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
Short summary
This modelling study describes a methodology for describing pollutant discharges from ships to the sea. The pilot area used is the Baltic Sea area and discharges of bilge, ballast, sewage, wash water as well as stern tube oil are reported for the year 2012. This work also reports the release of SOx scrubber effluents. This technique may be used by ships to comply with tight sulfur limits inside Emission Control Areas, but it also introduces a new pollutant stream from ships to the 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
Short summary
Very little is currently known about the activities and emissions of private leisure boats. To change this, a new model was created (BEAM). The model was used for the Baltic Sea to estimate leisure boat emissions, also considering antifouling paint leach. When compared to commercial shipping, the modeled leisure boat emissions were seen to be surprisingly large for some pollutant species, and these emissions were heavily concentrated on coastal inhabited areas during summer and early autumn.
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.
Donnelly, C., Andersson, J. C. M., and Arheimer, B.:
Using flow signatures and catchment similarities to evaluate the E-HYPE multi-basin model across Europe,
Hydrol. Sci. J.,
61, 255–273. https://doi.org/10.1080/02626667.2015.1027710, 2016.
Döös, K., Meier, H. E. M., and Döscher, R.:
The Baltic haline conveyor belt or the overturning circulation and mixing in the Baltic,
Ambio,
33, 261–266, https://doi.org/10.1579/0044-7447-33.4.261, 2004.
Dybowski, D., Jakacki, J., Janecki, M., Nowicki, A., Rak, D., and Dzierzbicka-Glowacka, L.:
High-resolution ecosystem model of the Puck Bay (Southern Baltic Sea)—hydrodynamic component evaluation,
Water,
11, 2057, https://doi.org/10.3390/w11102057, 2019.
Eilola, K., Meier, H. M., and Almroth, E.:
On the dynamics of oxygen, phosphorus and cyanobacteria in the Baltic Sea; A model study,
J. Marine Syst.,
75, 163–184, https://doi.org/10.1016/j.jmarsys.2008.08.009, 2009.
Elken, J., Raudsepp, U., and Lips, U.:
On the estuarine transport reversal in deep layers of the Gulf of Finland,
J. Sea Res.,
49, 267–274, https://doi.org/10.1016/S1385-1101(03)00018-2, 2003.
Elken, J., Raudsepp, U., Laanemets, J., Passenko, J., Maljutenko, I., Pärn, O., and Keevallik, S.:
Increased frequency of wintertime stratification collapse events in the Gulf of Finland since the 1990s,
J. Marine Syst.,
129, 47–55, https://doi.org/10.1016/j.jmarsys.2013.04.015, 2014.
Gräwe, U., Holtermann, P., Klingbeil, K., and Burchard, H.:
Advantages of vertically adaptive coordinates in numerical models of stratified shelf seas,
Ocean Model.,
92, 56–68, https://doi.org/10.1016/j.ocemod.2015.05.008, 2015.
Gustafsson, B. G. and Rodriguez Medina, M.:
Validation data set compiled from Baltic Environmental Database-version 2,
Baltic Nest Institute, Stockholm Resilience Centre, Stockholm University, 2011.
Hastie, T., Tibshirani, R., and Friedman, J.:
The Elements of Statistical Learning. Data Mining, Inference, and Prediction,
Springer, 745 pp, 2009.
Holt, J. T., Allen, J. I., Proctor, R., and Gilbert, F.:
Error quantification of a high-resolution coupled hydrodynamic-ecosystem coastal-ocean model: Part 1 model overview and assessment of the hydrodynamics,
J. Marine Syst.,
57, 167–188, https://doi.org/10.1016/j.jmarsys.2005.04.008, 2005.
Holtermann, P. L., Burchard, H., Gräwe, U., Klingbeil, K., and Umlauf, L.:
Deep-water dynamics and boundary mixing in a nontidal stratified basin: A modeling study of the Baltic Sea,
J. Geophys. Res.-Oceans,
119, 1465–1487, https://doi.org/10.1002/2013JC009483, 2014.
Jain, A. K.:
Data clustering: 50 years beyond K-means,
Pattern Recogn. Lett.,
31, 651–666, https://doi.org/10.1016/j.patrec.2009.09.011, 2010.
Jakobsson, M., Stranne, C., O'Regan, M., Greenwood, S. L., Gustafsson, B., Humborg, C., and Weidner, E.: Bathymetric properties of the Baltic Sea, Ocean Sci., 15, 905–924, https://doi.org/10.5194/os-15-905-2019, 2019.
