Bat algorithm and neural network for monthly streamflow prediction

Nuratiah Zaini, Marlinda Abdul Malek, Marina Yusoff, Siti Fatimah Che Osmi, Nurul Hani Mardi, Shuhairy Norhisham @ Masam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Streamflow prediction has a significance influence on improving water supply management and flood prevention. The applications of artificial intelligence (AI) have been proved to have better performance as compared to conventional statistical method in streamflow prediction. Therefore, this study proposed on the development of streamflow prediction model AI techniques namely Bat algorithm (BA) and backpropagation neural network (BPNN). BA is an optimization technique, which is to optimize BPNN in deciding optimum parameters and then improve the prediction accuracy. The study area chosen is Kuantan river and Kenau river, located in Kuantan, Malaysia. Two prediction models are proposed in this study which are BPNN and hybrid Bat-BPNN. Monthly historical rainfall data, antecedent river flow data and meteorology parameters data for two different rivers were used as the input to the proposed models. The performance of the proposed prediction models for Kuantan river and Kenau river are then being compared and evaluated in term of RMSE and R2. It is found that hybrid model, Bat-BPNN yields lower RMSE and provides higher R2 as compared to BPNN model at both Kuantan river and Kenau river. Therefore, it can be concluded that, proposed hybrid model yields better performances as compared to BPNN model for monthly streamflow prediction.

Original languageEnglish
Title of host publicationGreen Design and Manufacture
Subtitle of host publicationAdvanced and Emerging Applications: Proceeding of the 4th International Conference on Green Design and Manufacture 2018
EditorsMuhammad Faheem Bin Mohd Tahir, Romisuhani Ahmad, Mohd Nasir Bin Mat Saad, Mohd Fathullah Bin Ghazli, Mohd Mustafa Al-Bakri Abdullah, Shayfull Zamree Bin Abd. Rahim, Liyana Binti Jamaludin
PublisherAmerican Institute of Physics Inc.
ISBN (Electronic)9780735417526
DOIs
Publication statusPublished - 09 Nov 2018
Event4th International Conference on Green Design and Manufacture 2018, IConGDM 2018 - Ho Chi Minh, Viet Nam
Duration: 29 Apr 201830 Apr 2018

Publication series

NameAIP Conference Proceedings
Volume2030
ISSN (Print)0094-243X
ISSN (Electronic)1551-7616

Other

Other4th International Conference on Green Design and Manufacture 2018, IConGDM 2018
CountryViet Nam
CityHo Chi Minh
Period29/04/1830/04/18

Fingerprint

bats
rivers
predictions
artificial intelligence
Malaysia
meteorology
optimization

All Science Journal Classification (ASJC) codes

  • Physics and Astronomy(all)

