Water quality modelling using principal component analysis and artificial neural network

Assessment of groundwater quality in arid regions utilizing principal component analysis, GIS, and machine learning techniques

Assessing water quality in arid regions is vital due to scarce resources, impacting health and sustainable management.This study examines groundwater quality in Assuit Governorate, Egypt, using Principal Component Analysis, GIS, and Machine Learning Techniques. Data from 217 wells across 12 parameters were analyzed, including TDS, EC, Cl-, Fe++, Ca++, Mg++, Na+, SO4--, Mn++, HCO3-, K+, and pH. The Water Quality Index (WQI) was calculated, and ArcGIS mapped its spatial distribution. Machine learning algorithms, including Ridge Regression, XGBoost, Decision Tree, Random Forest, and K-Nearest Neighbors, were used for predictive analysis. Higher concentrations of Na, K, Ca, Mg, Mn, and Fe were correlated with industrial and densely populated areas. Most samples exhibited excellent or good quality, with a small percentage unsuitable for consumption. Ridge Regression showed the lowest MAPE rates (0.22 % training, 0.26 % in testing). This research highlights the importance of advanced machine learning for sustainable groundwater management in arid regions. Thus, our results could provide valuable assistance to both national and local authorities involved in water management decisions, particularly for water resource managers and decision-makers. This information can aid in the development of regulations aimed at safeguarding and sustainably managing groundwater resources, which are essential for the overall prosperity of the country.

Data-driven evolution of water quality models: An in-depth investigation of innovative outlier detection approaches-A case study of Irish Water Quality Index (IEWQI) model

Recently, there has been a significant advancement in the water quality index (WQI) models utilizing data-driven approaches, especially those integrating machine learning and artificial intelligence (ML/AI) technology. Although, several recent studies have revealed that the data-driven model has produced inconsistent results due to the data outliers, which significantly impact model reliability and accuracy. The present study was carried out to assess the impact of data outliers on a recently developed Irish Water Quality Index (IEWQI) model, which relies on data-driven techniques. To the author's best knowledge, there has been no systematic framework for evaluating the influence of data outliers on such models. For the purposes of assessing the outlier impact of the data outliers on the water quality (WQ) model, this was the first initiative in research to introduce a comprehensive approach that combines machine learning with advanced statistical techniques. The proposed framework was implemented in Cork Harbour, Ireland, to evaluate the IEWQI model's sensitivity to outliers in input indicators to assess the water quality. In order to detect the data outlier, the study utilized two widely used ML techniques, including Isolation Forest (IF) and Kernel Density Estimation (KDE) within the dataset, for predicting WQ with and without these outliers. For validating the ML results, the study used five commonly used statistical measures. The performance metric (R2) indicates that the model performance improved slightly (R2 increased from 0.92 to 0.95) in predicting WQ after removing the data outlier from the input. But the IEWQI scores revealed that there were no statistically significant differences among the actual values, predictions with outliers, and predictions without outliers, with a 95 % confidence interval at p < 0.05. The results of model uncertainty also revealed that the model contributed <1 % uncertainty to the final assessment results for using both datasets (with and without outliers). In addition, all statistical measures indicated that the ML techniques provided reliable results that can be utilized for detecting outliers and their impacts on the IEWQI model. The findings of the research reveal that although the data outliers had no significant impact on the IEWQI model architecture, they had moderate impacts on the rating schemes' of the model. This finding indicated that detecting the data outliers could improve the accuracy of the IEWQI model in rating WQ as well as be helpful in mitigating the model eclipsing problem. In addition, the results of the research provide evidence of how the data outliers influenced the data-driven model in predicting WQ and reliability, particularly since the study confirmed that the IEWQI model's could be effective for accurately rating WQ despite the presence of the data outliers in the input. It could occur due to the spatio-temporal variability inherent in WQ indicators. However, the research assesses the influence of data input outliers on the IEWQI model and underscores important areas for future investigation. These areas include expanding temporal analysis using multi-year data, examining spatial outlier patterns, and evaluating detection methods. Moreover, it is essential to explore the real-world impacts of revised rating categories, involve stakeholders in outlier management, and fine-tune model parameters. Analysing model performance across varying temporal and spatial resolutions and incorporating additional environmental data can significantly enhance the accuracy of WQ assessment. Consequently, this study offers valuable insights to strengthen the IEWQI model's robustness and provides avenues for enhancing its utility in broader WQ assessment applications. Moreover, the study successfully adopted the framework for evaluating how data input outliers affect the data-driven model, such as the IEWQI model. The current study has been carried out in Cork Harbour for only a single year of WQ data. The framework should be tested across various domains for evaluating the response of the IEWQI model's in terms of the spatio-temporal resolution of the domain. Nevertheless, the study recommended that future research should be conducted to adjust or revise the IEWQI model's rating schemes and investigate the practical effects of data outliers on updated rating categories. However, the study provides potential recommendations for enhancing the IEWQI model's adaptability and reveals its effectiveness in expanding its applicability in more general WQ assessment scenarios.

