scholarly journals A Remote Sensing and Machine Learning-Based Approach to Forecast the Onset of Harmful Algal Bloom

2021 ◽  
Vol 13 (19) ◽  
pp. 3863
Author(s):  
Moein Izadi ◽  
Mohamed Sultan ◽  
Racha El Kadiri ◽  
Amin Ghannadi ◽  
Karem Abdelmohsen
Keyword(s):  
Machine Learning ◽  
Satellite Data ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Harmful Algal Bloom ◽  
Lag Time ◽  
Controlling Factors ◽  
Support Vector ◽  
Red Tides ◽  
Temporal Models

In the last few decades, harmful algal blooms (HABs, also known as “red tides”) have become one of the most detrimental natural phenomena in Florida’s coastal areas. Karenia brevis produces toxins that have harmful effects on humans, fisheries, and ecosystems. In this study, we developed and compared the efficiency of state-of-the-art machine learning models (e.g., XGBoost, Random Forest, and Support Vector Machine) in predicting the occurrence of HABs. In the proposed models the K. brevis abundance is used as the target, and 10 level-02 ocean color products extracted from daily archival MODIS satellite data are used as controlling factors. The adopted approach addresses two main shortcomings of earlier models: (1) the paucity of satellite data due to cloudy scenes and (2) the lag time between the period at which a variable reaches its highest correlation with the target and the time the bloom occurs. Eleven spatio-temporal models were generated, each from 3 consecutive day satellite datasets, with a forecasting span from 1 to 11 days. The 3-day models addressed the potential variations in lag time for some of the temporal variables. One or more of the generated 11 models could be used to predict HAB occurrences depending on availability of the cloud-free consecutive days. Findings indicate that XGBoost outperformed the other methods, and the forecasting models of 5–9 days achieved the best results. The most reliable model can forecast eight days ahead of time with balanced overall accuracy, Kappa coefficient, F-Score, and AUC of 96%, 0.93, 0.97, and 0.98 respectively. The euphotic depth, sea surface temperature, and chlorophyll-a are always among the most significant controlling factors. The proposed models could potentially be used to develop an “early warning system” for HABs in southwest Florida.

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

2021 ◽  
Vol 9 (3) ◽  
pp. 283
Author(s):  
Rafaela C. Cruz ◽  
Pedro Reis Costa ◽  
Susana Vinga ◽  
Ludwig Krippahl ◽  
Marta B. Lopes
Keyword(s):  
Machine Learning ◽  
Graphical Models ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Data Availability ◽  
Mitigation Measures ◽  
Support Vector ◽  
Governmental Agencies ◽  
Vector Machines ◽  
Source Data

Harmful algal blooms (HABs) are among the most severe ecological marine problems worldwide. Under favorable climate and oceanographic conditions, toxin-producing microalgae species may proliferate, reach increasingly high cell concentrations in seawater, accumulate in shellfish, and threaten the health of seafood consumers. There is an urgent need for the development of effective tools to help shellfish farmers to cope and anticipate HAB events and shellfish contamination, which frequently leads to significant negative economic impacts. Statistical and machine learning forecasting tools have been developed in an attempt to better inform the shellfish industry to limit damages, improve mitigation measures and reduce production losses. This study presents a synoptic review covering the trends in machine learning methods for predicting HABs and shellfish biotoxin contamination, with a particular focus on autoregressive models, support vector machines, random forest, probabilistic graphical models, and artificial neural networks (ANN). Most efforts have been attempted to forecast HABs based on models of increased complexity over the years, coupled with increased multi-source data availability, with ANN architectures in the forefront to model these events. The purpose of this review is to help defining machine learning-based strategies to support shellfish industry to manage their harvesting/production, and decision making by governmental agencies with environmental responsibilities.

scholarly journals Machine Learning Classification Algorithms for Predicting Karenia brevis Blooms on the West Florida Shelf

