Digital imaging-in-flow (FlowCAM) and probabilistic machine learning to assess the sonolytic disinfection of cyanobacteria in sewage wastewater

Assessing the cyanobacteria disinfection in sewage and its compliance with international-standards requires determining the concentration and viability, which can be achieve using Imaging Flow Cytometry device called FlowCAM. The objective is to thoroughly investigate the sonolytic morphological changes and disinfection-performance towards toxic cyanobacteria existing in sewage using the FlowCAM. After optimizing the process conditions, over 80% decline in cyanobacterial cell counts was observed, accompanied by an additional 10-15% of cells exhibiting injuries, as confirmed through morphological investigation. Moreover, for the first time, the experimentally collected data was utilized to build deep-learning probabilistic-neural-networks (PNN) and natural-gradient-boosting (NGBoost) models for predicting disinfection efficiency and ABD area as target outputs. The findings suggest that the NGBoost model exhibited superior prediction performance for both targets, with high test coefficient of determination (R2 > 0.87) and lower test errors (RMSE < 7.10, MAE < 4.14). The confidence interval examination in NGBoost prediction performance showed a minute variation from the experimentally calculated values, suggesting a high accuracy in model prediction. Finally, SHAP analysis suggests the sonolytic time alone contributes around 50% to the cyanobacteria disinfection. Overall, the findings demonstrate the effectiveness of the FlowCAM device and the potential of machine-learning modeling in predicting disinfection outcomes.

Machine learning analysis to interpret the effect of the photocatalytic reaction rate constant (k) of semiconductor-based photocatalysts on dye removal

Photocatalytic reactions with semiconductor-based photocatalysts have been investigated extensively for application to wastewater treatment, especially dye degradation, yet the interactions between different process parameters have rarely been reported due to their complicated reaction mechanisms. Hence, this study aims to discern the impact of each factor, and each interaction between multiple factors on reaction rate constant (k) using a decision tree model. The dyes selected as target pollutants were indigo and malachite green, and 5 different semiconductor-based photocatalysts with 17 different compositions were tested, which generated 34 input features and 1527 data points. The Boruta Shapley Additive exPlanations (SHAP) feature selection for the 34 inputs found that 11 inputs were significantly important. The decision tree model exhibited for 11 input features with an R2 value of 0.94. The SHAP feature importance analysis suggested that photocatalytic experimental conditions, with an importance of 59%, was the most important input category, followed by atomic composition (39%) and physicochemical properties (2%). Additionally, the effects on k of the synergy between the metal cocatalysts and important experimental conditions were confirmed by two feature SHAP dependence plots, regardless of importance order. This work provides insight into the single and multiple factors that affect reaction rate and mechanism.

Machine learning-based water quality prediction using octennial in-situ Daphnia magna biological early warning system data

Biological early warning system (BEWS) has been globally used for surface water quality monitoring. Despite its extensive use, BEWS has exhibited limitations, including difficulties in biological interpretation and low alarm reproducibility. This study addressed these issues by applying machine learning (ML) models to eight years of in-situ BEWS data for Daphnia magna. Six ML models were adopted to predict contamination alarms from Daphnia behavioral parameters. The light gradient boosting machine model demonstrated the most significant improvement in predicting alarms from Daphnia behaviors. Compared with the traditional BEWS alarm index, the ML model enhanced the precision and recall by 29.50% and 43.41%, respectively. The speed distribution index and swimming speed were significant parameters for predicting water quality warnings. The nonlinear relationships between the monitored Daphnia behaviors and water physicochemical water quality parameters (i.e., flow rate, Chlorophyll-a concentration, water temperature, and conductivity) were identified by ML models for simulating Daphnia behavior based on the water contaminants. These findings suggest that ML models have the potential to establish a robust framework for advancing the predictive capabilities of BEWS, providing a promising avenue for real-time and accurate assessment of water quality. Thereby, it can contribute to more proactive and effective water quality management strategies.

Profiling emerging micropollutants in urban stormwater runoff using suspect and non-target screening via high-resolution mass spectrometry

Urban surface runoff contains chemicals that can negatively affect water quality. Urban runoff studies have determined the transport dynamics of many legacy pollutants. However, less attention has been paid to determining the first-flush effects (FFE) of emerging micropollutants using suspect and non-target screening (SNTS). Therefore, this study employed suspect and non-target analyses using liquid chromatography-high resolution mass spectrometry to detect emerging pollutants in urban receiving waters during stormwater events. Time-interval sampling was used to determine occurrence trends during stormwater events. Suspect screening tentatively identified 65 substances, then, their occurrence trend was grouped using correlation analysis. Non-target peaks were prioritized through hierarchical cluster analysis, focusing on the first flush-concentrated peaks. This approach revealed 38 substances using in silico identification. Simultaneously, substances identified through homologous series observation were evaluated for their observed trends in individual events using network analysis. The results of SNTS were normalized through internal standards to assess the FFE, and the most of tentatively identified substances showed observed FFE. Our findings suggested that diverse pollutants that could not be covered by target screening alone entered urban water through stormwater runoff during the first flush. This study showcases the applicability of the SNTS in evaluating the FFE of urban pollutants, offering insights for first-flush stormwater monitoring and management.

Predicting the distribution coefficient of cesium in solid phase groups using machine learning

The migration and retention of radioactive contaminants such as 137Cesium (137Cs) in various environmental media pose significant long-term storage challenges for nuclear waste. The distribution coefficient (Kd) is a critical parameter for assessing the mobility of radioactive contaminants and is influenced by various environmental conditions. This study presents machine-learning models based on the Japan Atomic Energy Agency Sorption Database (JAEA-SDB) to predict the Kd values for Cs in solid phase groups. We used three different machine learning models: random forest (RF), artificial neural network (ANN), and convolutional neural network (CNN). The models were trained on 14 input variables from the JAEA-SDB, including factors such as the Cs concentration, solid-phase properties, and solution conditions, which were preprocessed by normalization and log-transformation. The performances of the models were evaluated using the coefficient of determination (R2) and root mean squared error (RMSE). The RF, ANN, and CNN models achieved R2 values greater than 0.97, 0.86, and 0.88, respectively. We also analyzed the variable importance of RF using an out-of-bag (OOB) and a CNN with an attention module. Our results showed that the environmental media, initial radionuclide concentration, solid phase properties, and solution conditions were significant variables for Kd prediction. Our models accurately predict Kd values for different environmental conditions and can assess the environmental risk by analyzing the behavior of radionuclides in solid phase groups. The results of this study can improve safety analyses and long-term risk assessments related to waste disposal and prevent potential hazards and sources of contamination in the surrounding environment.

