River algal blooms are well predicted by antecedent environmental conditions

Which riverine water quality parameters can be predicted by meteorologically-driven deep learning?

River water quality has been significantly impacted by climate change and extreme weather events worldwide. Despite increasing studies on deep learning techniques for river water quality management, understanding which riverine water quality parameters can be well predicted by meteorologically-driven deep learning still requires further investigation. Here we explored the prediction performance of a traditional Recurrent Neural Network, a Long Short-Term Memory network (LSTM), and a Gated Recurrent Unit (GRU) using meteorological conditions as inputs in the Dahei River basin. We found that deep learning models (i.e., LSTM and GRU) demonstrated remarkable effectiveness in predicting multiple water quality parameters at daily scale, including water temperature, dissolved oxygen, electrical conductivity, chemical oxygen demand, ammonia nitrogen, total phosphorous, and total nitrogen, but not turbidity. The GRU model performed best with an average determination coefficient of 0.94. Compared to the daily-average prediction, the GRU model exhibited limited error increment of 10-40 % for most water quality parameters when predicting daily extreme values (i.e., the maximum and minimum). Moreover, deep learning showed superior performance in collective prediction for multiple water quality parameters than individual ones, enabling a more comprehensive understanding of the river water quality dynamics from meteorological data. This study holds the promise of applying meteorologically-driven deep learning techniques for water quality prediction to a broader range of watersheds, particularly in chemically ungauged areas.

Pollution loads in the middle-lower Yangtze river by coupling water quality models with machine learning

Pollution control and environmental protection of the Yangtze River have received major attention in China. However, modeling the river's pollution load remains challenging due to limited monitoring and unclear spatiotemporal distribution of pollution sources. Specifically, anthropogenic activities' contribution to the pollution have been underestimated in previous research. Here, we coupled a hydrodynamic-based water quality (HWQ) model with a machine learning (ML) model, namely attention-based Gated Recurrent Unit, to decipher the daily pollution loads (i.e., chemical oxygen demand, COD; total phosphorus, TP) and their sources in the Middle-Lower Yangtze River from 2014 to 2018. The coupled HWQ-ML model outperformed the standalone ML model with KGE values ranging 0.77-0.91 for COD and 0.47-0.64 for TP, while also reducing parameter uncertainty. When examining the relative contributions at the Middle Yangtze River Hankou cross-section, we observed that the main stream and tributaries, lateral anthropogenic discharges, and parameter uncertainty contributed 15, 66, and 19% to COD, and 58, 35, and 7% to TP, respectively. For the Lower Yangtze River Datong cross-section, the contributions were 6, 69, and 25% for COD and 41, 42, and 17% for TP. According to the attention weights of the coupled model, the primary drivers of lateral anthropogenic pollution sources, in descending order of importance, were temperature, date, and precipitation, reflecting seasonal pollution discharge, industrial effluent, and first flush effect and combined sewer overflows, respectively. This study emphasizes the synergy between physical modeling and machine learning, offering new insights into pollution load dynamics in the Yangtze River.

Purification Resistance Index: A new water quality assessment method toward drinking water production

Water quality assessment plays a significant role in ensuring the availability of clean and safe water. The Water Quality Index (WQI) model method has been developed to provide a basis for assessing water quality by integrating various water quality parameters. However, existing WQIs do not "actively" consider the difficulty of water treatment from raw water to specific water use scenarios. This study proposes a novel model framework, named as Purification Resistance Index (PRI), quantitatively evaluating not only the exceedance of pollutants but also how difficult they can be removed in the water treatment process. The framework is built based on the conventional drinking water treatment processes, with sub-indices for coagulation-sedimentation (rc), filtration (rf), disinfection (rd), and advanced treatment (ra). The model considers appropriate weights assigned to each sub-index to calculate the purification resistance, resulting in a comprehensive index for water quality evaluation. Case studies on nationwide and citywide water source reservoirs demonstrated the applicability of PRI approach. PRI breakthrough the traditional water quality risk assessment paradigm and extents to engineering region and provide useful tools for water source supervision, drinking water treatment plant planning and updating, operation control, and other purposes. Water authority, water utility and municipal design institute will all benefit. It is open for more localized practices validation and discussion.

Backwater makes the tributaries of large river becoming phosphorus "sink"

The complex hydrological conditions caused by the backwater effect at the confluence inevitably modify the geochemical processes of elements. However, there is still a lack of comprehensive understanding regarding the precise transformation mechanisms of nutrients in large river systems. This study aimed to investigate the hydrodynamic characteristics and their impact on phosphorus transfer in the lower Han River, which is influenced by backwater from the Yangtze River (the largest river in China). By establishing a hydrodynamic-water quality model, we have determined that the discharge ratio (the ratio of flow between the Han River discharge and the Yangtze River discharge) can be utilized as a representative indicator of the backwater effect from the Yangtze River on the Han River. Three distinct patterns were identified in this study: mixing, backwater, and intrusion. The corresponding discharge ratio values were categorized as >0.08, 0.01∼0.08, and <0.01 respectively. Additionally, the extent of the backwater zone was determined, revealing that the length of the backwater zone increased from 50 km (XG) to 100 km (FS) as the discharge ratio decreased from 0.08 to 0.01. Furthermore, it was observed that the water level at the confluence rose from 2.52 m to 6.83 m in accordance with these changes in discharge ratio values. The migration pattern of phosphorus primarily involved the settling and retention of particulate phosphorus, particularly the labile particulate organic phosphorus (LOP) and dissolved organic phosphorus (DOP). When the confluent patterns became the intrusion pattern, the backwater zone expanded to 150 m (XT), causing a 10.40 m increase in water level at the confluence. An intrusion zone formed, and its phosphorus concentrations were same as Yangtze River's. Above the intrusion area, a backwater region formed and its concentrations of LOP and DOP decreased, while the concentration of PO43- increased due to the release from resuspended particles. This release was induced by higher velocity of bottom water brought about by the water exchange of two rivers. The discharge ratio of 0.01-0.08 resulted in the sedimentation of LOP and DOP, causing the lower Han River to act as a "sink" for phosphorus, potentially exacerbating phosphorus pollution. Higher discharge ratios in spring led to phosphorus release from sediment, increasing dissolved phosphorus concentrations and raising the risk of algal blooms in the lower Han River. These findings have significant implications for larger rivers worldwide and provide insights into strategies for ecological management and prevention of algal blooms.

