Water Quality Processes Research Articles

Tree Planting Activity to Nurture Impactful Mission (Tanim) at Select Barangay in San Jose, Batangas

This study aimed to evaluate the impact of Tree Planting Activity to Nurture Impactful Mission (TANIM) at select barangay in San Jose, Batangas. The study design is descriptive-qualitative in nature. Based on the qualitative data analysis, two themes have emerged such as simple yet useful and the short-term and long-term ecological benefits. The respondents felt contentment and fulfillment with themselves and felt a sense of accomplishment as described as a sense of success and service from the heart which implied a profound sense of achievement and a heartfelt commitment to making a positive impact on the environment. The short-term ecological benefits as described by the participants were local biodiversity, soil protection, soil health improvement, air quality improvement, and microclimate regulation while the potential long-term ecological benefits were enhanced biodiversity, carbon sequestration, water quality improvement, climate resilience, nursery operations, seed collection and processing, community engagement, aesthetic and recreational value of planting more trees, and educational opportunities which implied the immediate gains and envisioned the lasting advantages. The output of the study is the action to increase participation in the Tree Planting Activity to Nurture Impactful Mission (TANIM).

Resolving spatially complex interactions between hydrodynamics and biogeochemical processing in a large reservoir with metalimnetic oxygen deficits

Deoxygenation in the deep water of stratified lakes and reservoirs due to climate warming and human activities poses a threat to crucial limnetic ecosystem services. Metalimnetic oxygen minima (MOM) typically occurs during the mid to late stages of limnetic stratification. To investigate the mechanism of MOM during stably stratified periods in the Panjiakou Reservoir, northern China, four years of in-situ monitoring was conducted in parallel with longitudinal-vertical 2D modeling. The model simulated the hydrodynamic, water quality, algal, and DO processes in 2017 and 2020, and was calibrated and verified by the measurements. Three scenarios were designed to test the impact of hydrological processes and the high oxygen-consuming sedimentation zones (HOCSZ). We concluded that the stratification and the corresponding advection generated in the metalimnion are the driving forces of MOM in the reservoir, and the limnetic eutrophication-related benthic HOCSZ are the seedbeds of the metalimnetic hypoxia. This unique spatial setting driving the biogeochemical processing and MOM dynamics required a new generation of modelling, incorporating spatial inhomogeneities of sediment characteristics and a sophisticated resolution of hydrodynamics. Metalimnetic horizontal advection, hypolimnetic upwelling currents, sedimentation hot spots and the formation of high oxygen consumption zones became the major initiation processes leading to MOM. The numerical modeling not only represented the occurrence, development, and extinction of MOM but also comprehensively explained the spatial differences in the vertical morphology of MOM and its inter-annual variations. Our studies help to identify management strategies to mitigate the impacts of MOM on aquatic ecological security and drinking water quality, thus supporting the optimization of reservoir regulations.

Characterizing PFASs in aquatic ecosystems with 3D hydrodynamic and water quality models

Understanding how per- and polyfluoroalkyl substances (PFASs) enter aquatic ecosystems is challenging due to the complex interplay of physical, chemical, and biological processes, as well as the influence of hydraulic and hydrological factors and pollution sources at the catchment scale. The spatiotemporal dynamics of PFASs across various media remain largely unknown. Here we show the fate and transport mechanisms of PFASs by integrating monitoring data from an estuarine reservoir in Singapore into a detailed 3D model. This model incorporates hydrological, hydrodynamic, and water quality processes to quantify the distributions of total PFASs, including the major components perfluorooctanoate (PFOA) and perfluorooctane sulfonate (PFOS), across water, particulate matter, and sediments within the reservoir. Our results, validated against four years of field measurements with most relative average deviations below 40%, demonstrate that this integrated approach effectively characterizes the occurrence, sources, sinks, and trends of PFASs. The majority of PFASs are found in the dissolved phase (>95%), followed by fractions sorbed to organic particles like detritus (1.0–3.5%) and phytoplankton (1–2%). We also assess the potential risks in both the water column and sediments of the reservoir. The risk quotients for PFOS and PFOA are <0.32 and < 0.00016, respectively, indicating an acceptable risk level for PFASs in this water body. The reservoir also exhibits substantial buffering capacity, even with a tenfold increase in external loading, particularly in managing the risks associated with PFOA compared to PFOS. This study not only enhances our understanding of the mechanisms influencing the fate and transport of surfactant contaminants but also establishes a framework for future research to explore how dominant environmental factors and processes can mitigate emerging contaminants in aquatic ecosystems.

