Stochastic modeling of chlorophyll-a for probabilistic assessment and monitoring of algae blooms in the Lower Nakdong River, South Korea

Real-time chlorophyll-a forecasting using machine learning framework with dimension reduction and hyperspectral data

Since water is an essential resource in various fields, it requires constant monitoring. Chlorophyll-a concentration is a crucial indicator of water quality and can be used to monitor water quality. In this study, we developed methods to forecast chlorophyll-a concentrations in real-time using hyperspectral data on IoT platform and various machine learning algorithms. Compared to regular cameras that record information only in the three broad color bands of red, green, and blue, the hyperspectral images of drinking water sources record the data in dozens or even hundreds of distinct small wavelength bands, providing each pixel in an image with a full spectrum. Different machine learning algorithms have been developed using hyperspectral data and field observations of water quality and weather conditions. Previous studies have predicted chlorophyll concentrations using either partial least squares (PLS), which is a dimensionality reduction method, or machine learning. In contrast, our study employed the PLS technique as a preprocessing step to diminish the dimensionality of the hyperspectral data, followed by the application of the machine learning techniques with optimized hyperparameters to improve the precision of the predictions, thereby introducing a real-time mechanism for chlorophyll-a prediction. Consequently, a machine learning algorithm with R2 values of 0.9 or above and sufficiently small RMSE was developed for real-time chlorophyll-a forecasting. Real-time chlorophyll-a forecasting using LightGBM has the best performance, with a mean R2 of 0.963 and a mean RMSE of 2.679. This paper is expected to have applications in algal bloom early detection on monitoring systems.

Robust clustering-based hybrid technique enabling reliable reservoir water quality prediction with uncertainty quantification and spatial analysis

Machine learning methodology has recently been considered a smart and reliable way to monitor water quality parameters in aquatic environments like reservoirs and lakes. This study employs both individual and hybrid-based techniques to boost the accuracy of dissolved oxygen (DO) and chlorophyll-a (Chl-a) predictions in the Wadi Dayqah Dam located in Oman. At first, an AAQ-RINKO device (CTD+ sensor) was used to collect water quality parameters from different locations and varying depths in the reservoir. Second, the dataset is segmented into homogeneous clusters based on DO and Chl-a parameters by leveraging an optimized K-means algorithm, facilitating precise estimations. Third, ten sophisticated variational-individual data-driven models, namely generalized regression neural network (GRNN), random forest (RF), gaussian process regression (GPR), decision tree (DT), least-squares boosting (LSB), bayesian ridge (BR), support vector regression (SVR), K-nearest neighbors (KNN), multilayer perceptron (MLP), and group method of data handling (GMDH) are employed to estimate DO and Chl-a concentrations. Fourth, to improve prediction accuracy, bayesian model averaging (BMA), entropy weighted (EW), and a new enhanced clustering-based hybrid technique called Entropy-ORNESS are employed to combine model outputs. The Entropy-ORNESS method incorporates a Genetic Algorithm (GA) to determine optimal weights and then combine them with EW weights. Finally, the inclusion of bootstrapping techniques introduces a stochastic assessment of model uncertainty, resulting in a robust estimator model. In the validation phase, the Entropy-ORNESS technique outperforms the independent models among the three fusion-based methods, yielding R2 values of 0.92 and 0.89 for DO and Chl-a clusters, respectively. The proposed hybrid-based methodology demonstrates reduced uncertainty compared to single data-driven models and two combination frameworks, with uncertainty levels of 0.24% and 1.16% for cluster 1 of DO and cluster 2 of Chl-a parameters. As a highlight point, the spatial analysis of DO and Chl-a concentrations exhibit similar pattern variations across varying depths of the dam according to the comparison of field measurements with the best hybrid technique, in which DO concentration values notably decrease during warmer seasons. These findings collectively underscore the potential of the upgraded weighted-based hybrid approach to provide more accurate estimations of DO and Chl-a concentrations in dynamic aquatic environments.

