A Review of Recent Machine Learning Advances for Forecasting Harmful Algal Blooms and Shellfish Contamination

Shellfish polysaccharides: A comprehensive review of extraction, purification, structural characterization, and beneficial health effects

Global food systems are currently facing great challenges, such as food sources, food safety, and environmental crises. Alternative nutritional resources have been proposed as part of the solution to meeting future global food demand. In the natural resources, shellfish are the major component of global aquatic animals. Although most studies focus on the allergy, toxin, and contamination of shellfish, it is also a delicious food to the human diet rich in proteins, polysaccharides, minerals, and omega-3. Among the functional ingredients, shellfish polysaccharides possess nutritional and medicinal values that arouse the great interest of researchers. The selection of the extraction approach and the experimental condition are the key factors that influence the extraction efficiency of shellfish polysaccharides. Importantly, the purification of crude polysaccharides comprises the enrichment of shellfish polysaccharides and isolation of fractions, also resulting in various structural characteristics and physicochemical properties. Chemical modification is also an efficient method to further improve the biological activities of shellfish polysaccharides. This review summarizes the extraction, purification, structural characterization, and chemical modification methods for shellfish polysaccharides. Additionally, the beneficial health effects of shellfish polysaccharides are highlighted, with an emphasis on their potential mechanism. Finally, current challenges and perspectives on shellfish polysaccharides are also spotlighted.

Recent advances in algal bloom detection and prediction technology using machine learning

Harmful algal blooms (HAB) including red tides and cyanobacteria are a significant environmental issue that can have harmful effects on aquatic ecosystems and human health. Traditional methods of detecting and managing algal blooms have been limited by their reliance on manual observation and analysis, which can be time-consuming and costly. Recent advances in machine learning (ML) technology have shown promise in improving the accuracy and efficiency of algal bloom detection and prediction. This paper provides an overview of the latest developments in using ML for algal bloom detection and prediction using various water quality parameters and environmental factors. First, we introduced ML for algal bloom prediction using regression and classification models. Then we explored image-based ML for algae detection by utilizing satellite images, surveillance cameras, and microscopic images. This study also highlights several real-world examples of successful implementation of ML for algal bloom detection and prediction. These examples show how ML can enhance the accuracy and efficiency of detecting and predicting algal blooms, contributing to the protection of aquatic ecosystems and human health. The study also outlines recent efforts to enhance the field applicability of ML models and suggests future research directions. A recent interest in explainable artificial intelligence (XAI) was discussed in an effort to understand the most influencing environmental factors on algal blooms. XAI facilitates interpretations of ML model results, thereby enhancing the models' usability for decision-making in field management and improving their overall applicability in real-world settings. We also emphasize the significance of obtaining high-quality, field-representative data to enhance the efficiency of ML applications. The effectiveness of ML models in detecting and predicting algal blooms can be improved through management strategies for data quality, such as pre-treating missing data and integrating diverse datasets into a unified database. Overall, this paper presents a comprehensive review of the latest advancements in managing algal blooms using ML technology and proposes future research directions to enhance the utilization of ML techniques.

A framework for identifying factors controlling cyanobacterium Microcystis flos-aquae blooms by coupled CCM-ECCM Bayesian networks

Cyanobacterial blooms in freshwater sources are a global concern, and gaining insight into their causes is crucial for effective resource management and control. In this study, we present a novel computational framework for the causal analysis of cyanobacterial harmful algal blooms (cyanoHABs) in Lake Kinneret. Our framework integrates Convergent Cross Mapping (CCM) and Extended CCM (ECCM) causal networks with Bayesian Network (BN) models. The constructed CCM-ECCM causal networks and BN models unveil significant interactions among factors influencing cyanoHAB formation. These interactions have been validated by domain experts and supported by evidence from peer-reviewed publications. Our findings suggest that Microcystis flos-aquae levels are influenced not only by community structure but also by ammonium, phosphate, oxygen, and temperature levels in the weeks preceding bloom occurrences. We demonstrated a non-parametric computational framework for causal analysis of a multivariate ecosystem. Our framework offers a more comprehensive understanding of the underlying mechanisms driving M. flos-aquae blooms in Lake Kinneret. It captures complex interactions and provides an explainable prediction model. By considering causal relationships, temporal dynamics, and joint probabilities of environmental factors, the proposed framework enhances our understanding of cyanoHABs in Lake Kinneret.

Effects of typhoon events on coastal hydrology, nutrients, and algal bloom dynamics: Insights from continuous observation and machine learning in semi-enclosed Zhanjiang Bay, China

Typhoons can induce variations in hydrodynamic conditions and biogeochemical processes, potentially escalating the risk of algal bloom occurrences impacting coastal ecosystems. However, the impacts of typhoons on instantaneous changes and the mechanisms behind typhoon-induced algal blooms remain poorly understood. This study utilized high-frequency in situ observation and machine learning model to track the dynamic variations in meteorological, hydrological, physicochemical, and Chlorophyll-a (Chl-a) levels through the complete Typhoon Talim landing in Zhanjiang Bay (ZJB) in July 2023. The results showed that a delayed onset of algal bloom occurring 10 days after typhoon's arrival. Subsequently, as temperatures reached a suitable range, with an ample supply of nutrients and water stability, Chl-a peaked at 121.49 μg L-1 in algal bloom period. Additionally, water temperature and air temperature decreased by 1.61 °C and 2.8 °C during the typhoon, respectively. In addition, wind speed and flow speed increased by 1.34 and 0.015 m s-1 h-1 to peak values, respectively. Moreover, the slow decline of 8.2 % in salinity suggested a substantial freshwater input, leading to an increase in nutrients. For instance, the mean DIN and DIP were 2.2 and 8.5 times higher than those of the pre-typhoon period, resulting in a decrease in DIN/DIP (closer to16) and the alleviation of P limitation. Furthermore, pH and dissolved oxygen (DO) were both low during the typhoon period and then peaked at 8.93 and 19.05 mg L-1 during the algal bloom period, respectively, but subsequently decreased, remaining lower than those of the pre-typhoon period. A preliminary learning machine model was established to predict Chl-a and exhibited good accuracy, with R2 of 0.73. This study revealed the mechanisms of eutrophication status formation and algal blooms occurrence in the coastal waters, providing insights into the effects of typhoon events on tropical coastal biogeochemistry and ecology.