Towards a Canadian National River Water Quality-Modelling System: State of Science and Future Prospects

Water quality is of significant concern and ultimately critical to every Canadian’s quality of life and security. Canada has diverse and vast landscapes and stressors that impact various waterbodies differentially, with influencing factors including contaminant and nutrient loads from human activity (mining effluent, wastewater, agricultural runoff, plastics), landscape change (wetland drainage, urbanization) and climate change (warming water temperatures, longer open water seasons, extreme hydrological events, intensifying wildfires). Canadian rivers are especially important to the overall biogeochemistry, hydrology, biodiversity, and ultimate health of aquatic and terrestrial ecosystems. While each of Canada’s provinces and territories has extensive river water quality (physical, chemical, biotic) data and monitoring programs, Environment and Climate Change Canada coordinates various national programs that contribute to the collection and consolidation of these data and conducts extensive research into the study and modelling of key river water quality processes. Despite program-specific efforts, there remains poor capacity to predict current and future conditions in monitored and unmonitored Canadian rivers, particularly remote or northern rivers, due to a myriad of factors including lack of coordination amongst groups and examination of areas in which modelling efforts might be integrated. Herein, we review and analyse the current state of data availability, process studies, and modelling systems for Canadian river water quality. Our synthesis reveals that specific physical processes (water temperature, ice formation, permafrost thaw, sediment dynamics), biogeochemical processes (dissolved oxygen, dissolved organic matter, nutrient cycling, metals/contaminants) and ecological/biological features (biota mass, functional indicators) are well understood, though complex, and are amenable to empirical or mechanistic modelling. Review of this information assists us in identifying opportunities and challenges for developing a national water quality modelling system (NWQMS), that would eventually include similar modelling activities for parallel processes in lakes and integrated watersheds. We identify needs for stronger coordination of monitoring programs in remote areas, recommend use of novel remote sensing technologies, and development of a flexible, iterative ‘process’ for integrated modelling to which stakeholders beyond government can contribute. Such a platform would support short and long-term predictive models of Canadian water quality and ecosystem health, inform effluent concentration limits, and be an early warning system for source waters.

The influence of recent bushfires on water quality and the operation of water purification systems in regional NSW

Over the past decade, escalating extreme weather events have significantly affected New South Wales (NSW), Australia, with unprecedented droughts and intense fires. Yet, the impact on water quality and purification processes remains insufficiently studied. This research focuses on the immediate changes in NSW's environmental water quality and issues in water purification unit operations following the 2019 bushfires. Water samples and maintenance records from affected catchments, intakes, purification units, and reservoirs were analysed. Compared to control samples, post-bushfire water exhibited high turbidity. Sediment and ash shock loads posed significant threats to aquatic ecosystems. Elevated turbidity, suspended sediments, pH, and alkalinity were major concerns for water purification. Raw water samples showed turbidity exceeding 195 NTU, with flocculation and sedimentation most impacted. Immediate measures included sediment traps, aeration, pre-chlorination, and inline monitoring. These findings inform strategies to mitigate bushfire impacts on water quality and optimise water purification in fire-prone regions.

Modeling and optimization of dyeing process of polyamide 6 and woolen fabrics with plum-tree leaves using artificial intelligence

The dyeing process of textile materials is inherently intricate, influenced by a myriad of factors, including dye concentration, dyeing time, pH level, temperature, type of dye, fiber composition, mechanical agitation, salt concentration, mordants, fixatives, water quality, dyeing method, and pre-treatment processes. The intricacy of achieving optimal settings during dyeing poses a significant challenge. In response, this study introduces a novel algorithmic approach that integrates response surface methodology (RSM), artificial neural network (ANN), and genetic algorithm (GA) techniques for the precise fine-tuning of concentration, time, pH, and temperature. The primary focus is on quantifying color strength, represented as K/S, as the response variable in the dyeing process of polyamide 6 and woolen fabric, utilizing plum-tree leaves as a sustainable dye source. Results indicate that ANN (R2 ~ 1) performs much better than RSM (R2 > 0.92). The optimization results, employing ANN-GA integration, indicate that a concentration of 100 wt.%, time of 86.06 min, pH level of 8.28, and a temperature of 100 °C yield a K/S value of 10.21 for polyamide 6 fabric. Similarly, a concentration of 55.85 wt.%, time of 120 min, pH level of 5, and temperature of 100 °C yield a K/S value of 7.65 for woolen fabric. This proposed methodology not only paves the way for sustainable textile dyeing but also facilitates the optimization of diverse dyeing processes for textile materials.