Development of a basin-scale total nitrogen prediction model by integrating clustering and regression methods

Nutrient runoff into rivers caused by human activity has led to global eutrophication issues. The Nakdong River in South Korea is currently facing significant challenges related to eutrophication and harmful algal blooms, underscoring the critical importance of managing total nitrogen (T-N) levels. However, traditional methods of indoor analysis, which depend on sampling, are labor-intensive and face limitations in collecting high-frequency data. Despite advancements in sensor allowing for the measurement of various parameters, sensors still cannot directly measure T-N, necessitating surrogate regression methods. Therefore, we conducted T-N predictions using a water quality dataset collected from 2018 to 2022 at 157 observatories within the Nakdong River basin. To account for the water quality characteristics of each location, we employed a clustering technique to divide the basin and compared a Gaussian mixture model with K-means clustering. Moreover, optimal regressor for each cluster was selected by comparing multiple linear regression (MLR), random forest, and XGBoost. The results showed that forming four clusters via K-means clustering was the most suitable approach and MLR was reasonably accurate for all clusters. Subsequently, recursive feature elimination cross-validation was used to identify suitable parameters for T-N prediction, thus leading to the construction of high-accuracy T-N prediction models. Clustering was useful not only for improving the regressors but also for spatially analyzing the water quality characteristics of the Nakdong River. The MLR model can reveal causal relationships and thus is useful for decision-making. The results of this study revealed that the combination of a simple linear regression model and clustering method can be applied to a wide watershed. The clustering-based regression model showed potential for accurately predicting T-N at the basin level and is expected to contribute to nationwide water quality management through future applications in various fields.

Spatial dynamics and risk assessment of phosphorus in the river sediment continuum (Qinhuai River basin, China)

This study investigated the concentration and fractionation of phosphorus (P) using sequential P extraction and their influencing factors by introducing the PLS-SEM model (partial least squares structural equation model) along this continuum from the Qinhuai River. The results showed that the average concentrations of inorganic P (IP) occurred in the following order: urban sediment (1499.1 mg/kg) > suburban sediment (846.1-911.9 mg/kg) > rural sediment (661.1 mg/kg) > natural sediment (179.9 mg/kg), and makes up to 53.9-87.1% of total P (TP). The same as the pattern of IP, OP nearly increased dramatically with increasing the urbanization gradient. This spatial heterogenicity of P along a river was attributed mainly to land use patterns and environmental factors (relative contribution affecting the P fractions: sediment nutrients > metals > grain size). In addition, the highest values of TP (2876.5 mg/kg), BAP (biologically active P, avg, 675.7 mg/kg), and PPI (P pollution index, ≥ 2.0) were found in urban sediments among four regions, indicating a higher environmental risk of P release, which may increase the risk of eutrophication in overlying water bodies. Collectively, this work improves the understanding of the spatial dynamics of P in the natural-rural-urban river sediment continuum, highlights the need to control P pollution in urban sediments, and provides a scientific basis for the future usage and disposal of P in sediments.

Rapid measurement of brown tide algae using Zernike moments and ensemble learning based on excitation-emission matrix fluorescence

Accurate real-time prediction of microalgae density has great practical significance for taking countermeasures before the advent of Harmful algal blooms (HABs), and the non-destructive and sensitive property of excitation-emission matrix fluorescence (EEMF) spectroscopy makes it applicable to online monitoring and control. In this study, an efficient image preprocessing algorithm based on Zernike moments (ZMs) was proposed to extract compelling features from EEM intensities images. The determination of the highest order of ZMs considered both reconstruction error and computational cost, then the optimal subset of preliminarily extracted 36 ZMs was screened via the BorutaShap algorithm. Aureococcus anophagefferens concentration prediction models were developed by combining BorutaShap and ensemble learning models (random forest (RF), gradient boosting decision tree (GBDT), and XGBoost). The experimental results show that BorutaShap_GBDT preserved the superior subset of ZMs, and the integration of BorutaShap_GBDT and XGBoost achieved the highest prediction accuracy. This research provides a new and promising strategy for rapidly measuring microalgae cell density.

Modeling, challenges, and strategies for understanding impacts of climate extremes (droughts and floods) on water quality in Asia: A review

The increasing frequency and intensity of extreme climate events are among the most expected and recognized consequences of climate change. Prediction of water quality parameters becomes more challenging with these extremes since water quality is strongly related to hydro-meteorological conditions and is particularly sensitive to climate change. The evidence linking the influence of hydro-meteorological factors on water quality provides insights into future climatic extremes. Despite recent breakthroughs in water quality modeling and evaluations of climate change's impact on water quality, climate extreme informed water quality modeling methodologies remain restricted. This review aims to summarize the causal mechanisms across climate extremes considering water quality parameters and Asian water quality modeling methods associated with climate extremes, such as floods and droughts. In this review, we (1) identify current scientific approaches to water quality modeling and prediction in the context of flood and drought assessment, (2) discuss the challenges and impediments, and (3) propose potential solutions to these challenges to improve understanding of the impact of climate extremes on water quality and mitigate their negative impacts. This study emphasizes that one crucial step toward enhancing our aquatic ecosystems is by comprehending the connections between climate extreme events and water quality through collective efforts. The connections between the climate indices and water quality indicators were demonstrated to better understand the link between climate extremes and water quality for a selected watershed basin.