2021 ◽  
Vol 9 (9) ◽  
pp. 999
Author(s):  
Marvin F. Li ◽  
Patricia M. Glibert ◽  
Vyacheslav Lyubchich
Keyword(s):  
Machine Learning ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Large River ◽  
Karenia Brevis ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Economic Damage ◽  
The West ◽  
Machine Learning Classification

Harmful algal blooms (HABs), events that kill fish, impact human health in multiple ways, and contaminate water supplies, have increased in frequency, magnitude, and impacts in numerous marine and freshwaters around the world. Blooms of the toxic dinoflagellate Karenia brevis have resulted in thousands of tons of dead fish, deaths to many other marine organisms, numerous respiratory-related hospitalizations, and tens to hundreds of millions of dollars in economic damage along the West Florida coast in recent years. Four types of machine learning algorithms, Support Vector Machine (SVM), Relevance Vector Machine (RVM), Naïve Bayes classifier (NB), and Artificial Neural Network (ANN), were developed and compared in their ability to predict these blooms. Comparing the 21 year monitoring dataset of K. brevis abundance, RVM and NB were found to have better skills in bloom prediction than the other two approaches. The importance of upwelling-favorable northerly winds in increasing K. brevis probability, and of onshore westerly winds in preventing blooms from dispersing offshore, were quantified using RVM, and all models were used to explore the importance of large river flows and the nutrients they supply in regulating blooms. These models provide new tools for management of these devastating algal blooms.

An investigation on machine-learning models for the prediction of cyanobacteria growth

2020 ◽  
Vol 194 (2) ◽  
pp. 85-94
Author(s):  
Johannes Giere ◽  
Derek Riley ◽  
R.J. Nowling ◽  
Joshua McComack ◽  
Hedda Sander
Keyword(s):  
Machine Learning ◽  
General Public ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Prediction Models ◽  
Support Vector ◽  
Great Effort ◽  
Local Health ◽  
Sudden Increase ◽  
Freshwater Lakes

Harmful algal blooms, which are a danger to the lives of humans and animals, are caused by a sudden increase in the concentration of cyanobacteria in freshwater lakes. Cyanobacteria concentrations can be reliably measured using chemical and biological indicators, but the measurement process of the indicators is either labor-intensive or very costly. These limitations do not allow the general public to measure concentrations, so local health organizations or departments regularly assume the responsibility of measuring water quality. While computational models exist to predict algal concentrations, the accuracy of these models and need for customization due to varied lake conditions make them generally not yet reliable. We find that common regression-error functions cannot sufficiently evaluate the performance of cyanobacteria prediction models because the occurrence of harmful algal blooms is rare. Therefore, we present a method of forecasting cyanobacteria concentrations in freshwater lakes based on a machine-learning model trained on a dataset from Lake Utah with automatically-measured indicators from lake buoys. We compare several models and find that a support vector machine with a radial basis function kernel for regression reliably forecasts harmful algal blooms using comparatively few and easy-to-obtain input parameters. The special feature of the model is that it exclusively uses variables that can be measured by the general public without great effort and costs, and the amount of data necessary to train such a model is relatively minimal, allowing different models to be trained to accommodate for the nuances of different lakes.

scholarly journals Monitoring Coastal Chlorophyll-a Concentrations in Coastal Areas Using Machine Learning Models

Water ◽  
2018 ◽  
Vol 10 (8) ◽  
pp. 1020 ◽  
Author(s):  
Yong Kown ◽  
Seung Baek ◽  
Young Lim ◽  
JongCheol Pyo ◽  
Mayzonee Ligaray ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Chlorophyll A ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Support Vector ◽  
Landsat 8 ◽  
Artificial Neural

