Estimation of high frequency nutrient concentrations from water quality surrogates using machine learning methods

A rapid approach with machine learning for quantifying the relative burden of antimicrobial resistance in natural aquatic environments

The massive use and discharge of antibiotics have led to increasing concerns about antimicrobial resistance (AMR) in natural aquatic environments. Since the dose-response mechanisms of pathogens with AMR have not yet been fully understood, and the antibiotic resistance genes and bacteria-related data collection via field sampling and laboratory testing is time-consuming and expensive, designing a rapid approach to quantify the burden of AMR in the natural aquatic environment has become a challenge. To cope with such a challenge, a new approach involving an integrated machine-learning framework was developed by investigating the associations between the relative burden of AMR and easily accessible variables (i.e., relevant environmental variables and adjacent land-use patterns). The results, based on a real-world case analysis, demonstrate that the quantification speed has been reduced from 3-7 days, which is typical for traditional measurement procedures with field sampling and laboratory testing, to approximately 0.5 hours using the new approach. Moreover, all five metrics for AMR relative burden quantification exceed the threshold level of 85%, with F1-score surpassing 0.92. Compared to logistic regression, decision trees, and basic random forest, the adaptive random forest model within the framework significantly improves quantification accuracy without sacrificing model interpretability. Two environmental variables, dissolved oxygen and resistivity, along with the proportion of green areas were identified as three key feature variables for the rapid quantification. This study contributes to the enrichment of burden analyses and management practices for rapid quantification of the relative burden of AMR without dose-response information.

A novel coupling interpretable machine learning framework for water quality prediction and environmental effect understanding in different flow discharge regulations of hydro-projects

Machine learning models (MLMs) have been increasingly used to forecast water pollution. However, the "black box" characteristic for understanding mechanism processes still limits the applicability of MLMs for water quality management in hydro-projects under complex and frequently artificial regulation. This study proposes an interpretable machine learning framework for water quality prediction coupled with a hydrodynamic (flow discharge) scenario-based Random Forest (RF) model with multiple model-agnostic techniques and quantifies global, local, and joint interpretations (i.e., partial dependence, individual conditional expectation, and accumulated local effects) of environmental factor implications. The framework was applied and verified to predict the permanganate index (CODMn) under different flow discharge regulation scenarios in the Middle Route of the South-to-North Water Diversion Project of China (MRSNWDPC). A total of 4664 sampling cases data matrices, including water quality, meteorological, and hydrological indicators from eight national stations along the main canal of the MRSNWDPC, were collected from May 2019 to December 2020. The results showed that the RF models were effective in forecasting CODMn in all flow discharge scenarios, with a mean square error, coefficient of determination, and mean absolute error of 0.006-0.026, 0.481-0.792, and 0.069-0.104, respectively, in the testing dataset. A global interpretation indicated that dissolved oxygen, flow discharge, and surface pressure are the three most important variables of CODMn. Local and joint interpretations indicated that the RF-based prediction model provides a basic understanding of the physical mechanisms of environmental systems. The proposed framework can effectively learn the fundamental environmental implications of water quality variations and provide reliable prediction performance, highlighting the importance of model interpretability for trustworthy machine learning applications in water management projects. This study provides scientific references for applying advanced data-driven MLMs to water quality forecasting and a reliable methodological framework for water quality management and similar hydro-projects.

Stacked hybridization to enhance the performance of artificial neural networks (ANN) for prediction of water quality index in the Bagh river basin, India

Water quality assessment is paramount for environmental monitoring and resource management, particularly in regions experiencing rapid urbanization and industrialization. This study introduces Artificial Neural Networks (ANN) and its hybrid machine learning models, namely ANN-RF (Random Forest), ANN-SVM (Support Vector Machine), ANN-RSS (Random Subspace), ANN-M5P (M5 Pruned), and ANN-AR (Additive Regression) for water quality assessment in the rapidly urbanizing and industrializing Bagh River Basin, India. The Relief algorithm was employed to select the most influential water quality input parameters, including Nitrate (NO3-), Magnesium (Mg2+), Sulphate (SO42-), Calcium (Ca2+), and Potassium (K+). The comparative analysis of developed ANN and its hybrid models was carried out using statistical indicators (i.e., Nash-Sutcliffe Efficiency (NSE), Pearson Correlation Coefficient (PCC), Coefficient of Determination (R2), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Relative Root Square Error (RRSE), Relative Absolute Error (RAE), and Mean Bias Error (MBE)) and graphical representations (i.e., Taylor diagram). Results indicate that the integration of support vector machine (SVM) with ANN significantly improves performance, yielding impressive statistical indicators: NSE (0.879), R2 (0.904), MAE (22.349), and MBE (12.548). The methodology outlined in this study can serve as a template for enhancing the predictive capabilities of ANN models in various other environmental and ecological applications, contributing to sustainable development and safeguarding natural resources.

Dynamics of algal blooms in typical low-latitude plateau lakes: Spatiotemporal patterns and driving factors

The alpine lakes distributed on the plateau are crucial for the hydrological, and biogeochemical cycle, and also serve as a guarantee for regional economic development and human survival. However, under the influence of human interference and climate fluctuations, lakes are facing problems of eutrophication and subsequent algal blooms (ABs) with acceleration, and the development and driving factors of this phenomenon need to be considered as a whole. In this study, ten lakes located on the Yunnan-Guizhou Plateau were selected as the study area to analyze the spatiotemporal distribution of ABs and possible controlling forces. The FAI (Floating Algae Index) derived from multiple MODIS products and water quality data under high-frequency monitoring were selected as the data sources for characterizing ABs. Three nutrient parameters and five meteorological variables were used to explore the driving factors affecting ABs. Various methods of trend detection and correlation analysis have been applied. The main results are as follows: (1) Dianchi Lake (in lake area) and Xingyun Lake (in area proportion) are the two lakes with the most serious ABs in the historical period; (2) ABs are mainly distributed on the shoreline and northern edge of lakes, and tend to stay away from the lake center during high-temperature periods of the day; (3) Six lakes show a decreasing trend in ABs, especially after 2018, while other lakes (including Fuxian, Chenghai, Yangzong, and Erhai) are increasing, not only in peak value but also in duration; (4) Lakes with severe ABs are all P-restricted lakes, the minimum temperature is the most sensitive meteorological factor, while the impact of precipitation against ABs has a time lag; (5) Establishing a warning system of temperature and nutrient concentration is critical in ABs adaptive strategy. This study is expected to provide scientific references for regional water management and the restoration of the eutrophic aquatic ecosystem.

Spatiotemporal assessment of groundwater quality and quantity using geostatistical and ensemble artificial intelligence tools

The study investigated the spatiotemporal relationship between surface hydrological variables and groundwater quality/quantity using geostatistical and AI tools. AI models were developed to estimate groundwater quality from ground-based measurements and remote sensing images, reducing reliance on laboratory testing. Different Kriging techniques were employed to map ground-based measurements and fill data gaps. The methodology was applied to analyze the Maragheh aquifer in northwest Iran, revealing declining groundwater quality due to industrial. discharges and over-extraction. Spatiotemporal analysis indicated a relationship between groundwater depth/quality, precipitation, and temperature. The Root Mean Square Scaled Error (RMSSE) values for all variables ranged from 0.8508 to 1.1688, indicating acceptable performance of the semivariogram models in predicting the variables. Three AI models, namely Feed-Forward Neural Networks (FFNNs), Support Vector Regression (SVR), and Adaptive Neural Fuzzy Inference System (ANFIS), predicted groundwater quality for wet (June) and dry (October) months using input variables such as groundwater depth, temperature, precipitation, Normalized Difference Vegetation Index (NDVI), and Digital Elevation Model (DEM), with Groundwater Quality Index (GWQI) as the target variable. Ensemble methods were employed to combine the outputs of these models, enhancing performance. Results showed strong predictive capabilities, with coefficient of determination values of 0.88 and 0.84 for wet and dry seasons. Ensemble models improved performance by up to 6% and 12% for wet and dry seasons, respectively, potentially advancing groundwater quality modeling in the future.