Sulfate runoff processes during rainfall events in a small forested catchment on the sea of Japan side recovering from acidification under climate change

AbstractChanges in rainfall patterns due to climate change may accelerate the runoff of sulfate (SO42−), which is anthropogenically emitted and deposited as an air pollutant, cycled in forest ecosystems, and partly accumulated in forest soils. A forested catchment on the Sea of Japan side in central Japan is significantly affected by transboundary air pollution from the Asian continent due to northwesterly seasonal winds in winter. In this study, intensive 24‐h observations were conducted every hour eight times from 2019 to 2020 to clarify changes in stream water quality and runoff processes during rainfall events. The pH, electrical conductivity, and SO42− concentration in stream water decreased with increasing hourly average discharge rate (L sec−1). The SO42− concentration was negatively correlated with discharge rate. Hydrograph separations using the water isotopic parameter (deuterium excess, d‐excess = δ2H – 8 × δ18O) showed that most of the stream flow during the rain events was derived from pre‐storm water. A significant negative correlation between the d‐excess and stream water discharge was found for all six events where the water isotope analysis was applied. However, the S isotope ratio (δ34S) in stream water was not correlated with discharge rate during rainfall events and was obviously different (&gt;1.5‰) from rainwater δ34S in the same month. This suggests that rainwater SO42− during rainfall events did not directly flow to the stream but was retained in the forest ecosystem. The isotopically well homogenized internal SO42− appeared to be mainly released into the stream during rainfall events. Future climate change may further accelerate SO42− runoff from forest catchments and disrupt material cycles in the ecosystem if warming causes more intense rainfall.

Recent advances in vertical temperature profiler instrumentation and flux estimation methods facilitate groundwater – Surface water exchange studies in environments with strong discharge zones

Groundwater fluxes to many surface water systems are spatially heterogeneous with discharge focused into discrete, high-flux zones. Quantifying fluxes in these preferential discharge zones is critical to a range of surface water habitat and water quality processes, but characterization can be difficult due to short-scale spatial and temporal variability. Passive heat-as-a-tracer methods employing vertical temperature profiler (VTP) data can provide the necessary spatial and temporal resolution, but upward fluid flow strongly attenuates the thermal signals used for estimating fluxes. In preferential discharge zones it becomes difficult to measure the signals in the subsurface and the flux parameter can become insensitive in the analysis models, leading to large uncertainties. We use data from a high-flux site of contaminant-loaded groundwater discharge to the Quashnet River on Cape Cod, Massachusetts, USA, to demonstrate how recent advances in VTP instrumentation that allow for the acquisition of high-resolution (0.001 °C) temperature data at short (1 cm) offsets near the ground surface, combined with advances in flux estimation methods that exploit the information content of the high-resolution data, facilitate heat-as-a-tracer approaches for characterizing groundwater-surface water exchanges and make it possible to obtain accurate and statistically robust results in a preferential discharge zone with a specific discharge of ∼1 m/d.

Synthesis, characterization, and performance evaluation of AA/AMPS copolymers with different molecular weights and explanation of the inhibition mechanism of calcium carbonate and calcium sulfate

Polymeric scale inhibitors are widely acknowledged for their eco-friendliness, strong compatibility, and versatile nature. However, the impact of molecular weight variation on their inhibitory efficacy remains a relatively understudied aspect. In this investigation, AA/AMPS copolymers with distinct molecular weights (1000, 2000, 3000, 4000, 5000, 6000) were synthesized and probed for their influence on mineral scale inhibition across diverse water quality parameters (e.g., calcium ion concentration, pH) and process conditions (e.g., temperature, duration). Concurrently, the crystalline and morphological alterations of AA/AMPS during mineral scale inhibition were delved. By integrating molecular dynamics simulations and quantum chemical calculations, the effects of varying molecular weights of AA/AMPS on mineral scale inhibition were scrutinized. Moreover, the inhibition mechanism was thoroughly explored. Our findings revealed that AA/AMPS with molecular weights of 2000 and 3000 exhibited superior inhibition efficacy against calcium carbonate and calcium sulfate. This phenomenon was attributed to the movement velocity and binding energy of AA/AMPS with corresponding molecular weights towards the primary crystal growth surface. Additionally, the carboxyl oxygen atoms on the polymers facilitated chelation with calcium ions, thereby impeding further crystal formation and growth. Consequently, achieving heightened efficiency in scale inhibition.