Recent advances in algal bloom detection and prediction technology using machine learning

Harmful algal blooms (HAB) including red tides and cyanobacteria are a significant environmental issue that can have harmful effects on aquatic ecosystems and human health. Traditional methods of detecting and managing algal blooms have been limited by their reliance on manual observation and analysis, which can be time-consuming and costly. Recent advances in machine learning (ML) technology have shown promise in improving the accuracy and efficiency of algal bloom detection and prediction. This paper provides an overview of the latest developments in using ML for algal bloom detection and prediction using various water quality parameters and environmental factors. First, we introduced ML for algal bloom prediction using regression and classification models. Then we explored image-based ML for algae detection by utilizing satellite images, surveillance cameras, and microscopic images. This study also highlights several real-world examples of successful implementation of ML for algal bloom detection and prediction. These examples show how ML can enhance the accuracy and efficiency of detecting and predicting algal blooms, contributing to the protection of aquatic ecosystems and human health. The study also outlines recent efforts to enhance the field applicability of ML models and suggests future research directions. A recent interest in explainable artificial intelligence (XAI) was discussed in an effort to understand the most influencing environmental factors on algal blooms. XAI facilitates interpretations of ML model results, thereby enhancing the models' usability for decision-making in field management and improving their overall applicability in real-world settings. We also emphasize the significance of obtaining high-quality, field-representative data to enhance the efficiency of ML applications. The effectiveness of ML models in detecting and predicting algal blooms can be improved through management strategies for data quality, such as pre-treating missing data and integrating diverse datasets into a unified database. Overall, this paper presents a comprehensive review of the latest advancements in managing algal blooms using ML technology and proposes future research directions to enhance the utilization of ML techniques.

Water quality prediction based on sparse dataset using enhanced machine learning

Water quality in surface bodies remains a pressing issue worldwide. While some regions have rich water quality data, less attention is given to areas that lack sufficient data. Therefore, it is crucial to explore novel ways of managing source-oriented surface water pollution in scenarios with infrequent data collection such as weekly or monthly. Here we showed sparse-dataset-based prediction of water pollution using machine learning. We investigated the efficacy of a traditional Recurrent Neural Network alongside three Long Short-Term Memory (LSTM) models, integrated with the Load Estimator (LOADEST). The research was conducted at a river-lake confluence, an area with intricate hydrological patterns. We found that the Self-Attentive LSTM (SA-LSTM) model outperformed the other three machine learning models in predicting water quality, achieving Nash-Sutcliffe Efficiency (NSE) scores of 0.71 for CODMn and 0.57 for NH3N when utilizing LOADEST-augmented water quality data (referred to as the SA-LSTM-LOADEST model). The SA-LSTM-LOADEST model improved upon the standalone SA-LSTM model by reducing the Root Mean Square Error (RMSE) by 24.6% for CODMn and 21.3% for NH3N. Furthermore, the model maintained its predictive accuracy when data collection intervals were extended from weekly to monthly. Additionally, the SA-LSTM-LOADEST model demonstrated the capability to forecast pollution loads up to ten days in advance. This study shows promise for improving water quality modeling in regions with limited monitoring capabilities.

Integrating temporal decomposition and data-driven approaches for predicting coastal harmful algal blooms

Frequent coastal harmful algal blooms (HABs) threaten the ecological environment and human health. Biscayne Bay in southeastern Florida also faces algal bloom issues; however, the mechanisms driving these blooms are not fully understood, emphasizing the importance of HAB prediction for effective environmental management. The overarching goal of this study is to offer a robust HAB predictive framework and try to enhance the understanding of HAB dynamics. This study established three scenarios to predict chlorophyll-a concentrations, a recognized representative of HABs: Scenario 1 (S1) using single nonlinear machine learning (ML) algorithms, hybrid Scenario 2 (S2) combining linear models and nonlinear ML algorithms, and hybrid Scenario 3 (S3) combining temporal decomposition and ML (TD-ML) algorithms. The novel-developed S3 TD-ML hybrid models demonstrated superior predictive capabilities, achieving all R2 values above 0.9 and MAPE under 30% in tests, significantly outperforming the S1 with an average R2 of 0.16 and the S2 with an R2 of -0.06. S3 models effectively captured the algal dynamics, successfully predicting complex time series with extremes and noise. In addition, we unveiled the relationship between environmental variables and chlorophyll-a through correlation analysis and found that climate change might intensify the HABs in Biscayne Bay. This research developed a precise predictive framework for early warning and proactive management of HABs, offering potential global applicability and improved prediction accuracy to address HAB challenges.