Hybrid WT-CNN-GRU-based model for the estimation of reservoir water quality variables considering spatio-temporal features

Water quality indicators (WQIs), such as chlorophyll-a (Chl-a) and dissolved oxygen (DO), are crucial for understanding and assessing the health of aquatic ecosystems. Precise prediction of these indicators is fundamental for the efficient administration of rivers, lakes, and reservoirs. This research utilized two unique DL algorithms-namely, convolutional neural network (CNNs) and gated recurrent units (GRUs)-alongside their amalgamation, CNN-GRU, to precisely gauge the concentration of these indicators within a reservoir. Moreover, to optimize the outcomes of the developed hybrid model, we considered the impact of a decomposition technique, specifically the wavelet transform (WT). In addition to these efforts, we created two distinct machine learning (ML) algorithms-namely, random forest (RF) and support vector regression (SVR)-to demonstrate the superior performance of deep learning algorithms over individual ML ones. We initially gathered WQIs from diverse locations and varying depths within the reservoir using an AAQ-RINKO device in the study area to achieve this. It is important to highlight that, despite utilizing diverse data-driven models in water quality estimation, a significant gap persists in the existing literature regarding implementing a comprehensive hybrid algorithm. This algorithm integrates the wavelet transform, convolutional neural network (CNN), and gated recurrent unit (GRU) methodologies to estimate WQIs accurately within a spatiotemporal framework. Subsequently, the effectiveness of the models that were developed was assessed utilizing various statistical metrics, encompassing the correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE), and Nash-Sutcliffe efficiency (NSE) throughout both the training and testing phases. The findings demonstrated that the WT-CNN-GRU model exhibited better performance in comparison with the other algorithms by 13% (SVR), 13% (RF), 9% (CNN), and 8% (GRU) when R-squared and DO were considered as evaluation indices and WQIs, respectively.

Potential risk assessment and occurrence characteristic of heavy metals based on artificial neural network model along the Yangtze River Estuary, China

Pollution from heavy metals in estuaries poses potential risks to the aquatic environment and public health. The complexity of the estuarine water environment limits the accurate understanding of its pollution prediction. Field observations were conducted at seven sampling sites along the Yangtze River Estuary (YRE) during summer, autumn, and winter 2021 to analyze the concentrations of seven heavy metals (As, Cd, Cr, Pb, Cu, Ni, Zn) in water and surface sediments. The order of heavy metal concentrations in water samples from highest to lowest was Zn > As > Cu > Ni > Cr > Pb > Cd, while that in surface sediments samples was Zn > Cr > As > Ni > Pb > Cu > Cd. Human health risk assessment of the heavy metals in water samples indicated a chronic and carcinogenic risk associated with As. The risks of heavy metals in surface sediments were evaluated using the geo-accumulation index (Igeo) and potential ecological risk index (RI). Among the seven heavy metals, As and Cd were highly polluted, with Cd being the main contributor to potential ecological risks. Principal component analysis (PCA) was employed to identify the sources of the different heavy metals, revealing that As originated primarily from anthropogenic emissions, while Cd was primarily from atmospheric deposition. To further analyze the influence of water quality indicators on heavy metal pollution, an artificial neural network (ANN) model was utilized. A modified model was proposed, incorporating biochemical parameters to predict the level of heavy metal pollution, achieving an accuracy of 95.1%. This accuracy was 22.5% higher than that of the traditional model and particularly effective in predicting the maximum 20% of values. Results in this paper highlight the pollution of As and Cd along the YRE, and the proposed model provides valuable information for estimating heavy metal pollution in estuarine water environments, facilitating pollution prevention efforts.

