Improving Rainfall Forecasting Efficiency Using Modified Adaptive Neuro-Fuzzy Inference System (MANFIS)

Seyed Ahmad Akrami, Ahmed El-Shafie, Othman Jaafar

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Rainfall is one of the most complicated effective hydrologic processes in runoff prediction and water management. The adaptive neuro-fuzzy inference system (ANFIS) has been widely used for modeling different kinds of nonlinear systems including rainfall forecasting. Adaptive Neuro-Fuzzy Inference Systems (ANFIS) combines the capabilities of Artificial Neural Networks (ANN) and Fuzzy Inference Systems (FIS) to solve different kinds of problems, especially efficient in rainfall prediction. This paper after reconsidering conventional ANFIS architecture brings up a modified ANFlS (MANFlS) structure developed with attention to making ANFIS technique more efficient regarding to Root Mean Square Error (RMSE), Correlation Coefficient (R 2), Root Mean Absolute Error (RMAE), Signal to Noise Ratio (SNR) and computing epoch. The modified ANFIS (MANFIS) architecture is simpler than conventional ANFIS with nearly the same performance for modeling nonlinear systems. In this study, two scenarios were introduced; in the first scenario, monthly rainfall was used solely as an input in different time delays from the time (t) to the time (t-4) to conventional ANFIS, second scenario used the modified ANFIS to improve the rainfall forecasting efficiency. The result showed that the model based Modified ANFIS performed higher rainfall forecasting accuracy; low errors and lower computational complexity (total number of fitting parameters and convergence epochs) compared with the conventional ANFIS model.

Original languageEnglish
Pages (from-to)3507-3523
Number of pages17
JournalWater Resources Management
Volume27
Issue number9
DOIs
Publication statusPublished - Jul 2013

Fingerprint

Fuzzy inference
Rain
rainfall
prediction
Nonlinear systems
artificial neural network
signal-to-noise ratio
modeling
water management
runoff
Water management
Runoff
Mean square error
Computational complexity
Time delay
Signal to noise ratio
Neural networks

Keywords

  • Adaptive neuro-fuzzy Inference systems (ANFIS)
  • Converges of iterations
  • Fitting parameters
  • Fuzzy rules
  • Modified ANFIS
  • Rainfall prediction

ASJC Scopus subject areas

  • Water Science and Technology
  • Civil and Structural Engineering

Cite this

Improving Rainfall Forecasting Efficiency Using Modified Adaptive Neuro-Fuzzy Inference System (MANFIS). / Akrami, Seyed Ahmad; El-Shafie, Ahmed; Jaafar, Othman.

In: Water Resources Management, Vol. 27, No. 9, 07.2013, p. 3507-3523.

Research output: Contribution to journalArticle

@article{4e9242a4b3d64d289bf55b79055acb5d,
title = "Improving Rainfall Forecasting Efficiency Using Modified Adaptive Neuro-Fuzzy Inference System (MANFIS)",
abstract = "Rainfall is one of the most complicated effective hydrologic processes in runoff prediction and water management. The adaptive neuro-fuzzy inference system (ANFIS) has been widely used for modeling different kinds of nonlinear systems including rainfall forecasting. Adaptive Neuro-Fuzzy Inference Systems (ANFIS) combines the capabilities of Artificial Neural Networks (ANN) and Fuzzy Inference Systems (FIS) to solve different kinds of problems, especially efficient in rainfall prediction. This paper after reconsidering conventional ANFIS architecture brings up a modified ANFlS (MANFlS) structure developed with attention to making ANFIS technique more efficient regarding to Root Mean Square Error (RMSE), Correlation Coefficient (R 2), Root Mean Absolute Error (RMAE), Signal to Noise Ratio (SNR) and computing epoch. The modified ANFIS (MANFIS) architecture is simpler than conventional ANFIS with nearly the same performance for modeling nonlinear systems. In this study, two scenarios were introduced; in the first scenario, monthly rainfall was used solely as an input in different time delays from the time (t) to the time (t-4) to conventional ANFIS, second scenario used the modified ANFIS to improve the rainfall forecasting efficiency. The result showed that the model based Modified ANFIS performed higher rainfall forecasting accuracy; low errors and lower computational complexity (total number of fitting parameters and convergence epochs) compared with the conventional ANFIS model.",
keywords = "Adaptive neuro-fuzzy Inference systems (ANFIS), Converges of iterations, Fitting parameters, Fuzzy rules, Modified ANFIS, Rainfall prediction",
author = "Akrami, {Seyed Ahmad} and Ahmed El-Shafie and Othman Jaafar",
year = "2013",
month = "7",
doi = "10.1007/s11269-013-0361-9",
language = "English",
volume = "27",
pages = "3507--3523",
journal = "Water Resources Management",
issn = "0920-4741",
publisher = "Springer Netherlands",
number = "9",

