1. Title, Journal and Authors
Title : Development of early-warning protocol for predicting chlorophyll-a concentration using machine learning models in freshwater and estuarine reservoirs, Korea
Journal : Science of the Total Environment 502 (2015) 31–41
Authors : Yongeun Parka, Kyung Hwa Chob, Jihwan Parka, Sung Min Chac, Joon Ha Kima⁎a
a School of Environmental Science and Engineering, Gwangju Institute of Science and Technology (GIST), 261 Cheomdan-gwagiro, Buk-gu, Gwangju 500-712, Republic of Korea
b School of Urban and Environmental Engineering, Ulsan National Institute of Science and Technology (UNIST), 50 UNIST-gil, Eonyang-eup, Ulju-gun, Ulsan 689-798, Republic of Korea
c Jeollanam-do Environmental Industries Promotion Institute, 650-94 Songgye-ro, Seongjeon-myeon, Gangjin-gun, Jeollanam-do, 527-811, Republic of Korea
The purpose of this study was to research for the early-warning prediction of chlorophyll-a(Chl-a) concentration utilizing tow stochastic models in a reservoir system. Artificial neural network(ANN) and support vector machine(SVM) models were used to predict the Chl-a concentration with five from water quality data and two from meteorological data over a 7-year period. These models were evaluated in terms of a statistical evaluation and sensitivity analysis.
ANN consists of three layers having input nodes, and, hidden nodes, and one output node. The training functions used included the logistic sigmoid, tangent sigmoid, and linear function. Meanwhile, support vector regression(SVR) was applied to forecast the time-series data in this study.
In both site, SVM presented higher prediction accuracies in the validation step than ANN and showed good performance for different sampling intervals. The most sensitive input variable was PO4-P in two models.
Jeongwoo Moon (Intern student)
Environmental Systems Engineering Lab.
School of Environmental Science & Engineering
Gwangju Institute of Science and Technology
1 Oryong-dong Buk-gu Gwangju, 500-712, Korea
Phone : +82-10-9384-8271
Office : +82-62-715-2475
E-mail : firstname.lastname@example.org