River Water Salinity Prediction Using Hybrid Machine Learning Models

Abstract

Electrical conductivity (EC), one of the most widely used indices for water quality assessment, has been applied to predict the salinity of the Babol-Rood River, the greatest source of irrigation water in northern Iran. This study uses two individual—M5 Prime (M5P) and random forest (RF)—and eight novel hybrid algorithms—bagging-M5P, bagging-RF, random subspace (RS)-M5P, RS-RF, random committee (RC)-M5P, RC-RF, additive regression (AR)-M5P, and AR-RF—to predict EC. Thirty-six years of observations collected by the Mazandaran Regional Water Authority were randomly divided into two sets: 70% from the period 1980 to 2008 was used as model-training data and 30% from 2009 to 2016 was used as testing data to validate the models. Several water quality variables—pH, HCO3−, Cl−, SO42−, Na+, Mg2+, Ca2+, river discharge (Q), and total dissolved solids (TDS)—were modeling inputs. Using EC and the correlation coefficients (CC) of the water quality variables, a set of nine input combinations were established. TDS, the most effective input variable, had the highest EC-CC (r = 0.91), and it was also determined to be the most important input variable among the input combinations. All models were trained and each model’s prediction power was evaluated with the testing data. Several quantitative criteria and visual comparisons were used to evaluate modeling capabilities. Results indicate that, in most cases, hybrid algorithms enhance individual algorithms’ predictive powers. The AR algorithm enhanced both M5P and RF predictions better than bagging, RS, and RC. M5P performed better than RF. Further, AR-M5P outperformed all other algorithms (R2 = 0.995, RMSE = 8.90 μs/cm, MAE = 6.20 μs/cm, NSE = 0.994 and PBIAS = −0.042). The hybridization of machine learning methods has significantly improved model performance to capture maximum salinity values, which is essential in water resource management.

Modelling Freshwater Eutrophication with Limited Limnological Data Using Artificial Neural Networks

“…ANNs are evaluated based on several performance indices for their test set [33]. The Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are some commonly used performance indices and have the following mathematical formulas, respectively [34,35]:…”

Application of machine learning and genetic optimization algorithms for modeling and optimizing soybean yield using its component traits

“…The performance of the RF algorithm relies on processing large dimensional data based on generalized error estimation [ 100 , 101 ]. Also, there is no assumption requirement for RF about the distribution of data [ 102 ], and this algorithm can isolate outliers in a small region of the variable space resulted in acceptable performance against nonlinear environmental effects [ 102 , 103 ].…”

Bayesian Model Averaging: A Unique Model Enhancing Forecasting Accuracy for Daily Streamflow Based on Different Antecedent Time Series

“…As one of the continuous projects for streamflow forecasting, the different forecasting models (e.g., seasonal autoregressive integrated moving average (SARIMA) [66,67] and bootstrap aggregation (bagging) [68]), which demonstrated their superiority for temporal forecasting in previous literature, can be applied to compare and evaluate the performance accuracy of BMA model. In addition, different nature-inspired evolutionary algorithms and data pre-processing approaches can be joined with the BMA model to increase the forecasting accuracy of hydrological processes including streamflow, water stage, and groundwater, etc.…”