No abstract

No abstract

No abstract

Ensemble learning methods have received remarkable attention in the recent years and led to considerable advancement in the performance of the regression and classification problems. Bagging and boosting are among the most popular ensemble learning techniques proposed to reduce the prediction error of learning machines. In this study, bagging and gradient boosting algorithms are incorporated into the model creation process for daily streamflow prediction. This paper compares two tree-based ensembles (bagged regression trees BRT & gradient boosted regression trees GBRT) and two artificial neural networks ensembles (bagged artificial neural networks BANN & gradient boosted artificial neural networks GBANN). Proposed ensembles are benchmarked to a conventional ANN (multilayer perceptron MLP). Coefficient of determination, mean absolute error and the root mean squared error measures are used for prediction performance evaluation. The results obtained in this study indicate that ensemble learning models yield better prediction accuracy than a conventional ANN model. Moreover, ANN ensembles are superior to tree-based ensembles.

In recent years, the importance of investigation of behavior and transportation of heavy metals in water systems that are dangerous for human health with toxic characteristics has been increasing and hence work on developing new methods and models are undertaken. The aim of this study is to implement a heavy metal model in a three -dimensional numerical model, ECOMSED in order to investigate the behavior and transportation of heavy metals. ECOMSED is capable of predicting flow circulation, salt and non-cohesive sediment transportation, deposition and re-suspension with hydrodynamic and sediment modules. In the heavy metal model adopted, the behavior of heavy metals was investigated by taking into consideration the effect of partition coefficient (k d ) on particulate and dissolved heavy metal concentrations. The model is set up for a simple open channel test case and the effect of flow structure, partition coefficient, concentration of suspended sediment and bed load on particulate and dissolved heavy metal concentrations are investigated. This study is an attempt in modeling transportation of heavy metals and the results found to be encouraging for this initial state.