Search

Chlorophyll-a (hereafter referred to as Chl-a) is a recognized indicator for phytoplankton abundance and biomass –hence, an effective estimation of the trophic condition– of water bodies as lakes, reservoirs and oceans. Indeed, Chl-a is the primary molecule responsible for photosynthesis. A strong and robust Bayesian nonparametric technique, termed Gaussian process regression (GPR) approach, for foretelling the dependent variable Chl-a concentration in Tanes reservoir from a dataset concerning to 268 samples is shown in this paper. Ten years (2006–2015) of monitoring water quality variables (biological and physico-chemical independent variables) in the Tanes reservoir were used to build this mathematical GPR-relied model. As an optimizer, the method known as Limited-memory Broyden-Fletcher-Goldfarb-Shanno (LBFGSB) iterative algorithm was used; this allows the selection of kernel optimal parameters during the GPR training phase, which greatly determines the regression precision. The results of the current investigation can be summarized in two. Firstly, the relevance of each input variable on Chl-a concentration in Tanes reservoir is determined. Secondly, the Chl-a can be successfully predicted using this hybrid LBFGSB/GPR–relied model (R2 and r values were 0.8597 and 0.9306, respectively). The concordance between observed data and the model clearly proves the high efficiency of this innovative approach.

Algal atypical proliferation is a consequence of water fertilization (also called eutrophication) and a worldwide environmental concern since water quality and its uses are seriously compromised. Prevention is the most effective measure given that once the algal proliferation starts, it is too difficult and costly to stop the process. This article presents a nonparametric machine learning algorithm that combines the gradient boosted regression tree (GBRT) model and an improved differential evolution algorithm (L-SHADE) for better understanding and control of the algal abnormal proliferation (usually estimated from Chlorophyll-a and Total Phosphorus concentrations) from physicochemical and biological variable values obtained in a northern Spain reservoir. This L-SHADE technique involves the optimization of the GBRT hyperparameters during the training process. Apart from successfully estimating algal atypical growth (coefficients of determination equal to 0.91 and 0.93 for Chlorophyll-a and Total Phosphorus concentrations were obtained, respectively), this hybrid model allows here to establish the ranking of each independent biological and physicochemical variable according to its importance in the algal enhanced growth.

Total phosphorus (from now on mentioned as TP) and chlorophyll-a (from now on mentioned as Chl-a) are recognized indicators for phytoplankton large quantity and biomass-thus, actual estimates of the eutrophic state-of water bodies (i.e., reservoirs, lakes and seas). A robust nonparametric method, called support vector regression (SVR) approach, for forecasting the output Chl-a and TP concentrations coming from 268 samples obtained in Tanes reservoir is described in this investigation. Previously, we have carried out a selection of the main features (biological and physico-chemical predictors) employing the multivariate adaptive regression splines approximation to construct reduced models for the purpose of making them easier to interpret for researchers/readers and to reduce the overfitting. As an optimizer, the heuristic technique termed as whale optimization iterative algorithm (WOA), was employed here to optimize the regression parameters with success. Two main results have been obtained. Firstly, the relative relevance of the models variables was stablished. Secondly, the Chl-a and TP can be successfully foretold employing this hybrid WOA/SVR-based approximation. The coincidence between the predicted approximation and the observed data obviously demonstrates the quality of this novel technique.

Cyanotoxins are a type of cyanobacteria that is poisonous and poses a health threat in waters that could be used for drinking or recreational purposes. Thus, it is necessary to predict their presence to avoid risks. This paper presents a nonparametric machine learning approach using a gradient boosted regression tree model (GBRT) for prediction of cyanotoxin contents from cyanobacterial concentrations determined experimentally in a reservoir located in the north of Spain. GBRT models seek and obtain good predictions in highly nonlinear problems, like the one treated here, where the studied variable presents low concentrations of cyanotoxins mixed with high concentration peaks. Two types of results have been obtained: firstly, the model allows the ranking or the dependent variables according to its importance in the model. Finally, the high performance and the simplicity of the model make the gradient boosted tree method attractive compared to conventional forecasting techniques.

After the scientific development of biotic ligand models (BLMs) in recent decades, these models are now considered suitable for implementation in regulatory risk assessment of metals in freshwater bodies. The BLM approach has been described in many peer-reviewed publications, and the original complex BLMs have been applied in prospectiverisk assessment reports for metals and metal compounds. BLMs are now also recommended as suitable concepts for the site-specific evaluation of monitoring data in the context of the EuropeanWater Framework Directive. However, the use is hampered by the data requirements for the original BLMs (about 10 water parameters). Recently, several user-friendly BLM-based bioavailability software tools for assessing the aquatic toxicity of relevant metals (mainly copper, nickel, and zinc) became available. These tools only need a basic set of commonly determined water parameters as input (i.e., pH, hardness, dissolved organic matter, and dissolved metal concentration). Such tools seem appropriate to foster the implementation of routine site-specific water quality assessments. This work aims to review the existing bioavailability-based regulatory approaches and the application of available BLMbased bioavailability tools for this purpose. Advantages and possible drawbacks of these tools (e.g., feasibility, boundaries of validity) are discussed, and recommendations for further implementation are given.