Hydrological modeling using a dynamic neuro-fuzzy system with on-line and local learning algorithm

• Published in: Advances in water resources Vol. 32; no. 1; pp. 110 - 119
• Main Authors: Hong, Yoon-Seok Timothy, White, Paul A.
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 2009; Elsevier
• Subjects: algorithms; dynamic neuro-fuzzy local modeling system; Dynamic neuro-fuzzy system; dynamic Takagi-Sugeno fuzzy inference system; Earth sciences; Earth, ocean, space; Exact sciences and technology; Extended Kalman filtering algorithm; Freshwater; fuzzy logic; hydrologic models; Hydrological modeling; Hydrology; Hydrology. Hydrogeology; Hydropower station discharge; Local generalization; mathematical models; neural networks; On-line clustering algorithm; simulation models; Spring flow forecasting; springs (water); water flow; New Zealand; South Island; New Zealand, South I; On-line clustering algorithm; Extended Kalman filtering algorithm; Local generalization; Hydropower station discharge; Hydrological modeling; Spring flow forecasting; Dynamic neuro-fuzzy system; algorithms; efficiency; springs; Australasia; adaptation; rain water; digital simulation; hydrological modeling; propagation; water resources; discharge; Kalman filters; flow
• ISSN: 0309-1708; 1872-9657
• DOI: 10.1016/j.advwatres.2008.10.006

This paper introduces the dynamic neuro-fuzzy local modeling system (DNFLMS) that is based on a dynamic Takagi–Sugeno (TS) type fuzzy inference system with on-line and local learning algorithm for complex dynamic hydrological modeling tasks. Our DNFLMS is aimed to implement a fast training speed with the capability of on-line simulation where model adaptation occurs at the arrival of each new item of hydrological data. The DNFLMS applies an on-line, one-pass, training procedure to create and update fuzzy local models dynamically. The extended Kalman filtering algorithm is then implemented to optimize the parameters of the consequence part of each fuzzy model during the training phase. Local generalization in the DNFLMS is employed to optimize the parameters of each fuzzy model separately, region-by-region, using subsets of training data rather than all training data.
The proposed DNFLMS is applied to develop a model to forecast the flow of Waikoropupu Springs, located in the Takaka Valley, South Island, New Zealand, and the influence of the operation of the 32 Megawatt Cobb hydropower station on spring flow. It is demonstrated that the proposed DNFLMS is superior in terms of model complexity and computational efficiency when compared with models that adopt global generalization such as a multi-layer perceptron (MLP) trained with the back propagation learning algorithm and the well-known adaptive neural-fuzzy system (ANFIS).