Search

Oxidation of micropollutants (MPs) by ozonation proceeds via the reactions with molecular ozone (O3) and hydroxyl radicals (•OH). To predict MP abatement during ozonation, a model that can accurately predict oxidant exposures (i.e., ∫ 0 t [ O 3 ] d t ⁢ a n d ⁢ ∫ 0 t [ O • H ] d t ) needs to be developed. This study demonstrates machine learning models based on the random forest (RF) algorithm to output oxidant exposures from water quality parameters (input variables) that include pH, alkalinity, dissolved organic carbon concentration, and fluorescence excitation-emission matrix (FEEM) data (to characterize organic matter). To develop the models, 60 different samples of natural waters and wastewater effluents were collected and characterized, and the oxidant exposures in each sample were determined at a specific O3 dose (2.5 mg/L). Four RF models were developed depending on how FEEM data were utilized (i.e., one model free of FEEM data, and three other models that used FEEM data of different resolutions). The regression performance and Akaike information criterion (AIC) were evaluated for each model. The models using high-resolution FEEM data generally exhibited high prediction accuracy with reasonable AIC values, implying that organic matter characteristics quantified by FEEM can be important factors to improve the accuracy of the prediction model. The developed models can be applied to predict the abatement of MPs in drinking water and wastewater ozonation processes and to optimize the O3 dose for the intended removal of target MPs. The machine learning models using higher-resolution FEEM data offer more accurate prediction by better calculating the complex nonlinear relationship between organic characteristics and oxidant exposures.

9 pages, 6 figures, supplementary data https://doi.org/10.1016/j.scitotenv.2021.150866, The impact of inorganic salts and organic matter (OM) on the production of primary marine aerosols is still under debate. To constrain their impact, we investigated primary aerosols generated by a sea-spray generator chamber using surface water samples from rivers, estuaries, and seas that were collected along salinity gradients in two temperate Korean coastal systems and one Arctic coastal system. Salinity values showed an increasing trend along the river–estuary–coastal water transition, indicating the lowest amount of inorganic salts in the river but the highest amount in the sea. In river samples, the lowest number concentration of primary aerosol particles (1.01 × 103 cm−3) was observed at the highest OM content, suggesting that low salinity controls aerosol production. Moreover, the number concentration of primary aerosols increased drastically in estuarine (1.13 × 104 cm−3) and seawater (1.35 × 104 cm−3) samples as the OM content decreased. Our results indicate that inorganic salts associated with increasing salinity play a much larger role than OM in aerosol production in river-dominated coastal systems. Laboratory studies using NaCl solution supported the conclusion that inorganic salt is a critical factor in modulating the particles produced from river water and seawater. Accordingly, this study highlights that inorganic salts are a critical factor in modulating the production of primary marine aerosols, This work was supported by grants from the Korean Government (MSIT) (NRF-2021M1A5A1065425) (KOPRI-PN21011) and from the Korean Government (MSIT) (NRF-2016R1A2B3015388) (KOPRI-PN19100), With the institutional support of the ‘Severo Ochoa Centre of Excellence’ accreditation (CEX2019-000928-S)

In several countries, the public health and fishery industries have suffered from harmful algal blooms (HABs) that have escalated to become a global issue. Though computational modeling offers an effective means to understand and mitigate the adverse effects of HABs, it is challenging to design models that adequately reflect the complexity of HAB dynamics. This paper presents a method involving the application of deep learning to an ocean model for simulating blooms of Alexandrium catenella. The classification and regression convolutional neural network (CNN) models are used for simulating the blooms. The classification CNN determines the bloom initiation while the regression CNN estimates the bloom density. GoogleNet and Resnet 101 are identified as the best structures for the classification and regression CNNs, respectively. The corresponding accuracy and root means square error values are determined as 96.8% and 1.20 [log(cells L–1)], respectively. The results obtained in this study reveal the simulated distribution to follow the Alexandrium catenella bloom. Moreover, Grad-CAM identifies that the salinity and temperature contributed to the initiation of the bloom whereas NH4-N influenced the growth of the bloom.

The presence of micropollutants (MPs), including pharmaceutical, industrial, and pesticidal compounds, threatens both human health and the aquatic ecosystem. The development and extensive use of new chemicals have also inevitably led to the accumulation of MPs in aquatic environments. Recreational beaches are especially vulnerable to contamination, affecting humans and aquatic animals via the absorption of MPs in water during marine activities (e.g., swimming, sailing, and windsurfing). Additionally, marine outfalls in an urbanized coastal city can cause serious chemical and microbial pollution on recreational beaches, leading to an increase in adverse effects on public health and the ecological system. Therefore, the aim of this study was to, with the use of network and decision tree analyses, identify the features and factors that influence the change in MP concentrations in a marine outfall. These analyses were conducted to inspect the relationship between each MP and its hierarchical structure as well as hydrometeorological variables. Additionally, a risk analysis was conducted in this study in which the MPs were prioritized based on their optimized risk quotient values. During our monitoring of MP concentrations over time at the marine outfall, high concentrations of pharmaceutical and industrial compounds were detected when the tide level was low after rainfall. Furthermore, results of the risk analysis and the prioritization revealed that a total of 18 substances identified in our study posed a risk to the ecosystem; these include major ecotoxicologically hazardous substances such as telmisartan, mevinphos, and methiocarb. Results of the network analysis demonstrated distinct trends for pharmaceutical and industrial substances, whilst those for pesticide compounds were irregular. Additionally, the hierarchical structures for most MPs consisted of rainfall, tide level, and antecedent dry hours; this implies that these factors influence MP dynamics. These findings will be helpful for establishing chemical contamination management plans for recreational beaches in the future.

Massive cyanobacterial blooms in river water causes adverse impacts on aquatic ecosystems and water quality. Complex and diverse data sources are available to investigate the cyanobacteria phenomena, including in situ data, synthetic measurements, and remote sensing images. Deep learning attention models can process these intricate sources to forecast cyanobacteria by identifying important variables in the data sources. However, deep learning attention models for predicting cyanobacteria have rarely been studied using an assemblage of various datasets. Thus, in this study, a convolutional neural network (CNN) model with a convolutional block attention module (CNNan) was developed to predict cyanobacterial cell concentrations by using the observed cell data from field monitoring, chlorophyll-a distribution map from hyperspectral image sensing, and simulated water quality outputs from a hydrodynamic model. Then, the prediction performance of the CNNan model was compared to an environmental fluid dynamics code (EFDC) simulation and a CNN model without an attention network. The seasonal variations of the predicted cyanobacteria that was obtained from CNNan showed the best agreement with the observed variations with Nash–Sutcliffe efficiency values higher than 0.76 when compared to the EFDC and CNN predictions. The daily hydrodynamic outputs allowed the prediction of cyanobacteria cells, while the rich information of the chlorophyll-a map contributed to the improvement of the prediction performance at certain periods. Moreover, the attention network visualized the importance of the additional chlorophyll-a map and improved the CNNan model prediction performance by refining the input features. Therefore, this study demonstrated that a deep learning model with data assemblage is practically feasible for predicting the presence of harmful algae in inland water.

