Using Machine-Learning Algorithms for Eutrophication Modeling: Case Study of Mar Menor Lagoon (Spain)

Classifying eutrophication spatio-temporal dynamics in river systems using deep learning technique

Eutrophication is a major cause of water quality degradation in South Korea, owing to severe algal blooms. To manage eutrophication, the South Korean government provided the Trophic State Index (TSIko), which was revised according to Carlson's TSI. The TSIko levels were simulated using mechanistic water quality modeling. However, the computational complexity of model parameter calibration and the nonlinearity of water quality kinetics complicate analyzing accurate eutrophication conditions. Deep learning models have been considered alternatives to numerical model approaches because they directly extract water quality variables without prior knowledge. In particular, the convolutional neural network (CNN) model showed robust feature extraction from the complex datasets. This study constructed and optimized a CNN model using water quality data from the Han, Guem, Yeongsan, and Nakdong Rivers in South Korea over nine years from 2014 to 2022 to classify the TSIko. The CNN model provided validation results using the statistical measurement of classification accuracy, known as the F1 score, which is the harmonic mean of precision and recall. The F1 scores were 0.922, 0.950, 0.964, and 0.896 for oligotrophic, mesotrophic, eutrophic, and hypertrophic statuses, respectively. The CNN model outperformed conventional machine learning models. Subsequently, a eutrophication map for the four major rivers was generated using the CNN model to simulate the spatial and temporal variations of the eutrophication index, mimicking high spatio-temporal eutrophic dynamics with respect to the mainstream and tributaries of the Yeongsan and Nakdong Rivers. Therefore, this study demonstrates the capability of the CNN model to analyze eutrophication conditions at various spatial and temporal scales of major rivers in South Korea.

Ammonium nitrogen and phosphorus removal by bacterial-algal symbiotic dynamic sponge bioremediation system in micropolluted water: Operational mechanism and transformation pathways

Construct a bacteria-algae symbiotic dynamic sponge bioremediation system to simultaneously remove multiple pollutants under micro-pollution conditions. The average removal efficiencies of NH4+-N, PO43--P, total nitrogen (TN), and Ca2+ were 98.35, 78.74, 95.64, and 84.92 %, respectively. Comparative studies with Auxenochlorella sp. sponge and bacterial sponge bioremediation system confirmed that NH4+-N and TN were mainly removed by bacterial heterotrophic nitrification - aerobic denitrification (HN-AD). PO43--P was removed by algal assimilation and the generation of Ca3(PO4)2 and Ca5(PO4)3OH, and Ca2+ was removed by algal electron transfer formation of precipitates and microbially induced calcium precipitation (MICP) by bacteria. Algae provided an aerobic environment for the bacterial HN-AD process through photosynthesis, while respiration produced CO2 and adsorbed Ca2+ to promote the formation of calcium precipitates. Immobilization of Ca2+ with microalgae via bacterial MICP helped to lift microalgal photoinhibition. The bioremediation system provides theoretical support for research on micropolluted water treatment while increasing phosphorus recovery pathways.

Coastal Water Quality Modelling Using E. coli, Meteorological Parameters and Machine Learning Algorithms

In this study, machine learning models were implemented to predict the classification of coastal waters in the region of Eastern Macedonia and Thrace (EMT) concerning Escherichia coli (E. coli) concentration and weather variables in the framework of the Directive 2006/7/EC. Six sampling stations of EMT, located on beaches of the regional units of Kavala, Xanthi, Rhodopi, Evros, Thasos and Samothraki, were selected. All 1039 samples were collected from May to September within a 14-year follow-up period (2009-2021). The weather parameters were acquired from nearby meteorological stations. The samples were analysed according to the ISO 9308-1 for the detection and the enumeration of E. coli. The vast majority of the samples fall into category 1 (Excellent), which is a mark of the high quality of the coastal waters of EMT. The experimental results disclose, additionally, that two-class classifiers, namely Decision Forest, Decision Jungle and Boosted Decision Tree, achieved high Accuracy scores over 99%. In addition, comparing our performance metrics with those of other researchers, diversity is observed in using algorithms for water quality prediction, with algorithms such as Decision Tree, Artificial Neural Networks and Bayesian Belief Networks demonstrating satisfactory results. Machine learning approaches can provide critical information about the dynamic of E. coli contamination and, concurrently, consider the meteorological parameters for coastal waters classification.