Deep learning-based efficient drone-borne sensing of cyanobacterial blooms using a clique-based feature extraction approach

Recent advances in remote sensing techniques provide a new horizon for monitoring the spatiotemporal variations of harmful algal blooms (HABs) using hyperspectral data in inland water. In this study, a hierarchical concatenated variational autoencoder (HCVAE) is proposed as an efficient and accurate deep learning (DL) based bio-optical model. To demonstrate its usefulness in retrieving algal pigments, the HCVAE is applied to bloom-prone regions in Daecheong Lake, South Korea. By abstracting the similarity between highly related features using layer-wise clique-based latent-feature extraction, HCVAE reduces the computational loads in deriving outputs while preventing performance degradation. Graph-based clique-detection uses information theory-based criteria to group the related reflectance spectra. Consequently, six latent features were extracted from 79 spectral bands to consist of a multilevel hierarchy of HCVAE that can simultaneously estimate concentrations of chlorophyll-a (Chl-a) and phycocyanin (PC). Despite the parsimonious model architecture, the Chl-a and PC concentrations estimated by HCVAE closely agree with the measured concentrations, with test R2 values of 0.76 and 0.82, respectively. In addition, spatial distribution maps of algal pigments obtained from HCVAE using drone-borne reflectance successfully capture the blooming spots. Based on its multilevel hierarchical architecture, HCVAE can provide the importance of latent features along with their individual wavelengths using Shapley additive explanations. The most important latent features covered the spectral regions associated with both Chl-a and PC. The lightweight neural network DNNsel, which uses only the spectral bands of highest importance in latent-feature extraction, performed comparably to HCVAE. The study results demonstrate the utility of the multilevel hierarchical architecture as a comprehensive assessment model for near-real-time drone-borne sensing of HABs. Moreover, HCVAE is applicable to a wide range of environmental big data, as it can handle numerous sets of features.

Projected climate change impact on cyanobacterial bloom phenology in temperate rivers based on temperature dependency

Climate warming is linked to earlier onset and extended duration of cyanobacterial blooms in temperate rivers. This causes an unpredictable extent of harm to the functioning of the ecosystem and public health. We used Microcystis spp. cell density data monitored for seven years (2016-2022) in ten sites across four temperate rivers of the Republic of Korea to define the phenology of cyanobacterial blooms and elucidate the climatic effect on their pattern. The day of year marking the onset, peak, and end of Microcystis growth were estimated using a Weibull function, and linear mixed-effect models were employed to analyze their relationships with environmental variables. These models identified river-specific temperatures at the beginning and end dates of cyanobacterial blooms. Furthermore, the most realistic models were employed to project future Microcystis bloom phenology, considering downscaled and quantile-mapped regional air temperatures from a general circulation model. Daily minimum and daily maximum air temperatures (mintemp and maxtemp) primarily drove the timing of the beginning and end of the bloom, respectively. The models successfully captured the spatiotemporal variations of the beginning and end dates, with mintemp and maxtemp predicted to be 24℃ (R2 = 0.68) and 16℃ (R2 = 0.35), respectively. The beginning and end dates were projected to advance considerably in the future under the Representative Concentration Pathway 2.6, 4.5, and 8.5. The simulations suggested that the largest uncertainty lies in the timing of when the bloom ends, whereas the timing of when blooming begins has less variation. Our study highlights the dependency of cyanobacterial bloom phenology on temperatures and earlier and prolonged bloom development.

Transformer-based deep learning models for adsorption capacity prediction of heavy metal ions toward biochar-based adsorbents

Biochar adsorbents synthesized from food and agricultural wastes are commonly applied to eliminate heavy metal (HM) ions from wastewater. However, biochar's diverse characteristics and varied experimental conditions make the accurate estimation of their adsorption capacity (qe) challenging. Herein, various machine-learning (ML) and three deep learning (DL) models were built using 1518 data points to predict the qe of HM on various biochars. The recursive feature elimination technique with 28 inputs suggested that 14 inputs were significant for model building. FT-transformer with the highest test R2 (0.98) and lowest root mean square error (RMSE) (0.296) and mean absolute error (MAE) (0.145) outperformed various ML and DL models. The SHAP feature importance analysis of the FT-transformer model predicted that the adsorption conditions (72.12%) were more important than the pyrolysis conditions (25.73%), elemental composition (1.39%), and biochar's physical properties (0.73%). The two-feature SHAP analysis proposed the optimized process conditions including adsorbent loading of 0.25 g, initial concentration of 12 mg/L, and solution pH of 9 using phosphoric-acid pre-treated biochar synthesized from banana-peel with a higher O/C ratio. The t-SNE technique was applied to transform the 14-input matrix of the FT-Transformer into two-dimensional data. Finally, we outlined the study's environmental implications.

Molecular-level chemical composition of aerosol and its potential source tracking at Antarctic Peninsula

Marine organic aerosols play crucial roles in global climatic systems. However, their chemical properties and relationships with various potential organic sources still need clarification. This study employed high-resolution mass spectrometry to investigate the identity, origin, and transportation of organic aerosols in pristine Antarctic environments (King Sejong Station; 62.2°S, 58.8°W), where complex ocean-cryosphere-atmosphere interactions occur. First, we classified the aerosol samples into three clusters based on their air mass transport history. Next, we investigated the relationship between organic aerosols and their potential sources, including organic matter dissolved in the open ocean, coastal waters, and runoff waters. Cluster 1 (C1), in which the aerosols mainly originated from the open ocean area (i.e., pelagic zone-influenced), exhibited a higher abundance of lipid-like and protein-like organic aerosols than cluster 3 (C3), with ratios 1.8- and 1.6-times higher, respectively. In contrast, C3, characterized by longer air mass retention over sea ice and land areas (i.e., inshore-influenced), had higher lignin- and condensed aromatic structures (CAS)-like organic aerosols by 2.2- and 3.4-times compared to C1. Cluster 2 (C2) has intermediate characteristics between C1 and C3 concerning the chemical properties of the aerosols and air mass travel history. Notably, the chemical properties of the aerosols assigned to C1 are closely related to those of phytoplankton-derived organics enriched in the open ocean. In contrast, those of C3 are comparable to those of terrestrial plant-derived organics enriched in coastal and runoff waters. These findings help evaluate the source-dependent properties of organic aerosols in changing Antarctic environment.

Long short-term memory models of water quality in inland water environments

Water quality is substantially influenced by a multitude of dynamic and interrelated variables, including climate conditions, landuse and seasonal changes. Deep learning models have demonstrated predictive power of water quality due to the superior ability to automatically learn complex patterns and relationships from variables. Long short-term memory (LSTM), one of deep learning models for water quality prediction, is a type of recurrent neural network that can account for longer-term traits of time-dependent data. It is the most widely applied network used to predict the time series of water quality variables. First, we reviewed applications of a standalone LSTM and discussed its calculation time, prediction accuracy, and good robustness with process-driven numerical models and the other machine learning. This review was expanded into the LSTM model with data pre-processing techniques, including the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise method and Synchrosqueezed Wavelet Transform. The review then focused on the coupling of LSTM with a convolutional neural network, attention network, and transfer learning. The coupled networks demonstrated their performance over the standalone LSTM model. We also emphasized the influence of the static variables in the model and used the transformation method on the dataset. Outlook and further challenges were addressed. The outlook for research and application of LSTM in hydrology concludes the review.

