Optimización de un sistema de inferencia neuro-fuzzy adaptable para el mapeo del potencial de aguas subterráneas

Translated title of the contribution: Optimization of an adaptive neuro-fuzzy inference system for groundwater potential mapping

Seyed Vahid Razavi Termeh, Khabat Khosravi, Majid Sartaj*, Saskia Deborah Keesstra, Frank T.C. Tsai, Roel Dijksma, Binh Thai Pham

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

9 Citations (Scopus)

Abstract

The main goal of this study was to optimize an adaptive neuro-fuzzy inference system (ANFIS) using three meta-heuristic optimization algorithms—genetic algorithm (GA), biogeography-based optimization (BBO) and simulated annealing (SA)—to prepare groundwater potential maps. The methodology was applied to the Booshehr plain, Iran. The results of optimized models were compared with ANFIS individually and three bivariate models: frequency ratio (FR), evidential belief function (EBF), and the entropy model. First, 339 wells with groundwater yield higher than 11 m3/h were selected and randomly divided into two groups. In all, 238 wells (70%) were used for training the models and 101 wells (30%) were used for testing and validating the models. Fifteen conditioning factors were selected as input parameters for the modeling. The accuracy of the groundwater potential maps for the study area was determined using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and standard deviation of error (SD), as well as the area under the receiver operating characteristic (ROC) curve (AUC). Overall, the results demonstrated that ANFIS-GA had the highest prediction capability (AUC = 0.915) for groundwater potential mapping followed by ANFIS-BBO (0.903), entropy (0.862), FR (0.86), ANFIS-SA (0.83), ANFIS (0.82) and EBF (0.80). According to the entropy model, land-use, soil order and rainfall factors had the highest impact on groundwater potential in the study area. The results of this research show that the ANFIS models combined with meta-heuristic optimization algorithms can be a useful decision-making tool for assessment and management of groundwater resources.

Original languageSpanish
Pages (from-to)2511-2534
JournalHydrogeology Journal
Volume27
Issue number7
Early online date10 Aug 2019
DOIs
Publication statusPublished - Nov 2019

Fingerprint

groundwater
entropy
simulated annealing
heuristics
well
biogeography
groundwater resource
conditioning
decision making
land use
rainfall
methodology
prediction
modeling
soil

Cite this

Termeh, Seyed Vahid Razavi ; Khosravi, Khabat ; Sartaj, Majid ; Keesstra, Saskia Deborah ; Tsai, Frank T.C. ; Dijksma, Roel ; Pham, Binh Thai. / Optimización de un sistema de inferencia neuro-fuzzy adaptable para el mapeo del potencial de aguas subterráneas. In: Hydrogeology Journal. 2019 ; Vol. 27, No. 7. pp. 2511-2534.
@article{eba2b5c00ad444948c4a029892719b3a,
title = "Optimizaci{\'o}n de un sistema de inferencia neuro-fuzzy adaptable para el mapeo del potencial de aguas subterr{\'a}neas",
abstract = "The main goal of this study was to optimize an adaptive neuro-fuzzy inference system (ANFIS) using three meta-heuristic optimization algorithms—genetic algorithm (GA), biogeography-based optimization (BBO) and simulated annealing (SA)—to prepare groundwater potential maps. The methodology was applied to the Booshehr plain, Iran. The results of optimized models were compared with ANFIS individually and three bivariate models: frequency ratio (FR), evidential belief function (EBF), and the entropy model. First, 339 wells with groundwater yield higher than 11 m3/h were selected and randomly divided into two groups. In all, 238 wells (70{\%}) were used for training the models and 101 wells (30{\%}) were used for testing and validating the models. Fifteen conditioning factors were selected as input parameters for the modeling. The accuracy of the groundwater potential maps for the study area was determined using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and standard deviation of error (SD), as well as the area under the receiver operating characteristic (ROC) curve (AUC). Overall, the results demonstrated that ANFIS-GA had the highest prediction capability (AUC = 0.915) for groundwater potential mapping followed by ANFIS-BBO (0.903), entropy (0.862), FR (0.86), ANFIS-SA (0.83), ANFIS (0.82) and EBF (0.80). According to the entropy model, land-use, soil order and rainfall factors had the highest impact on groundwater potential in the study area. The results of this research show that the ANFIS models combined with meta-heuristic optimization algorithms can be a useful decision-making tool for assessment and management of groundwater resources.",
keywords = "Bivariate models, Groundwater management, Groundwater potential mapping, Iran, Optimization",
author = "Termeh, {Seyed Vahid Razavi} and Khabat Khosravi and Majid Sartaj and Keesstra, {Saskia Deborah} and Tsai, {Frank T.C.} and Roel Dijksma and Pham, {Binh Thai}",
year = "2019",
month = "11",
doi = "10.1007/s10040-019-02017-9",
language = "Spanish",
volume = "27",
pages = "2511--2534",
journal = "Hydrogeology Journal",
issn = "1431-2174",
publisher = "Springer Verlag",
number = "7",

