Investigation on the potential to integrate different artificial intelligence models with metaheuristic algorithms for improving river suspended sediment predictions

Mohammad Ehteram, Samira Ghotbi, Ozgur Kisi, Ali Najah Ahmed, Gasim Hayder, Chow Ming Fai, Mathivanan Krishnan, Haitham Abdulmohsin Afan, Ahmed EL-Shafie

Research output: Contribution to journalArticle

Abstract

Suspended sediment load (SLL) prediction is a significant field in hydrology and hydraulic sciences, as sedimentation processes change the soil quality. Although the adaptive neuro fuzzy system (ANFIS) and multilayer feed-forward neural network (MFNN) have been widely used to simulate hydrological variables, improving the accuracy of the above models is an important issue for hydrologists. In this article, the ANFIS and MFNN models were improved by the bat algorithm (BA) and weed algorithm (WA). Thus, the current paper introduces improved ANFIS and MFNN models: ANFIS-BA, ANFIS-WA, MFNN-BA, and MFNN-WA. The models were validated by applying river discharge, rainfall, and monthly suspended sediment load (SSL) for the Atrek basin in Iran. In addition, seven input groups were used to predict monthly SSL. The best models were identified through root-mean-square error (RMSE), Nash-Sutcliff efficiency (NSE), standard deviation ratio (RSR), percent bias (PBIAS) indices, and uncertainty analysis. For the ANFIS-BA model, RMSE and RSR varied from 1.5 to 2.5 ton/d and from 5% to 25%, respectively. In addition, a variation range of NSE was between very good and good performance (0.75 to 0.85 and 0.85 to 1). The uncertainty analysis showed that the ANFIS-BA had more reliable performance compared to other models. Thus, the ANFIS-BA model has high potential for predicting SSL.

Original languageEnglish
Article number4149
JournalApplied Sciences (Switzerland)
Volume9
Issue number19
DOIs
Publication statusPublished - 01 Oct 2019

Fingerprint

artificial intelligence
Suspended sediments
rivers
bats
Artificial intelligence
sediments
Rivers
Feedforward neural networks
Multilayer neural networks
predictions
Uncertainty analysis
root-mean-square errors
Mean square error
fuzzy systems
hydrology
Iran
Hydrology
Fuzzy systems
Sedimentation
Discharge (fluid mechanics)

All Science Journal Classification (ASJC) codes

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

Ehteram, Mohammad ; Ghotbi, Samira ; Kisi, Ozgur ; Ahmed, Ali Najah ; Hayder, Gasim ; Fai, Chow Ming ; Krishnan, Mathivanan ; Afan, Haitham Abdulmohsin ; EL-Shafie, Ahmed. / Investigation on the potential to integrate different artificial intelligence models with metaheuristic algorithms for improving river suspended sediment predictions. In: Applied Sciences (Switzerland). 2019 ; Vol. 9, No. 19.
@article{a732b588677546249dfac68283b8bda8,
title = "Investigation on the potential to integrate different artificial intelligence models with metaheuristic algorithms for improving river suspended sediment predictions",
abstract = "Suspended sediment load (SLL) prediction is a significant field in hydrology and hydraulic sciences, as sedimentation processes change the soil quality. Although the adaptive neuro fuzzy system (ANFIS) and multilayer feed-forward neural network (MFNN) have been widely used to simulate hydrological variables, improving the accuracy of the above models is an important issue for hydrologists. In this article, the ANFIS and MFNN models were improved by the bat algorithm (BA) and weed algorithm (WA). Thus, the current paper introduces improved ANFIS and MFNN models: ANFIS-BA, ANFIS-WA, MFNN-BA, and MFNN-WA. The models were validated by applying river discharge, rainfall, and monthly suspended sediment load (SSL) for the Atrek basin in Iran. In addition, seven input groups were used to predict monthly SSL. The best models were identified through root-mean-square error (RMSE), Nash-Sutcliff efficiency (NSE), standard deviation ratio (RSR), percent bias (PBIAS) indices, and uncertainty analysis. For the ANFIS-BA model, RMSE and RSR varied from 1.5 to 2.5 ton/d and from 5{\%} to 25{\%}, respectively. In addition, a variation range of NSE was between very good and good performance (0.75 to 0.85 and 0.85 to 1). The uncertainty analysis showed that the ANFIS-BA had more reliable performance compared to other models. Thus, the ANFIS-BA model has high potential for predicting SSL.",
author = "Mohammad Ehteram and Samira Ghotbi and Ozgur Kisi and Ahmed, {Ali Najah} and Gasim Hayder and Fai, {Chow Ming} and Mathivanan Krishnan and Afan, {Haitham Abdulmohsin} and Ahmed EL-Shafie",
year = "2019",
month = "10",
day = "1",
doi = "10.3390/app9194149",
language = "English",
volume = "9",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "19",