The health risks of marine biotoxins associated with high seafood consumption: Looking beyond the single dose, single outcome paradigm with a view towards addressing the needs of coastal Indigenous populations in British Columbia

People who consume high quantities of seafood are at a heightened risk for marine biotoxin exposure. Coastal Indigenous peoples may experience higher levels of risk than the general population due to their reliance on traditional marine foods. Most evidence on the health risks associated with biotoxins focus on a single exposure at one point in time. There is limited research on other types of exposures that may occur among those who regularly consume large quantities of seafood. The objective of this review is to assess what is known about the unique biotoxin exposure risks associated with the consumption patterns of many coastal Indigenous populations. These risks include [1]: repeated exposure to low doses of a single or multiple biotoxins [2]; repeated exposures to high doses of a single or multiple biotoxins; and [3] exposure to multiple biotoxins at a single point in time. We performed a literature search and collected 23 recent review articles on the human health effects of different biotoxins. Using a narrative framework synthesis approach, we collated what is known about the health effects of the exposure risks associated with the putative consumption patterns of coastal Indigenous populations. We found that the health effects of repeated low- or high-dose exposures and the chronic health effects of marine biotoxins are rarely studied or documented. There are gaps in our understanding of how risks differ by seafood species and preparation, cooking, and consumption practices. Together, these gaps contribute to a relatively poor understanding of how biotoxins impact the health of those who regularly consume large quantities of seafood. In the context of this uncertainty, we explore how known and potential risks associated with biotoxins can be mitigated, with special attention to coastal Indigenous populations routinely consuming seafood. Overall, we conclude that there is a need to move beyond the single-dose single-outcome model of exposure to better serve Indigenous communities and others who consume high quantities of seafood.

Predicting coastal harmful algal blooms using integrated data-driven analysis of environmental factors

Coastal harmful algal blooms (HABs) have become one of the challenging environmental problems in the world's thriving coastal cities due to the interference of multiple stressors from human activities and climate change. Past HAB predictions primarily relied on single-source data, overlooked upstream land use, and typically used a single prediction algorithm. To address these limitations, this study aims to develop predictive models to establish the relationship between the HAB indicator - chlorophyll-a (Chl-a) and various environmental stressors, under appropriate lagging predictive scenarios. To achieve this, we first applied the partial autocorrelation function (PACF) to Chl-a to precisely identify two prediction scenarios. We then combined multi-source data and several machine learning algorithms to predict harmful algae, using SHapley Additive exPlanations (SHAP) to extract key features influencing output from the prediction models. Our findings reveal an apparent 1-month autoregressive characteristic in Chl-a, leading us to create two scenarios: 1-month lead prediction and current-month prediction. The Extra Tree Regressor (ETR), with an R2 of 0.92, excelled in 1-month lead predictions, while the Random Forest Regressor (RFR) was most effective for current-month predictions with an R2 of 0.69. Additionally, we identified current month Chl-a, developed land use, total phosphorus, and nitrogen oxides (NOx) as critical features for accurate predictions. Our predictive framework, which can be applied to coastal regions worldwide, provides decision-makers with crucial tools for effectively predicting and mitigating HAB threats in major coastal cities.

Modeling the dynamics of harmful algal bloom events in two bays from the northern Chilean upwelling system

The bays of Tongoy and Guanaqueros are located in the Humboldt Current system, where Argopecten purpuratus has been the subject of intense aquaculture development. These bays lie in one of the most productive marine ecosystems on Earth and are dominated by permanent coastal upwelling at Lengua de Vaca Point and Choros Point, one of the three upwelling centers on the Chilean coast. Significantly, this productive system experiences a high recurrence of harmful algal bloom (HAB) events. This paper examines 9-year (2010-2018) samples of three toxic microalgal species collected in different monitoring programs and research projects. During this period, nine HAB events were detected in Guanaqueros Bay and 14 in Tongoy Bay. Among these, three HAB events were produced simultaneously in both bays by Pseudo-nitzschia australis, and two events produced simultaneously were detected in one bay by Alexandrium spp. and the other by Dinophysis acuminata. Before El Niño 2015-16, there were more HAB events of longer duration by the three species. Since El Niño, the number and duration of events were reduced and only produced by P. australis. HAB events were simulated with the FVCOM model and a virtual particle tracker model to evaluate the dynamics of bays and their relationship with HAB events. The results showed retention in bays during the relaxation conditions of upwelling and low connectivity between bays, which explains why almost no simultaneous events were recorded.