Harmful algal blooms have negatively affected the aquaculture industry and aquatic ecosystems globally. Remote sensing using satellite sensor systems has been applied on large spatial scales with high temporal resolutions for effective monitoring of harmful algal blooms in coastal waters. However, oceanic color satellites have limitations, such as low spatial resolution of sensor systems and the optical complexity of coastal waters. In this study, bands 1 to 4, obtained from Landsat-8 Operational Land Imager satellite images, were used to evaluate the performance of empirical ocean chlorophyll algorithms using machine learning techniques. Artificial neural network and support vector machine techniques were used to develop an optimal chlorophyll-a model. Four-band, four-band-ratio, and mixed reflectance datasets were tested to select the appropriate input dataset for estimating chlorophyll-a concentration using the two machine learning models. While the ocean chlorophyll algorithm application on Landsat-8 Operational Land Imager showed relatively low performance, the machine learning methods showed improved performance during both the training and validation steps. The artificial neural network and support vector machine demonstrated a similar level of prediction accuracy. Overall, the support vector machine showed slightly superior performance to that of the artificial neural network during the validation step. This study provides practical information about effective monitoring systems for coastal algal blooms.

Using Fundamental Optical Property Sensors for Characterization of Biogeochemical Materials and Processes in Marine Waters

2008 ◽  
Vol 42 (1) ◽  
pp. 75-83 ◽  
Author(s):  
Casey Moore
Keyword(s):  
Optical Properties ◽  
Optical Property ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Natural Waters ◽  
Harmful Algal Bloom ◽  
Light Level ◽  
Ecosystem Dynamics ◽  
Wide Range ◽  
Biogeochemical Parameters

Over the past ten years, efforts to characterize the optical properties of Earth's natural waters have largely merged with the need to better understand underlying biological and chemical processes. Fundamental optical properties such as light level, absorption, scattering and fluorescence are now being utilized with increasing effectiveness to specify particulate and dissolved in-water components in a wide range of applications, including detection of harmful algal blooms, studying ecosystem dynamics, monitoring the effect of industrial and agricultural pollutants, and understanding carbon sequestration processes in the oceans. A diverse offering of commercial optical sensing products capable for research, routine measurements, and in some cases, operational monitoring are now available. These technologies have provided the scientific community with a set of tools for developing, testing, and placing into practice analytical and semi-analytical methods to infer specific biogeochemical parameters and processes. As a result, new, more specialized sensors are now emerging. New sensors couple basic optical property measurements with processing algorithms to provide specific indicators for Harmful Algal Bloom (HAB) identification, carbon products, nutrients, and particle size distributions. The basic measurement methods are described and examples of devices incorporating them are provided to illustrate their use in modern oceanographic research and monitoring.

scholarly journals The Southeast Alaska Tribal Ocean Research (SEATOR) Partnership: Addressing Data Gaps in Harmful Algal Bloom Monitoring and Shellfish Safety in Southeast Alaska

Toxins ◽  
2020 ◽  
Vol 12 (6) ◽  
pp. 407 ◽  
Author(s):  
John R. Harley ◽  
Kari Lanphier ◽  
Esther G. Kennedy ◽  
Tod A. Leighfield ◽  
Allison Bidlack ◽  
...  
Keyword(s):  
Surface Temperature ◽  
Sea Surface Temperature ◽  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Harmful Algal Bloom ◽  
Sea Surface ◽  
Southeast Alaska ◽  
Paralytic Shellfish Toxins ◽  
Tribal Governments ◽  
Salinity Data

Many communities in Southeast Alaska harvest shellfish such as mussels and clams as an important part of a subsistence or traditional diet. Harmful algal blooms (HABs) of phytoplankton such as Alexandrium spp. produce toxins that can accumulate in shellfish tissues to concentrations that can pose a hazard for human health. Since 2013, several tribal governments and communities have pooled resources to form the Southeast Alaska Tribal Ocean Research (SEATOR) network, with the goal of minimizing risks to seafood harvest and enhancing food security. SEATOR monitors toxin concentrations in shellfish and collects and consolidates data on environmental variables that may be important predictors of toxin levels such as sea surface temperature and salinity. Data from SEATOR are publicly available and are encouraged to be used for the development and testing of predictive algorithms that could improve seafood risk assessment in Southeast Alaska. To date, more than 1700 shellfish samples have been analyzed for paralytic shellfish toxins (PSTs) in more than 20 locations, with potentially lethal concentrations observed in blue mussels (Mytilus trossulus) and butter clams (Saxidomus gigantea). Concentrations of PSTs exhibit seasonality in some species, and observations of Alexandrium are correlated to sea surface temperature and salinity; however, concentrations above the threshold of concern have been found in all months, and substantial variation in concentrations of PSTs remain unexplained.