}

Investigation on the potential to integrate different artificial intelligence models with metaheuristic algorithms for improving river suspended sediment predictions. / Ehteram, Mohammad; Ghotbi, Samira; Kisi, Ozgur; Ahmed, Ali Najah; Hayder, Gasim; Fai, Chow Ming; Krishnan, Mathivanan; Afan, Haitham Abdulmohsin; EL-Shafie, Ahmed.

In: Applied Sciences (Switzerland), Vol. 9, No. 19, 4149, 01.10.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Investigation on the potential to integrate different artificial intelligence models with metaheuristic algorithms for improving river suspended sediment predictions

AU - Ehteram, Mohammad

AU - Ghotbi, Samira

AU - Kisi, Ozgur

AU - Ahmed, Ali Najah

AU - Hayder, Gasim

AU - Fai, Chow Ming

AU - Krishnan, Mathivanan

AU - Afan, Haitham Abdulmohsin

AU - EL-Shafie, Ahmed

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Suspended sediment load (SLL) prediction is a significant field in hydrology and hydraulic sciences, as sedimentation processes change the soil quality. Although the adaptive neuro fuzzy system (ANFIS) and multilayer feed-forward neural network (MFNN) have been widely used to simulate hydrological variables, improving the accuracy of the above models is an important issue for hydrologists. In this article, the ANFIS and MFNN models were improved by the bat algorithm (BA) and weed algorithm (WA). Thus, the current paper introduces improved ANFIS and MFNN models: ANFIS-BA, ANFIS-WA, MFNN-BA, and MFNN-WA. The models were validated by applying river discharge, rainfall, and monthly suspended sediment load (SSL) for the Atrek basin in Iran. In addition, seven input groups were used to predict monthly SSL. The best models were identified through root-mean-square error (RMSE), Nash-Sutcliff efficiency (NSE), standard deviation ratio (RSR), percent bias (PBIAS) indices, and uncertainty analysis. For the ANFIS-BA model, RMSE and RSR varied from 1.5 to 2.5 ton/d and from 5% to 25%, respectively. In addition, a variation range of NSE was between very good and good performance (0.75 to 0.85 and 0.85 to 1). The uncertainty analysis showed that the ANFIS-BA had more reliable performance compared to other models. Thus, the ANFIS-BA model has high potential for predicting SSL.

AB - Suspended sediment load (SLL) prediction is a significant field in hydrology and hydraulic sciences, as sedimentation processes change the soil quality. Although the adaptive neuro fuzzy system (ANFIS) and multilayer feed-forward neural network (MFNN) have been widely used to simulate hydrological variables, improving the accuracy of the above models is an important issue for hydrologists. In this article, the ANFIS and MFNN models were improved by the bat algorithm (BA) and weed algorithm (WA). Thus, the current paper introduces improved ANFIS and MFNN models: ANFIS-BA, ANFIS-WA, MFNN-BA, and MFNN-WA. The models were validated by applying river discharge, rainfall, and monthly suspended sediment load (SSL) for the Atrek basin in Iran. In addition, seven input groups were used to predict monthly SSL. The best models were identified through root-mean-square error (RMSE), Nash-Sutcliff efficiency (NSE), standard deviation ratio (RSR), percent bias (PBIAS) indices, and uncertainty analysis. For the ANFIS-BA model, RMSE and RSR varied from 1.5 to 2.5 ton/d and from 5% to 25%, respectively. In addition, a variation range of NSE was between very good and good performance (0.75 to 0.85 and 0.85 to 1). The uncertainty analysis showed that the ANFIS-BA had more reliable performance compared to other models. Thus, the ANFIS-BA model has high potential for predicting SSL.

UR - http://www.scopus.com/inward/record.url?scp=85073276948&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073276948&partnerID=8YFLogxK

U2 - 10.3390/app9194149

DO - 10.3390/app9194149

M3 - Article

AN - SCOPUS:85073276948

VL - 9

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 19

M1 - 4149

ER -