Technological advances and resource constraints present scientists and engineers with renewed challenges in the design of methods to conduct water quality monitoring, and these decisions ultimately determine the degree of project success. Many professionals are exploring alternative lower-cost options because of cost constraints, and research and development is largely focused on in situ sensors that produce high temporal resolution data. While some guidance is available, contemporary information is needed to balance water quality monitoring decisions with financial and personnel constraints, while meeting data quality needs. This manuscript focuses on monitoring constituents, such as sediment, nutrients, and pathogens, at the field scale and in small watersheds. Specifically, the impacts on the costs and data quality of alternatives related to site selection, discharge measurement, and constituent concentration measurement, are explored. The present analysis showed that avoiding sites requiring extensive berm construction and the installation of electric power to reach distant sites greatly reduces the initial costs with little impact on data quality; however, other decisions directly impact data quality. For example, proper discharge measurement, high-frequency sampling, frequent site and equipment maintenance, and the purchase of backup power and monitoring equipment can be costly, but are important for high quality data collection. In contrast, other decisions such as the equipment type (mechanical samplers, electronic samplers, or in situ sensors) and whether to analyze discrete or composite samples greatly affect the costs, but have minimal impact on data quality. These decisions, therefore, can be based on other considerations (e.g., project goals, intended data uses, funding agency specifications, and agency protocols). We hope this guidance helps practitioners better design and implement water quality monitoring to satisfy resource constraints and data quality needs.

The novelty of the work: understanding turbidity and its relationship to UN SDGs.

Highlights Machine Learning (ML) models are identified, reviewed, and analyzed for HAB predictions. Data preprocessing is vital for efficient ML model development. ML models for toxin production and monitoring are limited. Abstract. Harmful algal blooms (HABs) are detrimental to livestock, humans, pets, the environment, and the global economy, which calls for a robust approach to their management. While process-based models can inform practitioners about HAB enabling conditions, they have inherent limitations in accurately predicting harmful algal blooms. To address these limitations, Machine Learning (ML) models can potentially leverage large volumes of IoT data to aid in near real-time predictions. ML models have evolved as efficient tools for understanding patterns and relationships between water quality parameters and HAB expansion. This review describes ML models currently used for predicting and forecasting HABs in freshwater ecosystems and presents model structures and their application for predicting algal parameters and related toxins. The review revealed that regression trees, random forest, Artificial Neural Network (ANN), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) are the most frequently used models for HABs monitoring. This review shows ML models' prowess in identifying significant variables influencing algal growth, HAB drivers, and multistep HAB prediction. Hybrid models also improve the prediction of algal-related parameters through improved optimization techniques and variable selection algorithms. While ML models often focus on algal biomass prediction, few studies apply ML models for toxin monitoring and prediction. This limitation can be associated with a lack of high-frequency toxin datasets for model development, and exploring this domain is encouraged. This review serves as a guide for policymakers and researchers to implement ML models for HAB prediction and reveals the potential of ML models for decision support and early prediction for HAB management. Keywords: Cyanobacteria, Freshwater, Harmful algal blooms, Machine learning, Water quality.

The use of data driven deep learning models to predict and monitor Harmful Algal Blooms (HABs) has evolved over the years due to increasing technologies, availability of high frequency data, and statistical prowess. Despite the prowess of these data driven models, they are limited by inherent model structure and uncertainty in the generating process. To overcome the limitations of data driven models, in this research, we introduced the concept of data assimilation (DA) to account for model errors and incorporate new observations into the data driven deep learning HABs prediction model. Data assimilation is a computational method that enhances the precision of predictions in dynamic systems by combining real-time observations with model forecasts. In this study, we developed 100 Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) to make one-day ahead prediction of chlorophyll-a, an indicator of HABs, using high-frequency pH, temperature, specific conductivity, turbidity, dissolved oxygen, saturated dissolved oxygen, and oxidation-reduction potential (ORP) data. We used an Ensemble Kalman Filter (EnKF) approach to assimilate chlorophyll-a observations of greater confidence into the HABs prediction model. We explored different assimilation frequencies to observe the appropriate timesteps required for introducing new information into the modeling system. The results showed improved chlorophyll-a prediction, as forecasted by the system when DA is applied. We found that increasing assimilation frequency tends to provide improved chlorophyll-a prediction, with daily assimilation having RMSE of 0.03 μg/l for GRU and 0.02 μg/l for LSTM, while monthly assimilation resulted in RMSE of 3.63 μg/l for GRU and 3.59 μg/l for LSTM. The study revealed the potential application of DA strategy to enhance the accuracy and reliability of deep learning models for HABs monitoring. In the presence of new chlorophyll-a observations, findings from this research inform on the appropriate frequency to which such information can be incorporated into a HABs prediction model framework. This process ensures that the model provides timely and accurate predictions to support effective HABs management and decision-making efforts.