Assessment of the trophic state of the Soła River dam cascade, Polish Carpathians: a comparison of the methodology

The aim of this research was to determine the trophic state of mountain dam reservoirs, which are characterized by greater hydrological and ecological dynamics than lowland reservoirs. The trophic state of three dam reservoirs forming a cascade system was investigated. Trophic evaluation was carried out based on multiple criteria, i.e., (1) the content of chlorophyll a in the water, (2) planktonic algal biomass, (3) groups and species of algae, (4) the total phosphorus concentration in the water, and (5) the Integral Trophic State index (ITS). The analyzed parameters were characterized by high variability during the study period, which to a large extent may have resulted from the mountain environmental conditions. The greatest dynamics concerned parameters related to phytoplankton development. Unequivocal determinations of the trophic states of the reservoirs were difficult; however, it was found that in successive reservoirs of the cascade (from the highest to the lowest), a reduction in water fertility occurred.

The novel chitosan-amphoteric starch dual flocculants for enhanced removal of Microcystis aeruginosa and algal organic matter

A novel flocculation strategy for simultaneously removing Microcystis aeruginosa and algal organic matter (AOM) was proposed using chitosan-amphoteric starch (C-A) dual flocculants in an efficient, cost-effective and ecologically friendly way, providing new insights for harmful algal blooms (HABs) control. A dual-functional starch-based flocculant, amphoteric starch (AS) with high anion degree of substitution (DS_A) and cation degree of substitution (DS_C), was prepared using a cationic moiety of 3-chloro-2-hydroxypropyltrimethylammonium chloride (CTA) coupled with an anion moiety of chloroacetic acid onto the backbone of starch simultaneously. In combination of the results of FTIR, XPS, ¹H NMR, ¹³C NMR, GPC, EA, TGA and SEM, it was evidenced that the successfully synthesized AS with excellent structural characteristics contributed to the enhanced flocculation of M. aeruginosa. Furthermore, the novel C-A dual flocculants could achieve not only the removal of >99.3 % of M. aeruginosa, but also the efficacious flocculation of algal organic matter (AOM) at optimal concentration of (0.8:24) mg/L, within a wide pH range of 3-11. The analysis of zeta potential and cellular morphology revealed that the dual effects of both enhanced charge neutralization and notable netting-bridging played a vital role in efficient M. aeruginosa removal.

A multivariate Chain-Bernoulli-based prediction model for cyanobacteria algal blooms at multiple stations in South Korea

Predicting the occurrence of algal blooms is of great importance in managing water quality. Moreover, the demand for predictive models, which are essential tools for understanding the drivers of algal blooms, is increasing with global warming. However, modeling cyanobacteria dynamics is a challenging task. We developed a multivariate Chain-Bernoulli-based prediction model to effectively forecast the monthly sequences of algal blooms considering hydro-environmental predictors (water temperature, total phosphorus, total nitrogen, and water velocity) at a network of stations. The proposed model effectively predicts the risk of harmful algal blooms, according to performance measures based on categorical metrics of a contingency table. More specifically, the model performance assessed by the LOO cross-validation and the skill score for the POD and CSI during the calibration period was over 0.8; FAR and MR were less than 0.15. We also explore the relationship between hydro-environmental predictors and algal blooms (based on cyanobacteria cell count) to understand the dynamics of algal blooms and the relative contribution of each potential predictor. A support vector machine is applied to delineate a plane separating the presence and absence of algal bloom occurrences determined by stochastic simulations using different combinations of predictors. The multivariate Chain-Bernoulli-based prediction model proposed here offers effective, scenario-based, and strategic options and remedies (e.g., controlling the governing environmental predictors) to relieve or reduce increases in cyanobacteria concentration and enable the development of water quality management and planning in river systems.