Automatic classification of microplastics and natural organic matter mixtures using a deep learning model

Several preprocessing procedures are required for the classification of microplastics (MPs) in aquatic systems using spectroscopic analysis. Procedures such as oxidation, which are employed to remove natural organic matter (NOM) from MPs, can be time- and cost-intensive. Furthermore, the identification process is prone to errors due to the subjective judgment of the operators. Therefore, in this study, deep learning (DL) was applied to improve the classification accuracies for mixtures of microplastic and natural organic matter (MP-NOM). A convolutional neural network (CNN)-based DL model with a spatial attention mechanism was adopted to classify substances from their Raman spectra. Subsequently, the classification results were compared with those obtained using conventional Raman spectral library software to evaluate the applicability of the model. Additionally, the crucial spectral band for training the DL model was investigated by applying gradient-weighted class activation mapping (Grad-CAM) as a post-processing technique. The model achieved an accuracy of 99.54%, which is much higher than the 31.44% achieved by the Raman spectral library. The Grad-CAM approach confirmed that the DL model can effectively identify MPs based on their visually prominent peaks in the Raman spectra. Furthermore, by tracking distinctive spectra without relying solely on visually prominent peaks, we can accurately classify MPs with less prominent peaks, which are characterized by a high standard deviation of intensity. These findings demonstrate the potential for automated and objective classification of MPs without the need for NOM preprocessing, indicating a promising direction for future research in microplastic classification.

Time-series modelling of harmful cyanobacteria blooms by convolutional neural networks and wavelet generated time-frequency images of environmental driving variables

Early warning systems for harmful cyanobacterial blooms (HCBs) that enable precautional control measures within water bodies and in water works are largely based on inferential time-series modelling. Among deep learning techniques, convolutional neural networks (CNNs) are widely applied for recognition of pictorial, acoustic and thermal images. Time-frequency images of environmental drivers generated by wavelets may provide crucial signals for modelling of HCBs to be recognized by CNNs. This study applies CNNs for time-series modelling of HCBs of Microcystis sp. in four South Korean rivers between 2016 and 2022 by means of time-frequency images of environmental drivers within the lead time of HCBs. After estimating the cardinal dates of beginning, peak, and ending of HCBs, wavelet analysis identified key drivers by phase analysis and generated time-frequency images of the drivers within the cardinal dates for 3, 4 and 5 years. Performances of CNNs were compared in terms of four determinants of input images: methods of estimating critical timings, the number of segments, time-series continuity, and image size. The resulting CNNs predicted high or low intensities of HCBs with a mean accuracy of 97.79 ± 0.06% and F1-score 97.49 ± 0.06% for training dataset, and a mean accuracy of 95.01 ± 0.06% and F1-score 93.30 ± 0.07% for testing dataset. Predictions of Microcystis abundances by CNNs achieved a mean MSE of 2.58 ± 2.46 and a mean R2 of 0.78 ± 0.20 for training, and a mean MSE of 2.76 ± 2.42 and a mean R2 of 0.55 ± 0.20 for testing dataset. Precipitation and discharge appeared to be the best performing drivers for qualitative and quantitative predictions of HCBs pointing at the nonstationary nature of river habitats. This study highlights the opportunities of time-series modelling by CNNs driven by wavelet generated time-frequency images of key environmental variables for forecasting of HCBs.

Assessment of Bladder Filling Type on Radiation Dose to Organs at Risk in MR-Guided Intracavity Brachytherapy for Cervical Cancer

PURPOSE/OBJECTIVE(S)

In this study, we evaluated whether the classification of bladder shape affects the absorbed dose (Gy) of OARs and its geometrical position to normal organs in MR-guided intracavitary brachytherapy (ICBT).

MATERIALS/METHODS

In this study, 269 patients who underwent MR-guided ICBT for cervical cancer from 2016 to 2022 were included. The applicator-inserted bladder filling type (BFT) classification was divided into three types (tilted, curved, and other shapes: group E). The anatomical positional relationship between the uterus and its surroundings was measured on pre-MR images and ICBT simulation MR images. Spearman's rank correlation analysis was used for bladder volume and OAR dose according to BFT. Anatomical differences were analyzed by ANOVA by measuring the distance from the center to both bladder walls.

RESULTS

In the correlation analysis considering the shape of the bladder, the tilted, curved, and group E had Spearman's ρ of 0.211; -0.323, 0.412; -0.307 and -0.035; -0.209 for maximum absorbed dose (D2cc) of bladder and small bowel, respectively. It was statistically significant in the tilted type and curved type. The average left and right bladder lengths differences of the tilted type were the highest at 8.47 cm and 7.11 cm, respectively. It was a statistically significant between bladder shape and the difference in left and right bladder lengths differences (p< 0.01).

CONCLUSION

In this study, it was confirmed that bladder distension increased the maximum bladder dose (D2cc) and decreased the maximum bowel dose (D2cc) to the tilted type and curved type. In addition, if the left and right bladder lengths are measured in pre-MR, the degree of bladder distension can be evaluated in advance by checking the shape of the bladder in the case of the tilting type before ICBT. Based on these findings, a prospective study is needed to evaluate the effect of ICBT on cervical cancer treatment outcomes through bladder type classification.

Ocean-atmosphere interactions: Different organic components across Pacific and Southern Oceans

Sea spray aerosol (SSA) particles strongly influence clouds and climate but the potential impact of ocean microbiota on SSA fluxes is still a matter of active research. Here-by means of in situ ship-borne measurements-we explore simultaneously molecular-level chemical properties of organic matter (OM) in oceans, sea ice, and the ambient PM_2.5 aerosols along a transect of 15,000 km from the western Pacific Ocean (36°13'N) to the Southern Ocean (75°15'S). By means of orbitrap mass spectrometry and optical characteristics, lignin-like material (24 ± 5 %) and humic material (57 ± 8 %) were found to dominate the pelagic Pacific Ocean surface, while intermediate conditions were observed in the Pacific-Southern Ocean waters. In the marine atmosphere, we found a gradient of features in the aerosol: lignin-like material (31 ± 9 %) dominating coastal areas and the pelagic Pacific Ocean, whereas lipid-like (23 ± 16 %) and protein-like (11 ± 10 %) OM controlled the sympagic Southern Ocean (sea ice-influence). The results of this study showed that the OM composition in the ocean, which changes with latitude, affects the OM in aerosol compositions in the atmosphere. This study highlights the importance of the global-scale OM monitoring of the close interaction between the ocean, sea ice, and the atmosphere. Sympagic primary marine aerosols in polar regions must be treated differently from other pelagic-type oceans.

Characterization of micropollutants in urban stormwater using high-resolution monitoring and machine learning

Urban rainfall events can lead to the runoff of pollutants, including industrial, pesticide, and pharmaceutical chemicals. Transporting micropollutants (MPs) into water systems can harm both human health and aquatic species. Therefore, it is necessary to investigate the dynamics of MPs during rainfall events. However, few studies have examined MPs during rainfall events due to the high analytical expenses and extensive spatiotemporal variability. Few studies have investigated the occurrence patterns of MPs and factors that influence their transport, such as rainfall duration, antecedent dry periods, and variations in streamflow. Moreover, while there have been many analyses of nutrients, suspended solids, and heavy metals during the first flush effect (FFE), studies on the transport of MPs during FFE are insufficient. This study aimed to identify the dynamics of MPs and FFE in an urban catchment, using high-resolution monitoring and machine learning methods. Hierarchical clustering analysis and partial least squares regression (PLSR) were implemented to estimate the similarity between each MP and identify the factors influencing their transport during rainfall events. Eleven dominant MPs comprised 75% of the total MP concentration and had a 100% detection frequency. During rainfall events, pesticides and pharmaceutical MPs showed a higher FFE than industrial MPs. Moreover, the initial 30% of the runoff volume contained 78.0% of pesticide and 50.1% of pharmaceutical substances for events W1 (July 5 to July 6, 2021) and W6 (August 31 to September 1, 2021), respectively. The PLSR model suggested that stormflow (m³/s) and the duration of antecedent dry hours (h) significantly influenced MP dynamics, yielding the variable importance on projection scores greater than 1.0. Hence, our findings indicate that MPs in urban waters should be managed by considering FFE.