Assessing the effectiveness of potential best management practices for science-informed decision support at the watershed scale: The case of the Mar Menor coastal lagoon, Spain

Coastal lagoons are ecosystems of high environmental importance but are quite vulnerable to human activities. The continuous inflow of pollutant loads can trigger negative impacts on the ecological status of these water bodies, which is contrary to the European Green Deal. One example is the Mar Menor coastal lagoon in Spain, which has experienced significant environmental degradation in recent years due to excessive external nutrient input, especially from non-point source (NPS) pollution. Mar Menor is one of the largest coastal lagoons of the Mediterranean region and a site of great ecological and socio-economic value. In this study, the highly anthropogenic and complex watershed of Mar Menor, known as Campo de Cartagena (1244 km²), was modelled with the Soil and Water Assessment Tool (SWAT) to analyse potential options for recovery of this unique system. The model was used to simulate several best management practices (BMP) proposed by recent Mar Menor regulations, such as vegetative filter strips, shoreline buffers, contour farming, removal of illegal agriculture, crop rotation management, waterway vegetation restoration, fertiliser management and greenhouse rainwater harvesting. Sixteen scenarios of individual and combined BMPs were analysed in this study. We found that, as individual measures, vegetative filter strips and contour farming were most effective in nutrient reduction: approximately 30 % for total nitrogen (TN) and 40 % for total phosphorus (TP). Moreover, waterway vegetation restoration showed the highest sediment (S) reduction at approximately 20 %. However, the combination of BMPs demonstrated clear synergistic effects, reducing S export by 38 %, TN by 67 %, and TP by 75 %. Selecting the most appropriate BMPs to be implemented at a watershed scale requires a holistic approach considering effectiveness in reducing NPS pollution loads and BMP implementation costs. Thus, we have demonstrated a way forward for enabling science-informed decision-making when choosing strategies to control NPS contamination at the watershed scale.

Assessment of Algorithm Performance on Predicting Total Dissolved Solids Using Artificial Neural Network and Multiple Linear Regression for the Groundwater Data

Estimating groundwater quality parameters through conventional methods is time-consuming through laboratory measurements for megacities. There is a need to develop models that can help decision-makers make policies for sustainable groundwater reserves. The current study compared the efficiency of multivariate linear regressions (MLR) and artificial neural network (ANN) models in the prediction of groundwater parameters for total dissolved solids (TDS) for three sub-divisions in Lahore, Pakistan. The data for this study were collected every quarter of a year for six years. ANN was applied to investigate the feasibility of feedforward, backpropagation neural networks with three training functions T-BR (Bayesian regularization backpropagation), T-LM (Levenberg–Marquardt backpropagation), and T-SCG (scaled conjugate backpropagation). Two activation functions were used to analyze the performance of algorithmic training functions, i.e., Logsig and Tanh. Input parameters of pH, electrical conductivity (EC), calcium (Ca2+), magnesium (Mg2+), chloride (Cl−), and sulfate (SO42−) was used to predict TDS as an output parameter. The computed values of TDS by ANN and MLR were in close agreement with their respective measured values. Comparative analysis of ANN and MLR showed that TDS root means square error (RMSE) for city sub-division and Pearson’s coefficient of correlation (r) for ANN and MLR were 2.9% and 0.981 and 4.5% and 0.978, respectively. Similarly, for the Farrukhabad sub-division, RMSE and r for ANN were 4.9% and 0.952, while RMSE and r for MLR were 5.5% and 0.941, respectively. For the Shahadra sub-division, RMSE was 10.8%, r was 0.869 for ANN, RMSE was 11.3%, and r was 0.860 for MLR. The results exhibited that the ANN model showed less error in results than MLR. Therefore, ANN can be employed successfully as a groundwater quality prediction tool for TDS assessment.

Water quality forecasting based on data decomposition, fuzzy clustering and deep learning neural network

Water quality forecasting can provide useful information for public health protection and support water resources management. In order to forecast water quality more accurately, this paper proposes a novel hybrid model by combining data decomposition, fuzzy C-means clustering and bidirectional gated recurrent unit. Firstly, the original water quality data is decomposed into several subseries by empirical wavelet transform, and then, the decomposed subseries are recombined by fuzzy C-means clustering. Next, for each clustered series, bidirectional gated recurrent unit is applied to develop prediction model. Finally, the forecast result is obtained by the summation of the predictions for the subseries. The proposed forecast model is evaluated by the water quality data of Poyang Lake, China. Results show that the proposed forecast model provides highly accurate forecast result for all of the six water quality data: the average of MAPE of the forecast results for the six water quality datasets is 4.59% for 7 day ahead prediction. Furthermore, our model shows better forecast performance than the other models. Particularly, compared with the single BiGRU model, MAPE decreased by 32.86% in average. Results demonstrate that the proposed forecast model can be used effectively for water quality forecasting.

