Multivariate Analysis of Groundwater-Quality Time-Series Using Self-organizing Maps and Sammon’s Mapping
- 423 Downloads
Groundwater extracted from alluvial aquifers close to rivers is vulnerable to contamination by infiltrating river water. Infiltration is often increased during high discharge events, when the levels of waterborne pathogens are also increased. Water suppliers with low-level treatment thus rely on alternative measures derived from information on system state to manage the resource and maintain drinking-water quality. In this study, a combination of Self-Organizing Maps and Sammon’s Mapping (SOM-SM) was used as a proxy analysis of a multivariate time-series to detect critical system states whereby contamination of the drinking water extraction wells is imminent. Groundwater head, temperature and electrical conductivity time-series from groundwater observation wells were analysed using the SOM-SM method. Independent measurements (spectral absorption coefficient, turbidity, particle density and river stage) were used. This approach can identify critical system states and can be integrated into an adaptive, online, automated groundwater-management process.
KeywordsGroundwater Time-series analysis Self-organizing map Sammon’s mapping Drinking water quality
The authors thank Stefan Scheidler from the Applied and Environmental Geology Group, University of Basel, Endress+Hauser Metso AG and the Waterworks Reinach and Surroundings (WWRuU) for their support. This work was funded by the Swiss Innovation Promotion Agency CTI (projects number 8999.1 PFIW-IW and 12611.2 PFIW-IW) and the Freiwillige Akademische Gesellschaft Basel.
- Affolter A, Huggenberger P, Scheidler S, Epting J (2010) Adaptive groundwater management in urban areas: effect of surface water-groundwater interaction using the example of artificial groundwater recharge and in- and exfiltration of the river Birs (Switzerland). Grundwasser 15(3):147–161CrossRefGoogle Scholar
- Auckenthaler A, Raso G, Huggenberger P (2002) Particle transport in a karst aquifer: natural and artificial tracer experiments with bacteria, bacteriophages and microspheres. Water Sci Technol 46(3):131–138Google Scholar
- Camplani M, Cannas B, Fanni A, Pautasso G, Sias G, Sonato P, Asdex Upgrade Team (2009) Tracking of the plasma states in a nuclear fusion device using SOMs. In: Engineering Applications of Neural Networks. Brown DP, Draganova C, Pimenidis E, Mouratidis H (eds.) Communications in Computer and Information Science 43, 430–437Google Scholar
- Kohonen T (2001) Self-organizing maps. SpringerGoogle Scholar
- O’Flynn B, Regan F, Lawlor A, Wallace J, Torres J, O’Mathuna C (2010) Experiences and recommendations in deploying a real-time, water quality monitoring system. Meas Sci Technol 21(124004):10Google Scholar
- Regli C, Rauber M, Huggenberger P (2003) Analysis of aquifer hetereogeneity within a well capture zone, comparison of model data with field experiments: a case study from the river Wiese, Switzerland. Aquat Sci 65(2):111–128Google Scholar
- Stefanovic N, Radojevic I, Ostojic A, Comic L, Topuzovi M (2015) Composite Web information system for management of water resources. Water Resour Manag 29:2285–2301Google Scholar
- Vesanto J, Himberg J, Alhoniemi E, Parhankangas J (2000) SOM toolbox for Matlab 5. Helsinki University of Technology, FinlandGoogle Scholar
- Zektser IS, Everett LG (2004) Groundwater resources of the world and their use. UNESCO IHP-VI, Series on Groundwater No.6Google Scholar