Short‐term flood forecasting with a neurofuzzy model

Abstract

[1] This study explores the potential of the neurofuzzy computing paradigm to model the rainfall-runoff process for forecasting the river flow of Kolar basin in India. The neurofuzzy computing technique is a combination of a fuzzy computing approach and an artificial neural network technique. Parameter optimization in the model was performed by a combination of backpropagation and least squares error methods. Performance of the neurofuzzy model was comprehensively evaluated with that of independent fuzzy and neural network models developed for the same basin. The values of three performance evaluation criteria, namely, the coefficient of efficiency, the root-mean-square error, and the coefficient of correlation, were found to be very good and consistent for flows forecasted 1 hour in advance by the neurofuzzy model. The value of the relative error in peak flow prediction was within reasonable limits for the neurofuzzy model. The neurofuzzy model forecasted 47.95% of the total number of flow values 1 hour in advance with less than 1% relative error, while for the neural network and fuzzy models the corresponding values were 36.96 and 18.89%, respectively. The forecasts by the neurofuzzy model at higher lead times (up to 6 hours) are found to be better than those from the neural network model or the fuzzy model, implying that the neurofuzzy model seems to be well suited to exploit the information to model the nonlinear dynamics of the rainfall-runoff process.

Deep Learning: Ứng Dụng Cho Dự Báo Lưu Lượng Nước Đến Hồ Chứa Hòa Bình

“…Các phương pháp học máy tiếp cận bài toán dự báo lưu lượng nước đổ về hồ chứa đã được nghiên cứu và đạt được nhiều kết quả khả quan [17,18,19]. Mạng nơron (neural) nhân tạo (ANN) được chứng minh bằng thực nghiệm cho thấy là một trong các phương pháp hiệu quả nhất và được dùng nhiều trong tính toán dự báo dạng chuỗi thời gian đối với bài toán thuộc dạng này [18,[20][21][22][23][24]. Trong những năm gần đây, phương pháp Deep learning (Học sâu) dựa trên nền tảng mạng nơron nhân tạo đang phát triển rất nhanh và thu hút đông đảo cộng đồng nghiên cứu tham gia.…”

Predicting air pollution in Tehran: Genetic algorithm and back propagation neural network

“…Neurology, Mathematics, statistics, physics, computer science and engineering are examples of mentioned sciences [5,6,7]. Most recently Multi Layer Perceptron (MLP) has been widely used to predict pollutants so that in most large cities around the world for MLP has been used to predict air pollutant.…”

“…It was reported that the detrimental effects of particulate matter on human health, is mostly due to being exposed to concentrations of particles. One of the most effective actions to control and reduce air pollution is to estimate the pollutants density and to describe the state of air quality in comparison with the standard conditions [7]. This paper tries to estimate and predict the air pollution of Tehran with two approaches.…”

Application of neural network and adaptive neuro-fuzzy inference systems for river flow prediction

“…Use of this technique for rainfall-runoff and river flow time series predictions has been reported by many researchers (e.g. Valenca & Ludermir, 2000;Chang & Chen, 2001Nayak et al, 2004Nayak et al, , 2005.…”