Jolliff, J. K., Kindle, J. C., Shulman, I., Penta, B., Friedrichs, M. A., Helber, R., and Arnone, R. A.:
Summary diagrams for coupled hydrodynamic-ecosystem model skill assessment,
J. Marine Syst.,
76, 64–82, https://doi.org/10.1016/j.jmarsys.2008.05.014, 2009.
Kondo, J.:
Air–sea bulk transfer coefficients in diabatic conditions,
Bound.-Lay. Meteorol.,
9, 91–112. https://doi.org/10.1007/BF00232256, 1975.
Kononenko, I. and Kukar, M.:
Machine Learning and Data Mining,
Elsevier, 454 pp., 2007.
Kõuts, M., Maljutenko, I., Elken, J., Liu Y., Hansson M., Viktorsson, L., and Raudsepp, U.:
Recent regime of persistent hypoxia in the baltic sea,
Environmental Research Communications,
3, 075004, https://doi.org/10.1088/2515-7620/ac0cc42021.
Lehmann, A. and Hinrichsen, H.-H.:
On the wind driven and thermohaline circulation of the Baltic Sea,
Phys. Chem. Earth Pt. B,
25, 183–189, https://doi.org/10.1016/S1464-1909(99)00140-9, 2000.
Leppäranta, M. and Myrberg, K.:
Physical oceanography of the Baltic Sea,
Springer Springer-Praxis, Heidelberg, Germany, 378 p., https://doi.org/10.1007/978-3-540-79703-6, 2009.
Luhamaa, A., Kimmel, K., Männik, A., and Rõõm, R.:
High resolution re-analysis for the Baltic Sea region during 1965-2005 period,
Clim. Dynam.,
36, 727–738, https://doi.org/10.1007/s00382-010-0842-y, 2011.
Maljutenko, I.: Source code for the GETM and GOTM software, Zenodo [code], https://doi.org/10.5281/zenodo.5267002, 2021.
Maljutenko, I. and Raudsepp, U.:
Data for A method for assessment of the general circulation model quality using K-means clustering algorithm,
Zenodo [data set],
https://doi.org/10.5281/zenodo.4588510, 2021.
Maljutenko, I. and Raudsepp, U.:
Validation of GETM model simulated long-term salinity fields in the pathway of saltwater transport in response to the Major Baltic Inflows in the Baltic Sea,
Measuring and Modeling of Multi-Scale Interactions in the Marine Environment – IEEE/OES Baltic International Symposium 2014, BALTIC 2014, 6887830, https://doi.org/10.1109/BALTIC.2014.6887830, 2014.
Maljutenko, I. and Raudsepp, U.:
Long-term mean, interannual and seasonal circulation in the Gulf of Finland—the wide salt wedge estuary or gulf type ROFI,
J. Marine Syst.,
195, 1–19, https://doi.org/10.1016/j.jmarsys.2019.03.004, 2019.
Meier, H. E. M.:
Modeling the pathways and ages of inflowing salt- and freshwater in the Baltic Sea,
Estuar. Coast. Shelf S.,
74, 610–627, https://doi.org/10.1016/j.ecss.2007.05.019, 2007.
Mohrholz, V.:
Major baltic inflow statistics–revised,
Frontiers in Marine Science,
5, 384, https://doi.org/10.3389/fmars.2018.00384, 2018.
Murphy, A. H.:
The coefficients of correlation and determination as measures of performance in forecast verification,
Weather Forecast.,
10, 681–688. https://doi.org/10.1175/1520-0434(1995)010<0681:TCOCAD>2.0.CO;2, 1995.
Murphy, A. H. and Epstein, E. S.:
Skill scores and correlation coefficients in model verification,
Mon. Weather Rev.,
117, 572–581, https://doi.org/10.1175/1520-0493(1989)117<0572:ssacci>2.0.co;2, 1989.
Nielsen, M. H.:
The baroclinic surface currents in the Kattegat,
J. Marine Syst.,
55, 97–121, https://doi.org/10.1016/j.jmarsys.2004.08.004, 2005.
Omstedt, A., Elken, J., Lehmann, A., Leppäranta, M., Meier, H. E. M., Myrberg, K., and Rutgersson, A.:
Progress in physical oceanography of the Baltic Sea during the 2003–2014 period,
Prog. Oceanogr.,
128, 139–171, https://doi.org/10.1016/j.pocean.2014.08.010, 2014.