Weakened hydrological oscillation period increased the frequency of river algal blooms

The evolution of riverine aquatic ecosystems typically exhibits notable characteristic with cumulative, enduring, and hysteresis. Exploring the non-linear response of riverine ecology to long-term hydrological fluctuations become a major challenge in contemporary interdisciplinary research. In response to the critical issue of frequent river algal blooms in the lower Han River, which is impacted by Asian largest inter-basin water diversion project. We identified the non-linear response of eco-hydrology across various time scales through the integration of Continuous Wavelet Transform (CWT) and Inverse Wavelet Transform (IWT). Our study revealed that: 1) Over the past half century, the hydrological regime in the lower Han river showed a significant downward trend, and existed three significant hydrological oscillation periods (HOPs), including the short-scale Intra-AC (180 days), the medium-scale AC (365 days, the first major period), and the long-scale Inter-AC (2500 days), the variation of Inter-AC changed most dramatically. 2) We further found that the Inter-AC variation of hydrology is more closely related to the formation of river algal blooms in the Han River, and when the hydrological Inter-AC shows steady state or downward trend, the frequency of algal blooms in the lower Han River increases significantly. 3) The river algal blooms in the lower Han River is a cumulative consequence to the long-term hydrological influences. Weakened hydrological Inter-AC is more likely to increase the frequency of river algal blooms, and 10-years Inter-AC cumulation increased the frequency by 60%. Therefore, the weaken of long-scale HOP will significantly increase the frequency of river algal blooms in the future. This study received a critical scientific insight and aimed at provide guidance for the optimization of ecological management within the framework of national large-scale water conservation.

Predicting coastal harmful algal blooms using integrated data-driven analysis of environmental factors

Coastal harmful algal blooms (HABs) have become one of the challenging environmental problems in the world's thriving coastal cities due to the interference of multiple stressors from human activities and climate change. Past HAB predictions primarily relied on single-source data, overlooked upstream land use, and typically used a single prediction algorithm. To address these limitations, this study aims to develop predictive models to establish the relationship between the HAB indicator - chlorophyll-a (Chl-a) and various environmental stressors, under appropriate lagging predictive scenarios. To achieve this, we first applied the partial autocorrelation function (PACF) to Chl-a to precisely identify two prediction scenarios. We then combined multi-source data and several machine learning algorithms to predict harmful algae, using SHapley Additive exPlanations (SHAP) to extract key features influencing output from the prediction models. Our findings reveal an apparent 1-month autoregressive characteristic in Chl-a, leading us to create two scenarios: 1-month lead prediction and current-month prediction. The Extra Tree Regressor (ETR), with an R2 of 0.92, excelled in 1-month lead predictions, while the Random Forest Regressor (RFR) was most effective for current-month predictions with an R2 of 0.69. Additionally, we identified current month Chl-a, developed land use, total phosphorus, and nitrogen oxides (NOx) as critical features for accurate predictions. Our predictive framework, which can be applied to coastal regions worldwide, provides decision-makers with crucial tools for effectively predicting and mitigating HAB threats in major coastal cities.

The influence mechanism of water level operation on algal blooms in canyon reservoirs and bloom prevention

The water level operation of reservoirs affects the spatiotemporal patterns of water quality, light-heat, hydrodynamics and phytoplankton, which have implications for algal bloom prevention. However, the theoretical analysis and practical applications of related research are limited. Based on prototype observations and numerical modeling, data on algae, water level operation and environmental factors in the Zipingpu Reservoir from April and September in 2015 to 2017 and 2020 to 2022 were collected. An in-depth analysis of the causal mechanisms between algal blooms and water level operation was performed, and prevention strategies with practical application assessments were developed. Water level operation control in the reservoir from April to September can be divided into five stages (falling-rising-oscillating-falling-rising), with algal blooms occurring only in the second stage. The rising water level with inflow into the middle layers shapes a closed-loop circulation in the surface waters. This distributes the nutrients that were trapped in the surface layer during the first stage, helping algae avoid to phosphorus limitation and thrive in the closed loop circulation, leading to algal blooms (chlorophyll-a exceeding 10 mg/m3). There is a significant positive correlation (p < 0.05) between algal blooms and the rapid rise in water levels in the second stage, occurring within a span of three days. To contain the algal bloom, a water level operation limit of rising waters on the third day after a two-day consecutive rise in water level was examined. This was found to be effective after its practical application to the case reservoir in 2022, with chlorophyll-a concentrations consistently below 10 mg/m3. This study unveils the mechanisms through which water level operation affects algal blooms and presents a successful case of bloom prevention. Furthermore, it serves as a valuable reference for the management of canyon reservoirs.

Damming exacerbates the discontinuities of phytoplankton in a subtropical river in China

Phytoplankton is sensitive to changes in river ecosystems. Increasing dams disrupt the continuity of river ecosystems. However, the spatial impacts of dams on phytoplankton have not been well documented. In this study, using multiple statistical analyses, the relationships between environmental drivers and phytoplankton community structures in natural background reaches, reservoirs, and corresponding post-dam reaches were explored in the Jiulong River with multiple cascaded dams, which encountered eutrophication and algal blooms in the past 15 years. Results illustrated that damming exacerbated longitudinal discontinuities of phytoplankton communities. The relative abundance of phytoplankton varied in three types of river sections. The average phytoplankton abundance in the reservoirs (1.62 × 105 cell·L-1) was higher than those in the natural background reaches (5.15 × 104 cell·L-1) and the corresponding downstream reaches (4.55 × 104 cell·L-1). The total β diversity ranged from 0.38 to 0.89 with an average of 0.64 and dominated by species replacement and least by species richness. The water environmental factors and hydraulic parameters rather than nutrients were more attributable to phytoplankton community variability in three river sections. These findings facilitate the management of rivers with multiple cascade dams by releasing environmental flows, jointly operating cascade hydropower stations, and developing nutrient reduction schemes to mitigate the negative impacts of damming in the river.