Use of Artificial Neural Networks as a Predictive Tool of Dissolved Oxygen Present in Surface Water Discharged in the Coastal Lagoon of the Mar Menor (Murcia, Spain)

The Mar Menor is a Mediterranean coastal saltwater lagoon (Murcia, Spain) that represents a unique ecosystem of vital importance for the area, from both an economic and ecological point of view. During the last decades, the intense agricultural activity has caused episodes of eutrophication due to the contribution of inorganic nutrients, especially nitrates. For this reason, it is important to control the quality of the water discharged into the Mar Menor lagoon, which can be performed through the measurement of dissolved oxygen (DO). Therefore, this article aimed to predict the DO in the water discharged into this lagoon through the El Albujón watercourse, for which two theoretical models consisting of a multiple linear regression (MLR) and a back-propagation neural network (RPROP) were developed. Data of temperature, pH, nitrates, chlorides, sulphates, electrical conductivity, phosphates and DO at the mouth of this watercourse, between January 2014 and January 2021, were used. A preliminary statistical study was performed to discard the variables with the lowest influence on DO. Finally, both theoretical models were compared by means of the coefficient of determination (R2), the root mean square errors (RMSE) and the mean absolute error (MAE), concluding that the neural network made a more accurate prediction of DO.

Drivers of harmful algal blooms in coastal areas of Eastern Mediterranean: a machine learning methodological approach

Harmful algal species are present in the Mediterranean Sea and are often associated with toxic events affecting the nearby coastal zones. The presence of 18 marine microalgae, at genus level, associated with potentially harmful characteristics was predicted using a number of machine learning techniques based exclusively on a small set of abiotic variables, already identified as drivers of blooms. Random Forest (RF) algorithm achieved the best predictive performance by correctly identifying the presence of most genera with a mean of 89.2% of total samples. Although, RF has shown lower predictive performance for genera present in a low number of samples, its predictive power remains at least "fair' in these cases. The main tree-based advantage of RF was thereafter used to assess the importance of the input variables in predicting the presence of the algal genera. Temperature had the most powerful effect on genera's presences, although this effect varies among genera. Finally, the genera were clustered based on their response to the considered abiotic variables and common trends in an ecological context were identified.

Inversion of Chlorophyll-a Concentration in Donghu Lake Based on Machine Learning Algorithm

Machine learning algorithm, as an important method for numerical modeling, has been widely used for chlorophyll-a concentration inversion modeling. In this work, a variety of models were built by applying five kinds of datasets and adopting back propagation neural network (BPNN), extreme learning machine (ELM), support vector machine (SVM). The results revealed that modeling with multi-factor datasets has the possibility to improve the accuracy of inversion model, and seven band combinations are better than seven single bands when modeling, Besides, SVM is more suitable than BPNN and ELM for chlorophyll-a concentration inversion modeling of Donghu Lake. The SVM model based on seven three-band combination dataset (SVM3) is the best inversion one among all multi-factor models that the mean relative error (MRE), mean absolute error (MAE), root mean square error (RMSE) of the SVM model based on single-factor dataset (SF-SVM) are 30.82%, 9.44 μg/L and 12.66 μg/L, respectively. SF-SVM performs best in single-factor models, MRE, MAE, RMSE of SF-SVM are 28.63%, 13.69 μg/L and 16.49 μg/L, respectively. In addition, the simulation effect of SVM3 is better than that of SF-SVM. On the whole, an effective model for retrieving chlorophyll-a concentration has been built based on machine learning algorithm, and our work provides a reliable basis and promotion for exploring accurate and applicable chlorophyll-a inversion model.

Machine Learning Based Predictions of Dissolved Oxygen in a Small Coastal Embayment

Coastal dissolved oxygen (DO) concentrations have a profound impact on nearshore ecosystems and, in recent years, there has been an increased prevalance of low DO hypoxic events that negatively impact nearshore organisms. Even with advanced numerical models, accurate prediction of coastal DO variability is challenging and computationally expensive. Here, we apply machine learning techniques in order to reconstruct and predict nearshore DO concentrations in a small coastal embayment while using a comprehensive set of nearshore and offshore measurements and easily measured input (training) parameters. We show that both random forest regression (RFR) and support vector regression (SVR) models accurately reproduce both the offshore DO and nearshore DO with extremely high accuracy. In general, RFR consistently peformed slightly better than SVR, the latter of which was more difficult to tune and took longer to train. Although each of the nearshore datasets were able to accurately predict DO values using training data from the same site, the model only had moderate success when using training data from one site to predict DO at another site, which was likely due to the the complexities in the underlying dynamics across the sites. We also show that high accuracy can be achieved with relatively little training data, highlighting a potential application for correcting time series with missing DO data due to quality control or sensor issues. This work establishes the ability of machine learning models to accurately reproduce DO concentrations in both offshore and nearshore coastal waters, with important implications for the ability to detect and indirectly measure coastal hypoxic events in near real-time. Future work should explore the ability of machine learning models in order to accurately forecast hypoxic events.