Prediction of Aureococcus anophageffens using machine learning and deep learning

The recurrent brown tide phenomenon, attributed to Aureococcus anophagefferens (A. anophagefferens), constitutes a significant threat to the Qinhuangdao sea area in China, leading to pronounced ecological degradation and substantial economic losses. This study utilized machine learning and deep learning techniques to predict A. anophagefferens population density, aiming to elucidate the occurrence mechanism and influencing factors of brown tide. Specifically, Random Forest (RF) algorithm was utilized to impute missing water quality data, facilitating its direct application in subsequent algal population prediction models. The results revealed that all four models-RF, Support Vector Regression (SVR), Multilayer Perceptron (MLP), and Convolutional Neural Network (CNN)-exhibited high accuracy in predicting A. anophagefferens population densities, with R2 values exceeding 0.75. RF, in particular, showed exceptional accuracy and reliability, with an R2 value surpassing 0.8. Additionally, the study ascertained five critical factors influencing A. anophagefferens population density: ammonia nitrogen, pH, total nitrogen, temperature, and silicate.

Prediction of weighted arithmetic water quality index for urban water quality using ensemble machine learning model

Urban water quality index (WQI) is an important factor for assessment quality of groundwater in the urban and rural area. In this research, the Weighted Arithmetic Water Quality Index (WA-WQI) was estimated for understanding the groundwater quality. Four machine learning (ML) models were developed including artificial neural network (ANN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XG-Boost) in addition to multiple linear regression (MLR) for WA-WQI prediction at the Ujjain city of Madhya Pradesh in India. Groundwater quality samples were collected from 54 wards under the urban area, the main eight different physiochemical parameters were selected for WA-WQI prediction. The different input parameters data were analysed and calculated for the relationships of their ability to predict the results of WA-WQI. The ML models performance were calculated using three statistical metrics such as determination coefficient (R2), mean absolute error (MAE), and root mean square error (RMSE). In this research shown the XG-Boost model is better results other than other ML models. The best modelling results over the training phase revealed R2 = 0.969, RMSE = 2.169, MAE = 2.013 and over the testing phase R2 = 0.987, RMSE = 3.273, MAE = 2.727). All the ML models results were validated using receiver operating characteristic (ROC) curve for the best models selection. The results of best model area under curve (AUC) was 0.9048. Hence, XG-Boost model was given the accurate prediction of WA-WQI in the urban area. Based on the graphical presentation evaluation, XG-Boost model showed similar results of superiority. The obtained modelling results emphasis the utility of computer aid models for better planning and essential information for decision-makers, and water experts. The implement agency can adopt the procedures of water quality to decrease pollution and safe and healthy water provide to entire Ujjain city.

Internet of Things and citizen science as alternative water quality monitoring approaches and the importance of effective water quality communication

The increasing demand for water and worsening climate change place significant pressure on this vital resource, making its preservation a global priority. Water quality monitoring programs are essential for effectively managing this resource. Current programs rely on traditional monitoring approaches, leading to limitations such as low spatiotemporal resolution and high operational costs. Despite the adoption of novel monitoring approaches that enable better data resolution, the public's comprehension of water quality matters remains low, primarily due to communication process deficiencies. This study explores the advantages and challenges of using Internet of Things (IoT) and citizen science as alternative monitoring approaches, emphasizing the need for enhancing public communication of water quality data. Through a systematic review of studies implemented on-field, we identify and propose strategies to address five key challenges that IoT and citizen science monitoring approaches must overcome to mature into robust sources of water quality information. Additionally, we highlight three fundamental problems affecting the water quality communication process and outline strategies to convey this topic effectively to the public.

Application of Machine Learning in Modeling the Relationship between Catchment Attributes and Instream Water Quality in Data-Scarce Regions

This research delves into the efficacy of machine learning models in predicting water quality parameters within a catchment area, focusing on unraveling the significance of individual input variables. In order to manage water quality, it is necessary to determine the relationship between the physical attributes of the catchment, such as geological permeability and hydrologic soil groups, and in-stream water quality parameters. Water quality data were acquired from the Iran Water Resource Management Company (WRMC) through monthly sampling. For statistical analysis, the study utilized 5-year means (1998-2002) of water quality data. A total of 88 final stations were included in the analysis. Using machine learning methods, the paper gives relations for 11 in-stream water quality parameters: Sodium Adsorption Ratio (SAR), Na+, Mg2+, Ca2+, SO42-, Cl-, HCO3-, K+, pH, conductivity (EC), and Total Dissolved Solids (TDS). To comprehensively evaluate model performance, the study employs diverse metrics, including Pearson's Linear Correlation Coefficient (R) and the mean absolute percentage error (MAPE). Notably, the Random Forest (RF) model emerges as the standout model across various water parameters. Integrating research outcomes enables targeted strategies for fostering environmental sustainability, contributing to the broader goal of cultivating resilient water ecosystems. As a practical pathway toward achieving a delicate balance between human activities and environmental preservation, this research actively contributes to sustainable water ecosystems.

Deep learning based soft-sensor for continuous chlorophyll estimation on decentralized data

Monitoring the concentration of pigments like chlorophyll (Chl) in water-bodies is a key task to contribute to their conservation. However, with the existing sensor technology, measurement in real-time and with enough frequency to ensure proper risk management is not completely feasible. In this work, with the concept of data-driven soft-sensing, three hydrophysical features are used together with three meteorological ones to estimate the concentration of Chl in two tributaries of the River Thames. Data driven models, specifically neural networks, are used with three learning approaches: individual, centralized and federated. Data reduction scenarios are proposed in order to analyze the performance of each approach when less data is available. The best results in the training are usually obtained with the individual approach. However, the federated learning provides better generalization ability. It was also observed that in most of the cases the results of the federated learning approach improve those of the centralized one.

Predicting aqueous sorption of organic pollutants on microplastics with machine learning

Microplastics (MPs) are ubiquitously distributed in freshwater systems and they can determine the environmental fate of organic pollutants (OPs) via sorption interaction. However, the diverse physicochemical properties of MPs and the wide range of OP species make a deeper understanding of sorption mechanisms challenging. Traditional isotherm-based sorption models are limited in their universality since they normally only consider the nature and characteristics of either sorbents or sorbates individually. Therefore, only specific equilibrium concentrations or specific sorption isotherms can be used to predict sorption. To systematically evaluate and predict OP sorption under the influence of both MPs and OPs properties, we collected 475 sorption data from peer-reviewed publications and developed a poly-parameter-linear-free-energy-relationship-embedded machine learning method to analyze the collected sorption datasets. Models of different algorithms were compared, and the genetic algorithm and support vector machine hybrid model displayed the best prediction performance (R2 of 0.93 and root-mean-square-error of 0.07). Finally, comparison results of three feature importance analysis tools (forward step wise method, Shapley method, and global sensitivity analysis) showed that chemical properties of MPs, excess molar refraction, and hydrogen-bonding interaction of OPs contribute the most to sorption, reflecting the dominant sorption mechanisms of hydrophobic partitioning, hydrogen bond formation, and π-π interaction, respectively. This study presents a novel sorbate-sorbent-based ML model with a wide applicability to expand our capacity in understanding the complicated process and mechanism of OP sorption on MPs.

Data mining from process monitoring of typical polluting enterprise

With the increasing volume of environmental monitoring data, extracting valuable insights from multivariate time series sensor data can facilitate comprehensive information utilization and support informed decision-making in environmental management. However, there is a dearth of comprehensive research on multivariate data analysis for process monitoring in typical polluting enterprises. In this study, an artificial neural network model based on back-propagation algorithm (BP-ANN) was developed to predict the wastewater and exhaust gas emissions using IoT data obtained from process monitoring of a typical polluting enterprise located in Taizhou, Zhejiang Province, China. The results indicate that the model constructed has a high predictive coefficient of determination (R2) with values of 0.8510, 0.9565, 0.9561, 0.9677, and 0.9061 for chemical oxygen demand (COD), potential of hydrogen (pH), electrical conductivity (EC), flue gas emission (FGE), and non-methane hydrocarbon concentration (NMHC) respectively. For the first time, the variable importance measure (VIM)-assisted BP-ANN was employed to investigate the internal and external correlations between wastewater and exhaust gas treatment, thereby enhancing the interpretability of mapping features in the BP-ANN model. The predicted errors for pH and FGE have been demonstrated to fall within the range of - 0.62 ~ 0.30 and - 0.21 ~ 0.15 m3/s, respectively, with average relative errors of 1.05% and 9.60%, which is advantageous in detecting anomalous data and forecasting pollution indicator values. Our approach successfully addresses the challenge of segregating data analysis for wastewater disposal and exhaust gas disposal in the process monitoring of polluting enterprises, while also unearthing potential variables that significantly contribute to the BP-ANN model, thereby facilitating the selection and extraction of characteristic variables.

