Title | Multivariate Statistical Methods and Neural Networks for the Identification of Pollution Sources and Classification of the Apulia Region Ground Waters |
Abstract | Multivariate statistical techniques such as Discriminant Function Analysis (DFA), Cluster
Analysis (CA), Principal Component Analysis (PCA), Absolute Principal Component Score (APCS)
and Neural Networks (NN) have been applied to a data set, of Apulian ground waters, formed by
1009 samples and 15 parameters: pH, Electrical Conductivity, Total Dissolved Solids, Dissolved Oxygen, Chemical Oxygen Demand, Na+, Ca2+, Mg2+, K+, Cl-, NO3-, SO42- and HCO3-, vital organismat 22 °C and 36 °C. Principal Component Analysis and Absolute Principal Component Scoresallowed to identify, for each province, as well the sites diverging from the mean cluster, as the
pollution sources (due to fertilizer applications, marine water intrusion, etc...) pressurizing the
sampling sites investigated. Discriminant Function Analysis allowed on the hand to identify variables
with bigger discriminatory power, on the other to obtain good results in discriminating among the
considered provinces and in forecasting. The application of Radial Basis Function Neural Networks
gives results with bigger accuracy than DFA and confirms the electrical conductivity has the bigger
relative importance.
The results obtained by multivariate statistical methods can be useful both to give suggestions to
stakeholders and to provide a valid tool to the authority for the assessing and managing of the
groundwater resources. |
Source | 21st Century Watershed Technology Workshops: Improving Water Quality and the Environment, Bari, 27 May-1 June 2012 |
Keywords | Ground watersneural networksprincipal component analysis |
Year | 2012 |
Type | Contributo in atti di convegno |
Authors | Ielpo P., Cassano D., Lopez A., Pappagallo G., Uricchio V.F., Trizio L., de Gennaro G. |
Text | 318063 2012 Ground waters neural networks principal component analysis Multivariate Statistical Methods and Neural Networks for the Identification of Pollution Sources and Classification of the Apulia Region Ground Waters Ielpo P., Cassano D., Lopez A., Pappagallo G., Uricchio V.F., Trizio L., de Gennaro G. IRSA CNR sede di Bari, ISAC CNR sede di lecce, Dipartimento di Chimica, Universita degli studi di Bari Multivariate statistical techniques such as Discriminant Function Analysis DFA , Cluster Analysis CA , Principal Component Analysis PCA , Absolute Principal Component Score APCS and Neural Networks NN have been applied to a data set, of Apulian ground waters, formed by 1009 samples and 15 parameters pH, Electrical Conductivity, Total Dissolved Solids, Dissolved Oxygen, Chemical Oxygen Demand, Na , Ca2 , Mg2 , K , Cl , NO3 , SO42 and HCO3 , vital organismat 22 °C and 36 °C. Principal Component Analysis and Absolute Principal Component Scoresallowed to identify, for each province, as well the sites diverging from the mean cluster, as the pollution sources due to fertilizer applications, marine water intrusion, etc... pressurizing the sampling sites investigated. Discriminant Function Analysis allowed on the hand to identify variables with bigger discriminatory power, on the other to obtain good results in discriminating among the considered provinces and in forecasting. The application of Radial Basis Function Neural Networks gives results with bigger accuracy than DFA and confirms the electrical conductivity has the bigger relative importance. The results obtained by multivariate statistical methods can be useful both to give suggestions to stakeholders and to provide a valid tool to the authority for the assessing and managing of the groundwater resources. 9781622769261 Published version 21st Century Watershed Technology Workshops Improving Water Quality and the Environment Bari 27 May 1 June 2012 Internazionale Contributo Multivariate Statistical Methods and Neural Networks for the Identification of Pollution Sources and Classification of the Apulia Region Ground Waters Watershed_conf_Ielpo_et_al.pdf Contributo in atti di convegno vitofelice.uricchio URICCHIO VITO FELICE pierina.ielpo IELPO PIERINA antonio.lopez LOPEZ ANTONIO |