An autopsy study of hollow fiber and multibore ultrafiltration membranes from a pilot-scale ultra high-recovery filtration system for surface water treatment

The organic fouling characteristics of hollow fiber ultrafiltration (HFUF) and multibore ultrafiltration (MBUF) membranes from long-term ultrafiltration (UF) membrane systems were systemically investigated in this study. The objective was to obtain insights into the fouling behavior of dissolved organic matter (DOM) in a pilot-scale ultra-high-recovery membrane filtration system (p-UHMS) used for surface water treatment. The pilot system consisted of a series of two different UF membranes (1st stage: polyvinylidene fluoride (PVDF) HFUF and 2nd stage: polyethersulfone (PES) MBUF). It was designed to feed the HFUF concentrate to the MBUF membranes to achieve ≥99.5 % total water recovery for surface water treatment, as these advances might enhance the production efficiencies of drinking water. The experimental results confirmed that hydrophobic DOM controlled the formation of HFUF membrane organic fouling, whereas hydrophilic DOM, including polysaccharide-like and protein-like matter, promoted MBUF membrane fouling. These opposing trends were attributed to the hydrophilic characteristics of the MBUF membrane surfaces (contact angle: PVDF = 90-130° and PES ≤ 80°), which reduced the hydrophobic interactions between the UF membrane surfaces and foulants. The performance declines of the MBUF membrane due to fouling layer formation was considerably severer than those of the HFUF membrane, decreasing total permeate water in the p-UHMS. Moreover, the quantity of the desorbed MBUF membrane foulants via 0.1 N NaOH was roughly 7.2 times larger than that of the desorbed HFUF membrane foulants through 0.1 N NaOH, indicating that alkaline-based cleaning agent could much more efficiently recover the performance of the fouled MBUF membranes. Hence, adequate cleaning strategies using alkaline-based agent for the MBUF membrane appeared to be essential for preventing the performance deterioration of the p-UHMS.

The risk assessment of arsenic contamination in the urbanized coastal aquifer of Rayong groundwater basin, Thailand using the machine learning approach

The rapid expansion of urbanization has resulted in an insufficient of groundwater resource. In order to use groundwater more efficiently, a risk assessment of groundwater pollution should be proposed. The present study used machine learning with three algorithms consisting of Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN) to locate risk areas of arsenic contamination in Rayong coastal aquifers, Thailand and selected the suitable model based on model performance and uncertainty for risk assessment. The parameters of 653 groundwater wells (Deep=236, Shallow=417) were selected based on the correlation of each hydrochemical parameters with arsenic concentration in deep and shallow aquifer environments. The models were validated with arsenic concentration collected from 27 well data in the field. The model's performance indicated that the RF algorithm has the highest performance as compared to those of SVM and ANN in both deep and shallow aquifers (Deep: AUC=0.72, Recall=0.61, F1 =0.69; Shallow: AUC=0.81, Recall=0.79, F1 =0.68). In addition, the uncertainty from the quantile regression of each model confirmed that the RF algorithm has the lowest uncertainty (Deep: PICP=0.20; Shallow: PICP=0.34). The result of the risk map obtained from the RF reveals that the deep aquifer, in the northern part of the Rayong basin has a higher risk for people to expose to As. In contrast, the shallow aquifer revealed that the southern part of the basin has a higher risk, which is also supported by the location of the landfill and industrial estates in the area. Therefore, health surveillance is important in monitoring the toxic effects on the residents who use groundwater from these contaminated wells. The outcome of this study can help policymakers in regions to manage the quality of groundwater resources and enhance the sustainable use of groundwater resources. The novelty process of this research can be used to further study other groundwater aquifers contaminated and increase the effectiveness of groundwater quality management.

An open-source deep learning model for predicting effluent concentration in capacitive deionization

To effectively evaluate the performance of capacitive deionization (CDI), an electrochemical ion separation technology, it is necessary to accurately estimate the number of ions removed (effluent concentration) according to energy consumption. Herein, we propose and evaluate a deep learning model for predicting the effluent concentration of a CDI process. The developed deep learning model exhibited excellent prediction accuracy for both constant current and constant voltage modes (R² ≥ 0.968), and the accuracy increased with the data size. This model was based on the open-source language, Python, and the code has since been distributed with proper instructions for general use. Owing to the nature of the data-oriented deep learning model, the findings of this study are not only applicable to conventional CDI but also to various types of CDI (membrane CDI, flow CDI, faradaic CDI, etc.). Therefore, by referring to the examples shown in this study, we hope that this open-source deep learning code will be widely used in CDI research.

Machine learning approaches to predict the photocatalytic performance of bismuth ferrite-based materials in the removal of malachite green

This study focuses on the potential capability of numerous machine learning models, namely CatBoost, GradientBoosting, HistGradientBoosting, ExtraTrees, XGBoost, DecisionTree, Bagging, light gradient boosting machine (LGBM), GaussianProcess, artificial neural network (ANN), and light long short-term memory (LightLSTM). These models were investigated to predict the photocatalytic degradation of malachite green from wastewater using various NM-BiFeO₃ composites. A comprehensive databank of 1200 data points was generated under various experimental conditions. The ten input variables selected were the catalyst type, reaction time, light intensity, initial concentration, catalyst loading, solution pH, humic acid concentration, anions, surface area, and pore volume of various photocatalysts. The MG dye degradation efficiency was selected as the output variable. An evaluation of the performance metrics suggested that the CatBoost model, with the highest test coefficient of determination (0.99) and lowest mean absolute error (0.64) and root-mean-square error (1.34), outperformed all other models. The CatBoost model showed that the photocatalytic reaction conditions were more important than the material properties. The modeling results suggested that the optimized process conditions were a light intensity of 105 W, catalyst loading of 1.5 g/L, initial MG dye concentration of 5 mg/L and solution pH of 7. Finally, the implications and drawbacks of the current study were stated in detail.

