Modeling water quality in an urban river using hydrological factors--data driven approaches

A comparative study of data-driven models for runoff, sediment, and nitrate forecasting

Effective prediction of qualitative and quantitative indicators for runoff is quite essential in water resources planning and management. However, although several data-driven and model-driven forecasting approaches have been employed in the literature for streamflow forecasting, to our knowledge, the literature lacks a comprehensive comparison of well-known data-driven and model-driven forecasting techniques for runoff evaluation in terms of quality and quantity. This study filled this knowledge gap by comparing the accuracy of runoff, sediment, and nitrate forecasting using four robust data-driven techniques: artificial neural network (ANN), long short-term memory (LSTM), wavelet artificial neural network (WANN), and wavelet long short-term memory (WLSTM) models. These comparisons were performed in two main tiers: (1) Comparing the machine learning algorithms' results with the model-driven approach; In order to simulate the runoff, sediment, and nitrate loads, the Soil and Water Assessment Tool (SWAT) model was employed, and (2) Comparing the machine learning algorithms with each other; The wavelet function was utilized in the ANN and LSTM algorithms. These comparisons were assessed based on the substantial statistical indices of coefficient of determination (R-Squared), Nash-Sutcliff efficiency coefficient (NSE), mean absolute error (MAE), and root mean square error (RMSE). Finally, to prove the applicability and efficiency of the proposed novel framework, it was successfully applied to Eagle Creek Watershed (ECW), Indiana, U.S. Results demonstrated that the data-driven algorithms significantly outperformed the model-driven models for both the calibration/training and validation/testing phases. Furthermore, it was found that the coupled ANN and LSTM models with wavelet function led to more accurate results than those without this function.

Source, fate, transport and modelling of selected emerging contaminants in the aquatic environment: Current status and future perspectives

The occurrence of emerging contaminants (ECs), such as pharmaceuticals and personal care products (PPCPs), perfluoroalkyl and polyfluoroalkyl substances (PFASs) and endocrine-disrupting chemicals (EDCs) in aquatic environments represent a major threat to water resources due to their potential risks to the ecosystem and humans even at trace levels. Mathematical modelling can be a useful tool as a comprehensive approach to study their fate and transport in natural waters. However, modelling studies of the occurrence, fate and transport of ECs in aquatic environments have generally received far less attention than the more widespread field and laboratory studies. In this study, we reviewed the current status of modelling ECs based on selected representative ECs, including their sources, fate and various mechanisms as well as their interactions with the surrounding environments in aquatic ecosystems, and explore future development and perspectives in this area. Most importantly, the principles, mathematical derivations, ongoing development and applications of various ECs models in different geographical regions are critically reviewed and discussed. The recommendations for improving data quality, monitoring planning, model development and applications were also suggested. The outcomes of this review can lay down a future framework in developing a comprehensive ECs modelling approach to help researchers and policymakers effectively manage water resources impacted by rising levels of ECs.

Advancing prediction of emerging contaminants in a tropical reservoir with general water quality indicators based on a hybrid process and data-driven approach

Monitoring and predicting the occurrence and dynamic distributions of emerging contaminants (ECs) in the aquatic environment has always been a great challenge. This study aims to explore the potential of fully utilizing the advantages of combining traditional process-based models (PBMs) and data-driven models (DDMs) with general water quality indicators in terms of improving the accuracy and efficiency of predicting ECs in aquatic ecosystems. Two representative ECs, namely Bisphenol A (BPA) and N, N-diethyltoluamide (DEET), in a tropical reservoir were chosen for this study. A total of 36 DDMs based on different input datasets using Artificial Neural Networks (ANN) and Random Forests (RF) were examined in three case studies. The models were applied in prognosis validation based on easily accessible data on water quality indicators. Our results revealed that all the models yielded good fits when compared to the observed data. These new insights into the advantages using the combination of traditional PBMs and DDMs with general water quality datasets help to overcome the constraints in terms of model accuracy and efficiency as well as technical and budget limitations due to monitoring surveys and laboratory experiments in the study of fate and transport of ECs in aquatic environments.