Prediction on daily spatial distribution of chlorophyll-a in coastal seas using a synthetic method of remote sensing, machine learning and numerical modeling

Harmful algal blooms (HABs) pose a severe environmental issue and have significant economic and ecological consequences on coastal oceans. Predicting the occurrence of these blooms has become increasingly vital for coastal communities. To facilitate this, chlorophyll-a (Chl-a) levels have been widely used to forecast algal blooms. Although Hydro-biogeochemical (HBGC) process-based models display reasonable accuracy in predicting hydrodynamic variables and nutrients, they are not as effective in predicting Chl-a. Purely data-driven machine learning techniques also have limitations in accurately predicting Chl-a of high spatio-temporal resolutions. In this study, a coupled HBGC-Convolutional Neural Network (CNN) model was developed to predict the daily surface Chl-a distribution. The HBGC-CNN model integrates the information gathered by the HBGC model on temperature, salinity, dissolved inorganic nitrogen, dissolved organic phosphorus, and zooplankton with the remote sensing Chl-a products for the CNN model training. The results revealed that the HBGC-CNN model can effectively reproduce both daily and seasonal Chl-a variations, and interpret spatiotemporal information related to an HAB event triggered by the heavy rainfall during typhoon Lekima in 2019. Furthermore, this method can be used for data reconstruction, producing gap-free Chl-a products for historical reanalysis, especially in nearshore regions. The successful implementation of the HBGC-CNN model in predicting Chl-a highlights its potential in being incorporated into an operational forecasting system from a regional scale to a global scale, reducing the adverse impact of HAB disasters and facilitating emergency treatment.

An automated and intelligent microfluidic platform for microalgae detection and monitoring

Microalgae not only play a vital role in the ecosystem but also hold promising commercial applications. Conventional methods of detecting and monitoring microalgae rely on field sampling followed by transportation to the laboratory for manual analysis, which is both time-consuming and laborious. Although machine learning (ML) algorithms have been introduced for microalgae detection in the laboratory, no integrated platform approach has yet emerged to enable real-time, on-site sampling and analysing. To solve this problem, here, we develop an automated and intelligent microfluidic platform (AIMP) that can offer automated system control, intelligent data analysis, and user interaction, providing an economical and portable solution to alleviate the drawbacks of conventional methods for microalgae detection and monitoring. We demonstrate the feasibility of the AIMP by detecting and classifying four microalgal species (Cosmarium, Closterium, Micrasterias, and Haematococcus Pluvialis) that exhibit varying sizes (from a few to hundreds of microns) and morphologies. The trained microalgae species detection network (MSDN, based on YOLOv5 architecture) achieves a high overall mean average precision at 0.5 intersection-over-union (mAP@0.5) of 92.8%. Furthermore, the versatility of the AIMP is demonstrated by long-term monitoring of astaxanthin production from Haematococcus Pluvialis over a period of 30 days. The AIMP achieved 97.5% accuracy in the detection of Haematococcus Pluvialis and 96.3% in further classification based on astaxanthin accumulation. This study opens up a new path towards microalgae detection and monitoring using portable intelligent devices, providing new ideas to accelerate progress in the ecological studies and commercial exploitation of microalgae.

Current status and prospects of algal bloom early warning technologies: A Review

In recent years, frequent occurrences of algal blooms due to environmental changes have posed significant threats to the environment and human health. This paper analyzes the reasons of algal bloom from the perspective of environmental factors such as nutrients, temperature, light, hydrodynamics factors and others. Various commonly used algal bloom monitoring methods are discussed, including traditional field monitoring methods, remote sensing techniques, molecular biology-based monitoring techniques, and sensor-based real-time monitoring techniques. The advantages and limitations of each method are summarized. Existing algal bloom prediction models, including traditional models and machine learning (ML) models, are introduced. Support Vector Machine (SVM), deep learning (DL), and other ML models are discussed in detail, along with their strengths and weaknesses. Finally, this paper provides an outlook on the future development of algal bloom warning techniques, proposing to combine various monitoring methods and prediction models to establish a multi-level and multi-perspective algal bloom monitoring system, further improving the accuracy and timeliness of early warning, and providing more effective safeguards for environmental protection and human health.

Know Before You Go: Data-Driven Beach Water Quality Forecasting

Forecasting environmental hazards is critical in preventing or building resilience to their impacts on human communities and ecosystems. Environmental data science is an emerging field that can be harnessed for forecasting, yet more work is needed to develop methodologies that can leverage increasingly large and complex data sets for decision support. Here, we design a data-driven framework that can, for the first time, forecast bacterial standard exceedances at marine beaches with 3 days lead time. Using historical data sets collected at two California sites, we train nearly 400 forecast models using statistical and machine learning techniques and test forecasts against predictions from both a naive "persistence" model and a baseline nowcast model. Overall, forecast models are found to have similar sensitivities and specificities to the persistence model, but significantly higher areas under the ROC curve (a metric distinguishing a model's ability to effectively parse classes across decision thresholds), suggesting that forecasts can provide enhanced information beyond past observations alone. Forecast model performance at all lead times was similar to that of nowcast models. Together, results suggest that integrating the forecasting framework developed in this study into beach management programs can enable better public notification and aid in proactive pollution and health risk management.

Modelling spatiotemporal distributions of Vulcanodinium rugosum and pinnatoxin G in French Mediterranean lagoons: Application to human health risk characterisation

Consumption of seafood contaminated by phycotoxins produced by harmful algae is a major issue in human public health. Harmful algal blooms are driven by a multitude of environmental variables; therefore predicting human dietary exposure to phycotoxins based on these variables is a promising approach in health risk management. In this study, we attempted to predict the human health risks associated with Vulcanodinium rugosum and its neurotoxins, pinnatoxins (PnTXs), which have been regularly found in Mediterranean lagoons since their identification in 2011. Based on environmental variables collected over 1 year in four Mediterranean lagoons, we developed linear mixed models to predict the presence of V. rugosum and PnTX G contamination of mussels. We found that the occurrence of V. rugosum was significantly associated with seawater temperature. PnTX G contamination of mussels was highest in summer but persisted throughout the year. This contamination was significantly associated with seawater temperature and the presence of V. rugosum with a time lag, but not with dissolved PnTX G in seawater. By using the contamination model predictions and their potential variability/uncertainty, we calculated the human acute dietary exposures throughout the year and predicted that 25% of people who consume mussels could exceed the provisional acute benchmark value during the warmest periods. We suggest specific recommendations to monitor V. rugosum and PnTX G.