A new framework for water quality forecasting coupling causal inference, time-frequency analysis and uncertainty quantification

Accurate forecasting of water quality variables in river systems is crucial for relevant administrators to identify potential water quality degradation issues and take countermeasures promptly. However, pure data-driven forecasting models are often insufficient to deal with the highly varying periodicity of water quality in today's more complex environment. This study presents a new holistic framework for time-series forecasting of water quality parameters by combining advanced deep learning algorithms (i.e., Long Short-Term Memory (LSTM) and Informer) with causal inference, time-frequency analysis, and uncertainty quantification. The framework was demonstrated for total nitrogen (TN) forecasting in the largest artificial lakes in Asia (i.e., the Danjiangkou Reservoir, China) with six-year monitoring data from January 2017 to June 2022. The results showed that the pre-processing techniques based on causal inference and wavelet decomposition can significantly improve the performance of deep learning algorithms. Compared to the individual LSTM and Informer models, wavelet-coupled approaches diminished well the apparent forecasting errors of TN concentrations, with 24.39%, 32.68%, and 41.26% reduction at most in the average, standard deviation, and maximum values of the errors, respectively. In addition, a post-processing algorithm based on the Copula function and Bayesian theory was designed to quantify the uncertainty of predictions. With the help of this algorithm, each deterministic prediction of our model can correspond to a range of possible outputs. The 95% forecast confidence interval covered almost all the observations, which proves a measure of the reliability and robustness of the predictions. This study provides rich scientific references for applying advanced data-driven methods in time-series forecasting tasks and a practical methodological framework for water resources management and similar projects.

Current status and prospects of algal bloom early warning technologies: A Review

In recent years, frequent occurrences of algal blooms due to environmental changes have posed significant threats to the environment and human health. This paper analyzes the reasons of algal bloom from the perspective of environmental factors such as nutrients, temperature, light, hydrodynamics factors and others. Various commonly used algal bloom monitoring methods are discussed, including traditional field monitoring methods, remote sensing techniques, molecular biology-based monitoring techniques, and sensor-based real-time monitoring techniques. The advantages and limitations of each method are summarized. Existing algal bloom prediction models, including traditional models and machine learning (ML) models, are introduced. Support Vector Machine (SVM), deep learning (DL), and other ML models are discussed in detail, along with their strengths and weaknesses. Finally, this paper provides an outlook on the future development of algal bloom warning techniques, proposing to combine various monitoring methods and prediction models to establish a multi-level and multi-perspective algal bloom monitoring system, further improving the accuracy and timeliness of early warning, and providing more effective safeguards for environmental protection and human health.

Exploring a multi-objective optimization operation model of water projects for boosting synergies and water quality improvement in big river systems

Due to excessive nutrient enrichment and rapidly increasing water demand, the occurrence of riverine environment deterioration events such as algal blooms in rivers of China has become more frequent and severe since the 1990s, which has imposed harmful consequences on riverine ecosystems. However, tackling river algal blooms as an important issue of restoring riverine environment is very challenging because the complex interaction mechanisms between the causes are impacted by multiple factors. The contributions of our study consist of: (1) optimizing joint operation of water projects for boosting synergies of water quality and quantity, and hydroelectricity; and (2) preventing algal bloom from perspectives of hydrological and water-quality conditions by regulating water releases of water projects. This study proposed a multi-objective optimization methodology grounded on the Non-dominated Sorting Genetic Algorithm to simultaneously minimize the excess values of algal bloom indicators (water quality, O1), minimize the used reservoir capacity for water supply (water quantity, O2), and maximize the hydropower generation (hydroelectricity, O3). The proposed methodology was applied to several catastrophic algal bloom events that took place between 2017 and 2021 and thirteen water projects in the Hanjiang River of China. The results indicated that the proposed methodology largely stimulated the synergistic benefits of the three objectives by reaching a 36.7% reduction in total nitrogen and phosphorus concentrations, a 33.1% improvement in the remaining reservoir capacity, and a 41.0% improvement in hydropower output, as compared with those of the standard operation policy (SOP). In addition, the optimal water release schemes of water projects would increase the minimum streamflow velocity of downstream algal bloom control stations by 8.6%-9.4%. This study provides a new perspective on water project operation in the environmental improvement in big river systems while boosting multi-objectives synergies to support environmentalists and decision-makers with scientific guidance on sustainable water resources management.