An improved adaptive neuro fuzzy inference system model using conjoined metaheuristic algorithms for electrical conductivity prediction

Precise prediction of water quality parameters plays a significant role in making an early alert of water pollution and making better decisions for the management of water resources. As one of the influential indicative parameters, electrical conductivity (EC) has a crucial role in calculating the proportion of mineralization. In this study, the integration of an adaptive hybrid of differential evolution and particle swarm optimization (A-DEPSO) with adaptive neuro fuzzy inference system (ANFIS) model is adopted for EC prediction. The A-DEPSO method uses unique mutation and crossover processes to correspondingly boost global and local search mechanisms. It also uses a refreshing operator to prevent the solution from being caught inside the local optimal solutions. This study uses A-DEPSO optimizer for ANFIS training phase to eliminate defects and predict accurately the EC water quality parameter every month at the Maroon River in the southwest of Iran. Accordingly, the recorded dataset originated from the Tange-Takab station from 1980 to 2016 was operated to develop the ANFIS-A-DEPSO model. Besides, the wavelet analysis was jointed to the proposed algorithm in which the original time series of EC was disintegrated into the sub-time series through two mother wavelets to boost the prediction certainty. In the following, the comparison between statistical metrics of the standalone ANFIS, least-square support vector machine (LSSVM), multivariate adaptive regression spline (MARS), generalized regression neural network (GRNN), wavelet-LSSVM (WLSSVM), wavelet-MARS (W-MARS), wavelet-ANFIS (W-ANFIS) and wavelet-GRNN (W-GRNN) models was implemented. As a result, it was apparent that not only was the W-ANFIS-A-DEPSO model able to rise remarkably the EC prediction certainty, but W-ANFIS-A-DEPSO (R = 0.988, RMSE = 53.841, and PI = 0.485) also had the edge over other models with Dmey mother in terms of EC prediction. Moreover, the W-ANFIS-A-DEPSO can improve the RMSE compared to the standalone ANFIS-DEPSO model, accounting for 80%. Hence, this model can create a closer approximation of EC value through W-ANFIS-A-DEPSO model, which is likely to act as a promising procedure to simulate the prediction of EC data.

Remote Sensing Inversion of Suspended Matter Concentration Using a Neural Network Model Optimized by the Partial Least Squares and Particle Swarm Optimization Algorithms

Suspended matter concentration is an important index for the assessment of a water environment and it is also one of the core parameters for remote sensing inversion of water color. Due to the optical complexity of a water body and the interaction between different water quality parameters, the remote sensing inversion accuracy of suspended matter concentration is currently limited. To solve this problem, based on the remote sensing images from Gaofen-2 (GF-2) and the field-measured suspended matter concentration, taking a section of the Haihe River as the study area, this study establishes a remote sensing inversion model. The model combines the partial least squares (PLS) algorithm and the particle swarm optimization (PSO) algorithm to optimize the back-propagation neural network (BPNN) model, i.e., the PLS-PSO-BPNN model. The partial least squares algorithm is involved in screening the input values of the neural network model. The particle swarm optimization algorithm optimizes the weights and thresholds of the neural network model and it thus effectively overcomes the over-fitting of the neural network. The inversion accuracy of the optimized neural network model is compared with that of the partial least squares model and the traditional neural network model by determining the coefficient, the mean absolute error, the root mean square error, the correlation coefficient and the relative root mean square error. The results indicate that the root mean squared error of the PLS-PSO-BPNN inversion model was 3.05 mg/L, which is higher than the accuracy of the statistical regression model. The developed PLS-PSO-BPNN model could be widely applied in other areas to better invert the water quality parameters of surface water.