A 15-Year Retrospective Review of Ciguatera in the Madeira Islands (North-East Atlantic, Portugal)

The first ciguatera fish poisoning (CFP) in Portugal dates from 2008 when 11 people reported CFP symptoms after consuming a 30 kg amberjack caught around the Selvagens Islands (Madeira Archipelago). Since then, 49 human poisonings have been reported. The emergence of a new threat challenged scientists and regulators, as methods for toxic microalgae analyses and ciguatoxin (CTX) detection were not implemented. To minimise the risk of ciguatera, the Madeira Archipelago authorities interdicted fisheries in Selvagens Islands and banned the capture of amberjacks weighing more than 10 kg in the entire region of Madeira Archipelago. The accurate identification and quantification of the benthic toxin-producing algae species spreading to new areas require efforts in terms of both microscopy and molecular techniques. Two ciguatera-causing dinoflagellates, Gambierdiscus excentricus and Gambierdiscus australes, were identified in the Madeira Island and Selvagens sub-archipelago, respectively. Regarding the CTX analysis (N2a cell-based assay and LC-MS) in fish, the results indicate that the Selvagens Islands are a ciguatera risk area and that fish vectoring CTX are not limited to top predator species. Nevertheless, advances and improvements in screening methods for the fast detection of toxicity in seafood along with certified reference material and sensitive and selective targeted analytical methods for the determination of CTX content are still pending. This study aims to revise the occurrence of ciguatera cases in the Madeira Archipelago since its first detection in 2008, to discuss the risk management strategy that was implemented, and to provide a summary of the available data on the bioaccumulation of CTX in marine fish throughout the marine food web, taking into consideration their ecological significance, ecosystem dynamics, and fisheries relevance.

Influence of resampling techniques on Bayesian network performance in predicting increased algal activity

Early warning of increased algal activity is important to mitigate potential impacts on aquatic life and human health. While many methods have been developed to predict increased algal activity, an ongoing issue is that severe algal blooms often occur with low frequency in water bodies. This results in imbalanced data sets available for model specification, leading to poor predictions of the frequency of increased algal activity. One approach to address this is to resample data sets of increased algal activity to increase the prevalence of higher than normal algal activity in calibration data and ultimately improve model predictions. This study aims to investigate the use of resampling techniques to address the imbalanced dataset and determine if such methods can improve the prediction of increased algal activity. Three techniques were investigated, Kmeans under-sampling (US_Kmeans), synthetic minority over-sampling technique (SMOTE), and 'SMOTE and cluster-based under-sampling technique' (SCUT). The resampling methods were applied to a Bayesian network (BN) model of Lake Burragorang in New South Wales, Australia. The model was developed to predict chlorophyll-a (chl-a) using a range of water quality parameters as predictors. The original data and each of the balanced datasets were used for BN structures and parameter learning. The results showed that the best graphical structure was obtained by adding synthetic data from SMOTE with the highest true positive rate (TPR) and area under the curve (AUC). When compared using a fixed graphical structure for the BN, all resampling techniques increased the ability of the BN to detect events with higher probability of increased algal activity. The resampling model results can also be used to better understand the most important influences on high chl-a concentrations and suggest future data collection and model development priorities.

Forecasting harmful algae blooms: Application to Dinophysis acuminata in northern Norway

Dinophysis acuminata produces Diarrhetic Shellfish Toxins (DST) that contaminate natural and farmed shellfish, leading to public health risks and economically impacting mussel farms. For this reason, there is a high interest in understanding and predicting D. acuminata blooms. This study assesses the environmental conditions and develops a sub-seasonal (7 - 28 days) forecast model to predict D. acuminata cells abundance in the Lyngen fjord located in northern Norway. A Support Vector Machine (SVM) model is trained to predict future D. acuminata cells abundance by using the past cell concentration, sea surface temperature (SST), Photosynthetic Active Radiation (PAR), and wind speed. Cells concentration of Dinophysis spp. are measured in-situ from 2006 to 2019, and SST, PAR, and surface wind speed are obtained by satellite remote sensing. D. acuminata only explains 40% of DST variability from 2006 to 2011, but it changes to 65% after 2011 when D. acuta prevalence reduced. The D. acuminata blooms can reach concentration up to 3954 cells l-1 and are restricted to the summer during warmer waters, varying from 7.8 to 12.7 °C. The forecast model predicts with fair accuracy the seasonal development of the blooms and the blooms amplitude, showing a coefficient of determination varying from 0.46 to 0.55. SST has been found to be a useful predictor for the seasonal development of the blooms, while the past cells abundance is needed for updating the current status and adjusting the blooms timing and amplitude. The calibrated model should be tested operationally in the future to provide an early warning of D. acuminata blooms in the Lyngen fjord. The approach can be generalized to other regions by recalibrating the model with local observations of D. acuminata blooms and remote sensing data.

Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine Learning

The use of bivalve mollusks as bioindicators in automated monitoring systems can provide real-time detection of emergency situations associated with the pollution of aquatic environments. The behavioral reactions of Unio pictorum (Linnaeus, 1758) were employed in the development of a comprehensive automated monitoring system for aquatic environments by the authors. The study used experimental data obtained by an automated system from the Chernaya River in the Sevastopol region of the Crimean Peninsula. Four traditional unsupervised machine learning techniques were implemented to detect emergency signals in the activity of bivalves: elliptic envelope, isolation forest (iForest), one-class support vector machine (SVM), and local outlier factor (LOF). The results showed that the use of the elliptic envelope, iForest, and LOF methods with proper hyperparameter tuning can detect anomalies in mollusk activity data without false alarms, with an F1 score of 1. A comparison of anomaly detection times revealed that the iForest method is the most efficient. These findings demonstrate the potential of using bivalve mollusks as bioindicators in automated monitoring systems for the early detection of pollution in aquatic environments.

Remote sensing for mapping algal blooms in freshwater lakes: a review

A large number of freshwater lakes around the world show recurring harmful algal blooms, particularly cyanobacterial blooms, that affect public health and ecosystem integrity. Prediction, early detection, and monitoring of algal blooms are inevitable for the mitigation and management of their negative impacts on the environment and human beings. Remote sensing provides an effective tool for detecting and spatiotemporal monitoring of these events. Various remote sensing platforms, such as ground-based, spaceborne, airborne, and UAV-based, have been used for mounting sensors for data acquisition and real-time monitoring of algal blooms in a cost-effective manner. This paper presents an updated review of various remote sensing platforms, data types, and algorithms for detecting and monitoring algal blooms in freshwater lakes. Recent studies on remote sensing using sophisticated sensors mounted on UAV platforms have revolutionized the detection and monitoring of water quality. Image processing algorithms based on Artificial Intelligence (AI) have been improved recently and predicting algal blooms based on such methods will have a key role in mitigating the negative impacts of eutrophication in the future.

Exploring long-term trends in microcystin toxin values associated with persistent harmful algal blooms in Grand Lake St Marys

High external nutrient loads from agricultural runoff have led to persistent and highly toxic algal blooms in Grand Lake St Marys (GLSM) for decades. These pervasive blooms are concurrent with long-term (2009 - 2021) toxin and environmental monitoring, providing a robust weekly dataset for modeling microcystins. Median weekly microcystin concentrations (23.2 µg/L) routinely exceeded World Health Organization recreational limits (20 µg/L) for the study period (ranged 0.03 - 185.0 µg/L). Here, we used a Bayesian hierarchical dynamic linear model to hindcast weekly microcystin toxins using external nutrient loads from tributary data as well as internal lake nutrient and physicochemical concentrations. Overall, lake TN was the biggest driver of microcystin concentration in GLSM. Likewise, TN:TP was a strong negative driver of microcystin (i.e. low N:P ratios align with lower total microcystins), suggesting that N availability directly impacts toxins. External nutrient loading was positively related to microcystin during winter and spring; however, there was no relationship detected between toxin and external loading during summer or fall (particulate phosphorus exhibited the strongest signal but all external nutrients were unsurprisingly correlated). This lack of direct correlation on a weekly timescale between external loads and cyanobacterial toxins during the summer months likely results from nutrient saturation and reflects the importance of internal loading for bloom maintenance as supported by the correlation between in-lake TN and microcystin. Thus, management goals to reduce the highest biomass and toxins in the summer should focus on reduction of winter and spring external nutrient loads. Supporting this, both 2010 and 2021 had lower rain in the first half of the year (winter/spring), resulting in less loading, and experienced smaller/later low toxicity blooms. This suggests that, although internal nutrient loads are important for bloom maintenance, reduced external loads are an effective management strategy even in nutrient saturated systems such as GLSM.

Quantifying Spatio-temporal risk of Harmful Algal Blooms and their impacts on bivalve shellfish mariculture using a data-driven modelling approach

Harmful algal blooms (HABs) intoxicate and asphyxiate marine life, causing devastating environmental and socio-economic impacts, costing at least $8bn/yr globally. Accumulation of phycotoxins from HAB phytoplankton in filter-feeding shellfish can poison human consumers, prompting harvesting closures at shellfish production sites. To quantify long-term intoxication risk from Dinophysis HAB species, we used historical HAB monitoring data (2009-2020) to develop a new modelling approach to predict Dinophysis toxin concentrations in a range of bivalve shellfish species at shellfish sites in Western Scotland, South-West England and Northern France. A spatiotemporal statistical modelling framework was developed within the Generalized Additive Model (GAM) framework to quantify long-term HAB risks for different bivalve shellfish species across each region, capturing seasonal variations, and spatiotemporal interactions. In all regions spatial functions were most important for predicting seasonal HAB risk, offering the potential to inform optimal siting of new shellfish operations and safe harvesting periods for businesses. A 10-fold cross-validation experiment was carried out for each region, to test the models' ability to predict toxin risk at harvesting locations for which data were withheld from the model. Performance was assessed by comparing ranked predicted and observed mean toxin levels at each site within each region: the correlation of ranks was 0.78 for Northern France, 0.64 for Western Scotland, and 0.34 for South-West England, indicating our approach has promise for predicting unknown HAB risk, depending on the region and suitability of training data.