Flow backward alleviated the river algal blooms

Mechanistic understanding and prediction of river algal blooms remain challenging. It is generally believed that these blooms are formed by the slowdown of water dynamics in tributaries due to the support of the main stream. However, few studies have investigated the impact of flow backward caused by the difference in water dynamics between the main stream and tributaries. Here, we focus on the eutrophication issue in the middle-lower reaches of the Han River, which is affected by the Middle Route of the South-to-North Water Diversion Project (SNWDP), the largest inter-basin water transfer project in Asia. We discover that the reversal of the Yangtze River water level could effectively alleviate the occurrence of Han River water blooms. The Yangtze River frequently back flows into the lower reaches of the Han River, with the probability of such events increasing as it nears the confluence (20 km from the Yangtze: 9.5 %, 10 km: 19.0 %, 8 km: 28.6 %). This flow backward carries nutrients that reduce the nitrogen to phosphorus ration (N:P), leading to a shift in the nutrient structure of the Han River. This change is concomitant with a significant decline in algae biomass (Chlorophyll-a = 11.19 µg·L-1 and algae density = 0.41×107 cells·L-1 under natural flow, Chlorophyll-a = 5.19 µg·L-1 and algae density = 0.18×107 cells·L-1 under flow backward), as well as a weakening of the correlation (R) between diatom density and chlorophyll-a concentration, i.e., R = 0.38 (p>0.05) under flow backward conditions versus R = 0.72 (p<0.01) under natural flow conditions. As phosphorus limitation typically suppresses algae growth, the correlation between diatom density and chlorophyll-a concentration can help to reveal the dominance of diatoms, with stronger correlations indicating greater diatom dominance. Consequently, our study provides evidence that the flow backward can alleviate river algal blooms by weakening the growth advantage of diatoms. This study could prove valuable in investigating the eutrophication mechanism within the complex hydrodynamic conditions of rivers. SYNOPSIS: Flow backward caused by the water level difference between the main streams and tributary alleviated the occurrence of river algal blooms in the confluence area.

Model evaluation of total phosphorus prediction based on model accuracy and interpretability for the surface water in the river network of the Jiangnan Plain, China

Due to climatic and hydrological changes and human activities, eutrophication and frequent outbreaks of cyanobacteria are prominent in the Jiangnan Plain basin of China. Therefore, building a suitable model to accurately predict the phosphorus concentration in surface water is of practical significance to prevent the above problems. This study built 10 models to predict the phosphorus element in the surface water of the river network in the Jiangnan Plain. The main water types in the basin include the Yangtze River, the Beijing-Hangzhou Canal, and the Gehu Lake. The 10 models in different datasets have been comprehensively evaluated by the prediction accuracy and interpretability of the model, and the calculation of the partial dependence diagram (PDP) and SHAP has proved that there is a transparent response relationship between phosphorus and different factors. The results show that the Yangtze River, Beijing-Hangzhou Canal, and Gehu Lake are suitable for random forest, linear regression, and random forest models, respectively, under the comprehensive evaluation of the prediction accuracy and interpretability of the model. Models with low prediction accuracy often show strong interpretability. In different water body types, turbidity, water temperature, and chlorophyll-a are the three factors that affect the model in predicting phosphorus.

Predicting aqueous sorption of organic pollutants on microplastics with machine learning

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

A novel framework to improve the consistency of water quality attribution from natural and anthropogenic factors

One critical question for water security and sustainable development is how water quality responses to the changes in natural factors and human activities, especially in light of the expected exacerbation in water scarcity. Although machine learning models have shown noticeable advances in water quality attribution analysis, they have limited interpretability in explaining the feature importance with theoretical guarantees of consistency. To fill this gap, this study built a modelling framework that employed the inverse distance weighting method and the extreme gradient boosting model to simulate the water quality at grid scale, and adapted the Shapley additive explanation to interpret the contributions of the drivers to water quality over the Yangtze River basin. Different from previous studies, we calculated the contribution of features to water quality at each grid within river basin and aggregated the contribution from all the grids as the feature importance. Our analysis revealed dramatic changes in response magnitudes of water quality to drivers within river basin. Air temperature had high importance in the variability of key water quality indicators (i.e. ammonia-nitrogen, total phosphorus, and chemical oxygen demand), and dominated the changes of water quality in Yangtze River basin, especially in the upstream region. In the mid- and downstream regions, water quality was mainly affected by human activities. This study provided a modelling framework applicable to robustly identify the feature importance by explaining the contribution of features to water quality at each grid.

Phosphorus - The main limiting factor in riverine ecosystems in China

River receive substantial nutrient inputs, and serve as the main channel for nitrogen and phosphorus to enter the lake, their nutrient control is of great significance to the alleviation of lake eutrophication. While nutrient limitation affects the primary productivity of water ecosystems and the biodiversity of aquatic communities, identifying the limiting factors in riverine ecosystems across China remains elusive. Here, we explore which nutrients have a stronger effect on nutritional balance and aquatic ecosystems in China's rivers based on the total nitrogen (TN) and total phosphorus (TP) observations from 1412 sampling sites in 2018. This study supports the following three main conclusions. Though the percentages of the sites with TN or TP exceeding the limits varied as per different mesotrophic targets, and TP (53.7 %) contributed more to nutrient enrichment than TN (46.3 %). In addition, the spatial distribution characteristics of river nutrients were high in the north (arid zone) and low in the south (humid zone) in China. According to four classification criteria of N:P ratio, 70.8 % of the sampling sites were attributed to phosphorus limiting, much higher than the sites with nitrogen limiting (4.1 %). TN and TP have a synergistic effect on river nutrients, while TP has a stronger regulation framework. Our results reveal that the nutrients in China's rivers are mainly phosphorus limiting, which implies that phosphorus-oriented best management practices are more likely to maintain the nutrient balance of rivers towards healthy aquatic ecosystems. Synopsis: Phosphorus is the key factor that affecting the stability and nutrient balance of riverine ecosystem.