Determination of Optimal Predictors and Sampling Frequency to Develop Nutrient Soft Sensors Using Random Forest

Despite advancements in sensor technology, monitoring nutrients in situ and in real-time is still challenging and expensive. Soft sensors, based on data-driven models, offer an alternative to direct nutrient measurements. However, the high demand for data required for their development poses logistical issues with data handling. To address this, the study aimed to determine the optimal subset of predictors and the sampling frequency for developing nutrient soft sensors using random forest. The study used water quality data at 15-min intervals from 2 automatic stations on the Main River, Germany, and included dissolved oxygen, temperature, conductivity, pH, streamflow, and cyclical time features as predictors. The optimal subset of predictors was identified using forward subset selection, and the models fitted with the optimal predictors produced R² values above 0.95 for nitrate, orthophosphate, and ammonium for both stations. The study then trained the models on 40 sampling frequencies, ranging from monthly to 15-min intervals. The results showed that as the sampling frequency increased, the model's performance, measured by RMSE, improved. The optimal balance between sampling frequency and model performance was identified using a knee-point determination algorithm. The optimal sampling frequency for nitrate was 3.6 and 2.8 h for the 2 stations, respectively. For orthophosphate, it was 2.4 and 1.8 h. For ammonium, it was 2.2 h for 1 station. The study highlights the utility of surrogate models for monitoring nutrient levels and demonstrates that nutrient soft sensors can function with fewer predictors at lower frequencies without significantly decreasing performance.

Value and limitations of machine learning in high-frequency nutrient data for gap-filling, forecasting, and transport process interpretation

High-frequency monitoring of water quality in catchments brings along the challenge of post-processing large amounts of data. Moreover, monitoring stations are often remote and technical issues resulting in data gaps are common. Machine learning algorithms can be applied to fill these gaps, and to a certain extent, for predictions and interpretation. The objectives of this study were (1) to evaluate six different machine learning models for gap-filling in a high-frequency nitrate and total phosphorus concentration time series, (2) to showcase the potential added value (and limitations) of machine learning to interpret underlying processes, and (3) to study the limits of machine learning algorithms for predictions outside the training period. We used a 4-year high-frequency dataset from a ditch draining one intensive dairy farm in the east of The Netherlands. Continuous time series of precipitation, evapotranspiration, groundwater levels, discharge, turbidity, and nitrate or total phosphorus were used as predictors for total phosphorus and nitrate concentrations respectively. Our results showed that the random forest algorithm had the best performance to fill in data-gaps, with R² higher than 0.92 and short computation times. The feature importance helped understanding the changes in transport processes linked to water conservation measures and rain variability. Applying the machine learning model outside the training period resulted in a low performance, largely due to system changes (manure surplus and water conservation) which were not included as predictors. This study offers a valuable and novel example of how to use and interpret machine learning models for post-processing high-frequency water quality data.

Forecasting and Optimizing Dual Media Filter Performance via Machine Learning

Four different machine learning algorithms, including Decision Tree (DT), Random Forest (RF), Multivariable Linear Regression (MLR), Support Vector Regressions (SVR), and Gaussian Process Regressions (GPR), were applied to predict the performance of a multi-media filter operating as a function of raw water quality and plant operating variables. The models were trained using data collected over a seven year period covering water quality and operating variables, including true colour, turbidity, plant flow, and chemical dose for chlorine, KMnO₄, FeCl₃, and Cationic Polymer (PolyDADMAC). The machine learning algorithms have shown that the best prediction is at a 1-day time lag between input variables and unit filter run volume (UFRV). Furthermore, the RF algorithm with grid search using the input metrics mentioned above with a 1-day time lag has provided the highest reliability in predicting UFRV with a RMSE and R² of 31.58 and 0.98, respectively. Similarly, RF with grid search has shown the shortest training time, prediction accuracy, and forecasting events using a ROC-AUC curve analysis (AUC over 0.8) in extreme wet weather events. Therefore, Random Forest with grid search and a 1-day time lag is an effective and robust machine learning algorithm that can predict the filter performance to aid water treatment operators in their decision makings by providing real-time warning of the potential turbidity breakthrough from the filters.

Coupling process-based modeling with machine learning for long-term simulation of wastewater treatment plant operations

Effective treatment of sewage by wastewater treatment plants (WWTPs) are essential to protecting water environment as well as people's health worldwide. However, operation of WWTPs is usually intricate due to precarious influent characteristics and nonlinear sewage treatment processes. Effective modeling of WWTPs can provide valuable decision-making support to facilitate their daily operations and management. In this study, we have built a novel hybrid model by combining a process-based WWTP model (GPS-X) with a data-driven machine learning model (Random Forest) to improve the simulation of long-term hourly effluent ammonium-nitrogen concentration of a WWTP. Our study results have shown that the hybrid GPS-X-RF model performs the best with a coefficient of determination (R²) of 0.95 and root mean squared error (RMSE) of 0.23 mg/L, followed by the GPS-X model with a R² of 0.93 and RMSE of 0.33 mg/L and last the Random Forest model with a R² of 0.84 and RMSE of 0.41 mg/L. Capable of incorporating wastewater treatment mechanisms and utilizing superior data mining capabilities of machine learning, the hybrid model adapts better to the large fluctuations in influent and operating conditions of the WWTP. The proposed hybrid modeling framework may be easily extended to WWTPs of various size and types to simulate their operations under increasingly variable environmental and operating conditions.

Groundwater vulnerability assessment of elevated arsenic in Gangetic plain of West Bengal, India; Using primary information, lithological transport, state-of-the-art approaches

Deterioration of groundwater quality is a long-term incident which leads unending vulnerability of groundwater. The present work was carried out in Murshidabad District, West Bengal, India to assess groundwater vulnerability due to elevated arsenic (As) and other heavy metal contamination in this area. The geographic distribution of arsenic and other heavy metals including physicochemical parameters of groundwater (in both pre-monsoon and post-monsoon season) and different physical factors were performed. GIS-machine learning model such as support vector machine (SVM), random forest (RF) and support vector regression (SVR) were used for this study. Results revealed that, the concentration of groundwater arsenic compasses from 0.093 to 0.448 mg/L in pre-monsoon and 0.078 to 0.539 mg/L in post-monsoon throughout the district; which indicate that all water samples of the Murshidabad District exceed the WHO's permissible limit (0.01 mg/L). The GIS-machine learning model outcomes states the values of area under the curve (AUC) of SVR, RF and SVM are 0.923, 0.901 and 0.897 (training datasets) and 0.910, 0.899 and 0.891 (validation datasets), respectively. Hence, "support vector regression" model is best fitted to predict the arsenic vulnerable zones of Murshidabad District. Then again, groundwater flow paths and arsenic transport was assessed by three dimensions underlying transport model (MODPATH). The particles discharging trends clearly revealed that the Holocene age aquifers are major contributor of As than Pleistocene age aquifers and this may be the main cause of As vulnerability of both northeast and southwest parts of Murshidabad District. Therefore, special attention should be paid on the predicted vulnerable areas for the safeguard of the public health. Moreover, this study can help to make a proper framework towards sustainable groundwater management.

A soft sensor for simulating algal cell density based on dynamic response to environmental changes in a eutrophic shallow lake

There is a great need for timely monitoring and rapid water quality assessment to control the algal blooms that often occur in eutrophic lakes. While algal cell density (ACD) is a critical indicator of algal growth, field monitoring is laborious and time-consuming, and rapid assessment of algal blooms based on ACD is often not possible. To address the limitations of conventional ACD detection, we proposed a soft sensor approach that uses surrogate indicators to simulate ACD in machine learning models. We conducted a case study using monitoring data from Chaohu Lake collected between 2016 and 2019. We found that ensemble learning models, especially extreme gradient boosting (XGBoost), outperformed traditional machine learning algorithms by comparing various machine learning algorithms. Also, considering the influence of input variable selection on model performance, we combined the results of different filter methods in the multi-stage variable selection process. Finally, we screened out seven key variables out of the 43 initial candidate variables, including dissolved oxygen (DO), chlorophyll-a (Chl-a), Secchi disk depth (SD), pH, permanganate index (COD_Mn), week of the year (WOY), and wind velocity (WV). Their inclusion substantially improved data accessibility and supported the development of a rapid simulation model. The final model was capable of reliable spatiotemporal generalization, with an overall R² value of 0.761. On the theoretical side, our study makes a new attempt to simulate ACD values in a eutrophic lake. For practical purposes, the soft sensor can facilitate the rapid assessment of bloom conditions, which helps the local administration with emergency prevention and control.