Fecal coliform bacteria (FCB) contamination of natural waters is a serious public health issue. Therefore, understanding and anticipating the fate and transport of FCB are important for reducing the risk of contracting diseases. The objective of this study was to analyze the impacts of climate change on the fate and transport of FCB. We modified both the soil and the in-stream bacteria modules in the soil and water assessment tool (SWAT) model and verified the prediction accuracy of seasonal variability of FCB loads using observations. Forty bias-correcting GCM-RCM projections were applied in the modified SWAT model to examine various future climate conditions at the end of this century (2076–2100). Lastly, we also compared the variability of FCB loads under current and future weather conditions using multi-model ensemble simulations (MMES). The modified SWAT model yielded a satisfactory performance with regard to the seasonal variability of FCB amounts in the soil and FCB loading to water bodies. The modified SWAT model presented substantial proliferation of FCB in the soil (30.1%–147.5%) due to an increase in temperature (25.1%). Also, increase in precipitation (53.3%) led to an increase in FCB loads (96.0%–115.5%) from the soil to water body. In the in-stream environment, resuspension from the stream bed was the dominant process affecting the amount of FCB in stream. Therefore, the final FCB loads increased by 71.2% because of the growing peak channel velocity and volume of water used due to an increase in precipitation. Based on the results of MMES, we concluded that the level of FCB would increase simultaneously in the soil as well as in stream by the end of this century. This study will aid in understanding the future variability of FCB loads as well as in preparing an effective management plan for FCB levels in natural waters.

Contamination of surface waters with microbiological pollutants is a major concern to public health. Although long-term and high-frequency Escherichia coli (E. coli) monitoring can help prevent diseases from fecal pathogenic microorganisms, such monitoring is time-consuming and expensive. Process-driven models are an alternative means for estimating concentrations of fecal pathogens. However, process-based modeling still has limitations in improving the model accuracy because of the complexity of relationships among hydrological and environmental variables. With the rise of data availability and computation power, the use of data-driven models is increasing. In this study, we simulated fate and transport of E. coli in a 0.6 km2 tropical headwater catchment located in the Lao People's Democratic Republic (Lao PDR) using a deep-learning model and a process-based model. The deep learning model was built using the long short-term memory (LSTM) methodology, whereas the process-based model was constructed using the Hydrological Simulation Program–FORTRAN (HSPF). First, we calibrated both models for surface as well as for subsurface flow. Then, we simulated the E. coli transport with 6 min time steps with both the HSPF and LSTM models. The LSTM provided accurate results for surface and subsurface flow with 0.51 and 0.64 of the Nash–Sutcliffe efficiency (NSE) values, respectively. In contrast, the NSE values yielded by the HSPF were −0.7 and 0.59 for surface and subsurface flow. The simulated E. coli concentrations from LSTM provided the NSE of 0.35, whereas the HSPF gave an unacceptable performance with an NSE value of −3.01 due to the limitations of HSPF in capturing the dynamics of E. coli with land-use change. The simulated E. coli concentration showed the rise and drop patterns corresponding to annual changes in land use. This study showcases the application of deep-learning-based models as an efficient alternative to process-based models for E. coli fate and transport simulation at the catchment scale.

A case study of CNN, a spatial deep learning model, is presented in this chapter for analyzing water quality with remote sensing data. Airborne remote sensing of cyanobacteria with multispectral/hyperspectral sensors is employed for input data and its water quality as output data.

Recent intensification in climate change have resulted in the rise of hydrological extreme events. This demands modeling of hydrological processes at high temporal resolution to better understand flow patterns in catchments. To model surface and sub-surface flows in a catchment we utilized a physically based model called Hydrological Simulated Program-FORTRAN and two deep learning-based models. One deep learning model consisted of only one long short-term memory (simple LSTM), whereas the other model simulated processes in each hydrological response unit (HRU) by defining one separate LSTM for each HRU (HRU-based LSTM). The models use environmental time-series data and two-dimensional spatial data to predict surface and sub-surface flows at 6-minute time step simultaneously. We tested our models in a tropical humid headwater catchment in northern Lao PDR and compared their performances. Our results showed that the simple LSTM model outperformed the other models on surface runoff prediction with the lowest MSE (7.4e - 5 m(3 )s(-1)), whereas HRU-based LSTM model better predicted patterns and slopes in sub-surface flow in comparison with the other models by having the smallest MSE value (3.2e - 4 m(3 )s(-1)). This study demonstrated the performance of a deep learning model when simulating hydrological cycle with high temporal resolution.

Hydrodynamic and water quality modeling have provided valuable simulation results that have enhanced the understanding of the spatial and temporal distribution of algal blooms. Typical model simulations are performed with point-based observational data that are used to configure initial and boundary conditions, and for parameter calibration. However, the application of such conventional modeling approaches is limited due to cost, labor, and time constraints that preclude the retrieval of high-resolution spatial data. Thus, the present study applied fine-resolution algal data to configure the initial conditions of a hydrodynamic and water quality model and compared the accuracy of short-term algal simulations with the results simulated using conventional point-based initial conditions. The environmental fluid dynamics code (EFDC) model was calibrated to simulate Chlorophyll-a (Chl-a) concentrations. Hyperspectral images were used to generate Chl-a maps based on a two-band ratio algorithm for configuring the initial condition of the EFDC model. The model simulation with hyperspectral-based initial conditions returned relatively accurate results for Chl-a, compared to the simulation based on point-based initial conditions. The simulations exhibited percent bias values of 9.93 and 14.23, respectively. Therefore, the results of this study demonstrate how hyperspectral-based initial conditions could improve the reliability of short-term algal bloom simulations in a hydrodynamic model.

Understanding the dynamics of harmful algal blooms is important to protect the aquatic ecosystem in regulated rivers and secure human health. In this study, artificial neural network (ANN) and support vector machine (SVM) models were used to predict algae alert levels for the early warning of blooms in a freshwater reservoir. Intensive water-quality, hydrodynamic, and meteorological data were used to train and validate both ANN and SVM models. The Latin-hypercube one-factor-at-a-time (LH-OAT) method and a pattern search algorithm were applied to perform sensitivity analyses for the input variables and to optimize the parameters of the models, respectively. The results indicated that the two models well reproduced the algae alert level based on the time-lag input and output data. In particular, the ANN model showed a better performance than the SVM model, displaying a higher performance value in both training and validation steps. Furthermore, a sampling frequency of 6- and 7-day were determined as efficient early-warning intervals for the freshwater reservoir. Therefore, this study presents an effective early-warning prediction method for algae alert level, which can improve the eutrophication management schemes for freshwater reservoirs.