Evaluation of water quality and trophic status in relation to seasonal water mixing in a highland Lake Ardibo, Ethiopia.

The aim of the present study was to evaluate the spatio-temporal variability of various physical and chemical parameters of water quality and to determine the trophic state of Lake Ardibo. Water samples were collected from October 2020 to September 2021 at three sampling stations in four different seasons. A total of 14 physico-chemical parameters, such as water temperature, pH, dissolved oxygen (DO), electrical conductivity, turbidity, alkalinity, Secchi-depth, nitrate, ammonia, silicon dioxide, soluble reactive phosphorus, total phosphorus, chloride, and fluoride were measured using standard methods. The results demonstrated that temporal variation existed throughout the study period. Except for turbidity, the water quality of the lake varied significantly within the four seasons (ANOVA, p < 0.05). DO levels decreased significantly during the dry season following water mixing events. Chlorophyll-a measurements showed significant seasonal differences ranging from 0.58 μg L-1 in the main-rainy season to 8.44 μg L-1 in the post-rainy period, indicating moderate algal biomass production. The overall category of Lake Ardibo was found to be under a mesotrophic state with medium biological productivity. A holistic lake basin approach management is suggested to maintain water quality and ecological processes and to improve the lake ecosystem services.

EDAR 4.0: Machine Learning and Visual Analytics for Wastewater Management

Wastewater treatment plant (WWTP) operations manage massive amounts of data that can be gathered with new Industry 4.0 technologies such as the Internet of Things and Big Data. These data are critical to allow the wastewater treatment industry to improve its operation, control, and maintenance. However, the data available need to be improved and enriched, partly due to their high dimensionality and low reliability, and the lack of appropriate data analysis and processing tools for such systems. This paper presents a visual analytics-based platform for WWTP that allows users to identify relationships among data through data inspection. The results show that the tool developed and implemented for a full-scale WWTP allows operators to construct machine learning (ML) models for water quality and other water treatment process variables. Consequently, analyzing and optimizing plant operation scenarios can enhance key variables, including energy, reagent consumption, and water quality. This improvement facilitates the development of a more sustainable WWTP, contributing to a beneficial environmental impact. Domain experts validated the variables influencing the created ML models and proved their appropriateness.

Geochemical Assessment of the Evolution of Groundwater under the Impact of Seawater Intrusion in the Mannar District of Sri Lanka

Groundwater is an important drinking water resource in the coastal regions of island countries and has suffered from heavy seawater intrusion. However, the areas specifically affected by seawater intrusion and their groundwater hydrogeochemical compositions and evolution processes remain unclear. This study analyzed the hydrogeochemical compositions, water quality, and evolution processes of groundwater in the Mannar district, Sri Lanka, during the dry season. A total of 56 samples were collected from shallow wells and tube wells across the region, and about 64.28% of groundwater samples had good quality (WQI &lt; 100). Geochemical compositions and water quality parameters had a high level in the north and south mainland regions, where they severely suffered from seawater intrusion with a high content of Cl− and Na+. The geochemical compositions of groundwater in the Mannar district were predominantly affected by rock weathering and/or evaporation processes. Cl-Na and HCO3-Ca facies were the main hydrochemical types, and the corresponding ions were mainly from silicate and halite dissolution. The reverse cation exchange process mainly occurred in seawater intrusion areas. The study highlights the impacts of seawater intrusion on the hydrogeochemical compositions and evolution processes in Mannar region groundwater, which will enhance the understanding of the local water quality and seawater intrusion situation and aid in protecting drinking water safety by routinely monitoring the groundwater quality and implementing targeted desalination techniques in the key areas.

