Real-time prediction of chlorophyll-a time series in a eutrophic agricultural reservoir in a coastal zone using recurrent neural networks with periodic chaos neurons

Harada Masayoshi, Takafumi Tominaga, Kazuaki Hiramatsu, Atsushi Marui

研究成果: ジャーナルへの寄稿記事

抄録

To assess the water environmental dynamics related to a phytoplankton, the water quality dynamics in a eutrophic reservoir in a flat low-lying agricultural area were analyzed from the viewpoint of short-time prediction of time series data using artificial intelligence. A recurrent neural network model with periodic chaos neurons was used for the real-time prediction of chlorophyll-a time series on the basis of on-site continuous observation data. These data consisted of the chlorophyll-a from four algae classes, Chlorophyceae, cyanobacteria, diatom/dinoflagellates, and cryptophytes, measured by a submerged fluorometer. The results suggest that study of a neural network could be performed sufficiently for teaching data of which a value of the fractal dimension calculated by the Higuchi method was smaller. In addition, it is possible to conduct a short-time prediction of chlorophyll-a time series such that an upper limit of lead time could be beyond 12h when there is an analogous time-frequency characteristic between the teaching and the predicting data. In conclusion, a recurrent chaotic neural network could be an effective analysis tool for short-time prediction of water quality on the basis of continuous observations, and the potential for prediction can be determined quantitatively using Higuchi's fractal dimension and time-frequency maps.

元の言語英語
ページ(範囲)36-43
ページ数8
ジャーナルIrrigation and Drainage
62
発行部数S1
DOI
出版物ステータス出版済み - 10 1 2013

Fingerprint

chaotic dynamics
neural networks
coastal zone
time series analysis
chlorophyll a
neurons
time series
chlorophyll
prediction
fractal dimensions
algae
water quality
teaching
Chlorophyceae
Bacillariophyceae
artificial intelligence
Cyanobacteria
dinoflagellate
phytoplankton
cyanobacterium

All Science Journal Classification (ASJC) codes

  • Agronomy and Crop Science
  • Soil Science

これを引用

@article{15b3be1ad61c4fe5b1a7a1e2a486ec19,
title = "Real-time prediction of chlorophyll-a time series in a eutrophic agricultural reservoir in a coastal zone using recurrent neural networks with periodic chaos neurons",
abstract = "To assess the water environmental dynamics related to a phytoplankton, the water quality dynamics in a eutrophic reservoir in a flat low-lying agricultural area were analyzed from the viewpoint of short-time prediction of time series data using artificial intelligence. A recurrent neural network model with periodic chaos neurons was used for the real-time prediction of chlorophyll-a time series on the basis of on-site continuous observation data. These data consisted of the chlorophyll-a from four algae classes, Chlorophyceae, cyanobacteria, diatom/dinoflagellates, and cryptophytes, measured by a submerged fluorometer. The results suggest that study of a neural network could be performed sufficiently for teaching data of which a value of the fractal dimension calculated by the Higuchi method was smaller. In addition, it is possible to conduct a short-time prediction of chlorophyll-a time series such that an upper limit of lead time could be beyond 12h when there is an analogous time-frequency characteristic between the teaching and the predicting data. In conclusion, a recurrent chaotic neural network could be an effective analysis tool for short-time prediction of water quality on the basis of continuous observations, and the potential for prediction can be determined quantitatively using Higuchi's fractal dimension and time-frequency maps.",
author = "Harada Masayoshi and Takafumi Tominaga and Kazuaki Hiramatsu and Atsushi Marui",
year = "2013",
month = "10",
day = "1",
doi = "10.1002/ird.1757",
language = "English",
volume = "62",
pages = "36--43",
journal = "Irrigation and Drainage",
issn = "1531-0353",
publisher = "John Wiley and Sons Ltd",
number = "S1",

}

TY - JOUR

T1 - Real-time prediction of chlorophyll-a time series in a eutrophic agricultural reservoir in a coastal zone using recurrent neural networks with periodic chaos neurons

AU - Masayoshi, Harada

AU - Tominaga, Takafumi

AU - Hiramatsu, Kazuaki

AU - Marui, Atsushi

PY - 2013/10/1

Y1 - 2013/10/1

N2 - To assess the water environmental dynamics related to a phytoplankton, the water quality dynamics in a eutrophic reservoir in a flat low-lying agricultural area were analyzed from the viewpoint of short-time prediction of time series data using artificial intelligence. A recurrent neural network model with periodic chaos neurons was used for the real-time prediction of chlorophyll-a time series on the basis of on-site continuous observation data. These data consisted of the chlorophyll-a from four algae classes, Chlorophyceae, cyanobacteria, diatom/dinoflagellates, and cryptophytes, measured by a submerged fluorometer. The results suggest that study of a neural network could be performed sufficiently for teaching data of which a value of the fractal dimension calculated by the Higuchi method was smaller. In addition, it is possible to conduct a short-time prediction of chlorophyll-a time series such that an upper limit of lead time could be beyond 12h when there is an analogous time-frequency characteristic between the teaching and the predicting data. In conclusion, a recurrent chaotic neural network could be an effective analysis tool for short-time prediction of water quality on the basis of continuous observations, and the potential for prediction can be determined quantitatively using Higuchi's fractal dimension and time-frequency maps.

AB - To assess the water environmental dynamics related to a phytoplankton, the water quality dynamics in a eutrophic reservoir in a flat low-lying agricultural area were analyzed from the viewpoint of short-time prediction of time series data using artificial intelligence. A recurrent neural network model with periodic chaos neurons was used for the real-time prediction of chlorophyll-a time series on the basis of on-site continuous observation data. These data consisted of the chlorophyll-a from four algae classes, Chlorophyceae, cyanobacteria, diatom/dinoflagellates, and cryptophytes, measured by a submerged fluorometer. The results suggest that study of a neural network could be performed sufficiently for teaching data of which a value of the fractal dimension calculated by the Higuchi method was smaller. In addition, it is possible to conduct a short-time prediction of chlorophyll-a time series such that an upper limit of lead time could be beyond 12h when there is an analogous time-frequency characteristic between the teaching and the predicting data. In conclusion, a recurrent chaotic neural network could be an effective analysis tool for short-time prediction of water quality on the basis of continuous observations, and the potential for prediction can be determined quantitatively using Higuchi's fractal dimension and time-frequency maps.

UR - http://www.scopus.com/inward/record.url?scp=84885141442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885141442&partnerID=8YFLogxK

U2 - 10.1002/ird.1757

DO - 10.1002/ird.1757

M3 - Article

VL - 62

SP - 36

EP - 43

JO - Irrigation and Drainage

JF - Irrigation and Drainage

SN - 1531-0353

IS - S1

ER -