Dissolved oxygen modelling of the Yamuna River using different ANFIS models

Dissolved oxygen (DO) is one of the prime parameters for assessing the water quality of any stream. Thus, the accurate estimation of DO is necessary to evolve measures for maintaining the riverine ecosystem and designing appropriate water quality improvement plans. Machine learning techniques are becoming valuable tools for the prediction and simulation of water quality parameters. A study has been performed in the Delhi stretch of the Yamuna River, India, and physiochemical parameters were examined for 5 years to simulate the DO using various machine learning techniques. Simulation and prediction competencies of adaptive neuro fuzzy inference system-grid partitioning (ANFIS-GP) and subtractive clustering (ANFIS-SC) were performed on high dimensional river characteristics. Four different models (M1, M2, M3 and M4) were developed using different combination of input parameters to predict DO. Results obtained from the models were evaluated using root mean square error and coefficient of determination (R²) to identify the appropriate combination of parameters to simulate the DO. Results suggest that both types of ANFIS models work adequately and accurately predict the DO; however, ANFIS-GP outperforms the ANFIS-SC. M4 generated R² of 0.953 from ANFIS-GP compared to 0.911 from ANFIS-SC.

Water Quality Assessment and Potential Source Contribution Using Multivariate Statistical Techniques in Jinwi River Watershed, South Korea

To investigate the effects of rapid urbanization on water pollution, the water quality, daily unit area pollutant load, water quality score, and real-time water quality index for the Jinwi River watershed were assessed. The contribution of known pollution sources was identified using multivariate statistical analysis and absolute principal component score-multiple linear regression. The water quality data were collected during the dry and wet seasons to compare the pollution characteristics with varying precipitation levels and flow rates. The highest level of urbanization is present in the upstream areas of the Hwangguji and Osan Streams. Most of the water quality parameter values were the highest in the downstream areas after the polluted rivers merged. The results showed a dilution effect with a lower pollution level in the wet season. Conversely, the daily unit area pollutant load was higher in the rainy season, indicating that the pollutants increased as the flow rate increased. A cluster analysis identified that the downstream water quality parameters are quite different from the upstream values. Upstream is an urban area with relatively high organic matter and nutrient loads. The upstream sewage treatment facilities were the main pollution sources. This study provides basic data for policymakers in urban water quality management.

Extent of detection of hidden relationships among different hydrological variables during floods using data-driven models

Understanding of flood dynamics forms the basis for the leading water resource management and flood risk mitigation practices. In particular, accurate prediction of river flow during massive flood events and capturing the hysteretic behavior of river stage-discharge are among the key interests in hydrological research. The literature demonstrates that data-driven models are significant in identifying complex and hidden relationships among dependent variables, without considering explicit physical schemes. In this regard, we aim to discover the extent to which data-driven models can recognize the hidden relationships among different hydrological variables, in order to generate accurate predictions of the river flow. A secondary aim involves the detection of whether data-driven models can digest the internal features of training inputs to extrapolate severe flood records beyond the training domain. To achieve these aims, we developed a recurrent neural network (RNN) model of two hidden layers to capture the hidden relationships among the inputs, and investigated the model's predictive capability using quantitative and qualitative analyses. The quantitative analysis comprised of a comparison between model predictions, and another set of precise independent records obtained through an advanced hydroacoustic system for reference. A qualitative approach was adopted to visualize the hysteretic behavior of the stage-discharge relations of the model records, with the high-resolution records of the hydroacoustic system. The findings display the potential of data-driven models for accurately predicting river flow. Consequently, the qualitative analysis revealed moderate correlations of stage-discharge loops as compared to the reference records. Additionally, the model was tested against severe destructive flood records generated from the East Asian monsoon and tropical cyclones. Its findings suggest that data-driven models cannot extrapolate new features beyond their training dataset. Overall, this study discusses the competence of RNNs in providing reliable and accurate river flow predictions during floods.

A study on water quality prediction by a hybrid CNN-LSTM model with attention mechanism

The water environment plays an essential role in the mangrove wetland ecosystem. Predicting water quality will help us better protect water resources from pollution, allowing the mangrove ecosystem to perform its normal ecological role. New approaches to solve such nonlinear problems need further research since the complexity of water quality data and they are easily affected by the noise. In this paper, we propose a water quality prediction model named CNN-LSTM with Attention (CLA) to predict the water quality variables. We conduct a case study on the water quality dataset of Beilun Estuary to predict pH and NH₃-N. Linear interpolation and wavelet techniques are used for missing data filling and data denoising, respectively. The hybrid model CNN-LSTM is highly capable of resolving nonlinear time series prediction problems, and the attention mechanism captures longer time dependence. The experimental results show that our model outperforms other ones, and can predict with different time lags in a stable manner.