Lysophosphatidic acid-induced amphiregulin secretion by cancer-associated fibroblasts augments cancer cell invasion

Cancer-associated fibroblasts (CAFs) are key structural components of the tumor microenvironment and are closely associated with tumor invasion and metastasis. Lysophosphatidic acid (LPA) is a biolipid produced extracellularly and involved in tumorigenesis and metastasis. LPA has recently been implicated in the education and transdifferentiation of normal fibroblasts (NFs) into CAFs. However, little is known about the effects of LPA on CAFs and their participation in cancer cell invasion. In the present study, we identified a critical role of LPA-induced amphiregulin (AREG) secreted from CAFs in cancer invasiveness. CAFs secrete higher amounts of AREG than NFs, and LPA induces AREG expression in CAFs to augment their invasiveness. Strikingly, knocking out the AREG gene in CAFs attenuates cancer invasiveness and metastasis. Mechanistically, LPA induces Yes-associated protein (YAP) activation and Zinc finger E-box binding homeobox 1 (Zeb1) expression through the LPAR1 and LPAR3/Gi/Rho signaling axes, leading to AREG expression. Furthermore, we provide evidence that metformin, a biguanide derivative, significantly inhibits LPA-induced AREG expression in CAFs to attenuate cancer cell invasiveness. Collectively, the present data show that LPA induces AREG expression through YAP and Zeb1 in CAFs to promote cancer cell invasiveness, with the process being inhibited by metformin, providing potential biomarkers and therapeutic avenues to interdict cancer cell invasion.

Automation of membrane capacitive deionization process using reinforcement learning

Capacitive deionization (CDI) is an alternative desalination technology that uses electrochemical ion separation. Although several attempts have been made to maximize the energy efficiency and productivity of CDI with conventional control methods, it is difficult to optimize the CDI processes because of the complex correlation between the operational conditions and the composition of feed water. To address these challenges, we applied deep reinforcement learning (DRL) to automatically control the membrane capacitive deionization (MCDI) process, which is one of the representative CDI processes, to accomplish high energy efficiency while desalinating water. In the DRL model, the numerical model is combined as the environment that provides states according to the actions. The feed water conditions, that is, the input state of the DRL, were assumed to have a random salt concentration and constant foulant concentration. The model was constructed to minimize energy consumption and maximize desalted water volume per cycle. After training of 1,000 episodes, the DRL model achieved a 22.07% reduction in specific energy consumption (from 0.054 to 0.042 kWh m^-3) and 11.60% increase in water desalted water volume per cycle (from 1.96×10^-5 to 2.19×10^-5 m³), achieving the desired degree of desalination, compared to the first episode. This improved performance was because the trained model selected the optimized operating conditions of current, voltage, and the number and intensity of flushing. Furthermore, it was possible to train the model depending on demand by modifying the reward function of the DRL model. The fundamental principle described in this study for applying the DRL model in MCDI operations can be the cornerstone of a fully automated water desalination process.

Deep reinforcement learning in an ultrafiltration system: Optimizing operating pressure and chemical cleaning conditions

Enhancing engineering efficiency and reducing operating costs are permanent subjects that face all engineers over the world. To effectively improve the performance of filtration systems, it is necessary to determine an optimal operating condition beyond conventional methods of periodic and empirical operation. Herein, this paper proposes an effective approach to finding an optimal operating strategy using deep reinforcement learning (DRL), particularly for an ultrafiltration (UF) system. Deep learning was developed to represent the UF system utilizing a long-short term memory and provided an environment for DRL. DRL was designed to control three actions; operating pressure, cleaning time, and cleaning concentration. Ultimately, DRL proposed the UF system to actively change the operating pressure and cleaning conditions over time toward better water productivity and operating efficiency. DRL denoted ∼20.9% of specific energy consumption can be reduced by increasing average water flux (39.5-43.7 L m^-2 h^-1) and reducing operating pressure (0.617-0.540 bar). Moreover, the optimal action of DRL was reasonable to achieve better performance beyond the conventional operation. Crucially, this study demonstrated that due to the nature of DRL, the approach is tractable for engineering systems that have structurally complex relationships among operating conditions and resultants.

Exploring potential machine learning application based on big data for prediction of wastewater quality from different full-scale wastewater treatment plants

Water pollution generated from intensive anthropogenic activities has emerged as a critical issue concerning ecosystem balance and livelihoods worldwide. Although optimizing wastewater treatment efficiency is widely regarded as the foremost step to minimize pollutants released into the environment, this widespread application has encountered two major problems: firstly, the significant variation of influent wastewater constituents; secondly, complex treatment processes within wastewater treatment plants (WWTPs). Based on the data collected hourly using real-time sensors in three different full-scale WWTPs (24 h × 365 days × 3 WWTPs × 10 wastewater parameters), this work introduced the potential application of Machine Learning (ML) to predict wastewater quality. In this work, six different ML algorithms were examined and compared, varying from shallow to deep learning architectures including Seasonal Autoregressive Integrated Moving Average (SARIMAX), Random Forest (RF), Support Vector Machine (SVM), Gradient Tree Boosting (GTB), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Long Short-Term Memory (LSTM). These models were developed to detect total phosphorus in the outlet (Outlet-TP), which served as an output variable due to the rising concerns about the eutrophication problem. Irrespective of WWTPs, SARIMAX consistently demonstrated the best performance for regression estimation as evidenced by the lowest values of Mean Square Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and the highest coefficient of determination (R²). In terms of computation efficiency, SARIMAX exhibited acceptable time computation, acknowledging the successful application of this algorithm for Outlet-TP modeling. In contrast, the complex structure of LSTM made it time-consuming and unstable coupled with noise, while other shallower architectures, i.e., RF, SVM, GTB, and ANFIS were unable to address large datasets with nonlinear and nonstationary behavior. Consequently, this study provides a reliable and accurate approach to forecast wastewater effluent quality, which is pivotal in terms of the socio-economic aspects of wastewater management.

Hierarchical deep learning model to simulate phytoplankton at phylum/class and genus levels and zooplankton at the genus level

Harmful algal blooms (HABs) have become a global issue, affecting public health and water industries in numerous countries. Because funds for monitoring HABs are limited, model development may be an alternative approach for understanding and managing HABs. Continuous monitoring based on grab sampling is time-consuming, costly, and labor-intensive. However, improving simulation performance remains a major challenge in modeling, and current methods are limited to simulating phytoplankton (e.g., Microcystis sp., Anabaena sp., Aulacoseira sp., Cyclotella sp., Pediastrum sp., and Eudorina sp.) and zooplankton (e.g., Cyclotella sp., Pediastrum sp., and Eudorina sp.) at the genus level. The traditional modeling approach is limited for evaluating the interactions between phytoplankton and zooplankton. Recently, deep learning (DL) models have been proposed for solving modeling problems because of their large data handling capabilities and model structure flexibilities. In this study, we evaluated the applicability of DL for simulating phytoplankton at the phylum/class and genus levels and zooplankton at the genus level. Our work was an explicit representation of the taxonomic and ecological hierarchy of the DL model structure. The prerequisite for this model design was the data collection at two taxonomic and hierarchical levels. Our model consisted of hierarchical DL with classification transformer (TF) and regression TF models. These DL models were hierarchically connected; the output of the phylum/class level model was transferred to the genus level simulation model, and the output of the genus level model was fed into the zooplankton simulation model. The classification TF model determined the phytoplankton occurrence initiation date, whereas the regression TF model quantified the cell concentration of plankton. The hierarchical DL showed potential to simulate phytoplankton at the phylum/class and genus levels by producing average R^2, and root mean standard error values of 0.42 and 0.83 [log(cells mL^-1)], respectively. All simulated plankton results closely matched the measured concentrations. Particularly, the simulated cyanobacteria showed good agreement with the measured cell concentration, with an R² value of 0.72. In addition, our simulated result showed good agreement in peak concentration compared to observations. However, a limitation remained in following the temporal variation of Tintinnopsis sp. and Bosmia sp. Using an importance map from the TF model, water temperature, total phosphorus, and total nitrogen were identified as significant variables influencing phytoplankton and zooplankton blooms. Overall, our study demonstrated that DL can be used for modeling HABs at the phylum/class and genus levels.

