Integrating Support Vector Regression with Particle Swarm
Optimization for numerical modeling for algal blooms of
freshwater
q
Inchio Lou
a
, Zhengchao Xie
a,
⇑
, Wai Kin Ung
b
, Kai Meng Mok
a
a
Faculty of Science and Technology, University of Macau, Macau
b
Laboratory & Research Center, Macao Water Co. Ltd., Macau
article info
Article history:
Received 22 July 2014
Received in revised form 29 March 2015
Accepted 13 April 2015
Available online 11 May 2015
Keywords:
Algal bloom
Phytoplankton abundance
Support Vector Regression
Particle Swarm Optimization
Prediction and forecast models
abstract
Algae-releasing cyanotoxins are cancer-causing and very harmful to the human being.
Therefore, it is of great significance to model how the algae population dynamically
changes in freshwater reservoirs. But the practical modeling is very difficult because water
variables and their internal mechanism are very complicated and non-linear. So, in order to
alleviate the algal bloom problems in Macau Main Storage Reservoir (MSR), this work pro-
poses and develops a hybrid intelligent model combining Support Vector Regression (SVR)
and Particle Swarm Optimization (PSO) to yield optimal control of parameters that predict
and forecast the phytoplan kton dynamics. In this process, collected data for current
month’s variables and previous months’ variables are used for model predict and forecast,
respectively. In the correlation analysis of 23 water variables that monitored monthly, 15
variables such as alkalinity, Bicarbonate (HCO
3
), dissolved oxygen (DO), total nitrogen
(TN), turbidity, conductivity, nitrate, suspended solid (SS) and total organic carbon (TOC)
are selected, and data from 2001 to 2008 for each of these selected variables are used
for training, while data from 2009 to 2011 which are the most recent three years are used
for testing. It can be seen from the numerical results that the prediction and forecast pow-
ers are respectively estimated at approximately 0.767 and 0.876, and naturally it can be
concluded that the newly proposed PSO–SVR is working well and can be adopted for fur-
ther studies.
Ó 2015 Elsevier Inc. All rights reserved.
1. Introduction
As a water pollution issue, freshwater algal bloom usually exists in eutrophic lakes or reservoirs due to excessive nutri-
ents. Most species of algae (also called phytoplankton) can generate different cyanotoxins including microcystins, cylindros-
permopsis and nodularin, which in turn will affect the water treatment processes and lead to negative impact on the health of
public [1]. So, it is very important to understand the population dynamics of algae in the raw water storage units.
http://dx.doi.org/10.1016/j.apm.2015.04.001
0307-904X/Ó 2015 Elsevier Inc. All rights reserved.
q
This article belongs to the Special Issue: ASPEC 2013 – 2013 International Applied Science and Precision Engineering Conference, October 2013 NanTou,
Taiwan.
⇑
Corresponding author.
E-mail address: zxie@umac.mo (Z. Xie).
Applied Mathematical Modelling 39 (2015) 5907–5916
Contents lists available at ScienceDirect
Applied Mathematical Modelling
journal homepage: www.elsevier.com/locate/apm