Modelling Freshwater Eutrophication with Limited Limnological Data Using Artificial Neural Networks

Artificial Neural Networks (ANNs) have wide applications in aquatic ecology and specifically in modelling water quality and biotic responses to environmental predictors. However, data scarcity is a common problem that raises the need to optimize modelling approaches to overcome data limitations. With this paper, we investigate the optimal k-fold cross validation in building an ANN using a small water-quality data set. The ANN was created to model the chlorophyll-a levels of a shallow eutrophic lake (Mikri Prespa) located in N. Greece. The typical water quality parameters serving as the ANN’s inputs are pH, dissolved oxygen, water temperature, phosphorus, nitrogen, electric conductivity, and Secchi disk depth. The available data set was small, containing only 89 data samples. For that reason, k-fold cross validation was used for training the ANN. To find the optimal k value for the k-fold cross validation, several values of k were tested (ranging from 3 to 30). Additionally, the leave-one-out (LOO) cross validation, which is an extreme case of the k-fold cross validation, was also applied. The ANN’s performance indices showed a clear trend to be improved as the k number was increased, while the best results were calculated for the LOO cross validation as expected. The computational times were calculated for each k value, where it was found the computational time is relatively low when applying the more expensive LOO cross validation; therefore, the LOO is recommended. Finally, a sensitivity analysis was examined using the ANN to investigate the interactions of the input parameters with the Chlorophyll-a, and hence examining the potential use of the ANN as a water management tool for nutrient control.

Explore spatio-temporal PM2.5 features in northern Taiwan using machine learning techniques

The complex mixtures of local emission sources and regional transportations of air pollutants make accurate PM2.5 prediction a very challenging yet crucial task, especially under high pollution conditions. A symbolic representation of spatio-temporal PM2.5 features is the key to effective air pollution regulatory plans that notify the public to take necessary precautions against air pollution. The self-organizing map (SOM) can cluster high-dimensional datasets to form a meaningful topological map. This study implements the SOM to effectively extract and clearly distinguish the spatio-temporal features of long-term regional PM2.5 concentrations in a visible two-dimensional topological map. The spatial distribution of the configured topological map spans the long-term datasets of 25 monitoring stations in northern Taiwan using the Kriging method, and the temporal behavior of PM2.5 concentrations at various time scales (i.e., yearly, seasonal, and hourly) are explored in detail. Finally, we establish a machine learning model to predict PM2.5 concentrations for high pollution events. The analytical results indicate that: (1) high population density and heavy traffic load correspond to high PM2.5 concentrations; (2) the change of seasons brings obvious effects on PM2.5 concentration variation; and (3) the key input variables of the prediction model identified by the Gamma Test can improve model's reliability and accuracy for multi-step-ahead PM2.5 prediction. The results demonstrated that machine learning techniques can skillfully summarize and visibly present the clusted spatio-temporal PM2.5 features as well as improve air quality prediction accuracy.

Explore the relationship between fish community and environmental factors by machine learning techniques

In the face of multiple habitat alterations originating from both natural and anthropogenic factors, the fast-changing environments pose significant challenges for maintaining ecosystem integrity. Machine learning is a powerful tool for modeling complex non-linear systems through exploratory data analysis. This study aims at exploring a machine learning-based approach to relate environmental factors with fish community for achieving sustainable riverine ecosystem management. A large number of datasets upon a wide variety of eco-environmental variables including river flow, water quality, and species composition were collected at various monitoring stations along the Xindian River of Taiwan during 2005 and 2012. Then the complicated relationship and scientific essences of these heterogonous datasets are extracted using machine learning techniques to have a more holistic consideration in searching a guiding reference useful for maintaining river-ecosystem integrity. We evaluate and select critical environmental variables by the analysis of variance (ANOVA) and the Gamma test (GT), and then we apply the adaptive network-based fuzzy inference system (ANFIS) for an estimation of fish bio-diversity using the Shannon Index (SI). The results show that the correlation between model estimation and the biodiversity index is higher than 0.75. The GT results demonstrate that biochemical oxygen demand (BOD), water temperature, total phosphorus (TP), and nitrate-nitrogen (NO₃-N) are important variables for biodiversity modeling. The ANFIS results further indicate lower BOD, higher TP, and larger habitat (flow regimes) would generally provide a more suitable environment for the survival of fish species. The proposed methodology not only possesses a robust estimation capacity but also can explore the impacts of environmental variables on fish biodiversity. This study also demonstrates that machine learning is a promising avenue toward sustainable environmental management in river-ecosystem integrity.

