TY - JOUR
T1 - Application of artificial neural network models to the estimation of chlorophyll a concentration in Lake Koyama, Tottori Prefecture, Japan
AU - Sai, Koji
AU - Harada, Masayoshi
AU - Yoshida, Isao
AU - Hiramatsu, Kazuaki
AU - Mori, Makito
PY - 2007/10/1
Y1 - 2007/10/1
N2 - An artificial neural network model with three-layer structure was applied to estimate chlorophyll a concentration in a lake located in Tottori Prefecture, Japan. First, input variables, which resulted in high calibration accuracy, were searched to examine the optimal network structure. The calibration accuracy was highest when input variables were set to TN, TP, DO, water temperature, solar radiation, air temperature, wind velocity, and Wedderburn number. This result means that the model incorporated the relationship between chlorophyll a concentration and the meteorological, hydraulic, and aquatic factors into the network structure. The adaptability of the estimation of chlorophyll a concentration was examined. As a result, chlorophyll a concentration could not be sufficiently estimated. To improve estimation accuracy, the network structure was reconstructed by considering the time history of the variation of the meteorological and water quality data for the previous 24 hours and incorporating such data into the input variables. The result showed that the estimation accuracy was remarkably improved.
AB - An artificial neural network model with three-layer structure was applied to estimate chlorophyll a concentration in a lake located in Tottori Prefecture, Japan. First, input variables, which resulted in high calibration accuracy, were searched to examine the optimal network structure. The calibration accuracy was highest when input variables were set to TN, TP, DO, water temperature, solar radiation, air temperature, wind velocity, and Wedderburn number. This result means that the model incorporated the relationship between chlorophyll a concentration and the meteorological, hydraulic, and aquatic factors into the network structure. The adaptability of the estimation of chlorophyll a concentration was examined. As a result, chlorophyll a concentration could not be sufficiently estimated. To improve estimation accuracy, the network structure was reconstructed by considering the time history of the variation of the meteorological and water quality data for the previous 24 hours and incorporating such data into the input variables. The result showed that the estimation accuracy was remarkably improved.
UR - http://www.scopus.com/inward/record.url?scp=36148960105&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=36148960105&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:36148960105
VL - 52
SP - 405
EP - 409
JO - Journal of the Faculty of Agriculture, Kyushu University
JF - Journal of the Faculty of Agriculture, Kyushu University
SN - 0023-6152
IS - 2
ER -