Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen's Self-Organizing Map

Peeters, Luk; Bação, Fernando; Lobo, Victor; Dassargues, Alain

doi:10.5194/hess-11-1309-2007

Cited by 45 publications

(31 citation statements)

References 28 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Le principe de l' algorithme des SOM consiste à effectuer une classification non linéaire des bases de données complexes en identifiant des groupes semblables. Ainsi, à partir d'un apprentissage non supervisé, cet algorithme recherche itérativement des similarités parmi les données observées et les représente sur une carte de sortie (ou carte de Kohonen) en préservant les voisinages (Peeters et al, 2006). L' apprentissage se fait avec différentes tailles de carte et la taille optimale est choisie en minimisant les erreurs dites de quantification (QE) et de topographie (TE) (Konan et al, 2006 ;Park et al, 2003 …”

Section: Caractérisation Des Processus De Minéralisation Des Eaux Du unclassified

Origines et modélisation de la minéralisation des eaux du Quaternaire d’Abidjan (Sud de la Côte d’Ivoire)

Douagui¹,

Kouamé²,

Koffi³

et al. 2010

International Journal of Biological and Chemical Sciences

View full text Add to dashboard Cite

RESUMELes eaux de 61 puits au sud du District d'Abidjan ont été caractérisées afin de connaître la variabilité spatiale de la minéralisation des eaux du Quaternaire. Le variogramme et le krigeage ordinaire ont été utilisés pour analyser la distribution spatiale de la minéralisation. La détermination des facteurs qui gouvernent cette minéralisation s'est faite à partir de l'algorithme de Kohonen et du calcul de l'indice d'échange de base. Les eaux des zones urbanisées (Treichville, Marcory, Koumassi et Port-Bouët) et celles situées en bordure de mer et des lagunes sont fortement minéralisées tandis que les zones rurales sont caractérisées par des eaux de faible minéralisation. Quatre facteurs expliquent cette répartition spatiale de la minéralisation : les échanges de bases et la dissolution des sels marins sont observés sur l'ensemble du site ; en revanche, la pollution anthropique et l'intrusion d'eaux marine et lagunaire traduites respectivement par les fortes concentrations de nitrate et de chlorure, affectent les eaux des zones urbanisées et celles en bordure des lagunes et de l'océan atlantique.

show abstract

Section: Caractérisation Des Processus De Minéralisation Des Eaux Du unclassified

Origines et modélisation de la minéralisation des eaux du Quaternaire d’Abidjan (Sud de la Côte d’Ivoire)

Douagui¹,

Kouamé²,

Koffi³

et al. 2010

International Journal of Biological and Chemical Sciences

View full text Add to dashboard Cite

show abstract

“…The SOM-algorithm as described by Peeters et al (2007) and Choi et al (2014), is used to diagnose the effect of the hydrogeochemical processes and on groundwater quality. The SOM-algorithm is based on unsupervised learning, which means that the desired output is not known a priori.…”

Section: Self-organizing Mapsmentioning

confidence: 99%

Hydrogeochemical assessment of groundwater quality in the Baya watershed (Eastern of Cte dIvoire)

Mangoua¹,

Gone²,

Kouassi³

et al. 2015

Afr. J. Agric. Res.

View full text Add to dashboard Cite

The large demand for drinking water in the Baya watershed (6324 km 2 ), located in East of Côte d'Ivoire is supplied from groundwater sources. This study investigated the specifics hydrogeochemical assessment of groundwater quality in the Baya's watershed by using statistical methods with graphical and self-organizing maps (SOM) neural network methods. It was carried out to identify the hydrogeochemical processes related to groundwater quality, conduct a hydrochemical evaluation of the aquifer systems and delineate the various factors controlling the water chemistry and general suitability for drinking purposes. To reach these goals, groundwater was sampled from 150 locations. Results indicated that the groundwater sampled is generally acid due to the acid character of the enclosing rocks (SiO 2 > 60), with an average pH of 6.54 ± 0.33 and an average electrical conductivity of 420.15 ± 248.15 μS/cm. they are moderately mineralized to the gaze of World Heath Organization (WHO) guidelines, with calc-magnesium hydrogen carbonate facies (84%) and calc-magnesium sulphate chlorinated facies. Major ions at the origin of mineralization of groundwater are produced by rock weathering, hydrolysis of silicate minerals. The NO 3 -, Cl -and SO 4 2-ions are derived from a human pollution due to human activities. Water boreholes located along the major rivers and the watershed outlet are highly mineralized but also proned to anthropogenic pollution. As for the locations of the north and southeast of the Baya's watershed, there are high levels of iron and manganese, which explains the reddish appearance of these waters.

show abstract

“…They concluded that the SOM (nonlinear method) for classification outperformed the linear method (PCA). SOMs have also been applied in evaluating the characteristics of sediment contamination, groundwater quality, soil contamination, and ecological communities (Alvarvez-Guerra et al 2008;Peeters et al 2006;Sanchez-Martos et al 2002;Song et al 2007;Subida et al 2013;Voyslavov et al 2012). Although the advantages of the SOM algorithm and its ability for classification and visualization of large environmental datasets is evident (Astel et al 2007), the results obtained through SOM analysis are only semiquantitative for the interpretation of such (Simeonova et al 2010).…”

mentioning

confidence: 97%

Differentiating the Spatiotemporal Distribution of Natural and Anthropogenic Processes on River Water–Quality Variation Using a Self-Organizing Map With Factor Analysis

Wang

Liu

Lee

2015

Arch Environ Contam Toxicol

View full text Add to dashboard Cite

To elucidate the historical improvement and advanced measure of river water quality in the Taipei metropolitan area, this study applied the self-organizing map (SOM) technique with factor analysis (FA) to differentiate the spatiotemporal distribution of natural and anthropogenic processes on river water-quality variation spanning two decades. The SOM clustered river water quality into five groups: very low pollution, low pollution, moderate pollution, high pollution, and very high pollution. FA was then used to extract four latent factors that dominated water quality from 1991 to 2011 including three anthropogenic process factors (organic, industrial, and copper pollution) and one natural process factor [suspended solids (SS) pollution]. The SOM revealed that the water quality improved substantially over time. However, the downstream river water quality was still classified as high pollution because of an increase in anthropogenic activity. FA showed the spatiotemporal pattern of each factor score decreasing over time, but the organic pollution factor downstream of the Tamsui River, as well as the SS factor scores in the upstream major tributary (the Dahan Stream), remained within the high pollution level. Therefore, we suggest that public sewage-treatment plants should be upgraded from their current secondary biological processing to advanced treatment processing. The conservation of water and soil must also be reinforced to decrease the SS loading of the Dahan Stream from natural erosion processes in the future.

show abstract

Exploratory data analysis and clustering of multivariate spatial hydrogeological data by means of GEO3DSOM, a variant of Kohonen's Self-Organizing Map

Cited by 45 publications

References 28 publications

Origines et modélisation de la minéralisation des eaux du Quaternaire d’Abidjan (Sud de la Côte d’Ivoire)

Origines et modélisation de la minéralisation des eaux du Quaternaire d’Abidjan (Sud de la Côte d’Ivoire)

Hydrogeochemical assessment of groundwater quality in the Baya watershed (Eastern of Cte dIvoire)

Differentiating the Spatiotemporal Distribution of Natural and Anthropogenic Processes on River Water–Quality Variation Using a Self-Organizing Map With Factor Analysis

Contact Info

Product

Resources

About