Raudsepp, U.:
Interannual and seasonal temperature and salinity variations in the Gulf of Riga and corresponding saline water inflow from the Baltic proper,
Nord. Hydrol.,
32, 135–160, https://doi.org/10.2166/nh.2001.0009, 2001.
Raudsepp, U., Legeais, J.-F., She, J., Maljutenko, I., and Jandt, S.:
Baltic Inflows,
in: Copernicus Marine Service Ocean State Report, Issue 2,
J. Oper. Oceanogr.,
11:sup1, s106–s110, https://doi.org/10.1080/1755876X.2018.1489208, 2018.
Raudsepp, U., Uiboupin, R., Laanemäe, K., and Maljutenko, I.:
Geographical and seasonal coverage of sea ice in the Baltic Sea,
in: Copernicus Marine Service Ocean State Report, Issue 4,
J. Oper. Oceanogr.,
13:sup1, s115–s121, https://doi.org/10.1080/1755876X.2020.1785097, 2020.
Seifert, T. and Kayser, B.:
A high resolution spherical grid topography of the Baltic Sea,
Meereswissenschaftliche Berichte,
9, 72–88, 1995.
SMHI:
Baltic Sea – Eutrophication and Acidity aggregated datasets 1902/2017 v2018, Aggregated datasets were generated in the
framework of EMODnet Chemistry III, under the support of DG MARE Call for Tender EASME/EMFF/2016/006 – lot4, EMODnet Chemistry [data set], https://doi.org/10.6092/595D233C-3F8C-4497-8BD2-52725CEFF96B, 2018.
Soosaar, E., Maljutenko, I., Raudsepp, U., and Elken, J.:
An investigation of anticyclonic circulation in the southern Gulf of Riga during the spring period,
Cont. Shelf Res.,
78, 75–84, https://doi.org/10.1016/j.csr.2014.02.009, 2014.
Soosaar, E., Maljutenko, I., Uiboupin, R., Skudra, M., and Raudsepp, U.: River bulge evolution and dynamics in a non-tidal sea – Daugava River plume in the Gulf of Riga, Baltic Sea, Ocean Sci., 12, 417–432, https://doi.org/10.5194/os-12-417-2016, 2016.
Stow, C. A., Jolliff, J., McGillicuddy Jr, D. J., Doney, S. C., Allen, J. I., Friedrichs, M. A., Rose, K. A., and Wallhead, P.:
Skill assessment for coupled biological/physical models of marine systems,
J. Marine Syst.,
76, 4–15, https://doi.org/10.1016/j.jmarsys.2008.03.011, 2009.
Taylor, K. E.:
Summarizing multiple aspects of model performance in a single diagram,
J. Geophys. Res.-Atmos.,
106, 7183–7192, https://doi.org/10.1029/2000JD900719, 2001.
Väli, G., Meier, H. M., and Elken, J.:
Simulated halocline variability in the Baltic Sea and its impact on hypoxia during 1961–2007,
J. Geophys. Res.-Oceans,
118, 6982–7000, https://doi.org/10.1002/2013JC009192, 2013.
Wȩglarczyk, S.:
The interdependence and applicability of some statistical quality measures for hydrological models,
J. Hydrol.,
206, 98–103, https://doi.org/10.1016/s0022-1694(98)00094-8, 1998.
Wulff, F., Sokolov, A., and Savchuk, O.: Nest – a decision support system for management of the Baltic Sea. A user manual, Technical Report No. 10, Baltic Nest Institute, Stockholm University Baltic Sea Centre, Stockholm University, Sweden,
Baltic Nest Institute
Stockholm University, Sweden, 70 pp., 2013.
Yuan, C. and Yang, H.:
Research on K-value selection method of K-means clustering algorithm,
J– Multidisciplinary Scientific Journal,
2, 226–235, https://doi.org/10.3390/j2020016, 2019.
Zhang, T., Ramakrishnan, R., and Livny, M.:
BIRCH: an efficient data clustering method for very large databases,
in: Proceedings of the 1996 ACM SIGMOD international conference on Management of data – SIGMOD '96, 103–114, https://doi.org/10.1145/233269.233324, 1996.
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.
A model's ability to reproduce the state of a simulated object is always a subject of...