Cite this

Zaini, N., Abdul Malek, M., Yusoff, M., Osmi, S. F. C., Mardi, N. H., & Norhisham @ Masam, S. (2018). Bat algorithm and neural network for monthly streamflow prediction. In M. F. B. M. Tahir, R. Ahmad, M. N. B. M. Saad, M. F. B. Ghazli, M. M. A-B. Abdullah, S. Z. B. A. Rahim, & L. B. Jamaludin (Eds.), Green Design and Manufacture: Advanced and Emerging Applications: Proceeding of the 4th International Conference on Green Design and Manufacture 2018 [020260] (AIP Conference Proceedings; Vol. 2030). American Institute of Physics Inc.. https://doi.org/10.1063/1.5066901
Zaini, Nuratiah ; Abdul Malek, Marlinda ; Yusoff, Marina ; Osmi, Siti Fatimah Che ; Mardi, Nurul Hani ; Norhisham @ Masam, Shuhairy. / Bat algorithm and neural network for monthly streamflow prediction. Green Design and Manufacture: Advanced and Emerging Applications: Proceeding of the 4th International Conference on Green Design and Manufacture 2018. editor / Muhammad Faheem Bin Mohd Tahir ; Romisuhani Ahmad ; Mohd Nasir Bin Mat Saad ; Mohd Fathullah Bin Ghazli ; Mohd Mustafa Al-Bakri Abdullah ; Shayfull Zamree Bin Abd. Rahim ; Liyana Binti Jamaludin. American Institute of Physics Inc., 2018. (AIP Conference Proceedings).
@inproceedings{0654f5df6a6544159cf45c31c2005dec,
title = "Bat algorithm and neural network for monthly streamflow prediction",
abstract = "Streamflow prediction has a significance influence on improving water supply management and flood prevention. The applications of artificial intelligence (AI) have been proved to have better performance as compared to conventional statistical method in streamflow prediction. Therefore, this study proposed on the development of streamflow prediction model AI techniques namely Bat algorithm (BA) and backpropagation neural network (BPNN). BA is an optimization technique, which is to optimize BPNN in deciding optimum parameters and then improve the prediction accuracy. The study area chosen is Kuantan river and Kenau river, located in Kuantan, Malaysia. Two prediction models are proposed in this study which are BPNN and hybrid Bat-BPNN. Monthly historical rainfall data, antecedent river flow data and meteorology parameters data for two different rivers were used as the input to the proposed models. The performance of the proposed prediction models for Kuantan river and Kenau river are then being compared and evaluated in term of RMSE and R2. It is found that hybrid model, Bat-BPNN yields lower RMSE and provides higher R2 as compared to BPNN model at both Kuantan river and Kenau river. Therefore, it can be concluded that, proposed hybrid model yields better performances as compared to BPNN model for monthly streamflow prediction.",
author = "Nuratiah Zaini and {Abdul Malek}, Marlinda and Marina Yusoff and Osmi, {Siti Fatimah Che} and Mardi, {Nurul Hani} and {Norhisham @ Masam}, Shuhairy",
year = "2018",
month = "11",
day = "9",
doi = "10.1063/1.5066901",
language = "English",
series = "AIP Conference Proceedings",
publisher = "American Institute of Physics Inc.",
editor = "Tahir, {Muhammad Faheem Bin Mohd} and Romisuhani Ahmad and Saad, {Mohd Nasir Bin Mat} and Ghazli, {Mohd Fathullah Bin} and Abdullah, {Mohd Mustafa Al-Bakri} and Rahim, {Shayfull Zamree Bin Abd.} and Jamaludin, {Liyana Binti}",
booktitle = "Green Design and Manufacture",

}

Zaini, N, Abdul Malek, M, Yusoff, M, Osmi, SFC, Mardi, NH & Norhisham @ Masam, S 2018, Bat algorithm and neural network for monthly streamflow prediction. in MFBM Tahir, R Ahmad, MNBM Saad, MFB Ghazli, MMA-B Abdullah, SZBA Rahim & LB Jamaludin (eds), Green Design and Manufacture: Advanced and Emerging Applications: Proceeding of the 4th International Conference on Green Design and Manufacture 2018., 020260, AIP Conference Proceedings, vol. 2030, American Institute of Physics Inc., 4th International Conference on Green Design and Manufacture 2018, IConGDM 2018, Ho Chi Minh, Viet Nam, 29/04/18. https://doi.org/10.1063/1.5066901

Bat algorithm and neural network for monthly streamflow prediction. / Zaini, Nuratiah; Abdul Malek, Marlinda; Yusoff, Marina; Osmi, Siti Fatimah Che; Mardi, Nurul Hani; Norhisham @ Masam, Shuhairy.

