APPROACHES TO MULTIVARIATE MODELING OF WATER RESOURCES TIME SERIES<sup>1</sup>

Salas, José D.; Tabios, Guillermo Q.; Bartolini, Paolo

doi:10.1111/j.1752-1688.1985.tb05383.x

Cited by 106 publications

(62 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The WilsonHilferty transformation fits well to the given data on the basis of chi-square statistics for different distributions. The procedure for a Wilson-Hilferty transformation (Salas et al, 1985) is as follows:…”

Section: Normalization Of the Seriesmentioning

confidence: 99%

Multivariate modelling of water resources time series using artificial neural networks

Raman

Sunilkumar

1995

Hydrological Sciences Journal

221

View full text Add to dashboard Cite

The artificial neural network (ANN) approach described in this paper for the synthesis of reservoir inflow series differs from the traditional approaches in synthetic hydrology in the sense that it belongs to a class of data-driven approaches as opposed to traditional model driven approaches. Most of the time series modelling procedures fall within the framework of multivariate autoregressive moving average (ARMA) models. Formal statistical modelling procedures suggest a fourstage iterative process, namely, model selection, model order identification, parameter estimation and diagnostic checks. Although a number of statistical tools are already available to follow such a modelling process, it is not an easy task, especially if higher order vector ARMA models are used. This paper investigates the use of artificial neural networks in the field of synthetic inflow generation. The various steps involved in the development of a neural network and a multivariate autoregressive model for synthesis are presented. The application of both types of model for synthesizing monthly inflow records for two reservoir sites is explained. The performance of the neural network is compared with the statistical method of synthetic inflow generation. Modélisationmultivariée de séries chronologiques hydrologiques grâce à l'utilisation de réseaux neuronaux artificiels Résumé L'approche par les réseaux neuronaux artificiels de la génération de séries d'apports à des réservoirs décrite dans cet article diffère des approches traditionnelles de l'hydrologie synthétique dans la mesure où elle s'appuie sur les données plutôt que sur les modèles. La plupart des procédures de modélisation des séries chronologiques se situent dans le cadre des modèles autorégressifs de moyenne mobile (ARMA). Les procédures de modélisation statistique traditionnelles suggèrent un processus itératif en quatre étapes à savoir, choix du modèle, détermination de l'ordre du modèle, estimation des paramètres et vérification. Bien qu'un grand nombre d'outils statistiques soient disponibles pour appliquer une telle procédure, la tâche n'est pas aisée, particulièrement en ce qui concerne les modèles ARMA d'ordre élevé. Ce papier explore les possibilités d'utilisation des réseaux neuronaux artificiels dans le domaine de la génération d'apports. Les différentes étapes du développement d'un réseau de neurones ainsi qu'un modèle de synthèse autorégressif multivarié y sont présentés. Il explique également l'application des différents modèles en vue de la génération d'apports mensuels pour deux sites de réservoirs. Il compare enfin les performances du réseau de neurones à celles de la méthode statistique de génération d'apports.

show abstract

Section: Normalization Of the Seriesmentioning

confidence: 99%

Multivariate modelling of water resources time series using artificial neural networks

Raman

Sunilkumar

1995

Hydrological Sciences Journal

221

View full text Add to dashboard Cite

show abstract

“…These include blackbox/stochastic models and physical/conceptual models (e.g. Salas et al, 1985;Hydrological Engineering Center, 1990). Although physically based models are useful for understanding the mechanisms involved in the process, the black-box models are easier to implement.…”

Section: Introductionmentioning

confidence: 99%

Enforced self‐organizing map neural networks for river flood forecasting

Chang

Wang

2007

Hydrological Processes

View full text Add to dashboard Cite

Abstract:Self-organizing maps (SOMs) have been successfully accepted widely in science and engineering problems; not only are their results unbiased, but they can also be visualized. In this study, we propose an enforced SOM (ESOM) coupled with a linear regression output layer for flood forecasting. The ESOM re-executes a few extra training patterns, e.g. the peak flow, as recycling input data increases the mapping space of peak flow in the topological structure of SOM, and the weighted sum of the extended output layer of the network improves the accuracy of forecasting peak flow. We have investigated an ESOM neural network by using the flood data of the Da-Chia River, Taiwan, and evaluated its performance based on the results obtained from a commonly used back-propagation neural network. The results demonstrate that the ESOM neural network has great efficiency for clustering, especially for the peak flow, and super capability of modelling the flood forecast. The topology maps created from the ESOM are interesting and informative.

show abstract

“…Since then, several multivariate models have been proposed in water resource literature. Different multivariate ARMA models are classified and reviewed by Salas et al (1985). The autoregressive model with constant parameters AR(p) (Salas et ai, 1980) is given below:…”

Section: Multivariate Time Series Modellingmentioning

confidence: 99%

Group-based estimation of missing hydrological data: I. Approach and general methodology

Elshorbagy¹,

Panu²,

Simonović́

2000

Hydrological Sciences Journal

View full text Add to dashboard Cite

In this first paper in a set of two, the problem of estimating missing segments in streamflow records is described. The group approach, different from the traditional single-valued approach, is proposed and explained. The approach perceives the hydrological data as sequence of groups rather than single-valued observations. The techniques suggested to handle the group approach are regression, time series analysis, partitioning modelling, and artificial neural networks. Pertinent literature is reviewed and background material is used to support the group approach. Implementation and comparisons of models' performance are deferred to the second paper.

show abstract

APPROACHES TO MULTIVARIATE MODELING OF WATER RESOURCES TIME SERIES¹

Cited by 106 publications

References 57 publications

Multivariate modelling of water resources time series using artificial neural networks

Multivariate modelling of water resources time series using artificial neural networks

Enforced self‐organizing map neural networks for river flood forecasting

Group-based estimation of missing hydrological data: I. Approach and general methodology

Contact Info

Product

Resources

About

APPROACHES TO MULTIVARIATE MODELING OF WATER RESOURCES TIME SERIES1

Cited by 106 publications

References 57 publications

Multivariate modelling of water resources time series using artificial neural networks

Multivariate modelling of water resources time series using artificial neural networks

Enforced self‐organizing map neural networks for river flood forecasting

Group-based estimation of missing hydrological data: I. Approach and general methodology

Contact Info

Product

Resources

About

APPROACHES TO MULTIVARIATE MODELING OF WATER RESOURCES TIME SERIES¹