Genetic programming expressions for effluent quality prediction: Towards AI-driven monitoring and management of wastewater treatment plants

Continuous effluent quality prediction in wastewater treatment processes is crucial to proactively reduce the risks to the environment and human health. However, wastewater treatment is an extremely complex process controlled by several uncertain, interdependent, and sometimes poorly characterized physico-chemical-biological process parameters. In addition, there are substantial spatiotemporal variations, uncertainties, and high non-linear interactions among the water quality parameters and process variables involved in the treatment process. Such complexities hinder efficient monitoring, operation, and management of wastewater treatment plants under normal and abnormal conditions. Typical mathematical and statistical tools most often fail to capture such complex interrelationships, and therefore data-driven techniques offer an attractive solution to effectively quantify the performance of wastewater treatment plants. Although several previous studies focused on applying regression-based data-driven models (e.g., artificial neural network) to predict some wastewater treatment effluent parameters, most of these studies employed a limited number of input variables to predict only one or two parameters characterizing the effluent quality (e.g., chemical oxygen demand (COD) and/or suspended solids (SS)). Harnessing the power of Artificial Intelligence (AI), the current study proposes multi-gene genetic programming (MGGP)-based models, using a dataset obtained from an operational wastewater treatment plant, deploying membrane aerated biofilm reactor, to predict the filtrated COD, ammonia (NH4), and SS concentrations along with the carbon-to-nitrogen ratio (C/N) within the effluent. Input features included a set of process variables characterizing the influent quality (e.g., filtered COD, NH4, and SS concentrations), water physics and chemistry parameters (e.g., temperature and pH), and operation conditions (e.g., applied air pressure). The developed MGGP-based models accurately reproduced the observations of the four output variables with correlation coefficient values that ranged between 0.98 and 0.99 during training and between 0.96 and 0.99 during testing, reflecting the power of the developed models in predicting the quality of the effluent from the treatment system. Interpretability analyses were subsequently deployed to confirm the intuitive understanding of input-output interrelations and to identify the governing parameters of the treatment process. The developed MGGP-based models can facilitate the AI-driven monitoring and management of wastewater treatment plants through devising optimal rapid operation and control schemes and assisting the plants’ operators in maintaining proper performance of the plants under various normal and disruptive operational conditions.

Start-up of biofilter for nitrification and effect of filtration rate on the ammonium removal efficiency in drinking water treatment on pilot plant

ABSTRACT Biological filtration is a process that can be used for ammonium removal from water. The removal of ammonium is based on the nitrification process. Nitrification depends on many factors, such as water quality and filtration process parameters. To investigate the influence of filtration rate on the nitrification efficiency, nitrifying biofilters were formed at the pilot plant in the industry for drinking water production from surface water. The new biological filters were started under optimal conditions for biofilm formation. After the biofilm formation, the influence of the filtration rate on nitrification was examined over 3 months (from November to January). The time required for the spontaneous growth of nitrifying bacteria on the new filters was around 70 days. The operating conditions at the start-up period were the continuous flow of water containing γ(NH4+) ≈ 1mg/L, dissolved oxygen in a concentration &amp;gt;9 mg/L, filtration rate &amp;lt;1 m/h, inlet water temperature &amp;gt;12 °C and pH from 7.8 to 8. After the complete formation of the nitrifying biofilm, the percentage of NH4+ removal was greater than 95% for all tested filtration rates, from 0.5 to 8.4 m/h, at γ(NH4+) from 1 to 2.5 mg/L and raw water temperature from 13 to 7°C.

Effectiveness and resilience of BMPs to watershed climate adaptation considering the uncertainty of hydrological model and GCMs

Climate change significantly impacts catchment hydrologic and water quality processes. Best management practices (BMPs) can serve as adaptation strategies to negate the impact of climate change on sediment and total nitrogen (TN) loads. One major controversial issue in climate change adaptation studies is the highly uncertain nature of such changes. Previous studies have rarely focused on the combined impact of the uncertainty in climate change and watershed model parameters, which could be the main sources of uncertainty in climate change adaptation research. In this study, the effectiveness and resilience (defined as continued effectiveness under a changing climate) of BMPs in reducing sediment and TN loads were explored under future climate change in the Shanmei Reservoir watershed (SMW) of Southeast China. Climate change projections provided by 10 general circulation models (GCMs) under the SSP1-2.6, SSP2-4.5, SSP3-7.0, and SSP5-8.5 scenarios from 2031 to 2060 were applied in the Annualized Agricultural Nonpoint Source (AnnAGNPS) model to evaluate the effectiveness and resilience of 4 BMPs (riparian buffers (RB), no-tillage (NT), fertilization reduction (FR), and parallel terraces (PT)). The ensemble average of 10 GCMs and 10 behavior parameter groups were adopted to reduce the uncertainty resulting from the hydrological model parameters and GCMs. The results indicated that the average annual temperature and precipitation in the SMW will increase in the future. On a seasonal scale, the average temperature during all seasons will increase, and precipitation will decrease in summer and autumn but increase in spring and winter. The annual sediment and TN loads will decrease, but the loads in spring and winter will increase. BMPs could be effective as climate adaptation strategies for reducing sediment and TN loads under future climate conditions, with PT as the most effective option. Structural BMPs were more effective in reducing sediment and TN loads in spring and winter, whereas nonstructural BMPs were more effective in reducing loads in summer and autumn. BMPs were more resilient when future watershed runoff changes were slight or climate sensitivity was reduced, with higher BMP resilience in spring and winter than in summer and autumn. This study aimed to provide systematic references for watersheds through the implementation of BMPs for mitigating the effects of climate change and extending the boundaries of the AnnAGNPS model application.