Use of industry 4.0 technologies to reduce and valorize seafood waste and by-products: A narrative review on current knowledge

Fish and other seafood products represent a valuable source of many nutrients and micronutrients for the human diet and contribute significantly to global food security. However, considerable amounts of seafood waste and by-products are generated along the seafood value and supply chain, from the sea to the consumer table, causing severe environmental damage and significant economic loss. Therefore, innovative solutions and alternative approaches are urgently needed to ensure a better management of seafood discards and mitigate their economic and environmental burdens. The use of emerging technologies, including the fourth industrial revolution (Industry 4.0) innovations (such as Artificial Intelligence, Big Data, smart sensors, and the Internet of Things, and other advanced technologies) to reduce and valorize seafood waste and by-products could be a promising strategy to enhance blue economy and food sustainability around the globe. This narrative review focuses on the issues and risks associated with the underutilization of waste and by-products resulting from fisheries and other seafood industries. Particularly, recent technological advances and digital tools being harnessed for the prevention and valorization of these natural invaluable resources are highlighted.

A multivariate Chain-Bernoulli-based prediction model for cyanobacteria algal blooms at multiple stations in South Korea

Predicting the occurrence of algal blooms is of great importance in managing water quality. Moreover, the demand for predictive models, which are essential tools for understanding the drivers of algal blooms, is increasing with global warming. However, modeling cyanobacteria dynamics is a challenging task. We developed a multivariate Chain-Bernoulli-based prediction model to effectively forecast the monthly sequences of algal blooms considering hydro-environmental predictors (water temperature, total phosphorus, total nitrogen, and water velocity) at a network of stations. The proposed model effectively predicts the risk of harmful algal blooms, according to performance measures based on categorical metrics of a contingency table. More specifically, the model performance assessed by the LOO cross-validation and the skill score for the POD and CSI during the calibration period was over 0.8; FAR and MR were less than 0.15. We also explore the relationship between hydro-environmental predictors and algal blooms (based on cyanobacteria cell count) to understand the dynamics of algal blooms and the relative contribution of each potential predictor. A support vector machine is applied to delineate a plane separating the presence and absence of algal bloom occurrences determined by stochastic simulations using different combinations of predictors. The multivariate Chain-Bernoulli-based prediction model proposed here offers effective, scenario-based, and strategic options and remedies (e.g., controlling the governing environmental predictors) to relieve or reduce increases in cyanobacteria concentration and enable the development of water quality management and planning in river systems.

Time-Lagged Correlation Analysis of Shellfish Toxicity Reveals Predictive Links to Adjacent Areas, Species, and Environmental Conditions

Diarrhetic Shellfish Poisoning (DSP) is an acute intoxication caused by the consumption of contaminated shellfish, which is common in many regions of the world. To safeguard human health, most countries implement programs focused on the surveillance of toxic phytoplankton abundance and shellfish toxicity levels, an effort that can be complemented by a deeper understanding of the underlying phenomena. In this work, we identify patterns of seasonality in shellfish toxicity across the Portuguese coast and analyse time-lagged correlations between this toxicity and various potential risk factors. We extend the understanding of these relations through the introduction of temporal lags, allowing the analysis of time series at different points in time and the study of the predictive power of the tested variables. This study confirms previous findings about toxicity seasonality patterns on the Portuguese coast and provides further quantitative data about the relations between shellfish toxicity and geographical location, shellfish species, toxic phytoplankton abundances, and environmental conditions. Furthermore, multiple pairs of areas and shellfish species are identified as having correlations high enough to allow for a predictive analysis. These results represent the first step towards understanding the dynamics of DSP toxicity in Portuguese shellfish producing areas, such as temporal and spatial variability, and towards the development of a shellfish safety forecasting system.

Chlorophyll soft-sensor based on machine learning models for algal bloom predictions

Harmful algal blooms (HABs) are a growing concern to public health and aquatic ecosystems. Long-term water monitoring conducted by hand poses several limitations to the proper implementation of water safety plans. This work combines automatic high-frequency monitoring (AFHM) systems with machine learning (ML) techniques to build a data-driven chlorophyll-a (Chl-a) soft-sensor. Massive data for water temperature, pH, electrical conductivity (EC) and system battery were taken for three years at intervals of 15 min from two different areas of As Conchas freshwater reservoir (NW Spain). We designed a set of soft-sensors based on compact and energy efficient ML algorithms to infer Chl-a fluorescence by using low-cost input variables and to be deployed on buoys with limited battery and hardware resources. Input and output aggregations were applied in ML models to increase their inference performance. A component capable of triggering a 10 [Formula: see text]g/L Chl-a alert was also developed. The results showed that Chl-a soft-sensors could be a rapid and inexpensive tool to support manual sampling in water bodies at risk.

Prediction of Microcystis Occurrences and Analysis Using Machine Learning in High-Dimension, Low-Sample-Size and Imbalanced Water Quality Data

Machine learning, Deep learning, and water quality data have been used in recent years to predict the outbreak of harmful algae, especially Microcystis, and analyze outbreak causes. However, for various reasons, water quality data are often High-Dimension, Low-Sample- Size (HDLSS), meaning the sample size is lower than the number of dimensions. Moreover, imbalance problems may arise due to bias in the occurrence frequency of Microcystis. These problems make predicting the occurrence of Microcystis and analyzing its causes with machine learning difficult. In this study, a machine learning model that applies Feature Engineering (FE) and Feature Selection (FS) algorithms are used to predict outbreaks of Microcystis and analyze the outbreak factors from imbalanced HDLSS water quality data. The prediction performance was verified with binary classification to determine whether Microcystis would occur in the future by applying three machine learning models to four data patterns. The cause analysis of Microcystis occurrence was performed by visualizing the results of applying FE and FS. For the test data, the predictive performance of FE and FS methods was significantly better than that of the conventional method, with an accuracy of .108 points and an F-value of .691 points higher than the conventional method. A prediction performance increase was observed with a smaller model capacity. Data-driven analysis suggested that total nitrogen, chemical oxygen demand, chlorophyll-a, dissolved oxygen saturation, and water temperature are associated with Microcystis occurrences. The results also indicated that basic statistics of the water quality distribution (especially mean, standard deviation, and skewness) over a year, not the concentrations of water components, are related to the occurrence of Microcystis. These are new findings not found in previous studies and are expected to contribute significantly to future studies of algae. This study provides a method for analyzing water quality data with high-dimensionality and small samples, imbalance problems, or both.

