Cyanotoxin level prediction in a reservoir using gradient boosted regression trees: a case study.

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.

Consideration of the bioavailability of metal/metalloid species in freshwaters: experiences regarding the implementation of biotic ligand model-based approaches in risk assessment frameworks.

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 prospective risk 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 European Water 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 BLM-based 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.