𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Counterpropagation fuzzy–neural network for streamflow reconstruction

✍ Scribed by Fi-John Chang; Hsiang-Fan Hu; Yen-Chang Chen

Publisher
John Wiley and Sons
Year
2001
Tongue
English
Weight
192 KB
Volume
15
Category
Article
ISSN
0885-6087

No coin nor oath required. For personal study only.

✦ Synopsis

Abstract

This study combines neural networks and fuzzy arithmetic to present a counterpropagation fuzzy–neural network (CFNN) for streamflow reconstruction. The CFNN has a rule‐based control, a modified self‐organizing counterpropagation network, and a fuzzy control predictor. It can generate rules automatically by increasing the training data to improve the accuracy of streamflow reconstruction. The CFNN establishes the input and output relationship of a watershed without set‐up parameters. The parameters are estimated systematically by the approach converging to an optimal solution. One sequence of data generated by the Monte Carlo method is used to demonstrate the accuracy of the CFNN. The streamflow data of the Da‐chia River, in central Taiwan, is also used to evaluate the performances of the CFNN. The results indicate the reliability and accuracy of the CFNN for streamflow reconstruction. Copyright © 2001 John Wiley & Sons, Ltd.

📜 SIMILAR VOLUMES

Rainfall-runoff models using artificial
Rainfall-runoff models using artificial neural networks for ensemble streamflow prediction
✍ Dae-Il Jeong; Young-Oh Kim 📂 Article 📅 2005 🏛 John Wiley and Sons 🌐 English ⚖ 865 KB

## Abstract Previous ensemble streamflow prediction (ESP) studies in Korea reported that modelling error significantly affects the accuracy of the ESP probabilistic winter and spring (i.e. dry season) forecasts, and thus suggested that improving the existing rainfall‐runoff model, TANK, would be cr

Conceptual fuzzy neural network model fo
Conceptual fuzzy neural network model for water quality simulation
✍ Paulo Chaves; Toshiharu Kojiri 📂 Article 📅 2007 🏛 John Wiley and Sons 🌐 English ⚖ 474 KB

## Abstract Artificial neural networks (ANNs) have been applied successfully in various fields. However, ANN models depend on large sets of historical data, and are of limited use when only vague and uncertain information is available, which leads to difficulties in defining the model architecture