Global patterns and edaphic-climatic controls of soil carbon decomposition kinetics predicted from incubation experiments

Knowledge about global patterns of the decomposition kinetics of distinct soil organic matter (SOM) pools is crucial to robust estimates of land-atmosphere carbon fluxes under climate change. However, the current Earth system models often adopt globally-consistent reference SOM decomposition rates (k_ref), ignoring effects from edaphic-climate heterogeneity. Here, we compile a comprehensive set of edaphic-climatic and SOM decomposition data from published incubation experiments and employ machine-learning techniques to develop models capable of predicting the expected sizes and k_ref of multiple SOM pools (fast, slow, and passive). We show that soil texture dominates the turnover of the fast pools, whereas pH predominantly regulates passive SOM decomposition. This suggests that pH-sensitive bacterial decomposers might have larger effects on stable SOM decomposition than previously believed. Using these predictive models, we provide a 1-km resolution global-scale dataset of the sizes and k_ref of these SOM pools, which may improve global biogeochemical model parameterization and predictions.

Short-term Lake Erie algal bloom prediction by classification and regression models

The recent outbreaks of harmful algal blooms in the western Lake Erie Basin (WLEB) have drawn tremendous attention to bloom prediction for better control and management. Many weekly to annual bloom prediction models have been reported, but they only employ small datasets, have limited types of input features, build linear regression or probabilistic models, or require complex process-based computations. To address these limitations, we conducted a comprehensive literature review, complied a large dataset containing chlorophyll-a index (from 2002 to 2019) as the output and a novel combination of riverine (the Maumee & Detroit Rivers) and meteorological (WLEB) features as the input, and built machine learning-based classification and regression models for 10-d scale bloom predictions. By analyzing the feature importance, we identified 8 most important features for the HAB control, including nitrogen loads, time, water levels, soluble reactive phosphorus load, and solar irradiance. Here, both long- and short-term nitrogen loads were for the first time considered in HAB models for Lake Erie. Based on these features, the 2-, 3-, and 4-level random forest classification models achieved an accuracy of 89.6%, 77.0%, and 66.7%, respectively, and the regression model achieved an R² value of 0.69. In addition, long-short term memory (LSTM) was implemented to predict temporal trends of four short-term features (N, solar irradiance, and two water levels) and achieved the Nash-Sutcliffe efficiency of 0.12-0.97. Feeding the LSTM model predictions for these features into the 2-level classification model reached an accuracy of 86.0% for predicting the HABs in 2017-2018, suggesting that we can provide short-term HAB forecasts even when the feature values are not available.

Algal community structure prediction by machine learning

The algal community structure is vital for aquatic management. However, the complicated environmental and biological processes make modeling challenging. To cope with this difficulty, we investigated using random forests (RF) to predict phytoplankton community shifting based on multi-source environmental factors (including physicochemical, hydrological, and meteorological variables). The RF models robustly predicted the algal communities composed by 13 major classes (Bray-Curtis dissimilarity = 9.2 ± 7.0%, validation NRMSE mostly <10%), with accurate simulations to the total biomass (validation R² > 0.74) in Norway's largest lake, Lake Mjosa. The importance analysis showed that the hydro-meteorological variables (Standardized MSE and Node Purity mostly >0.5) were the most influential factors in regulating the phytoplankton. Furthermore, an in-depth ecological interpretation uncovered the interactive stress-response effect on the algal community learned by the RF models. The interpretation results disclosed that the environmental drivers (i.e., temperature, lake inflow, and nutrients) can jointly pose strong influence on the algal community shifts. This study highlighted the power of machine learning in predicting complex algal community structures and provided insights into the model interpretability.

Self-optimization of training dataset improves forecasting of cyanobacterial bloom by machine learning

Data-driven model (DDM) prediction of aquatic ecological responses, such as cyanobacterial harmful algal blooms (CyanoHABs), is critically influenced by the choice of training dataset. However, a systematic method to choose the optimal training dataset considering data history has not yet been developed. Providing a comprehensive procedure with self-based optimal training dataset-selecting algorithm would self-improve the DDM performance. In this study, a novel algorithm was developed to self-generate possible training dataset candidates from the available input and output variable data and self-choose the optimal training dataset that maximizes CyanoHAB forecasting performance. Nine years of meteorological and water quality data (input) and CyanoHAB data (output) from a site on the Nakdong River, South Korea, were acquired and pretreated via an automated process. An artificial neural network (ANN) was chosen from among the DDM candidates by first-cut training and validation using the entire collected dataset. Optimal training datasets for the ANN were self-selected from among the possible self-generated training datasets by systematically simulating the performance in response to 46 periods and 40 sizes (number of data elements) of the generated training datasets. The best-performing models were screened to identify the candidate models. The best performance corresponded to 6-7 years of training data (∼18 % lower error) for forecasting 1-28 d ahead (1-28 d of forecasting lead time (FLT)). After the hyperparameters of the screened model candidates were fine-tuned, the best-performing model (7 years of data with 14 d FLT) was self-determined by comparing the forecasts with unseen CyanoHAB events. The self-determined model could reasonably predict CyanoHABs occurring in Korean waters (cyanobacteria cells/mL ≥ 1000). Thus, our proposed method of self-optimizing the training dataset effectively improved the predictive accuracy and operational efficiency of the DDM prediction of CyanoHAB.

A critical review of operational strategies for the management of harmful algal blooms (HABs) in inland reservoirs

Occurrences of freshwater harmful algal blooms (HABs) are increasing on a global scale, largely in part due to increased nutrient input and changing climate patterns. While reservoir management strategies that can influence phytoplankton are known, there is no published guideline or protocol for the management of harmful algal blooms. There is a need to establish what factors are the predominant drivers of blooms, and how common reservoir management strategies specifically influence each factor. The following literature review seeks to establish the benefits and drawbacks of operational management strategies that currently exist. The main focus is altering hydrodynamic conditions (hypolimnetic withdrawals, surface flushing, pulsed inflow, artificial mixing), in order to induce environmental changes within the reservoir itself. Since excess nutrients are one of the biggest contributors to worsening bloom conditions, internal nutrient dynamics and reduction are also discussed. Additionally, we review the predominant seasonal factors (stratification, light, temperature, and wind) that affect likelihood of bloom occurrence and duration. The ultimate objective of this review is to increase understanding of the relationships between HAB drivers and reservoir operations in order to inform the development of data, modeling, and management strategies for the prevention and mitigation of blooms.