Heavy metal contamination in soil disturbs the chemical, biological, and physical soil conditions and adversely affects the health of living organisms. Visible and near-infrared spectroscopy (VNIRS) shows a potential feasibility for estimating heavy metal elements in soil. Moreover, deep learning models have been shown to successfully deal with complex multi-dimensional and multivariate nonlinear data. Thus, this study implemented a deep learning method on reflectance spectra of soil samples to estimate heavy metal concentrations. A convolutional neural network (CNN) was adopted to estimate arsenic (As), copper (Cu), and lead (Pb) concentrations using measured soil reflectance. In addition, a convolutional autoencoder was utilized as a joint method with the CNN for dimensionality reduction of the reflectance spectra. Furthermore, artificial neural network (ANN) and random forest regression (RFR) models were built for heavy metal estimation. Principal component analysis was utilized for dimensionality reduction of the ANN and RFR models. Among these models, the CNN model with convolutional autoencoder showed the highest accuracies for As, Cu, and Pb estimates, having R2 values of 0.86, 0.74, and 0.82, respectively. The convolutional autoencoder disentangled the relevant features of multiple heavy metal elements and delivered robust features to the CNN model, thereby generating relatively accurate estimates.

Harmful algal blooms have caused critical problems worldwide because they pose serious threats to human health and aquatic ecosystems. In particular, red tide blooms of Cochlodinium polykrikoides have caused serious damage to aquaculture in Korean coastal waters. In this study, multiple linear regression, regression tree (RT), and Random Forest models were applied to detect C. polykrikoides blooms in coastal waters. Five types of input data sets were implemented to test the performance of the models. The observed number of C. polykrikoides cells and reflectance data from Geostationary Ocean Color Imager images obtained in a 3-year period (2013–2015) were used to train and validate the models. The RT model demonstrated the best prediction performance when four bands and three-band ratio data were simultaneously used as input data. The results obtained via iterative model development with randomly chosen input data indicate that the recognition of patterns in the training data caused variations in the prediction performance. This work provides useful tools for reliable estimation of the number of C. polykrikoides cells using reasonable coastal water reflectance data sets. It is expected that administrators and decision-makers whose work is associated with coastal waters will be able to easily access and manipulate the RT model.

Microbial contamination in beach water poses a public health threat due to waterborne diseases. To reduce the risk of exposure to fecal contamination, informing beachgoers in advance about the microbial water quality is important. Currently, determining the level of fecal contamination takes 24 h. The objective of this study is to predict the current level of fecal contamination (enterococcus [ENT] and ) using readily available environmental variables. Artificial neural network (ANN) and support vector regression (SVR) models were constructed using data from the Haeundae and Gwangalli Beaches in Busan City. The input variables included the tidal level, air and water temperature, solar radiation, wind direction and velocity, precipitation, discharge from the wastewater treatment plant, and suspended solid concentration in beach water. The dependence of fecal contamination on the input variables was statistically evaluated; precipitation, discharge from the wastewater treatment plant, and wind direction at the two beaches were positively correlated to the changes in the two bacterial concentrations ( < 0.01), whereas solar radiation was negatively correlated ( < 0.01). The performance of the ANN model for predicting ENT and at Gwangalli Beach was significantly higher than that of the SVR model with the training dataset ( < 0.05). Based on the comparison of residual values between the predicted and observed fecal indicator bacteria concentrations in two models, the ANN demonstrated better performance than SVR. This study suggests an effective prediction method to determine whether a beach is safe for recreational use.

A marine outfall can be a wastewater management system that discharges sewage and stormwater into the sea; hence, it is a source of microbial pollution on recreational beaches, including antibiotic resistant genes (ARGs), which lead to an increase in untreatable diseases. In this regard, a marine outfall must be efficiently located to mitigate these risks. This study aimed to 1) investigate the spatiotemporal variability of Escherichia coli (E. coli) and ARGs on a recreational beach and 2) design marine outfalls to reduce microbial risks. For this purpose, E. coli and ARGs with influential environmental variables were intensively monitored on Gwangalli beach, South Korea in this study. Environmental fluid dynamic code (EFDC) was used and calibrated using the monitoring data, and 12 outfall extension scenarios were explored (6 locations at 2 depths). The results revealed that repositioning the marine outfall can significantly reduce the concentrations of E. coli and ARGs on the beach by 46–99%. Offshore extended outfalls at the bottom of the sea reduced concentrations of E. coli and ARGs on the beach more effectively than onshore outfalls at the sea surface. These findings could be helpful in establishing microbial pollution management plans at recreational beaches in the future.

Practical modeling for assessing the efficiency of a full-scale reverse osmosis (RO) system may be a challenging task. This is because the operating conditions of RO systems can change significantly in actual practice owing to high seasonal variations and different progress of membrane fouling during long-term filtration. Accordingly, it is difficult to reliably model the RO performance if such conditions are excluded. In this study, we model a full-scale installation of a RO membrane system, considering actual operations of the industrial water treatment plant. A numerical model is built to describe spatiotemporal behavior of (water, salt, and foulant) mass transport inside a full-dimension pressure vessel. By performing a global sensitivity analysis, we evaluate the relative importance of key influential factors on model accuracy and specific energy consumption (SEC). The model and its parameters are optimized based on the sensitivity result and validated using best-fitted time-series measurement data of 3875 h. The results demonstrate the practical behaviors of fouling development and separation performance of the primary RO process. A regression tree analysis of SEC for 27 different operational scenarios in simulations may benefit decision making for energy efficient RO. Results reveal the high dependence of SEC on cleaning frequency in the feed temperature range.

The increasing release of nutrients to aquatic environments has led to great concern regarding eutrophication and the risk of unwanted algal blooms. Based on observational data of 20 water quality parameters measured on a monthly basis at 40 stations from 2011 to 2020, this study applied different Machine Learning (ML) algorithms to suggest the best option for algal bloom prediction in the Han River, a large river in South Korea. Eight different ML algorithms were categorized into several groups of statistical learning, regression family, and deep learning, and were then compared for their suitability to predict the chlorophyll-derived trophic index (TSI-Chla). ML algorithms helped identify the most important water quality parameters contributing to algal bloom prediction. The ML results confirmed that eutrophication and algal proliferation were governed by the complex interplay between nutrients (nitrogen and phosphorus), organic contaminants, and environmental factors. Of the models tested, the adaptive neuro-fuzzy inference system (ANFIS) exhibited the best performance owing to its consistent and outperforming prediction both quantitatively (i.e., via regression) and qualitatively (i.e., via classification), which was evidenced by the lowest value of mean absolute error (MAE) of 0.09, and the highest F1-score, Recall and Precision of 0.97, 0.98 and 0.96, respectively. In a further step, a representative web application was constructed to assist common users to predict the trophic status of the Han River. This study demonstrated that ML techniques are not only promising for highly accurate water quality modeling of urban rivers, but also reduce time and labor intensity for experiments, which decreases the number of monitored water quality parameters, providing further insights into the driving factors of water quality deterioration. They ultimately help devise proactive strategies for sustainable water management.