}

TY - JOUR

T1 - Improving Rainfall Forecasting Efficiency Using Modified Adaptive Neuro-Fuzzy Inference System (MANFIS)

AU - Akrami, Seyed Ahmad

AU - El-Shafie, Ahmed

AU - Jaafar, Othman

PY - 2013/7

Y1 - 2013/7

N2 - Rainfall is one of the most complicated effective hydrologic processes in runoff prediction and water management. The adaptive neuro-fuzzy inference system (ANFIS) has been widely used for modeling different kinds of nonlinear systems including rainfall forecasting. Adaptive Neuro-Fuzzy Inference Systems (ANFIS) combines the capabilities of Artificial Neural Networks (ANN) and Fuzzy Inference Systems (FIS) to solve different kinds of problems, especially efficient in rainfall prediction. This paper after reconsidering conventional ANFIS architecture brings up a modified ANFlS (MANFlS) structure developed with attention to making ANFIS technique more efficient regarding to Root Mean Square Error (RMSE), Correlation Coefficient (R 2), Root Mean Absolute Error (RMAE), Signal to Noise Ratio (SNR) and computing epoch. The modified ANFIS (MANFIS) architecture is simpler than conventional ANFIS with nearly the same performance for modeling nonlinear systems. In this study, two scenarios were introduced; in the first scenario, monthly rainfall was used solely as an input in different time delays from the time (t) to the time (t-4) to conventional ANFIS, second scenario used the modified ANFIS to improve the rainfall forecasting efficiency. The result showed that the model based Modified ANFIS performed higher rainfall forecasting accuracy; low errors and lower computational complexity (total number of fitting parameters and convergence epochs) compared with the conventional ANFIS model.

AB - Rainfall is one of the most complicated effective hydrologic processes in runoff prediction and water management. The adaptive neuro-fuzzy inference system (ANFIS) has been widely used for modeling different kinds of nonlinear systems including rainfall forecasting. Adaptive Neuro-Fuzzy Inference Systems (ANFIS) combines the capabilities of Artificial Neural Networks (ANN) and Fuzzy Inference Systems (FIS) to solve different kinds of problems, especially efficient in rainfall prediction. This paper after reconsidering conventional ANFIS architecture brings up a modified ANFlS (MANFlS) structure developed with attention to making ANFIS technique more efficient regarding to Root Mean Square Error (RMSE), Correlation Coefficient (R 2), Root Mean Absolute Error (RMAE), Signal to Noise Ratio (SNR) and computing epoch. The modified ANFIS (MANFIS) architecture is simpler than conventional ANFIS with nearly the same performance for modeling nonlinear systems. In this study, two scenarios were introduced; in the first scenario, monthly rainfall was used solely as an input in different time delays from the time (t) to the time (t-4) to conventional ANFIS, second scenario used the modified ANFIS to improve the rainfall forecasting efficiency. The result showed that the model based Modified ANFIS performed higher rainfall forecasting accuracy; low errors and lower computational complexity (total number of fitting parameters and convergence epochs) compared with the conventional ANFIS model.

KW - Adaptive neuro-fuzzy Inference systems (ANFIS)

KW - Converges of iterations

KW - Fitting parameters

KW - Fuzzy rules

KW - Modified ANFIS

KW - Rainfall prediction

UR - http://www.scopus.com/inward/record.url?scp=84878763355&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878763355&partnerID=8YFLogxK

U2 - 10.1007/s11269-013-0361-9

DO - 10.1007/s11269-013-0361-9

M3 - Article

VL - 27

SP - 3507

EP - 3523

JO - Water Resources Management

JF - Water Resources Management

SN - 0920-4741

IS - 9

ER -