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.

Identification of pollutant sources and evaluation of water quality improvement alternatives of a large river

While pollutants are the most important factors for the deterioration of surface water quality, the identification of major pollutant sources for rivers is challenging, especially in areas with diverse land covers and multiple pollutant inputs. This study aims to identify the significant pollutant sources from the tributaries that are affecting the water quality and identify the limiting nutrient for algal growth in the Geum river to provide a management alternative for an improvement of the water quality. The positive matrix factorization (PMF) was applied for pollutant source identification and apportionment of the two major tributaries, Gab-cheon and Miho-cheon. Positive matrix factorization identifies three and two major pollutant sources for Gab-cheon and Miho-cheon, respectively. For Gab-cheon, wastewater treatment plants, urban, and agricultural pollution are identified as major pollutant sources. Furthermore, for Miho-cheon, agricultural and urban pollution were identified as major pollutant sources. Total phosphorus (TP) is also identified as a limiting nutrient for algal growth in the Geum river. Water quality control scenarios were formulated and improvement of water quality in the river locations was simulated and analyzed with the Environmental Fluid Dynamic Code (EFDC). Scenario results were evaluated using a water quality index. The reduction of total phosphorus (TP) from the tributaries has greatly improved the water quality, especially algal bloom in the downstream stations.

Learning and inferring the diurnal variability of cyanobacterial blooms from high-frequency time-series satellite-based observations

Observational evidences have suggested that the surface scums of cyanobacterial harmful blooms (CyanoHABs) are highly patchy, and their spatial patterns can vary significantly within hours. This stresses the need for the capacity to monitor and predict their occurrence with better spatiotemporal continuity, in order to understand and mitigate their causes and impacts. Although polar-orbiting satellites have long been used to monitor CyanoHABs, these sensors cannot be used to capture the diurnal variability of the bloom patchiness due to their long revisit periods. In this study, we use the Himawari-8 geostationary satellite to generate high-frequency time-series observations of CyanoHABs on a sub-daily basis not possible from previous satellites. On top of that, we introduce a spatiotemporal deep learning method (ConvLSTM) to predict the dynamics of bloom patchiness at a lead time of 10 min. Our results show that the bloom scums were highly patchy and dynamic, and the diurnal variability was assumed to be largely associated with the migratory behavior of cyanobacteria. We also show that, ConvLSTM displayed fairly satisfactory performance with promising predictive capability, with Root Mean Square Error (RMSE) and determination coefficient (R²) varying between 0.66∼1.84 μg/L and 0.71∼0.94, respectively. This suggests that, by adequately capturing spatiotemporal features, the diurnal variability of CyanoHABs can be well learned and inferred by ConvLSTM. These results may have important practical implications, because they suggest that spatiotemporal deep learning integrated with high-frequency satellite observations could provide a new methodological paradigm in nowcasting of CyanoHABs.

Remote sensing for mapping algal blooms in freshwater lakes: a review

A large number of freshwater lakes around the world show recurring harmful algal blooms, particularly cyanobacterial blooms, that affect public health and ecosystem integrity. Prediction, early detection, and monitoring of algal blooms are inevitable for the mitigation and management of their negative impacts on the environment and human beings. Remote sensing provides an effective tool for detecting and spatiotemporal monitoring of these events. Various remote sensing platforms, such as ground-based, spaceborne, airborne, and UAV-based, have been used for mounting sensors for data acquisition and real-time monitoring of algal blooms in a cost-effective manner. This paper presents an updated review of various remote sensing platforms, data types, and algorithms for detecting and monitoring algal blooms in freshwater lakes. Recent studies on remote sensing using sophisticated sensors mounted on UAV platforms have revolutionized the detection and monitoring of water quality. Image processing algorithms based on Artificial Intelligence (AI) have been improved recently and predicting algal blooms based on such methods will have a key role in mitigating the negative impacts of eutrophication in the future.

Algal bloom forecasting with time-frequency analysis: A hybrid deep learning approach

The rapid emergence of deep learning long-short-term-memory (LSTM) technique presents a promising solution to algal bloom forecasting. However, the discontinuous and non-stationary processes within algal dynamics still largely limit the functions of LSTMs. To overcome this challenge, an advanced time-frequency wavelet analysis (WA) technique was introduced to enhance the prediction accuracy of LSTMs. Herein, the novel hybrid approach (named WLSTM) successfully decreased the algal forecasting inaccuracy of classic LSTMs by 41% ± 8% in Lake Mendota (Wisconsin, USA), with powerful one-step-ahead predictions at hourly, daily, and monthly time resolutions (R² = 0.976, 0.878, and 0.814, respectively). In addition, the WLSTM outperformed the other two widely used algal forecasting approaches - deep neural network (DNN), and autoregressive-integrated-moving-average (ARIMA) model, represented by average 72% and 85% decrease in root-mean-square-error, respectively. Furthermore, the WLSTM was implemented in an experimentally fertilized lake (Lake Tuesday, Michigan) for a multi-step forecasting examination. It satisfactorily forecasted the algal fluctuations involving substantial peak and extreme values (average R² > 0.900) and presented accurate judgment outcomes to their bloom levels with high accuracy > 95% on average. This work highlighted the utility of deep learning approaches in effective early-warning for algal blooms, and demonstrated an important direction for improving the adaptability of conventional deep learning approaches to the aquatic problems.

