Evaluation of sedimentation vulnerability at small hillside reservoirs in the semi-arid region of Tunisia using the Self-Organizing Map

Hentati, Achraf; Kawamura, Akira; Amaguchi, Hideo; Iseri, Yoshihiko

doi:10.1016/j.geomorph.2010.05.013

Cited by 56 publications

(32 citation statements)

References 24 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the properties of the SOM, the bigger the map size is, the higher the resolution for pattern recognition, while the topographical adjacency is further among the clusters. A reasonable optimum solution of the compromise among the accuracy of pattern classification and topographical proximity of clusters to determine the number of the SOM nodes is the heuristic rule of m ¼ 5 ffiffiffi n p , with m denoting the number of the SOM nodes and n representing the number of input data (Jin et al, 2011;Hentati et al, 2010;Jeong et al, 2010;Vesanto et al, 2000). In this study, this heuristic formula was used to determine the total number of nodes in the SOM.…”

Section: Methodsmentioning

confidence: 99%

“…In this study due to limited data, the linear initialization method was used, as it is more suitable for the pattern classification than the random initialization. The latter requires a large dataset and might cause boundary effects near the edges of the map (Jin et al, 2011;Hentati et al, 2010;Vesanto et al, 2000). In addition, the linear initialization approach can use eigenvalues and eigen vectors of the input data to set the initial reference vectors on the structured SOM.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Identification of spatio-seasonal hydrogeochemical characteristics of the unconfined groundwater in the Red River Delta, Vietnam

Nguyen

Kawamura

Tong

et al. 2015

Applied Geochemistry

Self Cite

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Identification of spatio-seasonal hydrogeochemical characteristics of the unconfined groundwater in the Red River Delta, Vietnam

Nguyen

Kawamura

Tong

et al. 2015

Applied Geochemistry

Self Cite

View full text Add to dashboard Cite

“…Therefore, the number of clusters showing the minimum DBI is optimal for the trained SOM. For hierarchical method, the Ward's linkage method is the most commonly used approach 6), 7) . In this study, the final fine-tuning cluster analysis was carried out by Ward's method using the optimal number of clusters.…”

Section: Methodsmentioning

confidence: 99%

“…This study is the first attempt to apply SOM in combination with a hierarchical cluster analysis for classification of groundwater chemistry monitoring data in the RRD. Many researchers have already demonstrated the usefulness of the SOM in other research fields 6), 7) . Chemical diagrams proposed by Gibbs 8) are widely uses to infer the mechanism controlling the chemistry of surface and groundwater.…”

Section: Introductionmentioning

confidence: 99%

Spatial classification of groundwater chemistry monitoring data in the Red River Delta, Vietnam using self-organizing maps

Nguyen

Kawamura

Tong³

et al. 2014

J. JSCE, Ser. B1

Self Cite

View full text Add to dashboard Cite

The groundwater in the Pleistocene confined aquifer (PCA) of the Red River Delta (RRD) was examined using self-organizing map (SOM) and Gibbs diagrams to determine, for the first time, its spatial classifications in terms of its hydrogeochemical characteristics. In this study, the groundwater chemistry dataset used in the analysis is composed of 8 major dissolved ions (i.e. Ca ) that are consistently found in 52 groundwater monitoring wells within the study area. Based on the results, the groundwater in the PCA monitoring wells of the delta can be classified into 2 major water types: high and low salinity. Each water type is composed of cluster-types that have similar hydrogeochemical characteristics. The high salinity water type has 2 clusters (or sub-types), while the low salinity (or fresh water) has 4. From the Gibbs diagrams, results indicate that the high salinity in the groundwater is mostly influenced by either (or both) anthropogenic activities and salt water intrusion.

show abstract

“…There is not an "a priori" rule which can provide the best network structure and different ones must be tested in order to find that which performs the best. Nevertheless, in order to reduce the number of structures to be tested, a heuristic rule has been proposed to estimate a number of neurons close to the optimum [26,33]:…”

Section: Self-organizing Map (Som)mentioning

confidence: 99%

Obtaining Key Parameters and Working Conditions of Wastewater Biological Nutrient Removal by Means of Artificial Intelligence Tools

Vega

Jaramillo-Morán

2018

Water

View full text Add to dashboard Cite

Abstract:The oxidation-reduction potential (ORP) and the dissolved oxygen (DO) have been monitored in a municipal wastewater treatment plant (WWTP). Three thousand two hundred aeration-non-aeration cycles were recorded. They were analyzed by defining 16 parameters to characterize each one of them. The vectors so obtained were treated with the box-plot tool to reject those with outliers (abnormally high or low values). The remaining data were processed by a neural network (self-organizing map: SOM) in order to classify them into classes and to obtain relations between parameters to identify those more representative of the system dynamics. They were: the oxygen uptake rate (OUR), the oxygen rise average slope (ORAS), and the oxidation-reduction potential "arrow" (ORP arrow , the maximum distance between the ORP curve and its linearization). Finally, the classes obtained from SOM were grouped into four macro-classes by means of the K-means algorithm in order to define four operation states related to seasonal and load characteristics, which may be taken into account, along with the key parameters, in the WWTP management with the aim of improving the nutrient removal performance by adapting their controllers to seasonal and load variations.

show abstract

Evaluation of sedimentation vulnerability at small hillside reservoirs in the semi-arid region of Tunisia using the Self-Organizing Map

Cited by 56 publications

References 24 publications

Identification of spatio-seasonal hydrogeochemical characteristics of the unconfined groundwater in the Red River Delta, Vietnam

Identification of spatio-seasonal hydrogeochemical characteristics of the unconfined groundwater in the Red River Delta, Vietnam

Spatial classification of groundwater chemistry monitoring data in the Red River Delta, Vietnam using self-organizing maps

Obtaining Key Parameters and Working Conditions of Wastewater Biological Nutrient Removal by Means of Artificial Intelligence Tools

Contact Info

Product

Resources

About