Clustering spatio-seasonal hydrogeochemical data using self-organizing maps for groundwater quality assessment in the Red River Delta, Vietnam

Summary The Red River Delta (RRD) is the second largest delta in Vietnam, and its local communities depend on groundwater sources for water supply. A clear understanding of the groundwater hydrogeochemical properties, particularly their changes from the dry to rainy seasons and spatial characteristics, is invaluable and indispensable for the management and protection of this important water resource. In this study, self-organizing maps was systematically applied for the first time to investigate the seasonal and spatial hydrogeochemical characteristics of groundwater in the Pleistocene confined aquifer of the RRD. The hydrogeochemical characteristics clustered by SOM were further examined using the Gibbs Diagrams. The groundwater chemistry dataset used in the analysis comprised eight major dissolved ions (i.e., Ca 2+ , Mg 2+ , Na + , K + , HCO 3 − , Cl − , SO 4 2− , and CO 3 2− ) and total dissolved solids that were collected from 52 groundwater monitoring wells within the study area during the dry and rainy seasons. Based on the results, the hydrogeochemical groundwater data of the confined aquifer monitoring wells for the delta were classified into 8 clusters, which revealed three basic representative water types: high salinity (2 clusters), low salinity (3 clusters), and freshwater (3 clusters). The high-salinity types were located in the middle-stream and coastal areas of the RRD, while the low-salinity types were observed near the western and northeastern boundaries of the delta. Cluster changes from the dry to rainy seasons were detected in approximately one-third of the observation wells. The increase in groundwater recharge during the rainy season is the main reason for these changes. Based on Gibbs diagrams, the source of soluble ions in the groundwater of the freshwater types was found to be the weathering of rock-forming minerals, while evaporation and marine activities (leaching from salty paleowater and salt water intrusion) were found to be the main factors affecting the chemistry of the groundwater characterized by the low- and high- salinity types, respectively.

[1]  Kenji Jinno,et al.  Comparison of pattern extraction capability between self-organizing maps and principal component analysis , 2009 .

[2]  A. Christiansen,et al.  Origin and extent of fresh groundwater, salty paleowaters and recent saltwater intrusions in Red River flood plain aquifers, Vietnam , 2012, Hydrogeology Journal.

[3]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[4]  A. M. Kalteh,et al.  Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application , 2008, Environ. Model. Softw..

[5]  N. Giri.  Multivariate Statistical Analysis : Revised And Expanded , 2003 .

[6]  A. Kawamura,et al.  Spatiotemporal classification of environmental monitoring data in the Yeongsan River basin, Korea, using self-organizing maps. , 2011, Journal of environmental monitoring : JEM.

[7]  A. Kawamura,et al.  Evaluation of sedimentation vulnerability at small hillside reservoirs in the semi-arid region of Tunisia using the Self-Organizing Map , 2010 .

[8]  W. D. Alberto,et al.  Pattern recognition techniques for the evaluation of spatial and temporal variations in water quality. A case study: Suquía River Basin (Cordoba-Argentina). , 2001 .

[9]  J. Olsson,et al.  Identification of typical synoptic patterns causing heavy rainfall in the rainy season in Japan by a Self-Organizing Map , 2007 .

[10]  Geological factors affecting the chemical characteristics of the thermal waters of the carbonate karstified aquifers of Northern Vietnam , 2000 .

[11]  S. Tanabe.  Song Hong (Red River) delta evolution related to millennium-scale Holocene sea-level changes , 2003 .

[12]  S. Arabia,et al.  Multivariate statistical analysis of groundwater quality in Wadi Ranyah, Saudi Arabia. , 2010 .

[13]  Mu-Chun Su,et al.  Improving the Self-Organizing Feature Map Algorithm Using an Efficient Initialization Scheme , 2002 .

[14]  A. W. Minns,et al.  The classification of hydrologically homogeneous regions , 1999 .

[15]  G. Panagopoulos,et al.  The use of multicomponent statistical analysis in hydrogeological environmental research. , 2004, Water research.