Advances in Catchment Science, Hydrochemistry, and Aquatic Ecology Enabled by High-Frequency Water Quality Measurements

High-frequency water quality measurements in streams and rivers have expanded in scope and sophistication during the last two decades. Existing technology allows in situ automated measurements of water quality constituents, including both solutes and particulates, at unprecedented frequencies from seconds to subdaily sampling intervals. This detailed chemical information can be combined with measurements of hydrological and biogeochemical processes, bringing new insights into the sources, transport pathways, and transformation processes of solutes and particulates in complex catchments and along the aquatic continuum. Here, we summarize established and emerging high-frequency water quality technologies, outline key high-frequency hydrochemical data sets, and review scientific advances in key focus areas enabled by the rapid development of high-frequency water quality measurements in streams and rivers. Finally, we discuss future directions and challenges for using high-frequency water quality measurements to bridge scientific and management gaps by promoting a holistic understanding of freshwater systems and catchment status, health, and function.

Managing landscape patterns at the riparian zone and sub-basin scale is equally important for water quality protection

Widespread attention has been given to understanding the effect of the landscape pattern on river water quality. However, which spatial scale (riparian zone versus sub-basin) has the greater impact on water quality has long been controversial, since the key metrics that affect water quality varied with spatial scale. Thus, quantifying the spatial scale effects of key landscape metrics on water quality is critical to clarifying which scale of landscape pattern is more conducive to water quality conservation. Here, we adopted variation partitioning analysis (VPA) and random forest models to quantify the landscape pattern impact on water quality at northern Erhai Lake during the 2019 rainy season (early, mid, and late), and comprehensively analyze the key landscape metrics on different scales. The results revealed that the riparian zone and sub-basin scale landscape patterns explained similar water quality variations (difference only 0.9%) in the mid (August) and late rainy season (October), but exhibited a large difference (24.1%) during the early rainy season (June). Furthermore, rivers were primarily stressed by nitrogen pollution. Maintaining the Grassland_ED > 27.99 m/ha, Grassland_LPI > 4.19%, Farmland_LSI < 3.2 in the riparian zone, and Construction_ED < 1.69 m/ha, Construction_LSI < 2.46, Farmland_PLADJ < 89.0% at the sub-basin scale could significantly reduce the TN concentration in the stream. Meanwhile, managing of these metrics can effectively prevent rapid increases of TN in rivers. Moreover, due to the low phosphorus concentration in the rivers, none of the landscape metrics significantly explained the variation in TP. This study explored the spatial scale effect of landscape patterns on water quality and revealed the driving factors of nutrient variation. This study will provide a scientific basis for aquatic environmental management in plateau watersheds.

Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring

To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitates using virtual sensing to predict them by utilizing easily measurable variables as inputs. While the predictive performance of these data-driven, virtual-sensor models depends on the use of adequate training samples (in quality and quantity), the procurement and operational cost of nitrogen and phosphorus sensors make it impractical to acquire sufficient samples. For this reason, the variational autoencoder, which is one of the most prominent methods in generative models, was utilized in the present work for generating synthetic data. The generation capacity of the model was verified using water-quality data from two tributaries of the River Thames in the United Kingdom. Compared to the current state of the art, our novel data augmentation-including proper experimental settings or hyperparameter optimization-improved the root mean squared errors by 23-63%, with the most significant improvements observed when up to three predictors were used. In comparing the predictive algorithms' performances (in terms of the predictive accuracy and computational cost), k-nearest neighbors and extremely randomized trees were the best-performing algorithms on average.

Water quality assessment of the Karasu River (Turkey) using various indices, multivariate statistics and APCS-MLR model

Determining the water quality status of a river and accurately identifying potential pollution sources threatening the river are pillars in effective control of pollution and sustainable water management. In this study, water quality indices, multivariate statistics and absolute principal component score-multiple linear regression (APCS-MLR) were applied to evaluate the water quality of the Karasu River, the main tributary of the Euphrates River (Turkey). For this, 19 water quality variables were monitored monthly at eight stations along the river during one year. Based on the mean dissolved oxygen (DO), electrical conductivity (EC), nitrate-nitrogen (NO₃-N), orthophosphate-phosphorus (PO₄-P), total phosphorus (TP), ammonium-nitrogen (NH4-N), chemical oxygen demand (COD) and total nitrogen (TN) levels, most stations of the river had "very good" water status according to surface water quality criteria. Spatial cluster analysis (CA) divided eight stations into three regions as clean region, moderate clean region and very clean region. The mean values of Nutrient Pollution Index indicated that the river was "no polluted". Similarly, Water Quality Index and Organic Pollution Index values indicated that the river water quality was between "good" and "excellent". A minimum water quality index (WQI_min) consisted of ten crucial parameters was not significantly different with the WQI based on all the 17 parameters. Discriminant analysis (DA) results showed that water temperature (WT), EC, chlorophyll-a (Chl-a), potassium (K), calcium (Ca), NO₃-N and COD are the variables responsible for temporal changes, while WT, total dissolves solids (TDS), Chl-a, K, magnesium (Mg), Ca, NH₄-N and COD are the variables responsible for spatial changes in the river water quality. Principal component analysis/factor analysis (PCA/FA) identified four potential sources, including anthropogenic, natural, seasonal and phytoplankton. Source apportionment in the APCS-MLR model revealed that seasonal and anthropogenic sources contributed 35.2% and 25.5% to river water quality parameters, respectively, followed by phytoplankton (21.4%) and natural sources (17.9%).

Effects of sampling strategy in rivers on load estimation for Nitrate-Nitrogen and total Phosphorus in a lowland agricultural area

The transport of nutrients into water bodies is one of the main causes of water eutrophication. It is therefore important to estimate the loads of nutrients. Discharge and nutrient concentrations are the fundamental elements to estimate the loads of nutrients, the latter can be affected by sampling strategies. As conducting sampling campaign and laboratory analysis are both expensive, it is necessary to find the best effective sampling strategy. The aim of this paper is to show how autocorrelation and standard statistical methods can be used to test the effects of different sampling strategies on the nutrient load estimation and to find the optimal sampling strategy. The data set in this study is from the 50 km² Kielstau catchment, a UNESCO demo site for ecohydrology in Northern Germany and consists of 14 years daily values of climate, hydrology, and water quality from 2006 to 2019. We calculated the autocorrelation (AC) of discharge (Q), precipitation, Nitrate-Nitrogen (NO₃-N) and total Phosphorus (Ptot). Then we tested the effects of sampling intervals from 7 to 56 days (1-8 weeks) on the nutrient loads. Our results showed a high AC of Q and NO₃-N for a long period, but the AC of Ptot and precipitation decreased very fast. An increase of the sampling interval (less frequent) increased the error of estimating the concentrations and loads. Consequently, we recommend that (1) the optimal sampling strategy for nutrient load estimation in an agriculture-dominant catchment should be continuously monitoring discharge combined with periodic grabbed samples; (2) the sampling frequency for NO₃-N is suggested to be monthly (every 28 days) and for Ptot weekly (every 7 days). The information will help those tasked with catchment monitoring to design appropriate sampling strategy to ensure adequate data for nutrients load estimation in lowland rivers.

Incorporating receiving waters responses into the framework of spatial optimization of LID-BMPs in plain river network region

Deep insights into the receiving waters responses to optimal spatial allocation of LID-BMPs are considered extremely important. This study addressed the urgent need to incorporate receiving waters responses into the spatial allocation optimization of LID-BMPs and demonstrated the efficiency of the approach to guide watershed management. The integration of an overland-river coupling model and the NSGA-III algorithm resulted in the proposal of a general simulation-optimization framework for the optimal layout of LID-BMPs. The coupled model was swapped out for the surrogates to increase computational efficiency. When 40.71%, 36.06%, and 61.80% reductions in runoff volume, flood volume, and TP concentration are achieved, the newly proposed framework can save 34.44% and 16.31% cost compared to the approach that does not consider receiving waters responses and refined spatial allocation, respectively. Results indicate that the incorporation of receiving waters responses and refined spatial allocation are essential for the optimal design of LID-BMPs. This new framework offers the potential for more cost-effective high-cost solutions. The results of spatial optimization are significantly influenced by imperviousness.