Variability patterns and phenology of harmful phytoplankton blooms off southern Portugal: Looking for region-specific environmental drivers and predictors

Harmful algal blooms (HABs) negatively impact coastal ecosystems, fisheries, and human health, and their prediction has become imperative for effective coastal management. This study aimed to evaluate spatial-temporal variability patterns and phenology for key toxigenic phytoplankton species off southern Portugal, during a 6-year period, and identify region-specific environmental drivers and predictors. Total abundance of species responsible for amnesic shellfish poisoning (Pseudo-nitzschia spp.), diarrhetic shellfish poisoning (Dinophysis spp.), and paralytic shellfish poisoning (G. catenatum) were retrieved, from the National Bivalve Mollusk Monitoring System public database. Contemporaneous environmental variables were acquired from satellite remote sensing, model-derived data, and in situ observations, and generalized additive models (GAMs) were used to explore the functional relationships between HABs and environmental variables and identify region-specific predictors. Pseudo-nitzschia spp. showed a bimodal annual cycle for most coastal production areas, with spring and summer maxima, reflecting the increase in light intensity during the mixed layer shoaling stage, and the later stimulatory effects of upwelling events, with a higher bloom frequency over coastal areas subjected to stronger upwelling intensity. Dinophysis spp. exhibited a unimodal annual cycle, with spring/summer maxima associated with stratified conditions, that typically promote dinoflagellates. Dinophysis spp. blooms were delayed with respect to Pseudo-nitzschia spp. spring blooms, and followed by Pseudo-nitzschia spp. summer blooms, probably reflecting upwelling-relaxation cycles. G. catenatum occurred occasionally, namely in areas more influenced by river discharges, under weaker upwelling. Statistical-empirical models (GAMs) explained 7-8%, and 21-54% of the variability in Pseudo-nitzschia spp. and Dinophysis spp., respectively. Overall, a set of four easily accessible environmental variables, surface photosynthetically available radiation, mixed layer depth, sea surface temperature, and chlorophyll-a concentration, emerged as the most influential predictors. Additionally, over the coastal production areas along the south coast, river discharges exerted minor negative effects on both HAB groups. Despite evidence supporting the role of upwelling intensity as an environmental driver of Pseudo-nitzschia spp., it was not identified as a relevant model predictor. Future model developments, such as the inclusion of additional environmental variables, and the implementation of species- and period-specific, and hybrid modelling approaches, may further support HAB operational forecasting and managing over complex coastal domains.

Prediction of Alexandrium and Dinophysis algal blooms and shellfish contamination in French Mediterranean Lagoons using decision trees and linear regression: a result of 10 years of sanitary monitoring

French Mediterranean lagoons are frequently subject to shellfish contamination by Diarrheic Shellfish Toxins (DSTs) and Paralytic Shellfish Toxins (PSTs). To predict the effect of various environmental factors (temperature, salinity and turbidity) on the abundance of the major toxins producing genera, Dinophysis and Alexandrium, and the link with shellfish contamination, we analysed a 10-year dataset collected from 2010 to 2019 in two major shellfish farming lagoons, Thau and Leucate, using two methods: decision trees and Zero Inflated Negative Binomial (ZINB) linear regression models. Analysis of these decision trees revealed that the highest risk of Dinophysis bloom events occurred at temperature <16.3°C and salinity <27.8, and of Alexandrium at temperature ranging from 10.4 to 21.5°C and salinity >39.2. The highest risk of shellfish contaminations by DSTs and PSTs occurred during the set of conditions associated with high risk of bloom events. Linear regression prediction enables us to understand whether temperature and salinity influence the presence of Alexandrium and affect its abundance. However, Dinophysis linear regression could not be validated due to overdispersion issues. This work demonstrates the tools which could help sanitary management of shellfish rearing areas.

Effects of Harmful Algal Blooms on Fish and Shellfish Species: A Case Study of New Zealand in a Changing Environment

Harmful algal blooms (HABs) have wide-ranging environmental impacts, including on aquatic species of social and commercial importance. In New Zealand (NZ), strategic growth of the aquaculture industry could be adversely affected by the occurrence of HABs. This review examines HAB species which are known to bloom both globally and in NZ and their effects on commercially important shellfish and fish species. Blooms of Karenia spp. have frequently been associated with mortalities of both fish and shellfish in NZ and the sub-lethal effects of other genera, notably Alexandrium spp., on shellfish (which includes paralysis, a lack of byssus production, and reduced growth) are also of concern. Climate change and anthropogenic impacts may alter HAB population structure and dynamics, as well as the physiological responses of fish and shellfish, potentially further compromising aquatic species. Those HAB species which have been detected in NZ and have the potential to bloom and harm marine life in the future are also discussed. The use of environmental DNA (eDNA) and relevant bioassays are practical tools which enable early detection of novel, problem HAB species and rapid toxin/HAB screening, and new data from HAB monitoring of aquaculture production sites using eDNA are presented. As aquaculture grows to supply a sizable proportion of the world’s protein, the effects of HABs in reducing productivity is of increasing significance. Research into the multiple stressor effects of climate change and HABs on cultured species and using local, recent, HAB strains is needed to accurately assess effects and inform stock management strategies.

