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

被引:76
作者
Cruz, Rafaela C. [1 ]
Reis Costa, Pedro [2 ,3 ]
Vinga, Susana [4 ]
Krippahl, Ludwig [1 ,5 ]
Lopes, Marta B. [1 ,5 ,6 ]
机构
[1] Univ NOVA Lisboa FCT NOVA, Fac Ciencias & Tecnol, P-2829516 Caparica, Portugal
[2] IPMA Inst Portugues Mar & Atmosfera, P-1495165 Lisbon, Portugal
[3] Univ Algarve, CCMAR Ctr Ciencias Mar, P-8005139 Faro, Portugal
[4] Univ Lisbon, Inst Super Tecn, INESC ID, P-1000029 Lisbon, Portugal
[5] FCT NOVA, NOVA Lab Comp Sci & Informat NOVA LINCS, P-2829516 Caparica, Portugal
[6] FCT NOVA, Ctr Math & Applicat CMA, P-2829516 Caparica, Portugal
关键词
marine biotoxins; shellfish production; harmful algal blooms; toxic phytoplankton; multivariate time series; time-series forecasting; artificial neural networks; machine learning; NEURAL-NETWORK APPROACH; MODEL; PREDICTION; RIVER; ALGORITHM; VARIABLES; MEMORY; SPP;
D O I
10.3390/jmse9030283
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
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.
引用
收藏
页数:17
相关论文
共 88 条
[1]   A high resolution hydrodynamic model system suitable for novel harmful algal bloom modelling in areas of complex coastline and topography [J].
Aleynik, Dmitry ;
Dale, Andrew C. ;
Porter, Marie ;
Davidson, Keith .
HARMFUL ALGAE, 2016, 53 :102-117
[2]   Microbiological composition of native and exotic clams from Tagus estuary: Effect of season and environmental parameters [J].
Anacleto, Patricia ;
Pedro, Sonia ;
Nunes, Maria Leonor ;
Rosa, Rui ;
Marques, Antonio .
MARINE POLLUTION BULLETIN, 2013, 74 (01) :116-124
[3]  
[Anonymous], 2009, CAUSALITY, DOI [DOI 10.1017/CBO9780511803161, 10.1017/CBO9780511803161]
[4]  
[Anonymous], 2017, P 26 INT JOINT C ART, DOI DOI 10.24963/IJCAI.2017/366
[5]  
[Anonymous], 2014, MULTIVARIATE TIME SE
[6]  
[Anonymous], 2002, J Hydroinformatics, DOI DOI 10.2166/HYDRO.2002.0013
[7]  
Babovic V., 2004, P 6 INT C HYDR WORLD, VVolume 2
[8]   Forecasting Groundwater Table in a Flood Prone Coastal City with Long Short-term Memory and Recurrent Neural Networks [J].
Bowes, Benjamin D. ;
Sadler, Jeffrey M. ;
Morsy, Mohamed M. ;
Behl, Madhur ;
Goodall, Jonathan L. .
WATER, 2019, 11 (05)
[9]  
Box G. E. P., 2016, Time series analysis forecasting and control, V5th
[10]  
Boyd-Graber J.L., 2018, 180902847 ARXIV