A Virtual Sensing Concept for Nitrogen and Phosphorus Monitoring Using Machine Learning Techniques

Harmful cyanobacterial bloom (HCB) is problematic for drinking water treatment, and some of its strains can produce toxins that significantly affect human health. To better control eutrophication and HCB, catchment managers need to continuously keep track of nitrogen (N) and phosphorus (P) in the water bodies. However, the high-frequency monitoring of these water quality indicators is not economical. In these cases, machine learning techniques may serve as viable alternatives since they can learn directly from the available surrogate data. In the present work, a random forest, extremely randomized trees (ET), extreme gradient boosting, k-nearest neighbors, a light gradient boosting machine, and bagging regressor-based virtual sensors were used to predict N and P in two catchments with contrasting land uses. The effect of data scaling and missing value imputation were also assessed, while the Shapley additive explanations were used to rank feature importance. A specification book, sensitivity analysis, and best practices for developing virtual sensors are discussed. Results show that ET, MinMax scaler, and a multivariate imputer were the best predictive model, scaler, and imputer, respectively. The highest predictive performance, reported in terms of R², was 97% in the rural catchment and 82% in an urban catchment.

Predicting Irrigation Water Quality Indices Based on Data-Driven Algorithms: Case Study in Semiarid Environment

Ascertaining water quality for irrigational use by employing conventional methods is often time taking and expensive due to the determination of multiple parameters needed, especially in developing countries. Therefore, constructing precise and adequate models may be beneficial in resolving this problem in agricultural water management to determine the suitable water quality classes for optimal crop yield production. To achieve this objective, five machine learning (ML) models, namely linear regression (LR), random subspace (RSS), additive regression (AR), reduced error pruning tree (REPTree), and support vector machine (SVM), have been developed and tested for predicting of six irrigation water quality (IWQ) indices such as sodium adsorption ratio (SAR), percent sodium (%Na), permeability index (PI), Kelly ratio (KR), soluble sodium percentage (SSP), and magnesium hazards (MH) in groundwater of the Nand Samand catchment of Rajasthan. The accuracy of these models was determined serially using the mean squared error (MSE), correlation coefficients (r), mean absolute error (MAE), and root mean square error (RMSE). The SVM model showed the best-fit model for all irrigation indices during testing, that is, RMSE: 0.0662, 4.0568, 3.0168, 0.1113, 3.7046, and 5.1066; r: 0.9364, 0.9618, 0.9588, 0.9819, 0.9547, and 0.8903; MSE: 0.004381, 16.45781, 9.101218, 0.012383, 13.72447, and 26.078; MAE: 0.042, 3.1999, 2.3584, 0.0726, 2.9603, and 4.0582 for KR, MH, SSP, SAR, %Na, and PI, respectively. The KR and SAR values were predicted accurately by the SVM model in comparison to the observed values. As a result, machine learning algorithms can improve irrigation water quality characteristics, which is critical for farmers and crop management in various irrigation procedures. Additionally, the findings of this research suggest that ML models are effective tools for reliably predicting groundwater quality using general water quality parameters that may be acquired directly on periodical basis. Assessment of water quality indices may also help in deriving optimal strategies to utilise inferior quality water conjunctively with fresh water resources in the water-limited areas.

Spatiotemporal variation evaluation of water quality in middle and lower Han River, China

As the water source for the middle route of the South-to-North Water Transfer Project, the Han River in China plays a role of the world’s largest inter-basin water transfer project. However, this human-interfered area has suffered from over-standard pollution emission and water blooms in recent years, which necessitates urgent awareness at both national and provincial scales. To perform a comprehensive analysis of the water quality condition of this study area, we apply both the water quality index (WQI) and minimal WQI (WQI_min) methods to investigate the spatiotemporal variation characteristics of water quality. The results show that 8 parameters consisting of permanganate index (PI), chemical oxygen demand (COD), total phosphorus (TP), fluoride (F-), arsenic (As), plumbum (Pb), copper (Cu), and zinc (Zn) have significant discrepancy in spatial scales, and the study basin also has a seasonal variation pattern with the lowest WQI values in summer and autumn. Moreover, compared to the traditional WQI, the WQI_min model, with the assistance of stepwise linear regression analysis, could exhibit more accurate explanation with the coefficient of determination (R²) and percentage error (PE) values being 0.895 and 5.515%, respectively. The proposed framework is of great importance to improve the spatiotemporal recognition of water quality patterns and further helps develop efficient water management strategies at a reduced cost.

Chlorophyll soft-sensor based on machine learning models for algal bloom predictions

Harmful algal blooms (HABs) are a growing concern to public health and aquatic ecosystems. Long-term water monitoring conducted by hand poses several limitations to the proper implementation of water safety plans. This work combines automatic high-frequency monitoring (AFHM) systems with machine learning (ML) techniques to build a data-driven chlorophyll-a (Chl-a) soft-sensor. Massive data for water temperature, pH, electrical conductivity (EC) and system battery were taken for three years at intervals of 15 min from two different areas of As Conchas freshwater reservoir (NW Spain). We designed a set of soft-sensors based on compact and energy efficient ML algorithms to infer Chl-a fluorescence by using low-cost input variables and to be deployed on buoys with limited battery and hardware resources. Input and output aggregations were applied in ML models to increase their inference performance. A component capable of triggering a 10 [Formula: see text]g/L Chl-a alert was also developed. The results showed that Chl-a soft-sensors could be a rapid and inexpensive tool to support manual sampling in water bodies at risk.

Machine learning-based estimation of riverine nutrient concentrations and associated uncertainties caused by sampling frequencies

Accurate and sufficient water quality data is essential for watershed management and sustainability. Machine learning models have shown great potentials for estimating water quality with the development of online sensors. However, accurate estimation is challenging because of uncertainties related to models used and data input. In this study, random forest (RF), support vector machine (SVM), and back-propagation neural network (BPNN) models are developed with three sampling frequency datasets (i.e., 4-hourly, daily, and weekly) and five conventional indicators (i.e., water temperature (WT), hydrogen ion concentration (pH), electrical conductivity (EC), dissolved oxygen (DO), and turbidity (TUR)) as surrogates to individually estimate riverine total phosphorus (TP), total nitrogen (TN), and ammonia nitrogen (NH₄⁺-N) in a small-scale coastal watershed. The results show that the RF model outperforms the SVM and BPNN machine learning models in terms of estimative performance, which explains much of the variation in TP (79 ± 1.3%), TN (84 ± 0.9%), and NH₄⁺-N (75 ± 1.3%), when using the 4-hourly sampling frequency dataset. The higher sampling frequency would help the RF obtain a significantly better performance for the three nutrient estimation measures (4-hourly > daily > weekly) for R² and NSE values. WT, EC, and TUR were the three key input indicators for nutrient estimations in RF. Our study highlights the importance of high-frequency data as input to machine learning model development. The RF model is shown to be viable for riverine nutrient estimation in small-scale watersheds of important local water security.

Geospatial Artificial Intelligence (GeoAI) in the Integrated Hydrological and Fluvial Systems Modeling: Review of Current Applications and Trends

This paper reviews the current GeoAI and machine learning applications in hydrological and hydraulic modeling, hydrological optimization problems, water quality modeling, and fluvial geomorphic and morphodynamic mapping. GeoAI effectively harnesses the vast amount of spatial and non-spatial data collected with the new automatic technologies. The fast development of GeoAI provides multiple methods and techniques, although it also makes comparisons between different methods challenging. Overall, selecting a particular GeoAI method depends on the application’s objective, data availability, and user expertise. GeoAI has shown advantages in non-linear modeling, computational efficiency, integration of multiple data sources, high accurate prediction capability, and the unraveling of new hydrological patterns and processes. A major drawback in most GeoAI models is the adequate model setting and low physical interpretability, explainability, and model generalization. The most recent research on hydrological GeoAI has focused on integrating the physical-based models’ principles with the GeoAI methods and on the progress towards autonomous prediction and forecasting systems.

A review of the application of machine learning in water quality evaluation

With the rapid increase in the volume of data on the aquatic environment, machine learning has become an important tool for data analysis, classification, and prediction. Unlike traditional models used in water-related research, data-driven models based on machine learning can efficiently solve more complex nonlinear problems. In water environment research, models and conclusions derived from machine learning have been applied to the construction, monitoring, simulation, evaluation, and optimization of various water treatment and management systems. Additionally, machine learning can provide solutions for water pollution control, water quality improvement, and watershed ecosystem security management. In this review, we describe the cases in which machine learning algorithms have been applied to evaluate the water quality in different water environments, such as surface water, groundwater, drinking water, sewage, and seawater. Furthermore, we propose possible future applications of machine learning approaches to water environments.

