Review of: "Flood Prediction Using Artificial Neural Networks: A Case Study in Temerloh, Pahang"
Résumé
The current paper is devoted to the development of an artificial neural network model for flood prediction in the Temerloh district, Pahang, Malaysia.The authors collected hydrological and meteorological data from the study area, performed correlation analysis, and proposed a two hidden layer ANN structure.The correlation analysis performed by the authors revealed that stream flow and water level are directly and highly correlated to floods, while temperature is inversely and moderately correlated to floods.The authors evaluated the developed model by performing three evaluation tests: confusion matrix, area under the receiver operating characteristic curve (ROC) curve (AUC), and error evaluations.The results revealed that the developed ANN model produced predictions in close agreement with measured data, evident in the high confusion matrix accuracy, high AUC, and low values of mean square error and root-mean-square error.The authors also created a Microsoft Power BI flood monitoring dashboard that could be used for interactive visualization and analysis of flood data.
Citer ce document
Accès au document
Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter
Voir l'article sur le site de la revueAuteur(s)
Statistiques
Consultations : 1
Téléchargements : 0