Supervised Machine Learning for Estimation of Total Suspended Solids in Urban Watersheds
Open Access
- 10 January 2021
- Vol. 13 (2), 147
- https://doi.org/10.3390/w13020147
Abstract
Machine Learning (ML) algorithms provide an alternative for the prediction of pollutant concentration. We compared eight ML algorithms (Linear Regression (LR), uniform weighting k-Nearest Neighbor (UW-kNN), variable weighting k-Nearest Neighbor (VW-kNN), Support Vector Regression (SVR), Artificial Neural Network (ANN), Regression Tree (RT), Random Forest (RF), and Adaptive Boosting (AdB)) to evaluate the feasibility of ML approaches for estimation of Total Suspended Solids (TSS) using the national stormwater quality database. Six factors were used as features to train the algorithms with TSS concentration as the target parameter: Drainage area, land use, percent of imperviousness, rainfall depth, runoff volume, and antecedent dry days. Comparisons among the ML methods demonstrated a higher degree of variability in model performance, with the coefficient of determination (R2) and Nash–Sutcliffe (NSE) values ranging from 0.15 to 0.77. The Root Mean Square (RMSE) values ranged from 110 mg/L to 220 mg/L. The best fit was obtained using the AdB and RF models, with R2 values of 0.77 and 0.74 in the training step and 0.67 and 0.64 in the prediction step. The NSE values were 0.76 and 0.72 in the training step and 0.67 and 0.62 in the prediction step. The predictions from AdB were sensitive to all six factors. However, the sensitivity level was variable.Funding Information
- South Dakota Board of Regents (MA2000007)
This publication has 61 references indexed in Scilit:
- Discriminating the papyrus vegetation (Cyperus papyrusL.) and its co-existent species using random forest and hyperspectral data resampled to HYMAPInternational Journal of Remote Sensing, 2011
- Suspended particle characteristics in storm runoff from urban impervious surfaces in Toowoomba, AustraliaUrban Water Journal, 2009
- Artificial neural network modeling of the river water quality—A case studyEcological Modelling, 2009
- Prediction of urban stormwater quality using artificial neural networksEnvironmental Modelling & Software, 2009
- Random forests as a tool for ecohydrological distribution modellingEcological Modelling, 2007
- Advanced Statistics: Linear Regression, Part II: Multiple Linear RegressionAcademic Emergency Medicine, 2004
- Vegetation effects on fecal bacteria, BOD, and suspended solid removal in constructed wetlands treating domestic wastewaterEcological Engineering, 2003
- Linear regression for calibration lines revisited: weighting schemes for bioanalytical methodsJournal of Chromatography B, 2002
- Evaluation of methods for estimating stormwater pollutant loadsWater Environment Research, 1998
- River flow forecasting through conceptual models part I — A discussion of principlesJournal of Hydrology, 1970