Prediction of irrigation groundwater quality parameters using ANN, LSTM, and MLR models

Forecasting the irrigation groundwater parameters helps plan irrigation water and crop, and it is commonly expensive because it needs various parameters, mainly in developing nations. Therefore, the present research's core objective is to create accurate and reliable machine learning models for irrigation parameters. To accomplish this determination, three machine learning (ML) models, viz. long short-term memory (LSTM), multi-linear regression (MLR), and artificial neural network (ANN), have been trained. It is validated with mean squared error (MSE) and correlation coefficients (r), root mean square error (RMSE), and mean absolute error (MAE). These machine learning models have been used and applied for predicating the six irrigation water quality parameters such as sodium absorption ratio (SAR), percentage of sodium (%Na), residual sodium carbonate (RSC), magnesium hazard (MH), Permeability Index (PI), and Kelly ratio (KR). Therefore, the two scenario performances of ANN, LSTM, and MLR have been developed for each model to predict irrigation water quality parameters. The first and second scenario performance was created based on all and second reduction input variables. The ANN, LSTM, and MLR models have discovered that excluding for ANN and MLR models shows high accuracy in first and second scenario models, respectively. These model's accuracy was checked based on the mean squared error (MSE), correlation coefficients (r), and root mean square error (RMSE) for training and testing processes serially. The RSC values are highly accurate predicated values using ANN and MLR models. As a result, machine learning models may improve irrigation water quality parameters, and such types of results are essential to farmers and crop planning in various irrigation processes.

Exploring Machine Learning Models in Predicting Irrigation Groundwater Quality Indices for Effective Decision Making in Medjerda River Basin, Tunisia

Over the last years, the global application of machine learning (ML) models in groundwater quality studies has proved to be a robust alternative tool to produce highly accurate results at a low cost. This research aims to evaluate the ability of machine learning (ML) models to predict the quality of groundwater for irrigation purposes in the downstream Medjerda river basin (DMB) in Tunisia. The random forest (RF), support vector regression (SVR), artificial neural networks (ANN), and adaptive boosting (AdaBoost) models were tested to predict the irrigation quality water parameters (IWQ): total dissolved solids (TDS), potential salinity (PS), sodium adsorption ratio (SAR), exchangeable sodium percentage (ESP), and magnesium adsorption ratio (MAR) through low-cost, in situ physicochemical parameters (T, pH, EC) as input variables. In view of this, seventy-two (72) representative groundwater samples have been collected and analysed for major cations and anions during pre-and post-monsoon seasons of 3 years (2019–2021) to compute IWQ parameters. The performance of the ML models was evaluated according to Pearson’s correlation coefficient (r), the root means square error (RMSE), and the relative bias (RBIAS). The model sensitivity analysis was evaluated to identify input parameters that considerably impact the model predictions using the one-factor-at-time (OFAT) method of the Monte Carlo (MC) approach. The results show that the AdaBoost model is the most appropriate model for predicting all parameters (r was ranged between 0.88 and 0.89), while the random forest model is suitable for predicting only four parameters: TDS, PS, SAR, and ESP (r was with 0.65 to 0.87). Added to that, this study found out that the ANN and SVR models perform well in predicting three parameters (TDS, PS, SAR) and two parameters (PS, SAR), respectively, with the most optimal value of generalization ability (GA) close to unity (between 1 and 0.98). Moreover, the results of the uncertainty analysis confirmed the prominent superiority and robustness of the ML models to produce excellent predictions with only a few physicochemical parameters as inputs. The developed ML models are relevant for predicting cost-effective irrigation water quality indices and can be applied as a DSS tool to improve water management in the Medjerda basin.

Smart Technologies for Sustainable Water Management: An Urban Analysis

As projections highlight that half of the global population will be living in regions facing severe water scarcity by 2050, sustainable water management policies and practices are more imperative than ever. Following the Sustainable Development Goals for equitable water access and prudent use of natural resources, emerging digital technologies may foster efficient monitoring, control, optimization, and forecasting of freshwater consumption and pollution. Indicatively, the use of sensors, Internet of Things, machine learning, and big data analytics has been catalyzing smart water management. With two-thirds of the global population to be living in urban areas by 2050, this research focuses on the impact of digitization on sustainable urban water management. More specifically, existing scientific literature studies were explored for providing meaningful insights on smart water technologies implemented in urban contexts, emphasizing supply and distribution networks. The review analysis outcomes were classified according to three main pillars identified: (i) level of analysis (i.e., municipal or residential/industrial); (ii) technology used (e.g., sensors, algorithms); and (iii) research scope/focus (e.g., monitoring, optimization), with the use of a systematic approach. Overall, this study is expected to act as a methodological tool and guiding map of the most pertinent state-of-the-art research efforts to integrate digitalization in the field of water stewardship and improve urban sustainability.

From Fully Physical to Virtual Sensing for Water Quality Assessment: A Comprehensive Review of the Relevant State-of-the-Art

Rapid urbanization, industrial development, and climate change have resulted in water pollution and in the quality deterioration of surface and groundwater at an alarming rate, deeming its quick, accurate, and inexpensive detection imperative. Despite the latest developments in sensor technologies, real-time determination of certain parameters is not easy or uneconomical. In such cases, the use of data-derived virtual sensors can be an effective alternative. In this paper, the feasibility of virtual sensing for water quality assessment is reviewed. The review focuses on the overview of key water quality parameters for a particular use case and the development of the corresponding cost estimates for their monitoring. The review further evaluates the current state-of-the-art in terms of the modeling approaches used, parameters studied, and whether the inputs were pre-processed by interrogating relevant literature published between 2001 and 2021. The review identified artificial neural networks, random forest, and multiple linear regression as dominant machine learning techniques used for developing inferential models. The survey also highlights the need for a comprehensive virtual sensing system in an internet of things environment. Thus, the review formulates the specification book for the advanced water quality assessment process (that involves a virtual sensing module) that can enable near real-time monitoring of water quality.

Machine learning in natural and engineered water systems

Water resources of desired quality and quantity are the foundation for human survival and sustainable development. To better protect the water environment and conserve water resources, efficient water management, purification, and transportation are of critical importance. In recent years, machine learning (ML) has exhibited its practicability, reliability, and high efficiency in numerous applications; furthermore, it has solved conventional and emerging problems in both natural and engineered water systems. For example, ML can predict various water quality indicators in situ and real-time by considering the complex interactions among water-related variables. ML approaches can also solve emerging pollution problems with proven rules or universal mechanisms summarized from the related research. Moreover, by applying image recognition technology to analyze the relationships between image information and physicochemical properties of the research object, ML can effectively identify and characterize specific contaminants. In view of the bright prospects of ML, this review comprehensively summarizes the development of ML applications in natural and engineered water systems. First, the concept and modeling steps of ML are briefly introduced, including data preparation, algorithm selection and model evaluation. In addition, comprehensive applications of ML in recent studies, including predicting water quality, mapping groundwater contaminants, classifying water resources, tracing contaminant sources, and evaluating pollutant toxicity in natural water systems, as well as modeling treatment techniques, assisting characterization analysis, purifying and distributing drinking water, and collecting and treating sewage water in engineered water systems, are summarized. Finally, the advantages and disadvantages of commonly used algorithms are analyzed according to their structures and mechanisms, and recommendations on the selection of ML algorithms for different studies, as well as prospects on the application and development of ML in water science are proposed. This review provides references for solving a wider range of water-related problems and brings further insights into the intelligent development of water science.

An appraisal of data collection, analysis, and reporting adopted for water quality assessment: A case of Nigeria water quality research

The appropriate acquisition and processing of water quality data are crucial for water resource management. As such, published articles on water quality monitoring and assessment are meant to convey essential and reliable information to water quality experts, decision-makers, researchers, students, and the public. The implication is that such information must emanate from data obtained and analysed in an up-to-date, scientifically sound manner. Thus, inappropriate data analysis and reporting techniques could yield misleading results and mar the endeavours of achieving error-free conclusions. This study utilises the findings on water quality assessment in Nigeria over the last 20 years to reveal the likely trends in water quality research regarding data collection, data analysis, and reporting for physicochemical, bacteriological parameters, and trace organics. A total of 123 Web of Science and quartile ranked (Q1-Q4) published articles involving water quality assessment in Nigeria were analysed. Results indicated shortcomings in various aspects of data analysis and reporting. Consequently, we use simulated heatmaps and graphs to illustrate preferred ways of analysing, reporting, and visualising some regularly used descriptive and inferential statistics of water quality variables. Finally, we highlight alternative approaches to the customarily applied water quality assessment methods in Nigeria and emphasise other areas of deficiency that need attention for improved water quality research.

