Harmful algal blooms prediction with machine learning models in Tolo Harbour

Machine learning (ML) techniques such as artificial neural network (ANN) and support vector machine (SVM) have been increasingly used to predict harmful algal blooms (HABs). In this paper, we use the biweekly data in Tolo Harbour, Hong Kong, and choose several machine learning methods to develop prediction models of algal blooms. Three different kinds of models are designed based on back-propagation (BP) neural network, generalized regression neural network (GRNN) and support vector machine (SVM) respectively. The experimental results show that the improved BP algorithm and SVM work better than GRNN methods, and the models based on SVM present the best performance in terms of goodness-of-fit measures, but need to be further improved in the running time. We develop these prediction models with different lead time (7-day and 14-day) to study further. The results indicate that the use of biweekly data can simulate the general trend of algal biomass reasonably, but it is not ideally suited for exact predictions. The use of higher frequency data may improve the accuracy of the predictions.

[1]  Wai Kin Ung,et al.  Freshwater Algal Bloom Prediction by Support Vector Machine in Macau Storage Reservoirs , 2012 .

[2]  Zhen-Dong Cui,et al.  An approach to forecast red tide using generalized regression neural network , 2012, 2012 8th International Conference on Natural Computation.

[3]  Nitin Muttil,et al.  Prediction of algal blooms using genetic programming. , 2010, Marine pollution bulletin.

[4]  K. Chau,et al.  Neural network and genetic programming for modelling coastal algal blooms , 2006 .

[5]  Hak-Keung Lam,et al.  Tuning of the structure and parameters of a neural network using an improved genetic algorithm , 2003, IEEE Trans. Neural Networks.

[6]  Li Jin,et al.  Review on Prediction, Prevention and Mitigation of Harmful Algal Blooms , 2013 .

[7]  Surya S. Durbha,et al.  A Machine Learning Based Spatio-Temporal Data Mining Approach for Detection of Harmful Algal Blooms in the Gulf of Mexico , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  Yan Huang,et al.  Neural network modelling of coastal algal blooms , 2003 .

[9]  Xin Qian,et al.  Modeling Chlorophyll-A in Taihu Lake with Machine Learning Models , 2009, 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

[10]  Ravi Sankar,et al.  Time Series Prediction Using Support Vector Machines: A Survey , 2009, IEEE Computational Intelligence Magazine.

[11]  Sun Park,et al.  Red tides prediction system using fuzzy reasoning and the ensemble method , 2013, Applied Intelligence.

[12]  T. Maekawa,et al.  Use of artificial neural network in the prediction of algal blooms. , 2001, Water research.

[13]  Zhang Chenghui.  Prediction Model for Red Tide at Yantai Sishili Bay Based on LMBP Algorithm , 2009 .

[14]  Jiping Xu,et al.  Research on Water Bloom Prediction Based on Least Squares Support Vector Machine , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.

[15]  LeeSeong Ro,et al.  Red tides prediction system using fuzzy reasoning and the ensemble method , 2014 .

[16]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.