Remote sensing techniques have been applied to monitor the spatiotemporal variation of harmful algal blooms (HABs) in many inland waters. However, these studies have been limited to monitor the vertical distribution of HABs due to the optical complexity of inland water. Therefore, this study applied a deep neural network model to monitor the vertical distribution of Chlorophyll-a (Chl-a), phycocyanin (PC), and turbidity (Turb) using drone-borne hyperspectral imagery, in-situ measurement, and meteoroidal data. The pigment concentrations were measured between depths of 0 m and 5.0 m with 0.05 m intervals. Here, four state-of-the-art data-driven model structures (ResNet-18, ResNet-101, GoogLeNet, and Inception v3) were adopted for estimating the vertical distributions of the harmful algal pigments. Among the four models, the ResNet-18 model showed the best performance, with an R2 value of 0.70. In addition, Gradient-weighted Class Activation Mapping (Grad-CAM) substantially provided informative reflectance band ranges near 490 nm and 620 nm in the hyperspectral image for the vertical estimation of pigments. Therefore, this study demonstrated that the explainable deep learning model with drone-borne hyperspectral images has the potential to estimate Chl-a, PC, and Turb vertical distributions and to show influential features that contribute to describing the vertical profile phenomena.

Understanding harmful algal blooms is imperative to protect aquatic ecosystems and human health. This study describes the spatial and temporal distributions of cyanobacterial blooms to identify the relations between blooms and environmental factors in the Baekje Reservoir. Two-year cyanobacterial cell data at one fixed station and four remotely sensed distributions of phycocyanin (PC) concentrations based on hyperspectral images (HSIs) were used to describe the relation between the spatial and temporal variations in the blooms and the affecting factors. An artificial neural network model and a three-dimensional hydrodynamic model were implemented to estimate the PC concentrations using remotely sensed HSIs and simulate the hydrodynamics, respectively. The statistical test results showed that the variations in the cyanobacterial biomass depended significantly on variations in the water temperature (slope = 0.13, p-value

Despite a growing awareness of the problems associated with cyanobacterial blooms in rivers, and particularly in regulated rivers, the drivers of bloom formation and abundance in rivers are not well understood. We developed a Bayesian hierarchical model to assess the relative importance of predictors of summer cyanobacteria abundance, and to test whether the relative importance of each predictor varies by site, using monitoring data from 16 sites in the four major rivers of South Korea. The results suggested that temperature and residence time, but not nutrient levels, are important predictors of summer cyanobacteria abundance in rivers. Although the two predictors were of similar significance across the sites, the residence time was marginally better in accounting for the variation in cyanobacteria abundance. The model with spatial hierarchy demonstrated that temperature played a consistently significant role at all sites, and showed no effect from site-specific factors. In contrast, the importance of residence time varied significantly from site to site. This variation was shown to depend on the trophic state, indicated by the chlorophyll-a and total phosphorus levels. Our results also suggested that the magnitude of weir inflow is a key factor determining the cyanobacteria abundance under baseline conditions.

Interest in anaerobic co-digestion (AcoD) has increased significantly in recent decades owing to enhanced biogas productivity due to the utilization of different organic wastes, such as food waste and sewage sludge. In this study, a robust AcoD model for biogas prediction is developed using deep learning (DL). We propose a hybrid DL architecture, i.e., DA-LSTM-VSN, wherein a dual-stage-attention (DA)-based long short-term memory (LSTM) network is integrated with variable selection networks (VSNs). To enhance the model predictability, we perform hyperparameter optimization. The model accuracy is validated using long-term AcoD monitoring data measured over two years of municipal wastewater treatment plant operation and then compared with those of two other DL-based models (i.e., DA-LSTM and the standard LSTM). In addition, the feature importance (FI) is analyzed to investigate the relative contribution of input variables to biogas production prediction. Finally, we demonstrate the successful application of the validated DL model to the AcoD process optimization. Results show that the model accuracy improved significantly by incorporating DA into LSTM, i.e., the coefficient of determination (R2) increased from 0.38 to 0.68; however, the R2 can be further increased to 0.76 by combining DA-LSTM with a VSN. For the biogas prediction of the AcoD model, the VSN contributes significantly by employing the discontinuous time series of measurement data on biodegradable organic-associated variables during AcoD. In addition, the VSN allows the AcoD model to be interpretable via FI analysis using its weighted input features. The FI results show that the relative importance is vital to variables associated with food waste leachate, whereas it is marginal for those associated with the primary and chemically assisted sedimentation sludges. In conclusion, the AcoD model proposed herein can be utilized in practical applications as a robust tool because it can provide the optimal sludge conditions to improve biogas production. This is because it facilitates the time-series biogas prediction at the full scale using unprocessed datasets with either missing value imputation or outlier removal.

Rechargeable seawater battery (SWB) is a unique energy storage system that can directly transform seawater into renewable energy. Placing a desalination compartment between SWB anode and cathode (denoted as seawater battery desalination; SWB‐D) enables seawater desalination while charging SWB. Since seawater desalination is a mature technology, primarily occupied by membrane‐based processes such as reverse osmosis (RO), the energy cost has to be considered for alternative desalination technologies. So far, the feasibility of the SWB‐D system based on the unit cost per desalinated water ($ m−3) has been insufficiently discussed. Therefore, this perspective aims to provide this information and offer future research directions based on the detailed cost analysis. Based on the calculations, the current SWB‐D system is expected to have an equipment cost of ≈1.02 $ m−3 (lower than 0.60–1.20 $ m−3 of RO), when 96% of the energy is recovered and stable performance for 1000 cycles is achieved. The anion exchange membrane (AEM) and separator contributes greatly to the material cost occupying 50% and 41% of the total cost, respectively. Therefore, future studies focusing on creating low cost AEMs and separators will pave the way for the large‐scale application of SWB‐D., Seawater battery desalination (SWB‐D) is a multifunctional system capable of storing energy and removing salt from water simultaneously. This perspective lays out a detailed cost analysis of the system, and provides an insight as to where SWB‐D currently stands in terms of its feasibility and what areas need to be improved to realize large scale applications.

The seawater battery (SWB) is a promising desalination technology that utilizes abundant sodium ions as an energy storage medium. Recently, the alternative desalination system, seawater battery desalination (SWB-D), was developed by placing an SWB next to the desalination compartment. This SWB-D system can desalt water while charging the SWB next to it. However, only a fixed catholyte solution has been investigated, although the catholytes impact the overall SWB-D performance. Therefore, we evaluated the effect of different catholytes on the desalination performance. High-saline reverse osmosis (RO) concentrate or brackish water exhibited excellent salt removal capability (>85.3% of sodium and >76.6% of chloride ions) with relatively short operation times (36.4 h for RO concentrate and 39.5 h for brackish water) upon charging, whereas the relatively low-saline river water showed the longest operation time (81.0 h), implying that river water should be excluded as a potential catholyte. The amount of desalinated water was marginally reduced due to osmosis through the anion exchange membrane; however, the amount of treated salt was >82.9% even after the reduction in water volume. These findings suggest that the catholyte with a resistance of >0.041 kΩ·cm can be ideal for the SWB-D.