Functionalization of remote sensing and on-site data for simulating surface water dissolved oxygen: Development of hybrid tree-based artificial intelligence models

Dissolved oxygen (DO) is an important indicator of river health for environmental engineers and ecological scientists to understand the state of river health. This study aims to evaluate the reliability of four feature selector algorithms i.e., Boruta, genetic algorithm (GA), multivariate adaptive regression splines (MARS), and extreme gradient boosting (XGBoost) to select the best suited predictor of the applied water quality (WQ) parameters; and compare four tree-based predictive models, namely, random forest (RF), conditional random forests (cForest), RANdom forest GEneRator (Ranger), and XGBoost to predict the changes of dissolved oxygen (DO) in the Klang River, Malaysia. The total features including 15 WQ parameters from monitoring site data and 7 hydrological components from remote sensing data. All predictive models performed well as per the features selected by the algorithms XGBoost and MARS in terms applied statistical evaluators. Besides, the best performance noted in case of XGBoost predictive model among all applied predictive models when the feature selected by MARS and XGBoost algorithms, with the coefficient of determination (R²) values of 0.84 and 0.85, respectively, nonetheless the marginal performance came up by Boruta-XGBoost model on in this scenario.

Machine Learning-Based Prediction of Chlorophyll-a Variations in Receiving Reservoir of World’s Largest Water Transfer Project—A Case Study in the Miyun Reservoir, North China

Although water transfer projects can alleviate the water crisis, they may cause potential risks to water quality safety in receiving areas. The Miyun Reservoir in northern China, one of the receiving reservoirs of the world’s largest water transfer project (South-to-North Water Transfer Project, SNWTP), was selected as a case study. Considering its potential eutrophication trend, two machine learning models, i.e., the support vector machine (SVM) model and the random forest (RF) model, were built to investigate the trophic state by predicting the variations of chlorophyll-a (Chl-a) concentrations, the typical reflection of eutrophication, in the reservoir after the implementation of SNWTP. The results showed that compared with the SVM model, the RF model had higher prediction accuracy and more robust prediction ability with abnormal data, and was thus more suitable for predicting Chl-a concentration variations in the receiving reservoir. Additionally, short-term water transfer would not cause significant variations of Chl-a concentrations. After the project implementation, the impact of transferred water on the water quality of the receiving reservoir would have gradually increased. After a 10-year implementation, transferred water would cause a significant decline in the receiving reservoir’s water quality, and Chl-a concentrations would increase, especially from July to August. This led to a potential risk of trophic state change in the Miyun Reservoir and required further attention from managers. This study can provide prediction techniques and advice on water quality security management associated with eutrophication risks resulting from water transfer projects.

Machine learning for manually-measured water quality prediction in fish farming

Monitoring variables such as dissolved oxygen, pH, and pond temperature is a key aspect of high-quality fish farming. Machine learning (ML) techniques have been proposed to model the dynamics of such variables to improve the fish farmer's decision-making. Most of the research on ML in aquaculture has focused on scenarios where devices for real-time data acquisition, storage, and remote monitoring are available, making it easy to develop accurate ML techniques. However, fish farmers do not necessarily have access to such devices. Many of them prefer to use equipment to manually measure these variables limiting the amount of available data to process. In this work, we study the use of random forests, multivariate linear regression, and artificial neural networks in scenarios with limited amount of measurements to analyze data from water-quality variables that are commonly measured in fish farming. We propose a methodology to build models in two scenarios: i) estimation of unobserved variables based on the observed ones, and ii) forecasting when a low amount of data is available for training. We show that random forests can be used to forecast dissolved oxygen, pond temperature, pH, ammonia, and ammonium when the water pond variables are measured only twice per day. Moreover, we showed that these prediction models can be implemented on a mobile-based information system and run in an average smartphone that fish farmers can afford.

Data Analytics for Environmental Science and Engineering Research

The advent of new data acquisition and handling techniques has opened the door to alternative and more comprehensive approaches to environmental monitoring that will improve our capacity to understand and manage environmental systems. Researchers have recently begun using machine learning (ML) techniques to analyze complex environmental systems and their associated data. Herein, we provide an overview of data analytics frameworks suitable for various Environmental Science and Engineering (ESE) research applications. We present current applications of ML algorithms within the ESE domain using three representative case studies: (1) Metagenomic data analysis for characterizing and tracking antimicrobial resistance in the environment; (2) Nontarget analysis for environmental pollutant profiling; and (3) Detection of anomalies in continuous data generated by engineered water systems. We conclude by proposing a path to advance incorporation of data analytics approaches in ESE research and application.

Predictive models using "cheap and easy" field measurements: Can they fill a gap in planning, monitoring, and implementing fecal sludge management solutions?

The characteristics of fecal sludge delivered to treatment plants are highly variable. Adapting treatment process operations accordingly is challenging due to a lack of analytical capacity for characterization and monitoring at many treatment plants. Cost-efficient and simple field measurements such as photographs and probe readings could be proxies for process control parameters that normally require laboratory analysis. To investigate this, we evaluated questionnaire data, expert assessments, and simple analytical measurements for fecal sludge collected from 421 onsite containments. This data served as inputs to models of varying complexity. Random forest and linear regression models were able to predict physical-chemical characteristics including total solids (TS) and ammonium (NH₄⁺-N) concentrations, and solid-liquid separation performance including settling efficiency and filtration time (R² from 0.51-0.66) based on image analysis of photographs (sludge color, supernatant color, and texture) and probe readings (conductivity (EC) and pH). Supernatant color was the best predictor of settling efficiency and filtration time, EC was the best predictor of NH₄⁺-N, and texture was the best predictor of TS. Predictive models have the potential to be applied for real-time monitoring and process control if a database of measurements is developed and models are validated in other cities. Simple decision tree models based on the single classifier of containment type can also be used to make predictions about citywide planning, where a lower degree of accuracy is required.

Prediction of stream nitrogen and phosphorus concentrations from high-frequency sensors using Random Forests Regression

Stream nutrient concentrations exhibit marked temporal variation due to hydrology and other factors such as the seasonality of biological processes. Many water quality monitoring programs sample too infrequently (i.e., weekly or monthly) to fully characterize lotic nutrient conditions and to accurately estimate nutrient loadings. A popular solution to this problem is the surrogate-regression approach, a method by which nutrient concentrations are estimated from related parameters (e.g., conductivity or turbidity) that can easily be measured in situ at high frequency using sensors. However, stream water quality data often exhibit skewed distributions, nonlinear relationships, and multicollinearity, all of which can be problematic for linear-regression models. Here, we use a flexible and robust machine learning technique, Random Forests Regression (RFR), to estimate stream nitrogen (N) and phosphorus (P) concentrations from sensor data within a forested, mountainous drainage area in upstate New York. When compared to actual nutrient data from samples tested in the laboratory, this approach explained much of the variation in nitrate (89%), total N (85%), particulate P (76%), and total P (74%). The models were less accurate for total soluble P (47%) and soluble reactive P (32%), though concentrations of these latter parameters were in a relatively low range. Although soil moisture and fluorescent dissolved organic matter are not commonly used as surrogates in nutrient-regression models, they were important predictors in this study. We conclude that RFR shows great promise as a tool for modeling instantaneous stream nutrient concentrations from high-frequency sensor data, and encourage others to evaluate this approach for supplementing traditional (laboratory-determined) nutrient datasets.

Predicting stream water quality under different urban development pattern scenarios with an interpretable machine learning approach

Urban development pattern significantly impacts stream water quality by influencing pollutant generation, build-up, and wash-off processes. It is thus necessary to understand and predict stream water quality in accordance with different urban development patterns to effectively advise urban growth planning and policies. To do so, we collected pollutant concentration data on nitrate (NO₃^--N), total phosphate (TP), and Escherichia coli (E. coli) from 1047 sampling stations in the Texas Gulf Region. We utilized a Random Forest (RF) machine learning model to predict stream water quality under four planning scenarios with different urban densities and configurations. SHapley Additive exPlanations (SHAP) was used to prove the importance of urban development pattern in influencing stream water quality. The spatial variations of the impact of these patterns were explored with Geographically Weighted Regression (GWR). SHAP results indicated that Largest Patch Index (LPI), Patch Cohesion Index (COHESION), Splitting Index (SPLIT), and Landscape Division Index (DIVISION) were the most important urban development pattern metrics affecting stream water quality. The spatial variations of such patterns were shown to impact stream water quality depending on pollutants, seasonality, climate, and urbanization level. RF prediction results suggested that high density aggregated development was more effective in reducing TP and NO₃^--N concentrations than the current sprawl development, but had the potential risk of increasing E. coli pollution in the wet season. The results of this study provide empirical evidence and a potential mechanistic explanation that stream water quality degradation is a consequence of urban sprawl. Lastly, machine learning is a powerful tool for scenario prediction in land use planning to forecast environmental impacts under different urban development pattern scenarios.