}

Optimización de un sistema de inferencia neuro-fuzzy adaptable para el mapeo del potencial de aguas subterráneas. / Termeh, Seyed Vahid Razavi; Khosravi, Khabat; Sartaj, Majid; Keesstra, Saskia Deborah; Tsai, Frank T.C.; Dijksma, Roel; Pham, Binh Thai.

In: Hydrogeology Journal, Vol. 27, No. 7, 11.2019, p. 2511-2534.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Optimización de un sistema de inferencia neuro-fuzzy adaptable para el mapeo del potencial de aguas subterráneas

AU - Termeh, Seyed Vahid Razavi

AU - Khosravi, Khabat

AU - Sartaj, Majid

AU - Keesstra, Saskia Deborah

AU - Tsai, Frank T.C.

AU - Dijksma, Roel

AU - Pham, Binh Thai

PY - 2019/11

Y1 - 2019/11

N2 - The main goal of this study was to optimize an adaptive neuro-fuzzy inference system (ANFIS) using three meta-heuristic optimization algorithms—genetic algorithm (GA), biogeography-based optimization (BBO) and simulated annealing (SA)—to prepare groundwater potential maps. The methodology was applied to the Booshehr plain, Iran. The results of optimized models were compared with ANFIS individually and three bivariate models: frequency ratio (FR), evidential belief function (EBF), and the entropy model. First, 339 wells with groundwater yield higher than 11 m3/h were selected and randomly divided into two groups. In all, 238 wells (70%) were used for training the models and 101 wells (30%) were used for testing and validating the models. Fifteen conditioning factors were selected as input parameters for the modeling. The accuracy of the groundwater potential maps for the study area was determined using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and standard deviation of error (SD), as well as the area under the receiver operating characteristic (ROC) curve (AUC). Overall, the results demonstrated that ANFIS-GA had the highest prediction capability (AUC = 0.915) for groundwater potential mapping followed by ANFIS-BBO (0.903), entropy (0.862), FR (0.86), ANFIS-SA (0.83), ANFIS (0.82) and EBF (0.80). According to the entropy model, land-use, soil order and rainfall factors had the highest impact on groundwater potential in the study area. The results of this research show that the ANFIS models combined with meta-heuristic optimization algorithms can be a useful decision-making tool for assessment and management of groundwater resources.

AB - The main goal of this study was to optimize an adaptive neuro-fuzzy inference system (ANFIS) using three meta-heuristic optimization algorithms—genetic algorithm (GA), biogeography-based optimization (BBO) and simulated annealing (SA)—to prepare groundwater potential maps. The methodology was applied to the Booshehr plain, Iran. The results of optimized models were compared with ANFIS individually and three bivariate models: frequency ratio (FR), evidential belief function (EBF), and the entropy model. First, 339 wells with groundwater yield higher than 11 m3/h were selected and randomly divided into two groups. In all, 238 wells (70%) were used for training the models and 101 wells (30%) were used for testing and validating the models. Fifteen conditioning factors were selected as input parameters for the modeling. The accuracy of the groundwater potential maps for the study area was determined using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and standard deviation of error (SD), as well as the area under the receiver operating characteristic (ROC) curve (AUC). Overall, the results demonstrated that ANFIS-GA had the highest prediction capability (AUC = 0.915) for groundwater potential mapping followed by ANFIS-BBO (0.903), entropy (0.862), FR (0.86), ANFIS-SA (0.83), ANFIS (0.82) and EBF (0.80). According to the entropy model, land-use, soil order and rainfall factors had the highest impact on groundwater potential in the study area. The results of this research show that the ANFIS models combined with meta-heuristic optimization algorithms can be a useful decision-making tool for assessment and management of groundwater resources.

KW - Bivariate models

KW - Groundwater management

KW - Groundwater potential mapping

KW - Iran

KW - Optimization

U2 - 10.1007/s10040-019-02017-9

DO - 10.1007/s10040-019-02017-9

M3 - Article

VL - 27

SP - 2511

EP - 2534

JO - Hydrogeology Journal

JF - Hydrogeology Journal

SN - 1431-2174

IS - 7

ER -