Comparison of self-organizing maps classification approach with cluster and principal components analysis for large environmental data sets

Relating Water Quality and Age in Drinking Water Distribution Systems Using Self-Organising Maps

“…Therefore, by comparing component planes for different input variables one can identify general (potentially non-linear) correlations, or correlations that are specific to just a portion of the input data. SOMs can also be interpreted using a U-matrix, which is a visualisation of the dissimilarity between the reference A review of the use of SOMs in the water resources domain is presented in Kalteh et al [32] and a comparison against similar approaches appears in Astel et al [33]. Mounce et al [34] proposed their use in data mining microbiological and physio-chemical analytical results data from a laboratory scale pipe rig.…”

“…Figure 5 shows the number of data per hexagon in the component planes for all data sets. A review of the use of SOMs in the water resources domain is presented in Kalteh et al [32] and a comparison against similar approaches appears in Astel et al [33]. Mounce et al [34] proposed their use in data mining microbiological and physio-chemical analytical results data from a laboratory scale pipe rig.…”

Spatial and temporal variations of nitrogen pollution in Wen-Rui Tang River watershed, Zhejiang, China

“…Based on the monitoring program, the government has established a set of water quality standards to protect waterbodies and guide remediation activities. To fully understand water quality issues, many researchers have successfully investigated the application of multivariate and GIS analyses to address the spatial and temporal variations of water quality in various regions (Grande et al 2003;Mingoti and Lima 2006;Kallioinen et al 2006;Holbrook et al 2006;Singh et al 2006;Astel et al 2007;Shreshtha and Kazama 2007;Zhang et al 2009). Many of these studies have been able to geographically link water quality deterioration with specific human activities, which can then be used to guide remediation efforts.…”

A Review of Self-Organizing Map Applications in Meteorology and Oceanography

“…They also found that the SOM was more robust than the PCA in extracting the predefined patterns of variability. Annas et al (2007) and Astel et al (2007) further confirmed the superior performance of the SOM over the PCA. These advantages, of course, must be tempered by the fact that PCA uses an empirical vector space that spans the data space, hence aspects of the data space may be quantitatively reconstructed from the vector space (Liu, 2006;Liu & Weisberg, 2005).…”