Comprehensive effects of climate, land use/cover and management practices on runoff and nutrient variations in a rapidly urbanizing watershed

As non-point source pollution has emerged as a significant global and regional concern, climate change (CC), land use/cover transformation (LUCT), and management practices (MP) play vital roles in addressing nutrient pollution. However, current studies lack comprehensive quantification and consistent conclusions on the response to these factors, especially for management practices. To quantify and elucidate the impact of representative environmental factors on rapidly urbanizing regions, this study focused on the Shenzhen River, which serves as the most typical urbanizing watershed. Using a process-based distributed hydrological model with a factor-controlled simulation method, we identified significant differences in nutrient concentrations and the impacts of climate variability, land use/cover changes, and anthropogenic interventions from 2003 to 2020. Moreover, effective measures greatly improved water quality in the Shenzhen River during study period, as evident from trend and cluster analysis. However, ecological water supplements implemented since 2016 have led to a slight reduction in simulated runoff performance, and CC may amplify the synergistic effects of precipitation and temperature on the river system. While the implemented practices have been effective in reducing total nitrogen (TN) and total phosphorus (TP) loads, strong TN pollution control is still needed in rapidly urbanizing areas due to the results of land use/cover type changes. Our findings emphasize the intricate interplay among CC, LUCT, and MP in shaping water quality and hydrological processes in rapidly urbanizing watersheds, and clarify the independent effects of these factors on nutrients. This study contributes to a better understanding of the complex interactions between multiple factors in watersheds and provides guidance for sustainable watershed management.

Evolution of water quality in rainwater harvesting systems during long-term storage in non-rainy seasons

The development of rainwater utilization strategies has relied on rainwater harvesting (RWH) systems for centuries to alleviate the pressure on water resources. However, there are still significant knowledge gaps regarding the changes in water quality in RWH systems during long-term storage in non-rainy seasons. This study evaluated the water quality processes in RWH systems through static rainwater storage experiments for approximately 60 days. The results revealed that nutrients in rainwater accumulated in sediment during storage. Disturbance and redox conditions at the rainwater-sediment interface contribute to the release of sedimentary facies materials. The rainwater showed distinct DO stratification, with the biochemical reactions of sedimentary facies being the primary factor driving oxygen consumption. ORP and turbidity showed positive correlations with COD (r = 0.582; 0.572), TOC (r = 0.678; 0.681), TN (r = 0.452; 0.439), and NH4+-N (r = 0.502; 0.553) (P < 0.05). The regulation of water quality and extension of the usage cycle were identified as critical factors influenced by DO. In addition, bacteria share similar ecological niche preferences. These findings provide scientific evidence for the high-quality reuse of rainwater in decentralized RWH systems during long-term storage in non-rainy seasons.

Venice lagoon chlorophyll-a evaluation under climate change conditions: A hybrid water quality machine learning and biogeochemical-based framework