A framework for exploring environmental risk of the longest inter-basin water diversion project under the influence of multiple factors: A case study in China

Multi-factor risk assessment is an important prerequisite for water quality protection and the safe operation of mega hydro-projects. As the largest long-distance inter-basin water diversion project in the world, the Middle Route of the South-to-North Water Diversion Project of China (MRSNWDPC) has been in operation for 8 years and has benefited 79 million people along the canal. However, concerns have been raised in recent years about the potential negative effects of abnormal algal proliferation in the MRSNWDPC. It is very important for the safety of water supply to carry out relevant risk analysis and formulate regulatory management. In order to quantitatively evaluate the risk of algal proliferation in the MRSNWDPC under the influence of multiple factors, a multivariate risk assessment method based on Vine Copula theory and Monte Carlo simulation was proposed. Five key factors (water temperature, flow velocity, flow rate, algal cell density, and dissolved oxygen) were used and multiple dependency models in each section of the MRSNWDPC from January 2016 to January 2019 were established to study the risk of algal proliferation under multiple scenarios. The results demonstrate that water temperature can be used as an appropriate early-warning indicator of algal proliferation. The early-warning interval (unit: °C) of water temperature in the upper, middle, and lower reaches are 26-29°C, 23-26°C, and 21-23°C, respectively. Unlike bivariate analysis, the multiple dependency model describes the relationship between variables more accurately and enriches the scenarios of multiple conditional probabilities. When the water temperature fluctuates in the early-warning interval, regulating the upstream, midstream, and downstream flow velocity to be higher than 0.6 m/s, 0.5 m/s, and 0.6 m/s, respectively, can effectively reduce the risk of algal proliferation. This research not only provides a reference for the ecological control of algae in the MRSNWDPC and similar mega hydro-projects but also enriches the application of the Vine Copula theory coupled with the random sampling method for multi-variable risk analysis.

Modeling Dinophysis in Western Andalucía using an autoregressive hidden Markov model

Dinophysis spp. can produce diarrhetic shellfish toxins (DST) including okadaic acid and dinophysistoxins, and some strains can also produce non-diarrheic pectenotoxins. Although DSTs are of human health concern and have motivated environmental monitoring programs in many locations, these monitoring programs often have temporal data gaps (e.g., days without measurements). This paper presents a model for the historical time-series, on a daily basis, of DST-producing toxigenic Dinophysis in 8 monitored locations in western Andalucía over 2015-2020, incorporating measurements of algae counts and DST levels. We fitted a bivariate hidden Markov Model (HMM) incorporating an autoregressive correlation among the observed DST measurements to account for environmental persistence of DST. We then reconstruct the maximum-likelihood profile of algae presence in the water column at daily intervals using the Viterbi algorithm. Using historical monitoring data from Andalucía, the model estimated that potentially toxigenic Dinophysis algae is present at greater than or equal to 250 cells/L between < 1% and >10% of the year depending on the site and year. The historical time-series reconstruction enabled by this method may facilitate future investigations into temporal dynamics of toxigenic Dinophysis blooms.

Water quality monitoring with Sentinel-2 and Landsat-8 satellites during the 2021 volcanic eruption in La Palma (Canary Islands)

In this study, seawater quality was monitored with high-resolution satellite imagery during the 2021 volcanic eruption (September-December) on La Palma Island (Spain), the longest recorded in the history of the island, and the most destructive in the last century in Europe. The Sentinel-2A/B twin satellites and Landsat-8 satellite were jointly used as an optical constellation, which allowed us to successfully characterize the short- and medium-term evolution of the new lava delta and subsequent impact on the seawater. Robust atmospheric and sunglint correction approaches were applied to thoroughly quantify the environmental changes caused on the adjacent coastal waters. The cloud and volcanic ash coverage remained very high over the coast during the event, so restricted information with 14 images (45% of the total scenes) was retrieved from the multi-sensor approach. Nevertheless, the availability of pre-, syn-, and post-eruption satellite products allowed us to map and detect the main water quality variations in the marine environment. On the one hand, during the eruption, a change in the properties of the water quality was observed, with a markedly increased turbidity on the western side of the island near the new lava delta due to the deposition of volcanic ash and material. On the other hand, chlorophyll-a concentration did not significantly increase, algal blooms were not observed, and oligotrophic conditions were not swiftly altered towards eutrophic conditions. This information offered an excellent opportunity to characterize the emplacement of the new lava delta and its impact on the marine environment in La Palma. The present multi-sensor strategy is an excellent opportunity to highlight the potential of remote sensing technology as a relevant and powerful tool for future hazard monitoring and assessment during catastrophes and for a better interpretation of their impact on the marine environment.

