“…If C was too small, the model would place insufficient stress on the fitting of training data. On the contrary, an overfitted output might be obtained when a large C value was employed (Sajan et al, 2015;Xu et al, 2015). The SVM model with LKF had a large penalty parameter C equal to 256 and led to an overfitted output with a high R 2 of 0.97 for the training dataset and a low R 2 of 0.11 for the validation dataset.…”
Section: Model Development and Performance Evaluationmentioning
“…If C was too small, the model would place insufficient stress on the fitting of training data. On the contrary, an overfitted output might be obtained when a large C value was employed (Sajan et al, 2015;Xu et al, 2015). The SVM model with LKF had a large penalty parameter C equal to 256 and led to an overfitted output with a high R 2 of 0.97 for the training dataset and a low R 2 of 0.11 for the validation dataset.…”
Section: Model Development and Performance Evaluationmentioning
“…However, the apparent time of the NPS-TP concentration peak and flow peak is inconsistent in different rainfall patterns. Xu et al [40] introduced the support vector regression (SVR) model to develop a quantitative relationship between the environmental factors and the eutrophic indices compared with the ANN. The results show that the correlation coefficients of the NPS-TP are greater than those for the NPS-TN, indicating that the model effect of the NPS-TP is improved over the NPS-TN.…”
Section: Training Results Of the Annusing The Complete Datamentioning
Event-based runoff-pollutant relationships have been the key for water quality management, but the scarcity of measured data results in poor model performance, especially for multiple rainfall events. In this study, a new framework was proposed for event-based non-point source (NPS) prediction and evaluation. The artificial neural network (ANN) was used to extend the runoff-pollutant relationship from complete data events to other data-scarce events. The interpolation method was then used to solve the problem of tail deviation in the simulated pollutographs. In addition, the entropy method was utilized to train the ANN for comprehensive evaluations. A case study was performed in the Three Gorges Reservoir Region, China. Results showed that the ANN performed well in the NPS simulation, especially for light rainfall events, and the phosphorus predictions were always more accurate than the nitrogen predictions under scarce data conditions. In addition, peak pollutant data scarcity had a significant impact on the model performance. Furthermore, these traditional indicators would lead to certain information loss during the model evaluation, but the entropy weighting method could provide a more accurate model evaluation. These results would be valuable for monitoring schemes and the quantitation of event-based NPS pollution, especially in data-poor catchments.
“…Several studies suggested using neural network (NN) methods to provide effective Chl-a prediction (Coad et al, 2014;Ieong et al, 2015;Xu et al, 2015). The IBM SPSS multilayer perceptron (MLP) NN tool was used to explore NN models using Lake Champlain monitoring station data.…”
Section: Training Processes Of Nn Modelsmentioning
Eutrophication is one of the main causes of the degradation of lake ecosystems. In this paper, multiple linear regression (MLR) and neural network (NN) methods were developed as empirical models to predict chlorophyll-a (Chl-a) concentrations in Lake Champlain. The models were developed using a large dataset collected from Lake Champlain over a 24-year period from 1992 to 2016. The dataset consisted of monitoring depth (Depth), total phosphorus (TP), total nitrogen (TN), alkalinity (RegAlk), temperature (TempC), chloride (Cl) and secchi depth (Secchi). Statistical analyses showed that TP, Secchi, TN and Depth demonstrated strong relationships with Chl-a concentrations. The simulation results revealed that both the MLR and NN models performed well in predicting Chl-a concentrations, especially for low to moderate concentrations of Chl-a (< 7.5 μg/L). The NN model showed better accuracy and generalization performance in comparison with the MLR model for both the training and verification processes. In addition, both the developed MLR and NN models produce good results when used to predict Chl-a concentrations from 2017 to 2021. However, neither the MLR nor NN models can accurately predict high Chl-a concentrations (> 7.5 μg/L). These models can be useful for improving lake management and providing early warnings regarding the problem of eutrophication.
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.