Effects of industry structures on water quality in different urbanized regions using an improved entropy-weighted matter-elementmethodology

Urbanization and industrialization significantly impact water quality, and detecting the specific factors which influence water quality change would greatly improve urban water environment management. In this study, an improved entropy-weighted matter-element method is used to assess the variations of water quality in two regions with different levels of urbanization in the Yangtze River Delta. Redundancy analysis was used to detect the effects of different industries on water quality. Results show that (1) an improved entropy weight-based matter-element method measures weights of pollutants and water quality levels more reliably and accurately; (2) the improvement rate of water quality in highly urbanized regions is 42.9% during 2005-2014 which is 17.2% higher than that in regions with low urbanization; (3) a decreasing concentration of total phosphorus is the main reason for changes of water quality in both regions, with decreasing concentrations of permanganate index and ammonium nitrogen having a strong influence on changes of water quality in the highly urbanized regions; (4) the decreasing proportion of fishery and heavy industries and the increasing proportion of the tertiary industries significantly influence water quality in highly urbanized regions while the decreasing proportion of animal husbandry is the most important factor influencing the changes of water quality in lowly urbanized regions.

The Applicability of LSTM-KNN Model for Real-Time Flood Forecasting in Different Climate Zones in China

Flow forecasting is an essential topic for flood prevention and mitigation. This study utilizes a data-driven approach, the Long Short-Term Memory neural network (LSTM), to simulate rainfall–runoff relationships for catchments with different climate conditions. The LSTM method presented was tested in three catchments with distinct climate zones in China. The recurrent neural network (RNN) was adopted for comparison to verify the superiority of the LSTM model in terms of time series prediction problems. The results of LSTM were also compared with a widely used process-based model, the Xinanjiang model (XAJ), as a benchmark to test the applicability of this novel method. The results suggest that LSTM could provide comparable quality predictions as the XAJ model and can be considered an efficient hydrology modeling approach. A real-time forecasting approach coupled with the k-nearest neighbor (KNN) algorithm as an updating method was proposed in this study to generalize the plausibility of the LSTM method for flood forecasting in a decision support system. We compared the simulation results of the LSTM and the LSTM-KNN model, which demonstrated the effectiveness of the LSTM-KNN model in the study areas and underscored the potential of the proposed model for real-time flood forecasting.

Mapping Water Quality Parameters in Urban Rivers from Hyperspectral Images Using a New Self-Adapting Selection of Multiple Artificial Neural Networks