Rapid in measurements of brown tide algae cell concentrations using fluorescence spectrometry and generalized regression neural network

The frequent occurrence of brown tide pollution in recent years has brought great losses to the economy of coastal areas. Therefore, accurate and efficient detection of the brown tide algae cell concentration is of great significance to the prevention of marine environmental pollution. In this paper, a combination of three-dimensional fluorescence spectroscopy and generalized regression neural network is used to detect the concentration of Aureococcus anophagefferens (A. anophagefferens). Firstly, the fluorescence spectrometer was used to collect spectra of A. anophagefferens with different growth cycles and different concentrations. In order to reduce the complexity of fluorescence spectral data and improve the efficiency of model calculation, the gradient boosting decision tree (GBDT) algorithm is used to rank the importance of spectral features, and select spectral features with great importance as input and concentration of algal cells as output. In view of the nonlinear relationship between input and output, a generalized regression neural network model optimized by the improved sparrow search algorithm (FASSA-GRNN) was established to predict the concentration of algae cells, The model results show that MSE is 0.0046, MAE is 0.0569, and R² is 0.9955. In addition, the FASSA-GRNN model is compared with the prediction results of the SSA-GRNN, GWO-GRNN, and GRNN models. The results show that the prediction accuracy of FASSA-GRNN is better than other models, and the improved sparrow search algorithm (FASSA) can reach the global optimum faster during the training process. This research provides a new method for predicting the concentration of algae cells.

Spatiotemporal evolution of chlorophyll-a concentration from MODIS data inversion in the middle and lower reaches of the Hanjiang River, China

Owing to limitations in monitoring technologies, monitoring the algae content index of water has lagged behind the conventional water quality index. As a result, sample monitoring in many rivers has been too sparse, and the monitoring data have been inconsistent; thus the evolution of water eutrophication has not been fully reflected. This study focused on the middle and lower reaches of the Hanjiang River, China, and correlated moderate-resolution imaging spectroradiometer (MODIS) remote sensing data with measured chlorophyll-a concentrations. Algorithm settings for chlorophyll-a inversion in the middle and lower reaches of the Hanjiang River were established via the trial and error method. The algorithm model for the middle and lower reaches of the Hanjiang River chlorophyll-a concentration inversion, and the results of the inversion analysis for the spatiotemporal evolution characteristics were subsequently used to determine the influence of various environmental factors on changes in the chlorophyll-a concentration. The results indicate that (1) the band combinations B7/(B6 + B5), B7/B5, B4-B2, and B4/(B3 + B2) are well-correlated with the chlorophyll-a concentration; (2) the back propagation (BP) neural network model inversion achieved a better fit and more accurate inversion results than the band ratio model; (3) temporally, algal outbreaks were mostly concentrated occurring in February and March, with higher chlorophyll-a concentrations in the water column during 2000, 2006, 2007, and 2008; (4) spatially, high chlorophyll-a concentrations were observed in the Zhongxiang, the Shayang, and upper Xiantao sections; and (5) increases in the water temperature and decreases in the water level and flow rate could lead to higher chlorophyll-a concentrations; similarly, nutrient salts were identified to be a major factor contributing to changes in the chlorophyll-a concentrations.

Development of a Risk Characterization Tool for Harmful Cyanobacteria Blooms on the Ohio River

A data-driven approach to characterizing the risk of cyanobacteria-based harmful algal blooms (cyanoHABs) was undertaken for the Ohio River. Twenty-five years of river discharge data were used to develop Bayesian regression models that are currently applicable to 20 sites spread-out along the entire 1579 km of the river’s length. Two site-level prediction models were developed based on the antecedent flow conditions of the two blooms that occurred on the river in 2015 and 2019: one predicts if the current year will have a bloom (the occurrence model), and another predicts bloom persistence (the persistence model). Predictors for both models were based on time-lagged average flow exceedances and a site’s characteristic residence time under low flow conditions. Model results are presented in terms of probabilities of occurrence or persistence with uncertainty. Although the occurrence of the 2019 bloom was well predicted with the modeling approach, the limited number of events constrained formal model validation. However, as a measure of performance, leave-one-out cross validation returned low misclassification rates, suggesting that future years with flow time series like the previous bloom years will be correctly predicted and characterized for persistence potential. The prediction probabilities are served in real time as a component of a risk characterization tool/web application. In addition to presenting the model’s results, the tool was designed with visualization options for studying water quality trends among eight river sites currently collecting data that could be associated with or indicative of bloom conditions. The tool is made accessible to river water quality professionals to support risk communication to stakeholders, as well as serving as a real-time water data monitoring utility.