scholarly journals Unsteady Multi-Element Time Series Analysis and Prediction Based on Spatial-Temporal Attention and Error Forecast Fusion

2020 ◽  
Vol 12 (2) ◽  
pp. 34
Author(s):  
Xiaofan Wang ◽  
Lingyu Xu
Keyword(s):  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Short Term Memory ◽  
Sudden Change ◽  
Back Propagation ◽  
Red Tides ◽  
Model Errors ◽  
Chl A ◽  
Error Forecast ◽  
Concentration Prediction

Harmful algal blooms (HABs) often cause great harm to fishery production and the safety of human lives. Therefore, the detection and prediction of HABs has become an important issue. Machine learning has been increasingly used to predict HABs at home and abroad. However, few of them can capture the sudden change of Chl-a in advance and handle the long-term dependencies appropriately. In order to address these challenges, the Long Short-Term Memory (LSTM) based spatial-temporal attentions model for Chlorophyll-a (Chl-a) concentration prediction is proposed, a model which can capture the correlation between various factors and Chl-a adaptively and catch dynamic temporal information from previous time intervals for making predictions. The model can also capture the stage of Chl-a when values soar as red tide breaks out in advance. Due to the instability of the current Chl-a concentration prediction model, the model is also applied to make a prediction about the forecast reliability, to have a basic understanding of the range and fluctuation of model errors and provide a reference to describe the range of marine disasters. The data used in the experiment is retrieved from Fujian Marine Forecasts Station from 2009 to 2011 and is combined into 8-dimension data. Results show that the proposed approach performs better than other Chl-a prediction algorithms (such as Attention LSTM and Seq2seq and back propagation). The result of error prediction also reveals that the error forecast method possesses established advantages for red tides prevention and control.

scholarly journals Omics Analysis for Dinoflagellates Biology Research

2019 ◽  
Vol 7 (9) ◽  
pp. 288 ◽  
Author(s):  
Bi ◽  
Wang ◽  
Zhang
Keyword(s):  
Harmful Algal Blooms ◽  
Algal Blooms ◽  
Liquid Crystalline ◽  
Molecular Mechanisms ◽  
Harmful Algal Bloom ◽  
Biological Properties ◽  
Shellfish Poisoning ◽  
Omics Technologies ◽  
Metabolic Characteristics ◽  
Essential Components

Dinoflagellates are important primary producers for marine ecosystems and are also responsible for certain essential components in human foods. However, they are also notorious for their ability to form harmful algal blooms, and cause shellfish poisoning. Although much work has been devoted to dinoflagellates in recent decades, our understanding of them at a molecular level is still limited owing to some of their challenging biological properties, such as large genome size, permanently condensed liquid-crystalline chromosomes, and the 10-fold lower ratio of protein to DNA than other eukaryotic species. In recent years, omics technologies, such as genomics, transcriptomics, proteomics, and metabolomics, have been applied to the study of marine dinoflagellates and have uncovered many new physiological and metabolic characteristics of dinoflagellates. In this article, we review recent application of omics technologies in revealing some of the unusual features of dinoflagellate genomes and molecular mechanisms relevant to their biology, including the mechanism of harmful algal bloom formations, toxin biosynthesis, symbiosis, lipid biosynthesis, as well as species identification and evolution. We also discuss the challenges and provide prospective further study directions and applications of dinoflagellates.

Sign in / Sign up

Export Citation Format

Share Document