In recent years, as agricultural activities and types of crops have become diverse, the occurrence of micro-pollutants has been reported more frequently in rural areas. These pollutants have detrimental effects on human health and ecological systems; thus, it is important to manage and monitor their presence in the environment. The modeling approach could be an effective way to understand and manage these pollutants. This study predicts the concentrations of micro-pollutants (MPs) using deep learning (DL) models, and the results are then compared with simulation results obtained from the soil water assessment tool (SWAT) model. The SWAT model showed an unacceptable performance owing to the resulting negative Nash–Sutcliffe efficiency (NSE) values for the simulations. This may be caused by the limitations of SWAT, which pertains to adopting simplified equations to simulate micro-pollutants. In addition, the ambiguous plan of pesticide application increased the model uncertainty, thereby deteriorating the model result. Here, we developed two different DL models: long short-term memory (LSTM) and convolutional neural network (CNN). LSTM exhibited the highest model performance, with NSE values of 0.99 and 0.75 for the training and validation steps, respectively. In the multi-target MP model, the error decreased as the number of simulated pollutants increased. The simulation of the four pollutants had the highest error, while the six-target simulation had the lowest error. In conclusion, this study demonstrated that the LSTM model has the potential to improve the prediction of MPs in aquatic systems.

Remote sensing can detect and map algal blooms. The HydroLight (Sequoia Scientific Inc., Bellevue, Washington, DC, USA) model generates the reflectance profiles of various water bodies. However, the influence of model parameters has rarely been investigated for inland water. Moreover, the simulation time of the HydroLight model increases as the amount of input data increases, which limits the practicality of the HydroLight model. This study developed a graphical user interface (GUI) software for the sensitivity analysis of the HydroLight model through multiple executions. The GUI software stably performed parameter sensitivity analysis and substantially reduced the simulation time by up to 92%. The GUI software results for lake water show that the backscattering ratio was the most important parameter for estimating vertical reflectance profiles. Based on the sensitivity analysis results, parameter calibration of the HydroLight model was performed. The reflectance profiles obtained using the optimized parameters agreed with observed profiles, with R2 values of over 0.98. Thus, a strong relationship between the backscattering coefficient and the observed cyanobacteria genera cells was identified.

Bacteria are a primary contaminant in natural surface water. The instream concentration of fecal coliform, a potential indicator of pathogens, is influenced by meteorological conditions and land-use characteristics. However, the relationships between these conditions and fecal coliforms are not fully understood. Furthermore, the sources of large variability in fecal coliform counts, e.g., temporal or spatial sources, remain unexplained, especially at large scales. This study proposes the use of Bayesian overdispersed Poisson models, whereby the combined effects of temperature, rainfall, and land-use characteristics on fecal coliform concentration are quantified with predictive uncertainty, and the sources of variability in fecal coliform concentration are assessed. The models were developed using 8-year weekly observations of fecal coliforms obtained from the Wachusett Reservoir watershed in Massachusetts, USA. The results highlight the importance of interactions among meteorological and land-use characteristics in controlling the instream fecal coliform concentration; the increase in fecal coliform concentration with temperature increase was more drastic when rainfall occurred. Also, the responses of fecal coliforms to temperature increases were more pronounced in forest-dominated than in urban-dominated areas. In contrast, the fecal coliform concentration increased more rapidly with rainfall increases in urban-dominated than in forest-dominated areas. The models also demonstrate that among the sources of variability, the monthly component made the most significant contribution to the variability in fecal coliform concentrations. Our results suggest that seasonally dependent processes, including surface runoff, are critical factors that regulate fecal coliform concentration in streams.

Fecal coliforms are indicators of pathogens and thereby, understanding of their fate and transport in surface waters is important to protect drinking water sources and public health. We compiled fecal coliform observations from four different sites in the USA and Korea and found a seasonal variability with a significant connection to temperature levels. In all observations, fecal coliform concentrations were relatively higher in summer and lower during the winter season. This could be explained by the seasonal dominance of growth or die-off of bacteria in soil and in-stream. Existing hydrologic models, however, have limitations in simulating the seasonal variability of fecal coliform. Soil and in-stream bacterial modules of the Soil and Water Assessment Tool (SWAT) model are oversimplified in that they exclude simulations of alternating bacterial growth. This study develops a new bacteria subroutine for the SWAT in an attempt to improve its prediction accuracy. We introduced critical temperatures as a parameter to simulate the onset of bacterial growth/die-off and to reproduce the seasonal variability of bacteria. The module developed in this study will improve modeling for environmental management schemes.

In the Mekong River basin, groundwater from tube-wells is a major drinking water source. However, arsenic (As) contamination in groundwater resources has become a critical issue in the watershed. In this study, As species such as total As (As TOT ), As(III), and As(V), were monitored across the watershed to investigate their characteristics and inter-relationships with water quality parameters, including pH and redox potential (Eh). The data illustrated a dramatic change in the relationship between As TOT and Eh over a specific Eh range, suggesting the importance of Eh in predicting As TOT . Thus, a Bayesian change-point model was developed to predict As TOT concentrations based on Eh and pH, to determine changes in the As TOT –Eh relationship. The model captured the Eh change-point (∼−100 ± 15 mV), which was compatible with the data. Importantly, the inclusion of this change-point in the model resulted in improved model fit and prediction accuracy; As TOT concentrations were strongly negatively related to Eh values higher than the change-point. The process underlying this relationship was subsequently posited to be the reductive dissolution of mineral oxides and As release. Overall, As TOT showed a weak positive relationship with Eh at a lower range, similar to those commonly observed in the Mekong River basin delta. It is expected that these results would serve as a guide for establishing public health strategies in the Mekong River Basin.

In the past few decades, membrane-based processes have become mainstream in water desalination because of their relatively high water flux, salt rejection, and reasonable operating cost over thermal-based desalination processes. The energy consumption of the membrane process has been continuously lowered (from >10 kWh m−3 to ~3 kWh m−3) over the past decades but remains higher than the theoretical minimum value (~0.8 kWh m−3) for seawater desalination. Thus, the high energy consumption of membrane processes has led to the development of alternative processes, such as the electrochemical, that use relatively less energy. Decades of research have revealed that the low energy consumption of the electrochemical process is closely coupled with a relatively low extent of desalination. Recent studies indicate that electrochemical process must overcome efficiency rather than energy consumption hurdles. This short perspective aims to provide platforms to compare the energy efficiency of the representative membrane and electrochemical processes based on the working principle of each process. Future water desalination methods and the potential role of nanotechnology as an efficient tool to overcome current limitations are also discussed.