Application of attached algae flow-ways for coupling biomass production with the utilization of dilute non-point source nutrients in the Upper Laguna Madre, TX

The purpose of this study is to determine the potential for an attached algae flow-way system to efficiently produce algal biomass in estuarine surface waters by utilizing dilute non-point source nutrients from local urban, industrial, and agricultural discharges into the Upper Laguna Madre, Corpus Christi, Texas. The study was conducted over the course of two years to establish seasonal base-line biomass productivity and composition for bioproducts applications, and to identify key environmental factors and flow-way cohorts impacting biomass production. For the entire cultivation period, continuous ash-free biomass production at 4 to 10 g/m²/day (corresponding to nutrient recovery at 300 to 500 mg of nitrogen/m²/day and 15 to 30 mg of phosphorus/m²/day) was successfully achieved without system restart. Upon start-up, a latency period was observed which indicates roles for species succession from relatively low productivity, high ash content pioneer periphytic culture composed primarily of benthic diatoms from the source waters to higher productivity, reduced ash content, and more resilient culture mainly composed of filamentous chlorophyta, Ulva lactuca. Principal Component Analysis (PCA) was used to identify environmental factors driving biomass production, and machine learning (ML) models were constructed to assess the predictive capability of the data set for system performance using the local multi-season environmental variations. Environmental datasets were segregated for ML training, validation, and testing using three methods: regression tree, ensemble regression, and Gaussian process regression (GPR). The predicted ash-free biomass productivity using ML models resulted in root-squared-mean-errors (RSME) from 1.78 to 1.86 g/m²/day, and R² values from 0.67 to 0.75 using different methods. The greatest contributor to net productivity was total solar irradiation, followed by air temperature, salinity, and pH. The results of the study should be useful as a decision-making tool to application of attached algae flow-ways for biomass production while preventing algal blooms in the environment.

Approach based on TOPSIS and Monte Carlo simulation methods to evaluate lake eutrophication levels

This study presents an approach for eutrophication evaluation based on the technique for order preference by similarity to an ideal solution (TOPSIS) method and Monte Carlo simulation (MCS). The MCS is employed to produce a normally distributed dataset based on the observed data while the TOPSIS method and membership function are used to evaluate the level of eutrophication. Herein, a eutrophication problem in Lake Erhai is evaluated to check the performance of the proposed approach. The evaluation results were consistent with the real situation when the coefficient P in the membership function is equal to 1. Moreover, the developed approach is able to (i) deal with evaluation items with inherent fuzziness and uncertainties, (ii) improve the reliability of evaluation results via MCS, and (iii) raise the tolerance to errors in measured data. A global sensitivity analysis indicated that the potassium permanganate index (COD_Mn) and Secchi disc (SD) are the most sensitive factors in the developed approach. Finally, a range for the coefficient P value in the membership function was recommended.

Estimation of nitrogen and phosphorus concentrations from water quality surrogates using machine learning in the Tri An Reservoir, Vietnam

Surface water eutrophication due to excessive nutrients has become a major environmental problem around the world in the past few decades. Among these nutrients, nitrogen and phosphorus are two of the most important harmful cyanobacterial bloom (HCB) drivers. A reliable prediction of these parameters, therefore, is necessary for the management of rivers, lakes, and reservoirs. The aim of this study is to test the suitability of the powerful machine learning (ML) algorithm, random forest (RF), to provide information on water quality parameters for the Tri An Reservoir (TAR). Three species of nitrogen and phosphorus, including nitrite (N-NO₂^-), nitrate (N-NO₃^-), and phosphate (P-PO₄^3-), were empirically estimated using the field observation dataset (2009-2014) of six surrogates of total suspended solids (TSS), total dissolved solids (TDS), turbidity, electrical conductivity (EC), chemical oxygen demand (COD), and biochemical oxygen demand (BOD₅). Field data measurement showed that water quality in the TAR was eutrophic with an up-trend of N-NO₃^- and P-PO₄^3- during the study period. The RF regression model was reliable for N-NO₂^-, N-NO₃^-, and P-PO₄^3- prediction with a high R² of 0.812-0.844 for the training phase (2009-2012) and 0.888-0.903 for the validation phase (2013-2014). The results of land use and land cover change (LUCC) revealed that deforestation and shifting agriculture in the upper region of the basin were the major factors increasing nutrient loading in the TAR. Among the meteorological parameters, rainfall pattern was found to be one of the most influential factors in eutrophication, followed by average sunshine hour. Our results are expected to provide an advanced assessment tool for predicting nutrient loading and for giving an early warning of HCB in the TAR.

Developing Sensor Proxies for “Chemical Cocktails” of Trace Metals in Urban Streams

Understanding transport mechanisms and temporal patterns in the context of metal concentrations in urban streams is important for developing best management practices and restoration strategies to improve water quality. In some cases, in-situ sensors can be used to estimate unknown concentrations of trace metals or to interpolate between sampling events. Continuous sensor data from the United States Geological Survey were analyzed to determine statistically significant relationships between lead, copper, zinc, cadmium, and mercury with turbidity, specific conductance, dissolved oxygen, and discharge for the Hickey Run, Watts Branch, and Rock Creek watersheds in the Washington, D.C. region. We observed a significant negative linear relationship between concentrations of Cu and dissolved oxygen at Rock Creek (p < 0.05). Sometimes, turbidity had significant positive linear relationships with Pb and Hg concentrations. There were negative or positive linear relationships between Pb, Cd, Zn, and Hg and specific conductance. There also appeared to be relationships between watershed areal fluxes of Pb, Cu, Zn, and Cd in streams with turbidity. Watershed monitoring approaches using continuous sensor data have the potential to characterize the frequency, magnitude, and composition of pulses in concentrations and loads of trace metals, which could improve the management and restoration of urban streams.

Evaluation of water quality in the South-to-North Water Diversion Project of China using the water quality index (WQI) method

The world's longest trans-basin water diversion project, the Middle-Route (MR) of the South-to-North Water Diversion Project of China (SNWDPC), has officially been in operation for over 5 years since December 2014. Its water quality status has always attracted special attention because it is related to the health and safety of more than 58 million people and the integrity of an ecosystem covering more than 155,000 km². This study presented and analysed the spatio-temporal variations and trends of 16 water quality parameters, including pH, water temperature (WT), dissolved oxygen (DO), permanganate index (PI), five-day biochemical oxygen demand (BOD₅), fecal coliform (F. coli), total phosphorus (TP), total nitrogen (TN), ammonia nitrogen (NH₃^-N), sulphate (SO₄^2-), fluoride (F^-), mercury (Hg), arsenic (As), selenium (Se), copper (Cu), and zinc (Zn), which were determined monthly from samples collected at 27 water quality monitoring stations in the MR of the SNWDPC from March 2016 to February 2019. The water quality index (WQI) was used to evaluate the seasonal and spatial water quality changes during the monitoring period, and a new WQI_min model consisting of five crucial parameters, i.e., TP, F. coli, Hg, WT, and DO, was built by using stepwise multiple linear regression analysis. The results demonstrated that the water quality status of the MR of the SNWDPC has been steadily maintained at an "excellent" level during the monitoring period, with an overall average WQI value of 90.39 and twelve seasonal mean WQI values ranging from 87.67 to 91.82. The proposed WQI_min model that uses the selected five key parameters and the weights of those parameters has exhibited excellent performance in the water quality assessment of the project, with the coefficient of determination (R²), Root Mean Square Error (RMSE), and Percentage Error (PE) values of 0.901, 2.21, 1.93%, respectively, showing that the proposed WQI_min model is a useful and efficient tool to evaluate and manage the water quality. For the management department, the risk sources near certain stations with abnormally high values should be carefully inspected and strictly managed to maintain excellent water quality. The potential risks of algae proliferation in this project should be of concern in future research.