In the past few years, artificial neural networks (ANNs) have been used in describing and modelling wastewater treatment processes. Artificial neural network models can be identified without a detailed knowledge of the kinetics of the system to be modelled. Also, ANN models can potentially contain a great deal of information about the system itself, including the same type of information contained in conventional deterministic models. The fact that these models can be continuously updated with minimal resource requirements makes them very attractive for application in a real-time control scenario. In the current paper, applications of ANNs in the field of wastewater treatment performance prediction are reviewed. In addition, this paper presents a case study that reports some comprehensive modelling work to develop nonlinear neural network prediction models for the Gold Bar Wastewater Treatment Plant (GBWWTP), the largest sewage treatment facility in Edmonton, Alberta.Résumé : Au cours des dernières années, les réseaux neuronaux artificiels ont été utilisés pour décrire et modéliser les procédés de traitement des eaux usées. Les modèles utilisant les réseaux neuronaux artificiels peuvent être identifiés sans que l'on possède une connaissance particulièrement détaillée de la cinétique des systèmes à modéliser. De plus, les modèles utilisant les réseaux neuronaux artificiels peuvent potentiellement contenir beaucoup d'information sur le système lui-même, incluant le même genre d'information que celle contenue dans les modèles déterministes traditionnels. Ces modèles peuvent être continuellement mis à jour avec peu de ressources, ce qui les rend très attrayants pour l'utilisation dans un scénario de contrôle en temps réel. Cet article examine les applications des réseaux neuronaux artificiels dans le domaine des modèles de prévision du rendement du traitement des eaux usées. De plus, cet article présente une étude de cas qui comprend quelques travaux de modélisation complète afin de développer des modèles de prévision des réseaux neuronaux non linéaires pour la station de traitement des eaux usées Gold Bar, la plus grande installation de traitement des eaux d'égout à Edmonton (Alberta).
El Niño southern-oscillation (ENSO) is known to be the strongest climatic variation on seasonal to inter-annual time scales. It causes severe droughts, floods, fires, and hurricanes leading to economical disasters. This study explores the use of relatively simple inputs in developing artificial neural network (ANN) models for predicting the onset of ENSO by forecasting some of its indicators. Two indicators, southern oscillation index (SOI) and Niño3, were used one at a time to model the ENSO occurrence using monthly averaged data. Both models performed well in forecasting and predicting ENSO occurrence up to 12 months in advance. Correlation coefficient values of more than 0.8 and 0.9 (one month lead time), and above 0.7 and 0.8 (12 month lead time) were obtained for SOI and Niño3, respectively. Both models apply the feed forward multilayer perceptron network trained with error back-propagation algorithm. The final models were compared with each other and found to be highly consistent with 75% agreement in their forecasting ability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.