Water-stressed countries have been shifting their sources of clean water from inland freshwater to seawater. This led to a comprehensive exploration of seawater desalination processes to address water scarcity; however, membrane processes have expensive operational costs and high energy consumption. In this regard, this study presented a novel energy self-sufficient desalination system design that incorporates rechargeable seawater batteries as an additional energy storage system. Experimental data were projected using the reverse osmosis system analysis model to determine the configuration that achieved the lowest energy consumption and highest charging rate. The results show that the seawater battery achieved a satisfactory desalination performance with >90% and 74%−82% removal of sodium and chloride ions from actual water samples, respectively. Among the configurations, using ultrafiltration as pretreatment and applying 1.8 mA as initial current yielded the lowest energy consumption (1.35 kWh/m3) and the highest energy charging rate (1.01). Compared to the conventional reverse osmosis desalination plants (2.83 kWh/m3), the seawater battery-desalination system has a huge potential in addressing the major disadvantages of current desalination technologies.

The rapid increase of impervious area and climate change greatly affect the hydrological, environmental, and ecological system at the local, regional, and global scales. These phenomena can increase the peak flow and surface runoff carrying anthropogenic pollutants, thereby severely deteriorating the water quality of the surface waters. Low-impact development (LID) practices have been proposed as a promising urban management methodology to mitigate these environmental issues. Numerical models have been increasingly utilized as an analyzing tool for evaluating the LID performance. However, LID-associated numerical models are oversimplified in terms of water quality simulation by only considering the dilution effect by rainfall in LIDs. This study resolved this challenge by modifying the water quality module of LID in the stormwater management model (SWMM). We evaluated the module performance for simulating total suspended solids (TSS), chemical oxygen demand (COD), total nitrogen (TN), and total phosphorus (TP) of the LID facilities. Using the developed model, we conducted the LID scenario analysis under the climate change scenarios. The scenario analysis was applied in the urban area which focused on flow rate and TSS. The modified module provided accurate results for pollutant simulations, yielding an average value of Root mean square error-observation Standard deviation Ratio (RSR) of 0.52, while the original module showed an unacceptable performance, with an RSR value of 1.11. Scenario analysis showed that the hydrological outputs were sensitive to the volume of rainfall while the water quality results were sensitive to the temporal distribution of rainfall. Based on these statements, the modified water quality module in LID developed in this study will be useful in designing LID facilities and in formulating guidelines for LID installation.

Worldwide proliferation of cyanobacteria blooms in inland waters not only affects the intended use of water but potentially threatens human and animal health. In this study, a stacked autoencoder-deep neural network (SAE-DNN) was developed to estimate phycocyanin (PC) concentration by using in situ reflectance spectra in productive inland water. The estimated PC using the SAE-DNN was in close agreement with the measured PC, with an R2 of 0.87, root mean square error (RMSE) of 14.45 μg/L, and relative RMSE of 86.42%. The performance of the SAE-DNN was superior to that of the DNN and band-ratio algorithms. An analysis on the deep spectral features extracted using the SAE yielded the most useful spectral bands, namely 538, 596, and 735 nm, for the retrieval of PC. The estimation accuracy of the SAE-DNNPeaks, using only the aforementioned spectral bands as input variables, was comparable to that of the SAE-DNN, demonstrating that the high-level of abstraction using the SAE facilitated the improvement in feature learning. The application of the SAE-DNNPeaks to airborne hyperspectral image data resulted in an acceptable estimation accuracy, despite a bias toward underestimation, potentially arising from uncertainty associated with atmospheric correction, at high PC concentrations. Our results suggest that simple, empirical-based approaches, such as the SAE-DNNPeaks, have the potential to serve as a rapid assessment tool for the abundance and spatial distribution of cyanobacteria.

Frequency and intensity of the harmful algal blooms (HABs) increased globally since 1970s. The increase in HABs have negatively affected aquatic ecosystem and aquaculture industry. The economic losses were about $ 1 billion in Europe, $ 100 million in USA and $ 121 billion in Korea per year. There were various field monitoring campaigns for ecological and biological researches. However, traditional HABs monitoring has limitations on both spatial and temporal coverage. In these days, multispectral remote sensing methods using satellite sensors have been widely used to monitor HABs in ocean and coastal areas. However, the satellite systems used in ocean and coastal research, such as MODIS, SeaWiFS and etc. have limitations in study on complex coastline, because of their coarse spatial resolution (~ few km). In this research, we conducted two-year intensive monitoring on the South Sea of Korea from 2016 to 2017 at 62 sampling station and used landsat-8 operational land imager (OLI) satellite that has 30m spatial resolution. We used 4 band (band 1 to 4), 4-band ratio (band 1 over band 3 and 4, and band 2 over band 3 and 4) and mixed dataset of 4 band and 4-band ratio. The empirical OC algorithms showed poor performances, under 0.25 of r-squared. The machine learning techniques, i.e., artificial neural network (ANN) and support vector machine (SVM) were applied to enhance performance of estimating chl-a on landsat-8 application. Parameters for developing ANN and SVM model were optimized using a pattern search algorithm in MATLAB toolbox. All dataset were divided into 80 % of training and 20 % of validation data. In the training step, mixed dataset showed the best performance in both ANN and SVM models, whereas 4-band ratio and 4 band dataset in the validation step showed the best performance in ANN and SVM, respectively. The ANN model showed poor performance in low chl-a concentrations but SVM had more accurate performance in low and mid concentrations. Both models under-estimated chl-a in mid to high concentration range. For the mapping results, the ANN model using 4 band dataset showed very low concentration of chl-a in most of research area, whereas SVM showed high concentration of chl-a in coastal area and bay. The result using 4-band ratio dataset showed similar chl-a distribution in ANN and SVM. For mixed dataset results the ANN model estimated over 8 mg m-3 of chl-a at some of coastal, almost zero in near coastal area and over 2 mg m-3 chl-a concentration for off-shore area. In case of SVM, all region showed approximately 2 mg m-3 of chl-a concentration. Landsat-8 OLI was not proper system for OC algorithms. Machine learning techniques were effective tools for enhancing ocean chl-a estimation performance using landsat-8 OLI. Thus, this study showed potential of landsat-8 OLI application to coastal HAB monitoring.

