Real-time prediction of river chloride concentration using ensemble learning

Advances and applications of machine learning and deep learning in environmental ecology and health

Machine learning (ML) and deep learning (DL) possess excellent advantages in data analysis (e.g., feature extraction, clustering, classification, regression, image recognition and prediction) and risk assessment and management in environmental ecology and health (EEH). Considering the rapid growth and increasing complexity of data in EEH, it is of significance to summarize recent advances and applications of ML and DL in EEH. This review summarized the basic processes and fundamental algorithms of the ML and DL modeling, and indicated the urgent needs of ML and DL in EEH. Recent research hotspots such as environmental ecology and restoration, environmental fate of new pollutants, chemical exposures and risks, chemical hazard identification and control were highlighted. Various applications of ML and DL in EEH demonstrate their versatility and technological revolution, and present some challenges. The perspective of ML and DL in EEH were further outlined to promote the innovative analysis and cultivation of the ML-driven research paradigm.

Nowcasting of fecal coliform presence using an artificial neural network

At least 2 billion people worldwide use drinking water sources that are contaminated with feces, causing waterborne diseases; poor sanitation, poor hygiene, and unsafe drinking water result in a daily death rate of more than 800 children under 5 years of age from diarrheal diseases. This study shows the feasibility of a novel method to nowcast fecal coliforms' (FC) presence in drinking water sources by applying a multilayer perceptron artificial neuron network (MLP-ANN) model. The model gives a binary answer for FC presence or absence in drinking water sources using a minimum of water quality and geographical parameters, which can be monitored in real-time as predictors with low-cost and in-situ equipment. Using 51,400 samples to train, validate and test the model with temperature, pH, electrical conductivity, turbidity, dissolved oxygen, and total dissolved solids (TDS) as water-quality inputs and the water source type and location (as districts in India) as geographical inputs. The model achieved a total accuracy of 92.8% and a sensitivity of 98.2%, meaning that most FC-contaminated samples were classified correctly. In addition, precision reached 93.1%, meaning that most FC-contamination classifications were actually contaminated. The MLP-ANN performed better than the Linear Regression and K-Nearest Neighbors models, with lower accuracies of 90.2% and 91.0%, respectively. The MLP-ANN model could characterize the water quality geospatially, learn from the parameters whether the water is contaminated by FC, and predict with high accuracy on new testing data. This method can be used as a part of a sensor for FC monitoring and management in water, reducing the time gaps between routine lab testing and thus improving drinking water quality and addressing the SDG 6 targets.

Multi-Expression Programming (MEP): Water Quality Assessment Using Water Quality Indices

Water contamination is indeed a worldwide problem that threatens public health, environmental protection, and agricultural productivity. The distinctive attributes of machine learning (ML)-based modelling can provide in-depth understanding into increasing water quality challenges. This study presents the development of a multi-expression programming (MEP) based predictive model for water quality parameters, i.e., electrical conductivity (EC) and total dissolved solids (TDS) in the upper Indus River at two different outlet locations using 360 readings collected on a monthly basis. The optimized MEP models were assessed using different statistical measurements i.e., coefficient-of-determination (R2), root-mean-square error (RMSE), mean-absolute error (MAE), root-mean-square-logarithmic error (RMSLE) and mean-absolute-percent error (MAPE). The results show that the R2 in the testing phase (subjected to unseen data) for EC-MEP and TDS-MEP models is above 0.90, i.e., 0.9674 and 0.9725, respectively, reflecting the higher accuracy and generalized performance. Also, the error measures are quite lower. In accordance with MAPE statistics, both the MEP models shows an “excellent” performance in all three stages. In comparison with traditional non-linear regression models (NLRMs), the developed machine learning models have good generalization capabilities. The sensitivity analysis of the developed MEP models with regard to the significance of each input on the forecasted water quality parameters suggests that Cl and HCO3 have substantial impacts on the predictions of MEP models (EC and TDS), with a sensitiveness index above 0.90, although the influence of the Na is the less prominent. The results of this research suggest that the development of intelligence models for EC and TDS are cost effective and viable for the evaluation and monitoring of the quality of river water.