El Niño-Southern Oscillation forecasting using complex networks analysis of LSTM neural networks

Clifford Broni-Bedaiko; Ferdinand Apietu Katsriku; Tatsuo Unemi; Masayasu Atsumi; Jamal Deen Abdulai; Norihiko Shinomiya; Ebenezer Owusu

doi:10.1007/s10015-019-00540-2

El Niño-Southern Oscillation forecasting using complex networks analysis of LSTM neural networks

Clifford Broni-Bedaiko, Ferdinand Apietu Katsriku, Tatsuo Unemi, Masayasu Atsumi, Jamal Deen Abdulai, Norihiko Shinomiya, Ebenezer Owusu

Research output: Contribution to journal › Article › peer-review

36 Citations (Scopus)

Abstract

Arguably, El Niño-Southern Oscillation (ENSO) is the most influential climatological phenomenon that has been intensively researched during the past years. Currently, the scientific community knows much about the underlying processes of ENSO phenomenon, however, its predictability for longer horizons, which is very important for human society and the natural environment is still a challenge in the scientific community. Here we show an approach based on using various complex networks metrics extracted from climate networks with long short-term memory neural network to forecast ENSO phenomenon. The results suggest that the 12-network metrics extracted as predictors have predictive power and the potential for forecasting ENSO phenomenon longer multiple steps ahead.

Original language	English
Pages (from-to)	445-451
Number of pages	7
Journal	Artificial Life and Robotics
Volume	24
Issue number	4
DOIs	https://doi.org/10.1007/s10015-019-00540-2
Publication status	Published - 1 Dec 2019

Keywords

Complex networks
ENSO forecasting
LSTM neural networks
Time series forecasting

Access to Document

10.1007/s10015-019-00540-2

Cite this

@article{f9bbdc810ae04d599a22e6f86db8a033,

title = "El Ni{\~n}o-Southern Oscillation forecasting using complex networks analysis of LSTM neural networks",

abstract = "Arguably, El Ni{\~n}o-Southern Oscillation (ENSO) is the most influential climatological phenomenon that has been intensively researched during the past years. Currently, the scientific community knows much about the underlying processes of ENSO phenomenon, however, its predictability for longer horizons, which is very important for human society and the natural environment is still a challenge in the scientific community. Here we show an approach based on using various complex networks metrics extracted from climate networks with long short-term memory neural network to forecast ENSO phenomenon. The results suggest that the 12-network metrics extracted as predictors have predictive power and the potential for forecasting ENSO phenomenon longer multiple steps ahead.",

keywords = "Complex networks, ENSO forecasting, LSTM neural networks, Time series forecasting",

author = "Clifford Broni-Bedaiko and Katsriku, {Ferdinand Apietu} and Tatsuo Unemi and Masayasu Atsumi and Abdulai, {Jamal Deen} and Norihiko Shinomiya and Ebenezer Owusu",

note = "Publisher Copyright: {\textcopyright} 2019, International Society of Artificial Life and Robotics (ISAROB).",

year = "2019",

month = dec,

day = "1",

doi = "10.1007/s10015-019-00540-2",

language = "English",

volume = "24",

pages = "445--451",

journal = "Artificial Life and Robotics",

issn = "1433-5298",

publisher = "Springer Japan",

number = "4",

}

TY - JOUR

T1 - El Niño-Southern Oscillation forecasting using complex networks analysis of LSTM neural networks

AU - Broni-Bedaiko, Clifford

AU - Katsriku, Ferdinand Apietu

AU - Unemi, Tatsuo

AU - Atsumi, Masayasu

AU - Abdulai, Jamal Deen

AU - Shinomiya, Norihiko

AU - Owusu, Ebenezer

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Arguably, El Niño-Southern Oscillation (ENSO) is the most influential climatological phenomenon that has been intensively researched during the past years. Currently, the scientific community knows much about the underlying processes of ENSO phenomenon, however, its predictability for longer horizons, which is very important for human society and the natural environment is still a challenge in the scientific community. Here we show an approach based on using various complex networks metrics extracted from climate networks with long short-term memory neural network to forecast ENSO phenomenon. The results suggest that the 12-network metrics extracted as predictors have predictive power and the potential for forecasting ENSO phenomenon longer multiple steps ahead.

AB - Arguably, El Niño-Southern Oscillation (ENSO) is the most influential climatological phenomenon that has been intensively researched during the past years. Currently, the scientific community knows much about the underlying processes of ENSO phenomenon, however, its predictability for longer horizons, which is very important for human society and the natural environment is still a challenge in the scientific community. Here we show an approach based on using various complex networks metrics extracted from climate networks with long short-term memory neural network to forecast ENSO phenomenon. The results suggest that the 12-network metrics extracted as predictors have predictive power and the potential for forecasting ENSO phenomenon longer multiple steps ahead.

KW - Complex networks

KW - ENSO forecasting

KW - LSTM neural networks

KW - Time series forecasting

UR - http://www.scopus.com/inward/record.url?scp=85067239297&partnerID=8YFLogxK

U2 - 10.1007/s10015-019-00540-2

DO - 10.1007/s10015-019-00540-2

M3 - Article

AN - SCOPUS:85067239297

SN - 1433-5298

VL - 24

SP - 445

EP - 451

JO - Artificial Life and Robotics

JF - Artificial Life and Robotics

IS - 4

ER -

El Niño-Southern Oscillation forecasting using complex networks analysis of LSTM neural networks

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this