Remote sensing is useful technique to not only detect harmful algal bloom but also quantify the concentration of the harmful algae by using surface reflectance data. The hyperspectral image allows to investigate detail spatial information of harmful algae. Atmospheric correction is critical process in order to achieve an accurate optical signal in water surface. However, the influence of atmospheric correction performance on the estimation of PC concentration has rarely been studied. Thus, this study investigated the influence of three atmospheric correction method on the spatial distribution and concentration of phycocyanin (PC) concentration from estimation of the bio-optical algorithms. Atmospheric correction is an important image processing technique of hyperspectral image because the result of the correction is expected to influence bio-optical algorithms for quantifying phycocyanin (PC) concentration. From August to October, four field and airborne monitoring campaigns in the Baekje Weir in South Korea were implemented to measure water surface reflectance. PC concentrations in the surface water were analyzed using freezing and thawing method. The two band ratio algorithm, the three band ratio algorithm, the Li algorithm, and the Simis algorithm were utilized to estimate PC concentration. And, atmospheric correction of hyperspectral image was conducted by MODTRAN 6, ATCOR 4, and an artificial neural network (ANN). The ANN model utilized atmospheric parameters which generated from MODTRAN 6 to simulate water surface reflectance. Bio-optical algorithms were applied to the atmospherically corrected image for generating PC distribution map. Even though the atmospheric correction result from the ANN showed Nash-Sutcliffe efficiency (NSE) values of 0.80 and 0.76 for the training and validation steps, respectively, the PC concentration from the bio-optical algorithms showed NSE values ranged from 0.17 to 0.57. The ANN model was turned out to be required having large quantities of input data in order to have precise simulation performances. Atmospheric correction from MODTRAN 6 showed an NSE value over 0.8, whereas the correction from ATCOR 4 had a negative NSE value. However, the accuracy in certain regions of the reflectance spectra (λ 700 nm) was relatively low compared to the other spectra region because of insufficient atmospheric observation data during monitoring period. The relationship between atmospheric correction and bio-optical algorithm performance for MODTRAN 6, ATCOR 4, and ANN simulation showed different estimation of PC concentration in the atmospherically corrected images. The precise atmospheric correction by MODTRAN 6 enabled an accurate bio-optical algorithm performance and thus was critical to generating a satisfactory spatial distribution map of PC. In addition, the Li and Simis algorithms were revealed to be much more sensitive to the performance of the atmospheric correction than the other algorithms. Therefore, this study provides a useful tool for understanding importance of atmospheric correction influence of hyperspectral images on quantification of harmful algal blooms.

Land use change from annual crops to commercial tree plantations can modify flow and transport processes at the watershed scale, including the fate and transport of fecal indicator bacteria (FIB), such as Escherichia coli. The Soil and Water Assessment Tool (SWAT) is a useful means for integrating watershed characteristics and simulating water and contaminants. The objective of this study was to provide a comprehensive assessment of the impact of land use change on microbial transfer from soils to streams using the SWAT model. This study was conducted for the Houay Pano watershed located in northern Lao People's Democratic Republic. Under the observed weather conditions, the SWAT model predicted a decrease from 2011 to 2012 and an increase from 2012 to 2013 in surface runoff, suspended solids, and E. coli transferred from the soil surface to streams. The amount of precipitation was important in simulating surface runoff, and it subsequently affected the fate and transport of suspended solids and bacteria. In simulations of identical weather conditions and different land uses, E. coli fate and transport was more sensitive to the initial number of E. coli than to its drivers (i.e., surface runoff and suspended solids), and leaf area index was a significant factor influencing the determination of the initial number of E. coli on the soil surface. On the basis of these findings, this study identifies several limitations of the SWAT fertilizer and bacteria modules and suggests measures to improve our understanding of the impacts of land use change on FIB in tropical watersheds.

The ability to simulate algal systems is critical for watershed-scale models. The objective of this study was to develop and evaluate a modified algal module that simulates the dynamics of three major algal groups (cyanobacteria, green algae, and diatoms) in a stream using variables available in the Soil and Water Assessment Tool. The proposed module 1) models the dynamics of the three algal groups while accounting for nutrients from algal die-off and 2) has temperature multipliers that consider the effect of temperature changes on kinetic rates. Data to test the module were collected from a forest-dominated watershed over two years. The modified module was efficient in predicting seasonal variations in algal group biomass and simulated the regeneration of nutrients after algal die-off. This module will be useful in predicting the dynamics of the three studied algal groups and evaluating the best management practices for algal blooms in watersheds.

Continuous urbanization has negatively impacted the ecological and hydrological environments at the global, regional, and local scales. This issue was addressed by developing Low Impact Development (LID) practices to deliver better hydrologic function and improve the environmental, economic, social and cultural outcomes. This study developed a modeling software to simulate and optimize bioretentions among LID in a given watershed. The model calculated a detailed soil infiltration process in bioretention with hydrological conditions (e.g. unsaturated and saturated soil) and hydraulic facilities (e.g. riser and underdrain) and also generated an optimized plan using Flow Duration Curve (FDC). The optimization result from the simulation demonstrated that the location and size of bioretention, as well as the soil texture, are important elements for an efficient bioretention. We hope that this developed software will aid in establishing effective LID strategies for improving urban water sustainability and management.

Remote sensing is useful for detecting and quantifying cyanobacteria blooms for managing water systems. In particular, airborne hyperspectral remote sensing has an advantage in precise cyanobacteria detection with high spatial and spectral resolution. Many bio-optical algorithms have been developed and utilized to estimate algal concentration. However, achieving the optimal conventional optical model accuracy is still challenging in freshwater owing to the biophysical complexity of the inland water and the seasonal reflection of site-specific optical properties. Thus, this study applied convolutional neural network (CNN) with various input windows to estimate the concentrations of phycocyanin (PC) and chlorophyll-a (Chl-a), and generated a phytoplankton pigment map. We proposed that the Point-centered regression CNN (PRCNN) showed accurate PC and Chl-a simulations, with R2 > 0.86 and 0.73, respectively, and root mean square errors of

Hyperspectral imagery (HSI) provides substantial information on optical features of water bodies that is usually applicable to water quality monitoring. However, it generates considerable uncertainties in assessments of spatial and temporal variation in water quality. Thus, this study explored the influence of different optical methods on the spatial distribution and concentration of phycocyanin (PC), chlorophyll-a (Chl-a), and total suspended solids (TSSs) and evaluated the dependence of algal distribution on flow velocity. Four ground-based and airborne monitoring campaigns were conducted to measure water surface reflectance. The actual concentrations of PC, Chl-a, and TSSs were also determined, while four bio-optical algorithms were calibrated to estimate the PC and Chl-a concentrations. Artificial neural network atmospheric correction achieved Nash-Sutcliffe Efficiency (NSE) values of 0.80 and 0.76 for the training and validation steps, respectively. Moderate resolution atmospheric transmission 6 (MODTRAN 6) showed an NSE value >0.8; whereas, atmospheric and topographic correction 4 (ATCOR 4) yielded a negative NSE value. The MODTRAN 6 correction led to the highest R2 values and lowest root mean square error values for all algorithms in terms of PC and Chl-a. The PC:Chl-a distribution generated using HSI proved to be negatively dependent on flow velocity (p-value = 0.003) and successfully indicated cyanobacteria risk regions in the study area.