Protection of water environments is an important part of overall environmental protection; hence, many people devote their efforts to monitoring and improving water quality. In this study, a self-adapting selection method of multiple artificial neural networks (ANNs) using hyperspectral remote sensing and ground-measured water quality data is proposed to quantitatively predict water quality parameters, including phosphorus, nitrogen, biochemical oxygen demand (BOD), chemical oxygen demand (COD), and chlorophyll a. Seventy-nine ground measured data samples are used as training data in the establishment of the proposed model, and 30 samples are used as testing data. The proposed method based on traditional ANNs of numerical prediction involves feature selection of bands, self-adapting selection based on multiple selection criteria, stepwise backtracking, and combined weighted correlation. Water quality parameters are estimated with coefficient of determination R 2 ranging from 0.93 (phosphorus) to 0.98 (nitrogen), which is higher than the value (0.7 to 0.8) obtained by traditional ANNs. MPAE (mean percent of absolute error) values ranging from 5% to 11% are used rather than root mean square error to evaluate the predicting precision of the proposed model because the magnitude of each water quality parameter considerably differs, thereby providing reasonable and interpretable results. Compared with other ANNs with backpropagation, this study proposes an auto-adapting method assisted by the above-mentioned methods to select the best model with all settings, such as the number of hidden layers, number of neurons in each hidden layer, choice of optimizer, and activation function. Different settings for ANNS with backpropagation are important to improve precision and compatibility for different data. Furthermore, the proposed method is applied to hyperspectral remote sensing images collected using an unmanned aerial vehicle for monitoring the water quality in the Shiqi River, Zhongshan City, Guangdong Province, China. Obtained results indicate the locations of pollution sources.

Water demand modelling using evolutionary computation techniques: integrating water equity and justice for realization of the sustainable development goals

The purpose of this review is to establish and classify the diverse ways in which evolutionary computation (EC) techniques have been employed in water demand modelling and to identify important research challenges and future directions. This review also investigates the potentials of conventional EC techniques in influencing water demand management policies beyond an advisory role while recommending strategies for their use by policy-makers with the sustainable development goals (SDGs) in perspective. This review ultimately proposes a novel integrated water demand and management modelling framework (IWDMMF) that enables water policy-makers to assess the wider impact of water demand management decisions through the principles of egalitarianism, utilitarianism, libertarianism and sufficientarianism. This is necessary to ensure that water policy decisions incorporate equity and justice.

The Influence of Channel Morphological Changes on Environmental Flow Requirements in Urban Rivers

Previous research on environmental flows (e-flows) of urban rivers usually assumes that the channel morphology is fixed. However, due to the trapping of sediments by weirs, the channel morphology will undergo significant changes. In this research, the influence of channel morphological changes on e-flow requirements is explored in urban rivers. The hydrological connectivity is considered as a primary factor in e-flows, and three hydrological connectivity scenarios (i.e., high, medium, and low) are explored. The Shiwuli River is adopted as the case study. The results show that e-flows are significantly influenced by changes in river morphology. With an increase in siltation depth, the e-flow requirements will decrease. The sensitivity of e-flows to siltation varies among different river segments, especially in those with low weir heights. In addition, the change ratios of e-flows are different under different hydrological connectivity scenarios. Although siltation is beneficial to the satisfaction degree of e-flow supply, it also leads to a decrease in the flood control ability of rivers. The balance between e-flow and flood reduction is also discussed, and river segments are identified that should be the priority when adopting dredging measures.

Water quality modelling under unsteady state analysis: Strategies for planning and management

Recent water resources planning and management strategies state that the concepts of risk and variable inputs should be appraised in order to comply with multiple conditions. This becomes evident especially in environments with diverse uses of water, land use and climate change. In such a context, modelling of discharges and concentrations in rivers are valuable strategies to predict different scenarios. This research proposes an integrated analysis for modelling of flow and contaminant transport in rivers, based on hydrodynamics, time series, and water quality simulations. The first module estimates water volume and velocity, that have direct impact in pollutants transport; time series of concentrations are generated as synthetic pollutographs, using techniques based on flow conditions, time and statistical factors of a historical monitoring dataset - the objective is to match temporal scales of boundary conditions, since water quality data is usually available as irregular samples; the third module solves the advection-dispersion-reaction equation, exploring the different synthetic series as input. Results evidence that the input pollutograph, usually not explored in similar studies, may have a significant role in simulations for transport of substance in rivers under unsteady state; as consequence, corroborate with better estimates for planning strategies where temporal dynamic is relevant. The contributions lay the basis for further assessment of riverine systems linked to watershed dynamics, with multiple scenarios of data availability and input conditions.