Climate change presents a significant challenge to lagoon ecosystems, which are highly valued coastal environments known for their provision of unique ecosystem services. As important as fragile, lagoons are vulnerable to both natural processes and anthropogenic activities, and this vulnerability is exacerbated by the impacts of climate change, which are likely to result in severe ecological consequences. The complexity of water quality (WQ) processes, characterized by compounding and interconnected pressures, highlights the importance of adequate sophisticated methods to estimate future ecological impacts on lagoon environments. In this setting, a hybrid framework is introduced where Machine Learning (ML) and biogeochemical (BGC) models are integrated in a sequential modelling approach. This integration exploits the unique strengths offered by both models. The ML model allows capturing and learning linear and nonlinear correlations from historical data; the BGC interprets and simulates complex environmental systems subject to compounded pressures, building on identified causal relationships. Multi-Layer Perceptron (MLP) and Random Forest (RF) ML algorithms are trained, validated and tested within the Venice lagoon case study to assimilate historical WQ data (i.e., water temperature, salinity, and dissolved oxygen) and spatio-temporal information (i.e., monitoring station location and month), and to predict changes in chlorophyll-a (Chl-a) conditions. Then, projections from the BGC model SHYFEM-BFM for 2019, 2050, and 2100 timeframes under RCP 8.5 are integrated into the ML model (composing the hybrid ML-BGC model) to evaluate Chl-a variations under future biogeochemical conditions forced by climate change projections. Moreover, the SHYFEM-BFM standalone Chl-a projections are also used to compare the hybrid and the BGC scenarios. Annual and seasonal Chl-a predictions are developed by classes based on two classification modes (median and quartiles) established on the descriptive statistics computed on historical data. Results from the case study showed as the RF successfully classifies Chl-a with an overall model accuracy of about 80% for the median and 61% for the quartiles modes. Concerning future climate change scenarios, results revealed a decreasing trend for the lowest Chl-a values (below the first quartile, i.e. 0.85 µg/l) moving to the far future (2100), with an opposite rising trend for the highest Chl-a values (above the fourth quartile, i.e. 2.78 µg/l). On the seasonal level, summer remains the season with the highest Chl-a values in all scenarios, although in 2100 a strong increase in higher Chl-a values is also expected during the springtime one. The proposed hybrid framework represents a valuable approach to strengthen both multivariate Chl-a modelling and scenarios analysis, by placing artificial intelligence-based models alongside biogeochemical models.

An integrated modelling framework for multiple pollution source identification in surface water

Pollution source identification is vital in water safety management. An integrated simulation-optimization modelling framework comprising a process-based hydrodynamic water quality model, artificial neural network surrogate model and particle swarm optimization (PSO) was proposed to achieve rapid, accurate and reliable pollution source identification. In this study, the hydrodynamics and water quality processes in a straight lab-based flume were simulated to test pollution source identification under steady flow conditions. Additionally, the pollution source identification in the unsteady flow conditions was examined using a real-life estuary, specifically the Yangtze River estuary. First, we developed two process-based models to simulate hydrodynamics and water quality in the flume and estuary. Then, the data generated from the process-based models were used to develop surrogate models. Three typical artificial neural networks (ANNs) algorithms: backpropagation (BP), radial basis function (RBF) and general regression neural networks (GRNN) were selected to develop surrogates for process-based models (PBMs), and they were coupled with PSO algorithm to achieve the hybrid modelling framework for pollution source identification. Our results showed that hybrid PBM-ANNs-PSO models could be applied to identify the pollution source and quantify release intensity in spatial distribution when the discharge type was assumed as the point source with a continuous release. Multiple-performance criteria metrics, in terms of the coefficient of determination, root-mean-square error, mean absolute error, evaluated the model performance as “Excellent prediction”. The BP-PSO models consistently appear to be the top-performing source identification model within the developed models, with most cases of relative error (RE) values lower than 5%. The new insights from the hybrid modelling framework would provide useful information for the local government agency to make reasonable decisions regarding pollution source identification issues.

A Review on Applications of Artificial Intelligence in Wastewater Treatment

In recent years, artificial intelligence (AI), as a rapidly developing and powerful tool to solve practical problems, has attracted much attention and has been widely used in various areas. Owing to their strong learning and accurate prediction abilities, all sorts of AI models have also been applied in wastewater treatment (WWT) to optimize the process, predict the efficiency and evaluate the performance, so as to explore more cost-effective solutions to WWT. In this review, we summarize and analyze various AI models and their applications in WWT. Specifically, we briefly introduce the commonly used AI models and their purposes, advantages and disadvantages, and comprehensively review the inputs, outputs, objectives and major findings of particular AI applications in water quality monitoring, laboratory-scale research and process design. Although AI models have gained great success in WWT-related fields, there are some challenges and limitations that hinder the widespread applications of AI models in real WWT, such as low interpretability, poor model reproducibility and big data demand, as well as a lack of physical significance, mechanism explanation, academic transparency and fair comparison. To overcome these hurdles and successfully apply AI models in WWT, we make recommendations and discuss the future directions of AI applications.