Comparison of the performance of decision tree (DT) algorithms and extreme learning machine (ELM) model in the prediction of water quality of the Upper Green River watershed.

Abstract

Stream waters play a crucial role in catering to the world's needs with the required quality of water. Due to the discharges of wastewater from the various point and nonpoint sources, most of the watersheds are contaminated easily. The Upper Green River watershed in Kentucky, USA, is one such watershed that is contaminated over the years due to the runoff from rural areas and agricultural lands and combined sewer overflows (CSOs) from urban areas. Monitoring and characterizing the water quality status of streams in such watersheds has become of great importance, with multivariate statistical techniques such as regression, factor analysis, cluster analysis, and artificial intelligence methods such as artificial neural networks (ANNs). The water quality parameters, namely, fecal coliform (FC), turbidity, pH, and conductivity have been predicted quantitatively using ANNs to understand the water quality status of streams in the Upper Green River watershed elsewhere. In this study, a novel attempt has been made to predict the status of the quality of the Green River water with the predictive capabilities of a few decision tree (DT) algorithms such as classification and regression tree (CART) model, multivariate adaptive regression splines (MARS) model, random forest (RF) model, and extreme learning machine (ELM) model. The RF model's performance is better in predicting FC, turbidity, and pH than CART models in training and testing phases. Relatively, MARS and ELM models did better in testing though the performance is poorer in training. For example, we obtain the RMSE values of 2206, 2532, 1533, and 1969 using RF, CART, MARS, and ELM for FC in testing. A good correlation has been observed between conductivity and temperature, precipitation, and land-use factors for the MARS model. Overall, DT models are helpful in understanding, interpreting the outcomes, and visualizing the results compared with the other models. PRACTITIONER POINTS: The prediction of stream water quality parameters using decision trees is explored. The climate and land use parameters are used as input parameters to the modeling. The DT models of CART, MARS, RF, and ANNs such as ELM are explored to predict stream water quality. The RF model shows stable results compared with CART, MARS, and ELM for the data explored. Apart from the R2 value, RMSE and MAE indicate the effectiveness of DTs in prediction.