Trend analysis and modeling of nutrient concentrations in a preliminary eutrophic lake in China

Accurately measuring and estimating trends and variations in nutrient levels is a significant part of managing emerging eutrophic lakes in developing countries. This study developed an integrated approach containing Seasonal Trend Decomposition using Loess (STL) and a dynamic nonlinear autoregressive model with exogenous input (NARX) network to decompose and estimate the nutrient concentrations in Lake Erhai, a preliminary eutrophic lake in China. The STL decomposition results indicated that total nitrogen (TN) concentration of Lake Erhai progressively descended from 2006 to 2014, except for some agriculture area. The total phosphorus (TP) concentration showed an increasing trend from 2006 to 2013 and then decreased in 2014, but in the area near the tourist attractions, TP increased continuously from 2011 to 2014. Seasonal variations in TN and TP indicated that the lowest water quality of Lake Erhai occurred from July to October. Based on results obtained with STL, TP was selected as the sensitive parameter, as it showed a significant deterioration trend, and the area near the tourist attractions was selected as the sensitive area. Three variables (DO, pH, and water temperature) were selected as input parameters to estimate TP using the dynamic NARX model. The NARX modeling results demonstrated that it can accurately estimate TP concentrations with low root-mean-square error (0.0071 mg/L). The study establishes a new approach to better understand trends and variations in nutrient levels and to better refine estimates by identifying more easily accessible physical parameters in a preliminary eutrophic lake.

Hydrodynamic and water quality modeling of a large floodplain lake (Poyang Lake) in China

Floodplain lakes are valuable to humans because of their various functions and are characterized by dramatic hydrological condition variations. In this study, a two-dimensional coupled hydrodynamic and water quality model was applied in a large floodplain lake (i.e., Poyang Lake), to investigate spatial and temporal water quality variations. The model was established based on detailed data such as lake terrain, hydrological, and water quality. Observed lake water level and discharge and water quality parameters (TN, TP, COD_Mn, and NH₄-N) were used to assess model performance. The hydrodynamic model results showed satisfactory results with R² and MRE values ranging between 0.96 and 0.99 and between 2.45 and 6.14%, respectively, for lake water level simulations. The water quality model basically captured the temporal variations in water quality parameters with R² of TN, TP, COD_Mn, and NH₄-N simulation ranges of 0.56-0.91, 0.44-0.66, 0.64-0.67, and 0.44-0.57, respectively, with TP of Xingzi Station and COD_Mn of Duchang Station excluded, which may be further optimized with supplementation of sewage and industrial discharge data. The modeled average TN, TP, COD_Mn, and NH₄-N concentrations across the lake were 1.36, 0.05, 1.99, and 0.48 mg/L, respectively. The modeled spatial variations of the lake showed that the main channel of the lake acted as a main pollutant passageway, and the east part of the lake suffered high level of pollution. In addition, consistent with previous water quality evaluations based on field investigations, water quality was the highest (average TN = 1.35 mg/L) during high water level periods and the poorest (average TN = 1.96 mg/L) during low water level periods. Scenario analysis showed that by decreasing discharge of upstream flow by 20% could result in the increase of TN and TP concentrations by 25.6% and 23.2% respectively. In summary, the model successfully reproduced the complex water and pollutant exchange processes in the systems involving upstream rivers, the Poyang Lake, and the Yangtze River. The model is beneficial for future modeling of the impact of different load reduction and other hydrological regime changes on water quality variation and provides a relevant example for floodplain lake management.

Applications of Recurrent Neural Networks in Environmental Factor Forecasting: A Review

Analysis and forecasting of sequential data, key problems in various domains of engineering and science, have attracted the attention of many researchers from different communities. When predicting the future probability of events using time series, recurrent neural networks (RNNs) are an effective tool that have the learning ability of feedforward neural networks and expand their expression ability using dynamic equations. Moreover, RNNs are able to model several computational structures. Researchers have developed various RNNs with different architectures and topologies. To summarize the work of RNNs in forecasting and provide guidelines for modeling and novel applications in future studies, this review focuses on applications of RNNs for time series forecasting in environmental factor forecasting. We present the structure, processing flow, and advantages of RNNs and analyze the applications of various RNNs in time series forecasting. In addition, we discuss limitations and challenges of applications based on RNNs and future research directions. Finally, we summarize applications of RNNs in forecasting.