Chemical accidents in freshwater: Development of forecasting system for drinking water resources

Chemical accidents have threatened drinking water safety and aquatic systems when hazardous chemicals flow into inland waterbodies through pipelines in industrial complexes. In this study, a forecasting system was developed for the prevention of drinking water resource pollution by considering chemical transport/fate through both pipelines and river channels. To this end, we coupled a pipe network model (Storm Water Management Model) with a calibrated hydrodynamic model (Environmental Fluid Dynamics Code). In addition, we investigated whether chemical transport through pipelines would make a difference in chemical concentration predictions. For both pipelines and river channels, the results showed lower peak concentrations than those without pipelines, whereas the time of peak concentration did not change significantly. When chemicals were transported with both pipelines and river channels, the peak concentrations were 25.81% and 41.91% lower than those of chemicals carried directly into the Han and Geum Rivers without the pipeline transport. Further, our system is automated from scenario generation to analysis and usage is straightforward, with a simple input of accident information. The results of this study can be utilized to establish a safe water supply system and preliminary countermeasures against accidental water pollution in the future.

Abundance and diversity of antibiotic resistance genes and bacterial communities in the western Pacific and Southern Oceans

This study investigated the abundance and diversity of antibiotic resistance genes (ARGs) and the composition of bacterial communities along a transect covering the western Pacific Ocean (36°N) to the Southern Ocean (74°S) using the Korean icebreaker R/V Araon (total cruise distance: 14,942 km). The relative abundances of ARGs and bacteria were assessed with quantitative PCR and next generation sequencing, respectively. The absolute abundance of ARGs was 3.0 × 10⁶ ± 1.6 × 10⁶ copies/mL in the western Pacific Ocean, with the highest value (7.8 × 10⁶ copies/mL) recorded at a station in the Tasman Sea (37°S). The absolute abundance of ARGs in the Southern Ocean was 1.8-fold lower than that in the western Pacific Ocean, and slightly increased (0.7-fold) toward Terra Nova Bay in Antarctica, possibly resulting from natural terrestrial sources or human activity. β-Lactam and tetracycline resistance genes were dominant in all samples (88-99%), indicating that they are likely the key ARGs in the ocean. Correlation and network analysis showed that Bdellovibrionota, Bacteroidetes, Cyanobacteria, Margulisbacteria, and Proteobacteria were positively correlated with ARGs, suggesting that these bacteria are the most likely ARG carriers. This study highlights the latitudinal profile of ARG distribution in the open ocean system and provides insights that will help in monitoring emerging pollutants on a global scale.

A novel method for micropollutant quantification using deep learning and multi-objective optimization

Micropollutants (MPs) released into aquatic ecosystems have adverse effects on public health. Hence, monitoring and managing MPs in aquatic systems are imperative. MPs can be quantified by high-resolution mass spectrometry (HRMS) with stable isotope-labeled (SIL) standards. However, high cost of SIL solutions is a significant issue. This study aims to develop a rapid and cost-effective analytical approach to estimate MP concentrations in aquatic systems based on deep learning (DL) and multi-objective optimization. We hypothesized that internal standards could quantify the MP concentrations other than the target substance. Our approach considered the precision of intra-/inter-day repeatability and natural organic matter information to reduce instrumental error and matrix effect. We selected standard solutions to estimate the concentrations of 18 MPs. Among the optimal DL models, DarkNet-53 using nine standard solutions yielded the highest performance, while ResNet-50 yielded the lowest. Overall, this study demonstrated the capability of DL models for estimating MP concentrations.

When river water meets seawater: Insights into primary marine aerosol production

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.

Analysis of micropollutants in a marine outfall using network analysis and decision tree

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.

Interactions of E. coli with algae and aquatic vegetation in natural waters

Both algae and bacteria are essential inhabitants of surface waters. Their presence is of ecological significance and sometimes of public health concern triggering various control actions. Interactions of microalgae, macroalgae, submerged aquatic vegetation, and bacteria appear to be important phenomena necessitating a deeper understanding by those involved in research and management of microbial water quality. Given the long-standing reliance on Escherichia coli as an indicator of the potential presence of pathogens in natural waters, understanding its biology in aquatic systems is necessary. The major effects of algae and aquatic vegetation on E. coli growth and survival, including changes in the nutrient supply, modification of water properties and constituents, impact on sunlight radiation penetration, survival as related to substrate attachment, algal mediation of secondary habitats, and survival inhibition due to the release of toxic substances and antibiotics, are discussed in this review. An examination of horizontal gene transfer and antibiotic resistance potential, strain-specific interactions, effects on the microbial, microalgae, and grazer community structure, and hydrodynamic controls is given. Outlooks due to existing and expected consequences of climate change and advances in observation technologies via high-resolution satellite imaging, unmanned aerial vehicles (drones), and mathematical modeling are additionally covered. The multiplicity of interactions among bacteria, algae, and aquatic vegetation as well as multifaceted impacts of these interactions, create a wide spectrum of research opportunities and technology developments.

Improving the performance of machine learning models for early warning of harmful algal blooms using an adaptive synthetic sampling method

Many countries have attempted to monitor and predict harmful algal blooms to mitigate related problems and establish management practices. The current alert system-based sampling of cell density is used to intimate the bloom status and to inform rapid and adequate response from water-associated organizations. The objective of this study was to develop an early warning system for cyanobacterial blooms to allow for efficient decision making prior to the occurrence of algal blooms and to guide preemptive actions regarding management practices. In this study, two machine learning models: artificial neural network (ANN) and support vector machine (SVM), were constructed for the timely prediction of alert levels of algal bloom using eight years' worth of meteorological, hydrodynamic, and water quality data in a reservoir where harmful cyanobacterial blooms frequently occur during summer. However, the proportion imbalance on all alert level data as the output variable leads to biased training of the data-driven model and degradation of model prediction performance. Therefore, the synthetic data generated by an adaptive synthetic (ADASYN) sampling method were used to resolve the imbalance of minority class data in the original data and to improve the prediction performance of the models. The results showed that the overall prediction performance yielded by the caution level (L1) and warning level (L2) in the models constructed using a combination of original and synthetic data was higher than the models constructed using original data only. In particular, the optimal ANN and SVM constructed using a combination of original and synthetic data during both training (including validation) and test generated distinctively improved recall and precision values of L1, which is a very critical alert level as it indicates a transition status from normalcy to bloom formation. In addition, both optimal models constructed using synthetic-added data exhibited improvement in recall and precision by more than 33.7% while predicting L-1 and L-2 during the test. Therefore, the application of synthetic data can improve detection performance of machine learning models by solving the imbalance of observed data. Reliable prediction by the improved models can be used to aid the design of management practices to mitigate algal blooms within a reservoir.

Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river: A 10-year study of the Han River, South Korea

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.

Monitoring the vertical distribution of HABs using hyperspectral imagery and deep learning models

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.

Prediction of biogas production in anaerobic co-digestion of organic wastes using deep learning models

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.

Cyanobacteria cell prediction using interpretable deep learning model with observed, numerical, and sensing data assemblage

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 (CNN_an) 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 CNN_an 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 CNN_an 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 CNN_an 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.

Effect of hyperspectral image-based initial conditions on improving short-term algal simulation of hydrodynamic and water quality models

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.

Simultaneous Energy Storage and Seawater Desalination using Rechargeable Seawater Battery: Feasibility and Future Directions

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.

Changes in adsorption mechanisms of radioactive barium, cobalt, and strontium ions using spent coffee waste biochars via alkaline chemical activation: Enrichment effects of O-containing functional groups

The single adsorption of radioactive barium (Ba(II)), cobalt (Co(II)), and strontium (Sr(II)) ions using pristine (SCWB-P) and chemically activated spent coffee waste biochars with NaOH (SCWB-A) were thoroughly explored in order to provide deeper insights into the changes in their adsorption mechanisms through alkaline chemical activation. The greater removal efficiencies of SCWB-A (76.6-97.3%) than SCWB-P (45.6-75.2%) and the consistency between the adsorptive removal patterns (Ba(II) > Sr(II) > Co(II)) and oxygen bond dissociation enthalpies (BaO (562 kJ/mol) > SrO (426 kJ/mol) > CoO (397 kJ/mol)) of radioactive species supported the assumption that the adsorption removal of radioactive species with spent coffee waste biochars highly depended on the abundances of O-containing functional groups. The calculated R² values of the pseudo-first-order (SCWB-P = 0.998-0.999; SCWB-A = 0.850-0.921) and pseudo-second-order kinetic models (SCWB-P = 0.988-0.998; SCWB-A = 0.935-0.966) are evident that the physisorption mainly controlled the adsorption of radioactive species toward SCWB-P and the chemisorption played a crucial role in their adsorptive removal with SCWB-A. From the calculated intra-particle diffusion, isotherm, thermodynamic parameters, it can be concluded that the intra-particle diffusion and monolayer adsorption primarily governed the adsorption of radioactive species using SCWB-P and SCWB-A, and their adsorption processes occurred spontaneously and endothermically. The dominant adsorption mechanism of spent coffee waste biochars was changed from physisorption (ΔH° of SCWB-P = 21.6-29.8 kJ/mol) to chemisorption (ΔH° of SCWB-A = 42.4-81.3 kJ/mol) through alkaline chemical activation. The distinctive M-OH peak in the O1s XPS spectra of SCWB-A directly corresponding to the decrease in the abundances of O-containing functional groups confirms again that the enrichment of O-containing functional groups markedly facilitated the adsorption removal of radioactive species by chemisorption occurred at the inner and outer surfaces of spent coffee waste biochars.

Pharmaceutical removal at low energy consumption using membrane capacitive deionization

The performance of the membrane capacitive deionization (MCDI) system was evaluated during the removal of three selected pharmaceuticals, neutral acetaminophen (APAP), cationic atenolol (ATN), and anionic sulfamethoxazole (SMX), in batch experiments (feed solution: 2 mM NaCl and 0.01 mM of each pharmaceutical). Upon charging, the cationic ATN showed the highest removal rate of 97.65 ± 1.71%, followed by anionic SMX (93.22 ± 1.66%) and neutral APAP (68.08 ± 5.24%) due to the difference in electrostatic charge and hydrophobicity. The performance parameters (salt adsorption capacity, specific capacity, and cycling efficiency) and energy factors (specific energy consumption and recoverable energy) were further evaluated over ten consecutive cycles depending on the pharmaceutical addition. A significant decrease in the specific adsorption capacity (from 24.6 to ∼3 mg-NaCl g^-1) and specific capacity (from 17.6 to ∼2.5 mAh g^-1) were observed mainly due to the shortened charging and discharging time by pharmaceutical adsorption onto the electrode. This shortened charging time also led to an immediate drop in specific energy consumption from 0.41 to 0.04 Wh L^-1. Collectively, these findings suggest that MCDI can efficiently remove pharmaceuticals at a low energy demand; however, its performance changes dramatically as the pharmaceuticals are present in the target water.

Evaluating an on-line cleaning agent for mitigating organic fouling in a reverse osmosis membrane

Cleaning-in-place (CIP) is a representative fouling management process from which the filtration performances of fouled membranes can be recovered. However, CIP can cause significant inefficiency in water production because frequent system restabilization is necessary for cleaning processes. This study applied a newly developed on-line cleaning agent (OCA, a feed water additive for fouling mitigation), to reduce the number of CIP by enhancing water productivity. Reverse osmosis filtration was performed to evaluate the effect of on-line cleaning on the mitigation of organic fouling originating from humic acid (HA) and bovine serum albumin. OCA increased the permeate flux in proportion to OCA concentration. In particular, OCA effectively reduced the fouling layer thickness by 22% when fouling was influenced by HA-Ca²⁺ complexation, increasing water production by 5%. It also had a minor influence on bovine serum albumin fouling, producing a 1.4% increase in permeate flux. Furthermore, the pore blockage-cake filtration model was used to evaluate OCA cleaning performance through the reduction in fouling layer resistance and the growth parameter. The results demonstrated the advantages of OCA utilization for mitigating cake layer development. These findings imply that OCA can be an effective cleaning additive, especially in seawater and groundwater treatment processes with a high proportion of HA and calcium ions.

A machine learning approach for early warning of cyanobacterial bloom outbreaks in a freshwater reservoir

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.

Deep learning model for simulating influence of natural organic matter in nanofiltration

Controlling membrane fouling in a membrane filtration system is critical to ensure high filtration performance. A forecast of membrane fouling could enable preliminary actions to relieve the development of membrane fouling. Therefore, we established a long short-term memory (LSTM) model to investigate the variations in filtration performance and fouling growth. For data acquisition, we first conducted lab-scale membrane fouling experiments to identify the diverse fouling mechanisms of natural organic matter (NOM) in nanofiltration (NF) systems. Four types of NOMs were considered as model foulants: humic acid, bovine-serum-albumin, sodium alginate, and tannic acid. In addition, real-time 2D images were acquired via optical coherence tomography (OCT) to quantify the cake layer formed on the membrane. Subsequently, experimental data were used to train the LSTM model to predict permeate flux and fouling layer thickness as output variables. The model performance exhibited root mean square errors of <1 L/m²/h for permeate flux and <10 µm for fouling layer thickness in both the training and validation steps. In this study, we demonstrated that deep learning can be used to simulate the influence of NOMs on the NF system and also be applied to simulate other membrane processes.