[16]  Hydrogeochemical characteristics of groundwater from the two main aquifers in the Red River Delta, Vietnam , 2014 .

[17]  Deepali Marghade,et al.  Major ion chemistry of shallow groundwater of a fast growing city of Central India , 2012, Environmental Monitoring and Assessment.

[18]  Abderrahmane Boudoukha,et al.  A multivariate Statistical Analysis of Groundwater Chemistry Data , 2011 .

[19]  Reza Modarres,et al.  Identification of homogeneous regions for regionalization of watersheds by two-level self-organizing feature maps , 2014 .

[20]  B R Raghavan,et al.  The utility of multivariate statistical techniques in hydrogeochemical studies: an example from Karnataka, India. , 2002, Water research.

[21]  A. Ramachandra Rao,et al.  Regional flood frequency analysis by combining self-organizing feature map and fuzzy clustering , 2008 .

[22]  Jacek Namieśnik,et al.  Application of PCA and time series analysis in studies of precipitation in Tricity (Poland) , 2004 .

[23]  Sylvie Thiria,et al.  Detecting decadal changes in ENSO using neural networks , 2006 .

[24]  Yoon-Seok Timothy Hong,et al.  Analysis of a municipal wastewater treatment plant using a neural network-based pattern analysis. , 2003, Water research.

[25]  C. Güler,et al.  Delineation of hydrochemical facies distribution in a regional groundwater system by means of fuzzy c‐means clustering , 2004 .

[26]  P. Viet,et al.  Arsenic pollution of groundwater in Vietnam exacerbated by deep aquifer exploitation for more than a century , 2011, Proceedings of the National Academy of Sciences.

[27]  Bing Zhang,et al.  Hydrochemical characteristics and water quality assessment of surface water and groundwater in Songnen plain, Northeast China. , 2012, Water research.

[28]  A. Kawamura,et al.  Spatio-temporal analysis of recent groundwater-level trends in the Red River Delta, Vietnam , 2012, Hydrogeology Journal.

[29]  R. Gibbs.  Mechanisms Controlling World Water Chemistry , 1970, Science.

[30]  M. Hussein.  Hydrochemical evaluation of groundwater in the Blue Nile Basin, eastern Sudan, using conventional and multivariate techniques , 2004 .

[31]  M. Montréjaud-Vignoles,et al.  Monitoring of water quality from roof runoff: Interpretation using multivariate analysis. , 2011, Water research.

[32]  S. Yidana,et al.  Analysis of groundwater quality using multivariate and spatial analyses in the Keta basin, Ghana , 2010 .

[33]  M. Jalali.  Geochemistry characterization of groundwater in an agricultural area of Razan, Hamadan, Iran , 2009 .

[34]  Akira Kawamura,et al.  Identification of aquifer system in the whole Red River Delta, Vietnam , 2011 .

[35]  Keith Turner,et al.  Evaluation of graphical and multivariate statistical methods for classification of water chemistry data , 2002 .

[36]  Jörg Dietrich,et al.  A one-step similarity approach for the regionalization of hydrological model parameters based on Self-Organizing Maps , 2013 .

[37]  Iván Machón González,et al.  Self-organizing map and clustering for wastewater treatment monitoring , 2004, Eng. Appl. Artif. Intell..

[38]  Dong-Gyun Hong,et al.  Stream modification patterns in a river basin: Field survey and self-organizing map (SOM) application , 2010, Ecol. Informatics.

[39]  A. El-Fiky.  Hydrogeochemical characteristics and evolution of groundwater at the Ras Sudr-Abu Zenima Area, southwest Sinai, Egypt. , 2010 .

[40]  Genesis of economic relevant fresh groundwater resources in Pleistocene/ Neogene aquifers in Nam Dinh (Red River Delta, Vietnam). , 2012 .

[41]  U. Shukla,et al.  Hydrogeochemistry for the assessment of groundwater quality in Varanasi: a fast-urbanizing center in Uttar Pradesh, India , 2011, Environmental monitoring and assessment.