Microbial water quality lies in the nexus of human, animal, and environmental health. Multidisciplinary efforts are under way to understand how microbial water quality can be monitored, predicted, and managed. This special collection of papers in the Journal of Environmental Quality was inspired by the idea of creating a special section containing the panoramic view of advances and challenges in the arena of microbial water quality research. It addresses various facets of health-related microorganism release, transport, and survival in the environment. The papers analyze the spatiotemporal variability of microbial water quality, selection of predictors of the spatiotemporal variations, the role of bottom sediments and biofilms, correlations between concentrations of indicator and pathogenic organisms and the role for risk assessment techniques, use of molecular markers, subsurface microbial transport as related to microbial water quality, antibiotic resistance, real-time monitoring and nowcasting, watershed scale modeling, and monitoring design. Both authors and editors represent international experience in the field. The findings underscore the challenges of observing and understanding microbial water quality; they also suggest promising research directions for improving the knowledge base needed to protect and improve our water sources.

This study estimated water quality constituents especially in CBOD, TN, TP, and Chlorophyll-a in Sayeun reservoir by using CE-QUAL-W2 model. With water quality data in surface, middle, and bottom of water body, the model calibration was implemented by changing water quality parameters in the model. Using the calibrated model, we performed scenario analysis to investigate the variation of water quality in respond to different elevations. CBOD, TN, and Chlorophyll-a concentration predicted by the model showed a good agreement with the measured the trend of the concentrations. However, TP estimated was relatively low tendency by the model. We found that water quality (i.e., CBOD, TN, TP, and chlorophyll-a) at both water surface and middle layer was degraded in respond to the decrease of water level by 6.8m. Although results of CBOD in both surface and middle layers decreased to about 2% and 1%, respectively, in the surface layer, TN, TP, and Chlorophyll-a increased to about 4%, 3%, and 51% and, in the middle, TN and TP increased up to 12% and 3%, respectively. In the middle layer, especially, water quality degraded mainly due to increased organic matter from growth, mortality, decay, and sedimentation of algae and anaerobic release of nutrients from sediment. This study demonstrated that water quality could be influenced by controlling water surface elevation, implying that there is a need to control nutrient inflow and re-suspension from sediment in the reservoir.

Given that around eight million commuters use the Seoul Metropolitan Subway (SMS) each day, the indoor air quality (IAQ) of its stations has attracted much public attention. We have monitored the concentration of particulate matters (PMx) (i.e., PM10, PM2.5, and PM1) in six major transfer stations per minute for three weeks during the summer, autumn, and winter in 2014 and 2015. The data were analyzed to investigate the relationship between PMx concentration and multivariate environmental factors using statistical methods. The average PM concentration observed was approximately two or three times higher than outdoor PM10 concentration, showing similar temporal patterns at concourses and platforms. This implies that outdoor PM10 is the most significant factor in controlling indoor PM concentration. In addition, the station depth and number of trains passing through stations were found to be additional influences on PMx. Principal component analysis (PCA) and self-organizing map (SOM) were employed, through which we found that the number of trains influences PM concentration in the vicinity of platforms only, and PMx hotspots were determined. This study identifies the external and internal factors affecting PMx characteristics in six SMS stations, which can assist in the development of effective IAQ management plans to improve public health.

Summary To control algal blooms, the stressor–response relationships between water quality metrics, environmental variables, and algal growth need to be better understood and modeled. Machine-learning methods have been suggested as means to express the stressor–response relationships that are found when applying mechanistic water quality models. The objective of this work was to evaluate the efficiency of regression trees in the development of a stressor–response model for chlorophyll-a (Chl-a) concentrations, using the results from site-specific mechanistic water quality modeling. The 2-dimensional hydrodynamic and water quality model (CE-QUAL-W2) model was applied to simulate water quality using four-year observational data and additional scenarios of air temperature increases for the Yeongsan Reservoir in South Korea. Regression tree modeling was applied to the results of these simulations. Given the well-expressed seasonality in the simulated Chl-a dynamics, separate regression trees were developed for months from May to September. The regression trees provided a reasonably accurate representation of the stressor–response dependence generated by the CE-QUAL-W2 model. Different stressors were then selected as split variables for different months, and, in most cases, splits by the same stressor variable yielded the same correlation sign between the variable and the Chl-a concentration. Compared to physical variables, nutrient content appeared to better predict Chl-a responses. The highest Chl-a temperature sensitivities were found for May and June. Regression tree splits based on ammonium concentration resulted in a consistent trend of greater sensitivity in the groups of samples with higher ammonium concentrations. Regression tree models provided a transparent visual representation of the stressor–response relationships for Chl-a and its sensitivity. Overall, the representation of relationships using classification and regression tools can be considered a useful approach to assess the state of aquatic ecosystems and effectively determine significant stressor variables.

Groundwater contamination with arsenic (As) is one of the major issues in the world, especially for Southeast Asian (SEA) countries where groundwater is the major drinking water source, especially in rural areas. Unfortunately, quantification of groundwater As contamination is another burden for those countries because it requires sophisticated equipment, expensive analysis, and well-trained technicians. Here, we collected approximately 350 groundwater samples from three different SEA countries, including Cambodia, Lao PDR, and Thailand, in an attempt to quantify total As concentrations and conventional water quality variables. After that, two machine learning models (i.e. artificial neural network (ANN) and support vector machine (SVM)) were applied to predict groundwater As contamination using conventional water quality parameters. Prior to modeling approaches, the pattern search algorithm in MATLAB software was used to optimize the ANN and SVM model parameters, attempting to find the best param...

Exposure to highly toxic pesticides could potentially cause cancer and disrupt the development of vital systems. Monitoring activities were performed to assess the level of contamination; however, these were costly, laborious, and short-term leading to insufficient monitoring data. However, the performance of the existing Soil and Water Assessment Tool (SWAT model) can be restricted by its two-phase partitioning approach, which is inadequate when it comes to simulating pesticides with limited dataset. This study developed a modified SWAT pesticide model to address these challenges. The modified model considered the three-phase partitioning model that classifies the pesticide into three forms: dissolved, particle-bound, and dissolved organic carbon (DOC)-associated pesticide. The addition of DOC-associated pesticide particles increases the scope of the pesticide model by also considering the adherence of pesticides to the organic carbon in the soil. The modified SWAT and original SWAT pesticide model was applied to the Pagsanjan-Lumban (PL) basin, a highly agricultural region. Malathion was chosen as the target pesticide since it is commonly used in the basin. The pesticide models simulated the fate and transport of malathion in the PL basin and showed the temporal pattern of selected subbasins. The sensitivity analyses revealed that application efficiency and settling velocity were the most sensitive parameters for the original and modified SWAT model, respectively. Degradation of particulate-phase malathion were also significant to both models. The rate of determination (R2) and Nash-Sutcliffe efficiency (NSE) values showed that the modified model (R2 = 0.52; NSE = 0.36) gave a slightly better performance compared to the original (R2 = 0.39; NSE = 0.18). Results from this study will be able to aid the government and private agriculture sectors to have an in-depth understanding in managing pesticide usage in agricultural watersheds.