Discoidin Domain Receptor 2 Mediates Lysophosphatidic Acid-Induced Ovarian Cancer Aggressiveness

Lysophosphatidic acid (LPA), a bioactive lipid produced extracellularly by autotaxin (ATX), has been known to induce various pathophysiological events, including cancer cell invasion and metastasis. Discoidin domain receptor 2 (DDR2) expression is upregulated in ovarian cancer tissues, and is closely associated with poor clinical outcomes in ovarian cancer patients. In the present study, we determined a critical role and signaling cascade for the expression of DDR2 in LPA-induced ovarian cancer cell invasion. We also found ectopic expression of ATX or stimulation of ovarian cancer cells with LPA-induced DDR2 expression. However, the silencing of DDR2 expression significantly inhibited ATX- and LPA-induced ovarian cancer cell invasion. In addition, treatment of the cells with pharmacological inhibitors of phosphoinositide 3-kinase (PI3K), Akt, and mTOR abrogated LPA-induced DDR2 expression. Moreover, we observed that HIF-1α, located downstream of the mTOR, is implicated in LPA-induced DDR2 expression and ovarian cancer cell invasion. Finally, we provide evidence that LPA-induced HIF-1α expression mediates Twist1 expression to upregulate DDR2 expression. Collectively, the present study demonstrates that ATX, and thereby LPA, induces DDR2 expression through the activation of the PI3K/Akt/mTOR/HIF-1α/Twist1 signaling axes, aggravating ovarian cancer cell invasion.

Prediction of antibiotic-resistance genes occurrence at a recreational beach with deep learning models

Antibiotic resistance genes (ARGs) have been reported to threaten the public health of beachgoers worldwide. Although ARG monitoring and beach guidelines are necessary, substantial efforts are required for ARG sampling and analysis. Accordingly, in this study, we predicted ARGs occurrence that are primarily found on the coast after rainfall using a conventional long short-term memory (LSTM), LSTM-convolutional neural network (CNN) hybrid model, and input attention (IA)-LSTM. To develop the models, 10 categories of environmental data collected at 30-min intervals and concentration data of 4 types of major ARGs (i.e., aac(6'-Ib-cr), bla_TEM, sul1, and tetX) obtained at the Gwangalli Beach in South Korea, between 2018 and 2019 were used. When individually predicting ARGs occurrence, the conventional LSTM and IA-LSTM exhibited poor R² values during training and testing. In contrast, the LSTM-CNN exhibited a 2-6-times improvement in accuracy over those of the conventional LSTM and IA-LSTM. However, when predicting all ARGs occurrence simultaneously, the IA-LSTM model exhibited a superior performance overall compared to that of LSTM-CNN. Additionally, the influence of environmental variables on prediction was investigated using the IA-LSTM model, and the ranges of input variables that affect each ARG were identified. Consequently, this study demonstrated the possibility of predicting the occurrence and distribution of major ARGs at the beach based on various environmental variables, and the results are expected to contribute to management of ARG occurrence at a recreational beach.

Designing a marine outfall to reduce microbial risk on a recreational beach: Field experiment and modeling

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.

Identification of influencing factors of A. catenella bloom using machine learning and numerical simulation

Alexandrium catenella (A. catenella) is a notorious algal species known to cause paralytic shellfish poisoning (PSP) in Korean coastal waters. There have been numerous studies on its temporal and spatial blooms in Korea. However, its bloom dynamics have not been fully understood because of the complexity in physical, chemical, and biological environments. This study aims to identify the factors that influence A. catenella blooms by applying a numerical model and machine learning. Intensive monitoring of A. catenella was conducted to investigate temporal variations in its population and its spatial distribution in the area with frequent occurrences of PSP bloom initiation. Moreover, a numerical model was built to analyze the ocean physical factors related to the bloom of A. catenella. Based on the information obtained from the monitored and simulated results, the decision tree (DT) method was applied to identify factors that caused the bloom. The outbreak of A. catenella was observed in the eastern coastal water of Geoje Island in 2017, recording a peak density of 4 × 10⁴ (cell L^-1). Retention time and particle scattering demonstrated that the physical force in 2017 was weaker than that in 2018, as shown by the smaller effects of advection and dispersion in 2017. The decision tree model showed that (1) water temperature below 17.21 °C was ideal for the growth of A. catenella, (2) phosphate influenced the growth of the species, and (3) cell density was accelerated with increasing retention time. The results from DT can contribute to the prediction of A. catenella blooms by determining the conditions that cause bloom initiation. Further, they can be used as a practical approach for mitigating HABs. Thus, machine learning and numerical simulation in this study can be a potential approach for effectively managing the bloom of A. catenella.

Hydrometeorological Influence on Antibiotic-Resistance Genes (ARGs) and Bacterial Community at a Recreational Beach in Korea

We investigated the occurrence and distribution of antibiotic-resistance genes (ARGs) and the composition of a bacterial community under conditions of rainfall on a recreational beach in Korea. Seawater samples, collected every 1‒5 hours in June 2018 and May 2019, were analyzed using quantitative real-time polymerase chain reaction and next-generation sequencing. We found a substantial influence of rainfall and tidal levels on the relative abundance of total ARGs and bacterial operational taxonomic units (OTUs), which showed 1.9 × 10³ and 1.1 × 10¹ fold increases, respectively. In particular, the elevated levels of ARGs were maintained for up to 32 hours after rainfall. An increased abundance of sewage-related ARGs and bacterial OTUs suggested that combined sewer overflow (CSO) may be the major factor contributing to the increase in the number and diversity of ARGs and related bacterial communities. Network analysis of ARGs and OTUs indicated that, at the genus level, Acinetobacter, Pseudomonas, and Prevotella were the main potential pathogens carrying the observed ARGs in the recreational seawater. Overall, these findings highlight the potential threat to public health on beaches, and indicate the requirement for more adequate monitoring, with greater efforts to mitigate the propagation of ARGs arising from CSOs.

Influence of natural organic matter on membrane capacitive deionization performance

Membrane capacitive deionization (MCDI) is a prospective desalination technology that removes ions using an electric potential difference across charged porous carbon electrodes. Natural organic matter (NOM) in feed water could influence the electrochemical process by leading to pore-blockages or forming a cake layer on the ion-exchange membrane-coated porous carbon electrode, thereby hindering ion removal. In this study, we explored the influence of different types of NOM, namely, humic acid (HA) and tannic acid (TA), on the MCDI desalination process for feed waters with inorganic salts (NaCl and CaCl₂). HA significantly interfered with the adsorption process and reduced the salt removal rate by up to 68% in the case of NaCl-based feed water. However, the influence of HA on salt removal in the case of CaCl₂-based feed water was marginal owing to the formation of a charge-neutralized complex, which was caused by the egg-box effect between Ca²⁺ and HA. TA reduced removal rates of salts (NaCl and CaCl₂) by 37% and 60%, respectively. This is because of the lower molecular weight and smaller hydrodynamic diameter of TA relative to that of HA, owing to which TA exhibits a stronger adhesion to the electrode pore structure. Furthermore, as TA substantially reduces MCDI performance with regard to the adsorption of inorganic salts, its presence in feed water results in higher electrical resistance and energy consumption.

Prediction of Oxidant Exposures and Micropollutant Abatement during Ozonation Using a Machine Learning Method

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., ∫0t[O3]dt⁢  and⁢  ∫0t[O•H]dt) 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.