An Improved Transfer Learning Model for Cyanobacterial Bloom Concentration Prediction

The outbreak of cyanobacterial blooms is a serious water environmental problem, and the harm it brings to aquatic ecosystems and water supply systems cannot be underestimated. It is very important to establish an accurate prediction model of cyanobacterial bloom concentration, which is a challenging issue. Machine learning techniques can improve the prediction accuracy, but a large amount of historical monitoring data is needed to train these models. For some waters with an inconvenient geographical location or frequent sensor failures, there are not enough historical data to train the model. To deal with this problem, a fused model based on a transfer learning method is proposed in this paper. In this study, the data of water environment with a large amount of historical monitoring data are taken as the source domain in order to learn the knowledge of cyanobacterial bloom growth characteristics and train the prediction model. The data of the water environment with a small amount of historical monitoring data are taken as the target domain in order to load the model trained in the source domain. Then, the training set of the target domain is used to participate in the inter-layer fine-tuning training of the model to obtain the transfer learning model. At last, the transfer learning model is fused with a convolutional neural network to obtain the prediction model. Various experiments are conducted for a 2 h prediction on the test set of the target domain. The results show that the proposed model can significantly improve the prediction accuracy of cyanobacterial blooms for the water environment with a low data volume.

Mapping Benthic Algae and Cyanobacteria in River Channels from Aerial Photographs and Satellite Images: A Proof-of-Concept Investigation on the Buffalo National River, AR, USA

Although rivers are of immense practical, aesthetic, and recreational value, these aquatic habitats are particularly sensitive to environmental changes. Increasingly, changes in streamflow and water quality are resulting in blooms of bottom-attached (benthic) algae, also known as periphyton, which have become widespread in many water bodies of US national parks. Because these blooms degrade visitor experiences and threaten human and ecosystem health, improved methods of characterizing benthic algae are needed. This study evaluated the potential utility of remote sensing techniques for mapping variations in algal density in shallow, clear-flowing rivers. As part of an initial proof-of-concept investigation, field measurements of water depth and percent cover of benthic algae were collected from two reaches of the Buffalo National River along with aerial photographs and multispectral satellite images. Applying a band ratio algorithm to these data yielded reliable depth estimates, although a shallow bias and moderate level of precision were observed. Spectral distinctions among algal percent cover values ranging from 0 to 100% were subtle and became only slightly more pronounced when the data were aggregated to four ordinal levels. A bagged trees machine learning model trained using the original spectral bands and image-derived depth estimates as predictor variables was used to produce classified maps of algal density. The spatial and temporal patterns depicted in these maps were reasonable but overall classification accuracies were modest, up to 64.6%, due to a lack of spectral detail. To further advance remote sensing of benthic algae and other periphyton, future studies could adopt hyperspectral approaches and more quantitative, continuous metrics such as biomass.

Methodological Approaches for Monitoring Five Major Food Safety Hazards Affecting Food Production in the Galicia-Northern Portugal Euroregion

The agri-food industry has historically determined the socioeconomic characteristics of Galicia and Northern Portugal, and it was recently identified as an area for collaboration in the Euroregion. In particular, there is a need for action to help to ensure the provision of safe and healthy foods by taking advantage of key enabling technologies. The goals of the FOODSENS project are aligned with this major objective, specifically with the development of biosensors able to monitor hazards relevant to the safety of food produced in the Euroregion. The present review addresses the state of the art of analytical methodologies and techniques-whether commercially available or in various stages of development-for monitoring food hazards, such as harmful algal blooms, mycotoxins, Listeria monocytogenes, allergens, and polycyclic aromatic hydrocarbons. We discuss the pros and cons of these methodologies and techniques and address lines of research for point-of-care detection. Accordingly, the development of miniaturized automated monitoring strategies is considered a priority in terms of health and economic interest, with a significant impact in several areas, such as food safety, water quality, pollution control, and public health. Finally, we present potential market opportunities that could result from the availability of rapid and reliable commercial methodologies.

Machine learning methods for imbalanced data set for prediction of faecal contamination in beach waters

Predicting water contamination by statistical models is a useful tool to manage health risk in recreational beaches. Extreme contamination events, i.e. those exceeding normative are generally rare with respect to bathing conditions and thus the data is said to be imbalanced. Modeling and predicting those rare events present unique challenges. Here we introduce and evaluate several machine learning techniques and metrics to model imbalanced data and evaluate model performance. We do so by using a) simulated data-sets and b) a real data base with records of faecal coliform abundance monitored for 10 years in 21 recreational beaches in Uruguay (N ≈ 19000) using in situ and meteorological variables. We discuss advantages and disadvantages of the methods and provide a simple guide to perform models for a general audience. We also provide R codes to reproduce model fitting and testing. We found that most Machine Learning techniques are sensitive to imbalance and require specific data pre-treatment (e.g. upsampling) to improve performance. Accuracy (i.e. correctly classified cases over total cases) is not adequate to evaluate model performance on imbalanced data set. Instead, true positive rates (TPR) and false positive rates (FPR) are recommended. Among the 52 possible candidate algorithms tested, the stratified Random forest presented the better performance improving TPR in 50% with respect to baseline (0.4) and outperformed baseline in the evaluated metrics. Support vector machines combined with upsampling method or synthetic minority oversampling technique (SMOTE) performed well, similar to Adaboost with SMOTE. These results suggests that combining modeling strategies is necessary to improve our capacity to anticipate water contamination and avoid health risk.