Machine learning modeling and analysis of biohydrogen production from wastewater by dark fermentation process

Dark fermentation process for simultaneous wastewater treatment and H₂ production is gaining attention. This study aimed to use machine learning (ML) procedures to model and analyze H₂ production from wastewater during dark fermentation. Different ML procedures were assessed based on the mean squared error (MSE) and determination coefficient (R²) to select the most robust models for modeling the process. The research showed that gradient boosting machine (GBM), support vector machine (SVM), random forest (RF) and AdaBoost were the most appropriate models, which were optimized by grid search and deeply analyzed by permutation variable importance (PVI) to identify the relative importance of process variables. All four models demonstrated promising performances in predicting H₂ production with high R² values (0.893, 0.885, 0.902 and 0.889) and small MSE values (0.015, 0.015, 0.016 and 0.015). Moreover, RF-PVI demonstrated that acetate, butyrate, acetate/butyrate, ethanol, Fe and Ni were of high importance in decreasing order.

Eutrophication model driven by light and nutrients condition change in sluice-controlled river reaches

River eutrophication has become a challenging environmental problem worldwide because of the strong interference of anthropogenic activities and hydraulic structures. The driving mechanism of algae growth in sluice-controlled river reaches (SCRRs) is more complicated than that of natural rivers, because the operation mode of the sluices is an important influencing factor which changes the light and nutrient conditions of the water body. The main purpose of this study was to assess algal growth in SCRRs under external conditions and sluice regulation. In this study, a eutrophication model for SCRRs was developed based on the mechanism of river hydrodynamics and algae growth kinetics, considering the variation in underwater light intensity and nutrient condition. By choosing the light intensity, phosphorus concentration and sluice gate opening size as the influencing factors, 16 different combination conditions were proposed by orthogonal experimental design, and eutrophication of water bodies in the SCRRs was simulated using a eutrophication model. In the scenario design, four gate opening sizes were set, and the light intensity and nutrients were enlarged or reduced based on the original monitoring data. The results showed that both light intensity and nutrient concentration can promote the algal growth within a suitable range, and increasing the gate opening size can inhibit algal growth.

Emergent spatial patterns of competing benthic and pelagic algae in a river network: A parsimonious basin-scale modeling analysis

Algae, as primary producers in riverine ecosystems, are found in two distinct habitats: benthic and pelagic algae typically prevalent in shallow/small and deep/large streams, respectively. Over an entire river continuum, spatiotemporal patterns of the two algal communities reflect specificity in habitat preference determined by geomorphic structure, hydroclimatic controls, and spatiotemporal heterogeneity in nutrient loads from point- and diffuse-sources. By representing these complex interactions between geomorphic, hydrologic, geochemical, and ecological processes, we present here a new river-network-scale dynamic model (CⁿANDY) for pelagic (A) and benthic (B) algae competing for energy and one limiting nutrient (phosphorus, P). We used the urbanized Weser River Basin in Germany (7th-order; ~8.4 million population; ~46 K km²) as a case study and analyzed simulations for equilibrium mass and concentrations under steady median river discharge. We also examined P, A, and B spatial patterns in four sub-basins. We found an emerging pattern characterized by scaling of P and A concentrations over stream-order ω, whereas B concentration was described by three distinct phases. Furthermore, an abrupt algal regime shift occurred in intermediate streams from B dominance in ω≤3 to exclusive A presence in ω≥6. Modeled and long-term basin-scale monitored dissolved P concentrations matched well for ω>4, and with overlapping ranges in ω<3. Power-spectral analyses for the equilibrium P, A, and B mass distributions along hydrological flow paths showed stronger clustering compared to geomorphological attributes, and longer spatial autocorrelation distance for A compared to B. We discuss the implications of our findings for advancing hydro-ecological concepts, guiding monitoring, informing management of water quality, restoring aquatic habitat, and extending CⁿANDY model to other river basins.

Effects of hydrological change on the risk of riverine algal blooms: case study in the mid-downstream of the Han River in China

Algal blooms usually occur in semi-closed water bodies such as lakes or estuaries; however, it has occurred frequently in the mid-downstream of the Han River (MSHR) in China since the 1990s. We made a comparative analysis of the hydrological conditions and identified the hydrological condition thresholds that induce algal blooms. From the hydrodynamic point of view, the changes and characteristics of the hydrological conditions in the MSHR were analyzed. Furthermore, the influence on the risk of algal blooms under different design water transfer schemes for the middle route of the South-to-North Water Diversion Project (SNWDP) was studied. The results indicated that (1) the flow in the MSHR less than 900 m³/s and water level in the Yangtze River higher than 14 m provided a suitable hydrological environment for diatoms multiply. (2) The flow of the MSHR showed a downtrend, while the water level of the Yangtze River showed an uptrend. There were variations in hydrological processes. Through specific IHA index analysis, the fact of flow reduction in the MSHR was demonstrated, and further indicated that algal bloom outbreak was in low flow period. (3) The water transfer in the middle route of SNWDP affected the risk probability of algal blooms. The more the amount of water transfer, the greater the risk probability of algal blooms. It was the Water Diversion Project from Yangtze River to Han River (WDPYHR) that replenished flow of the MSHR and was conducive to the prevention and control of algal bloom risk.

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

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