A hybrid multi-model approach to river level forecasting
نویسندگان
چکیده
This paper presents four different approaches for integrating conventional and AI-based forecasting models to provide a hybridized solution to the continuous river level and flood prediction problem. Individual forecasting models were developed on a stand alone basis using historical time series data from the River Ouse in northern England. These include a hybrid neural network, a simple rule-based fuzzy logic model, an ARMA model and naive predictions (which use the current value as the forecast). The individual models were then integrated via four different approaches: calculation of an average, a Bayesian approach, and two fuzzy logic models, the first based purely on current and past river flow conditions and the second, a fuzzification of the crisp Bayesian method. Model performance was assessed using global statistics and a more specific flood related evaluation measure. The addition of fuzzy logic to the crisp Bayesian model yielded overall results that were superior to the other individual and integrated approaches. Approche multi-modèle hybride de la prévision du niveau des rivieres Résumé Cet article présente quatre exemples d'intégration de modèles prévisionnels conventionels et de modèles utilisant les techniques de l'intelligence artificielle afin de trouver une solution hybride au problème de la prévision des crues et du niveau des rivières. Différents modèles prévisionnels ont été développés séparément en utilisant les données historiques de la série chronologique de l'Ouse dans le nord de l'Angleterre, à savoir un réseau de neurones hybride, un modèle basé sur des règles utilisant la logique floue, un modèle ARMA (autorégressif à moyenne mobile) et des prévisions naïves. Ces modèles ont ensuite été intégrés en utilisant quatre méthodes différentes: le calcul d'une moyenne, la méthode de Bayes et deux modèles de logique floue, dont le premier s'appuie uniquement sur les conditions de l'écoulement fluvial actuel et antérieur alors que le second s'appuie sur la méthode de Bayes modifiée pour la rendre floue. La performance des modèles a été évaluée en utilisant des statistiques globales ainsi qu'un critère d'évaluation spécifique aux crues. L'introduction de la logique floue dans le modèle de Bayes a fourni des résultats supérieurs à ceux des autres modèles, qu'ils soient pris séparément ou intégrés.
منابع مشابه
Flood Forecasting Using Artificial Neural Networks: an Application of Multi-Model Data Fusion technique
Floods are among the natural disasters that cause human hardship and economic loss. Establishing a viable flood forecasting and warning system for communities at risk can mitigate these adverse effects. However, establishing an accurate flood forecasting system is still challenging due to the lack of knowledge about the effective variables in forecasting. The present study has indicated that th...
متن کاملEvaluation of the Neuro-Fuzzy and Hybrid Wavelet-Neural Models Efficiency in River Flow Forecasting (Case Study: Mohmmad Abad Watershed)
One of the most important issues in watersheds management is rainfall-runoff hydrological process forecasting. Using new models in this field can contribute to proper management and planning. In addition, river flow forecasting, especially in flood conditions, will allow authorities to reduce the risk of flood damage. Considering the importance of river flow forecasting in water resources ma...
متن کاملForecasting Air Pollution Concentrations in Iran, Using a Hybrid Model
The present study aims at developing a forecasting model to predict the next year’s air pollution concentrations in the atmosphere of Iran. In this regard, it proposes the use of ARIMA, SVR, and TSVR, as well as hybrid ARIMA-SVR and ARIMA-TSVR models, which combined the autoregressive part of the autoregressive integrated moving average (ARIMA) model with the support vector regression technique...
متن کاملA hybrid solution approach for a multi-objective closed-loop logistics network under uncertainty
The design of closed-loop logistics (forward and reverse logistics) has attracted growing attention with the stringent pressures of customer expectations, environmental concerns and economic factors. This paper considers a multi-product, multi-period and multi-objective closed-loop logistics network model with regard to facility expansion as a facility location–allocation problem, which more cl...
متن کاملHybrid Models Performance Assessment to Predict Flow of Gamasyab River
Awareness of the level of river flow and its fluctuations at different times is one of the significant factor to achieve sustainable development for water resource issues. Therefore, the present study two hybrid models, Wavelet- Adaptive Neural Fuzzy Interference System (WANFIS) and Wavelet- Artificial Neural Network (WANN) are used for flow prediction of Gamasyab River (Nahavand, Hamedan, Iran...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2000