Managing the hazardous waste cooking oil by conversion into bioenergy through the application of waste-derived green catalysts: A review

Waste cooking oil (WCO) is a hazardous waste generated at staggering values globally. WCO disposal into various ecosystems, including soil and water, could result in severe environmental consequences. On the other hand, mismanagement of this hazardous waste could also be translated into the loss of resources given its energy content. Hence, finding cost-effective and eco-friendly alternative pathways for simultaneous management and valorization of WCO, such as conversion into biodiesel, has been widely sought. Due to its low toxicity, high biodegradability, renewability, and the possibility of direct use in diesel engines, biodiesel is a promising alternative to mineral diesel. However, the conventional homogeneous or heterogeneous catalysts used in the biodiesel production process, i.e., transesterification, are generally toxic and derived from non-renewable resources. Therefore, to boost the sustainability features of the process, the development of catalysts derived from renewable waste-oriented resources is of significant importance. In light of the above, the present work aims to review and critically discuss the hazardous WCO application for bioenergy production. Moreover, various waste-oriented catalysts used to valorize this waste are presented and discussed.

Localized Surface Plasmon Resonance Decorated with Carbon Quantum Dots and Triangular Ag Nanoparticles for Chlorophyll Detection

This paper demonstrates carbon quantum dots (CQDs) with triangular silver nanoparticles (AgNPs) as the sensing materials of localized surface plasmon resonance (LSPR) sensors for chlorophyll detection. The CQDs and AgNPs were prepared by a one-step hydrothermal process and a direct chemical reduction process, respectively. FTIR analysis shows that a CQD consists of NH₂, OH, and COOH functional groups. The appearance of C=O and NH₂ at 399.5 eV and 529.6 eV in XPS analysis indicates that functional groups are available for adsorption sites for chlorophyll interaction. A AgNP-CQD composite was coated on the glass slide surface using (3-aminopropyl) triethoxysilane (APTES) as a coupling agent and acted as the active sensing layer for chlorophyll detection. In LSPR sensing, the linear response detection for AgNP-CQD demonstrates R² = 0.9581 and a sensitivity of 0.80 nm ppm^-1, with a detection limit of 4.71 ppm ranging from 0.2 to 10.0 ppm. Meanwhile, a AgNP shows a linear response of R² = 0.1541 and a sensitivity of 0.25 nm ppm^-1, with the detection limit of 52.76 ppm upon exposure to chlorophyll. Based on these results, the AgNP-CQD composite shows a better linearity response and a higher sensitivity than bare AgNPs when exposed to chlorophyll, highlighting the potential of AgNP-CQD as a sensing material in this study.

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.

Biomass Production Potential in a River under Climate Change Scenarios

Excessive production of biomass, in times of intensification of agriculture and climate change, is again becoming one of the biggest environmental issues. Identification of sources and effects of this phenomenon in a river catchment in the space-time continuum has been supported by advanced environmental modules combined on a digital platform (Macromodel DNS/SWAT). This tool enabled the simulation of nutrient loads and chlorophyll "a" for the Nielba River catchment (central-western Poland) for the biomass production potential (defined here as a TN:TP ratio) analysis. Major differences have been observed between sections of the Nielba River with low biomass production in the upper part, controlled by TN:TP ratios over 65, and high chlorophyll "a" concentrations in the lower part, affected by biomass transport for the flow-through lakes. Under the long and short-term RCP4.5 and RCP8.5 climate change scenarios, this pattern will be emphasized. The obtained results showed that unfavorable biomass production potential will be maintained in the upper riverine sections due to a further increase in phosphorus loads induced by precipitation growth. Precipitation alone will increase biomass production, while precipitation combined with temperature can even enhance this production in the existing hot spots.