>Water quality prediction of artificial intelligence model: a case of Huaihe River Basin, China

Accurate prediction of water quality contributes to the intelligent management of water resources. Water quality indices have time series characteristics and nonlinearity, but the existing models only focus on the forward time series when long short-term memory (LSTM) is introduced and do not consider the parallel computation on the model. Owing to this, a new neural network called LSTM-multihead attention (LMA) was constructed to predict water quality, using long short-term memory to process time series data and multihead attention for parallel computing and extracting feature information. Additionally, water quality indices have the issues of multiple data types and complex data correlations, as well as missing data and abnormal data problems in water quality data. In order to solve these problems, this study proposes a water quality prediction model called GRA-LMA-based linear interpolation, gray relational analysis and LMA. Two experiments are carried out to verify the predictive performance of the GRA-LMA with the water quality data of the Huaihe River Basin as a case study sample. The first experiment focuses on data processing, including the processing of missing data and abnormal data of water quality data, and the correlation analysis of water quality indices. Linear interpolation is adapted to process the missing data, while a combination of boxplot and histogram is adopted to analyze and eliminate the abnormal data, which is then repaired the abnormal data with linear interpolation. The gray relational analysis is adopted to calculate the correlation between different water quality indices, and water quality indices with high correlation are retained to determine the input variables of the water quality prediction model. The data processing results demonstrate that repairs can be made using linear interpolation without altering the pattern of data change and the model by using the gray relational analysis to reduce the quantity of data it needs as input. In the second experiment, the predictive capacity of GRA-LMA and existing models such as backpropagation neural network (BP), recurrent neural network (RNN), long short-term memory (LSTM), and gate recurrent unit (GRU) was evaluated and compared using different numerical and graphical performance evaluation metrics. Comparative experimental results show that the mean square error of pH, dissolved oxygen, chemical oxygen demand, ammonia nitrogen, electrical conductivity, turbidity, total phosphorus, and total nitrogen of GRA-LMA is reduced to 0.05890, 0.40196, 0.32454, 0.04368, 14.71003, 8.13252, 0.01558, and 0.14345. The results indicate that GRA-LMA has superior adaptability for predicting various water quality indices and can significantly lower the induced prediction error.

Identification of the Contamination Sources by PCBs Using Multivariate Analyses: The Case Study of the Annaba Bay (Algeria) Basin

Persistent Organic Pollutants (POPs), particularly the indicator polychlorinated biphenyls (PCBs), were first quantified in water and sediments of two wadis, Boujemaâ and Seybouse, as well as in the effluents from a fertilizer and phytosanitary production industrial plant (Fertial). Since these contaminated discharges end in Annaba Bay (Algeria) in the Mediterranean Sea, with a significant level of contamination, all the potential sources should be identified. In this work, this task is conducted by a multivariate analysis. Liquid-liquid extraction and gas chromatography/mass spectrometry (GC-MS) methods were applied to quantify seven PCB congeners, usually taken as indicators of contamination. The sum of the PCB concentrations in the sediments ranged from 1 to 6.4 μg/kg dw (dry weight) and up to 0.027 μg/L in waters. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) were used for the multivariate analysis, indicating that the main sources of PCB emissions in the bay are urban/domestic and agricultural/industrial. The outfalls that mostly contribute to the pollution of the gulf are the Boujemaâ wadi, followed by the Seybouse wadi, and finally by the Fertial cluster and more precisely the annex basin of the plant. Although referring to a specific site of local importance, the work aims to present a procedure and a methodological analysis that can be potentially applicable to further case studies all over the world.

Investigation and comparative analysis of ecological risk for heavy metals in sediment and surface water in east coast estuaries of India

The sediments and surface water from 8 stations each from Dhamara and Paradeep estuarine areas were sampled for investigation of heavy metals, Cd, Cu, Pb, Mn, Ni, Zn, Fe, and Cr contamination. The objective of the sediment and surface water characterization is to find the existing spatial and temporal intercorrelation. The sediment accumulation index (I_sed), enrichment index (I_En), ecological risk index (I_EcR) and probability heavy metals (p-HMI) reveal the contamination status with Mn, Ni, Zn, Cr, and Cu showing permissible (0 ≤ I_sed ≤ 1, I_En ˂ 2, I_EcR ≤ 150) to moderate (1 ≤ I_sed ≤ 2, 40 ≤ R_f ≤ 80) contamination. The p-HMI reflects the range from excellent (p-HMI = 14.89-14.54) to fair (p-HMI = 22.31-26.56) in off shore stations of the estuary. The spatial patterns of the heavy metals load index (I_HMc) along the coast lines indicate that the pollution hotspots are progressively divulged to trace metals pollution over time. Heavy metal source analysis coupled with correlation analysis and principal component analysis (PCA) was used as a data reduction technique, which reveals that the heavy metal pollution in marine coastline might originate from redox reactions (FeMn coupling) and anthropogenic sources.