Assessment of Potentially Toxic Elements as Non-Point Sources of Contamination in the Upper Crocodile Catchment Area, North-West Province, South Africa

The concentration of potential toxic elements (PTEs) in the Upper Crocodile river catchment area in North-west Province, South Africa, was investigated. Water and sediment samples were collected among different land uses in the upper Crocodile River catchment area and analysed using inductively-coupled plasma–mass spectrometry (ICP–MS). Several guidelines were used to gauge the level of contamination and possible toxic effect of PTEs. The physicochemical analysis showed that electrical conductivity (EC), pH, and total dissolved solids (TDS) values complied with the recommended values of Department of Water and Forestry (DWAF) guidelines for South Africa. The average concentration of Cu, Pb, Cd, Zn, As, Cr, Al, and Mn in the water samples were lower than the recommended levels for water-quality guidelines for aquatic environments except for Fe, which exceeded the recommended values of DWAF of 0.1 mg/L and EPA (US) of 0.3 mg/L. The level of contamination was measured using the enrichment factor, contamination factor, and geoaccumulation index. The level of Cr was above the stipulated threshold limit of the sediment quality guideline for adverse biological effects, suggesting an ecotoxicology risk of anthropogenic origin, which was confirmed by statistical analysis. The non-point sources of PTEs are spatially distributed according to land-use types and are strongly correlated to land use.

Water quality assessment with hierarchical cluster analysis based on Mahalanobis distance

Water quality assessment is crucial for assessment of marine eutrophication, prediction of harmful algal blooms, and environment protection. Previous studies have developed many numeric modeling methods and data driven approaches for water quality assessment. The cluster analysis, an approach widely used for grouping data, has also been employed. However, there are complex correlations between water quality variables, which play important roles in water quality assessment but have always been overlooked. In this paper, we analyze correlations between water quality variables and propose an alternative method for water quality assessment with hierarchical cluster analysis based on Mahalanobis distance. Further, we cluster water quality data collected form coastal water of Bohai Sea and North Yellow Sea of China, and apply clustering results to evaluate its water quality. To evaluate the validity, we also cluster the water quality data with cluster analysis based on Euclidean distance, which are widely adopted by previous studies. The results show that our method is more suitable for water quality assessment with many correlated water quality variables. To our knowledge, it is the first attempt to apply Mahalanobis distance for coastal water quality assessment.

Assessing the natural and anthropogenic influences on basin-wide fish species richness

Theory predicts that the number of fish species increases with river size in natural free-flowing rivers, but the relationship is lost under intensive exploitation of water resources associated with dams and/or landscape developments. In this paper, we aim to identify orthomorphic issues that disrupt theoretical species patterns based on a multi-year, basin-wide assessment in the Danshuei River Watershed of Taiwan. We hypothesize that multiple human-induced modifications fragment habitat areas leading to decreases of local fish species richness. We integrally relate natural and anthropogenic influences on fish species richness by a multiple linear regression model that is driven by a combination of factors including river network structure controls, water quality alterations of habitat, and disruption of channel connectivity with major discontinuities in habitat caused by dams. We found that stream order is a major forcing factor representing natural influence on fish species richness. In addition to stream order, we identified dams, dissolved oxygen deficiency (DO), and excessive total phosphorus (TP) as major anthropogenic influences on the richness of fish species. Our results showed that anthropogenic influences were operating at various spatial scales that inherently regulate the physical, chemical, and biological condition of fish habitats. Moreover, our probability-based risk assessment revealed causes of species richness reduction and opportunities for mitigation. Risks of species richness reduction caused by dams were determined by the position of dams and the contribution of tributaries in the drainage network. Risks associated with TP and DO were higher in human-activity-intensified downstream reaches. Our methodology provides a structural framework for assessing changes in basin-wide fish species richness under the mixed natural and human-modified river network and habitat conditions. Based on our analysis results, we recommend that a focus on landscape and riverine habitats and maintaining long-term monitoring programs are crucial for effective watershed management and river conservation plans.