Green Design and Manufacture: Advanced and Emerging Applications: Proceeding of the 4th International Conference on Green Design and Manufacture 2018. ed. / Muhammad Faheem Bin Mohd Tahir; Romisuhani Ahmad; Mohd Nasir Bin Mat Saad; Mohd Fathullah Bin Ghazli; Mohd Mustafa Al-Bakri Abdullah; Shayfull Zamree Bin Abd. Rahim; Liyana Binti Jamaludin. American Institute of Physics Inc., 2018. 020260 (AIP Conference Proceedings; Vol. 2030).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Bat algorithm and neural network for monthly streamflow prediction

AU - Zaini, Nuratiah

AU - Abdul Malek, Marlinda

AU - Yusoff, Marina

AU - Osmi, Siti Fatimah Che

AU - Mardi, Nurul Hani

AU - Norhisham @ Masam, Shuhairy

PY - 2018/11/9

Y1 - 2018/11/9

N2 - Streamflow prediction has a significance influence on improving water supply management and flood prevention. The applications of artificial intelligence (AI) have been proved to have better performance as compared to conventional statistical method in streamflow prediction. Therefore, this study proposed on the development of streamflow prediction model AI techniques namely Bat algorithm (BA) and backpropagation neural network (BPNN). BA is an optimization technique, which is to optimize BPNN in deciding optimum parameters and then improve the prediction accuracy. The study area chosen is Kuantan river and Kenau river, located in Kuantan, Malaysia. Two prediction models are proposed in this study which are BPNN and hybrid Bat-BPNN. Monthly historical rainfall data, antecedent river flow data and meteorology parameters data for two different rivers were used as the input to the proposed models. The performance of the proposed prediction models for Kuantan river and Kenau river are then being compared and evaluated in term of RMSE and R2. It is found that hybrid model, Bat-BPNN yields lower RMSE and provides higher R2 as compared to BPNN model at both Kuantan river and Kenau river. Therefore, it can be concluded that, proposed hybrid model yields better performances as compared to BPNN model for monthly streamflow prediction.

AB - Streamflow prediction has a significance influence on improving water supply management and flood prevention. The applications of artificial intelligence (AI) have been proved to have better performance as compared to conventional statistical method in streamflow prediction. Therefore, this study proposed on the development of streamflow prediction model AI techniques namely Bat algorithm (BA) and backpropagation neural network (BPNN). BA is an optimization technique, which is to optimize BPNN in deciding optimum parameters and then improve the prediction accuracy. The study area chosen is Kuantan river and Kenau river, located in Kuantan, Malaysia. Two prediction models are proposed in this study which are BPNN and hybrid Bat-BPNN. Monthly historical rainfall data, antecedent river flow data and meteorology parameters data for two different rivers were used as the input to the proposed models. The performance of the proposed prediction models for Kuantan river and Kenau river are then being compared and evaluated in term of RMSE and R2. It is found that hybrid model, Bat-BPNN yields lower RMSE and provides higher R2 as compared to BPNN model at both Kuantan river and Kenau river. Therefore, it can be concluded that, proposed hybrid model yields better performances as compared to BPNN model for monthly streamflow prediction.

UR - http://www.scopus.com/inward/record.url?scp=85057261770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057261770&partnerID=8YFLogxK

U2 - 10.1063/1.5066901

DO - 10.1063/1.5066901

M3 - Conference contribution

AN - SCOPUS:85057261770

T3 - AIP Conference Proceedings

BT - Green Design and Manufacture

A2 - Tahir, Muhammad Faheem Bin Mohd

A2 - Ahmad, Romisuhani

A2 - Saad, Mohd Nasir Bin Mat

A2 - Ghazli, Mohd Fathullah Bin

A2 - Abdullah, Mohd Mustafa Al-Bakri

A2 - Rahim, Shayfull Zamree Bin Abd.

A2 - Jamaludin, Liyana Binti

PB - American Institute of Physics Inc.

ER -

Zaini N, Abdul Malek M, Yusoff M, Osmi SFC, Mardi NH, Norhisham @ Masam S. Bat algorithm and neural network for monthly streamflow prediction. In Tahir MFBM, Ahmad R, Saad MNBM, Ghazli MFB, Abdullah MMA-B, Rahim SZBA, Jamaludin LB, editors, Green Design and Manufacture: Advanced and Emerging Applications: Proceeding of the 4th International Conference on Green Design and Manufacture 2018. American Institute of Physics Inc. 2018. 020260. (AIP Conference Proceedings). https://doi.org/10.1063/1.5066901