Time filter

Source Type

Tayyab M.,Huazhong University of Science and Technology | Tayyab M.,Hubei Key Laboratory of Digital Valley Science and Technology | Zhou J.,Huazhong University of Science and Technology | Zhou J.,Hubei Key Laboratory of Digital Valley Science and Technology | And 5 more authors.
Indonesian Journal of Electrical Engineering and Computer Science | Year: 2016

Precise and correct estimation of streamflow is important for the operative progression in water resources systems. The artificial intelligence approaches; such as artificial neural networks (ANN) have been applied for efficiently tackling the hydrological matters like streamflow forecasting in this study at upper Yangtze River. The objective is to investigate the certainty of monthly streamflow by applying artificial neural networks including Generalized Regression Network (GRNN). To overcome the non-linearity problem of streamflow, artificial neural networks integrated with discrete wavelet transform (DWT). Data has been analyzed by comparing the simulation outputs of the models with the correlation coefficient (R) root mean square errors (RMSE). It is found that the decomposition technique DWT has ability to improve the forecasting results as compare to single applied artificial neural networks. Moreover, all applied models are separately applies on the peak values as well which also have showed that intergrated model has more ability to catch the peak values. © 2016 Institute of Advanced Engineering and Science. All rights reserved.


Tayyab M.,Huazhong University of Science and Technology | Tayyab M.,Hubei Key Laboratory of Digital Valley Science and Technology | Zhou J.,Huazhong University of Science and Technology | Zhou J.,Hubei Key Laboratory of Digital Valley Science and Technology | And 3 more authors.
Indonesian Journal of Electrical Engineering and Computer Science | Year: 2017

This research highlights the precipitation trends and presents the results of the study in temporal and spatial scales. Precise predictions of precipitation trends can play imperative part in economic growth of a state. This study examined precipitation inconsistency for 23 stations at the Dongting Lake, China, over a 52-years study phase (1961–2012). Statistical, nonparametric Mann-Kendall (MK) and Spearman’s rho (SR) tests were applied to identify trends within monthly, seasonal, and annual precipitation. The trend-free prewhitening method used to exclude sequential correlation in the precipitation time series. The performance of the Mann-Kendall (MK) and Spearman’s rho (SR) tests was steady at the tested significance level. The results showed fusion of increasing (positive) and decreasing (negative) trends at different stations within monthly and seasonal time scale. In case of whole Dongting basin on monthly time scale, significant positive trend is found, while at Yuanjiang River and Xianjiag River both positive and negative significant trends are identified. © 2017 Institute of Advanced Engineering and Science. All rights reserved.


Ye L.,Huazhong University of Science and Technology | Ye L.,Hubei Key Laboratory of Digital Valley Science and Technology | Zhou J.,Huazhong University of Science and Technology | Zhou J.,Hubei Key Laboratory of Digital Valley Science and Technology | And 5 more authors.
Journal of Hydrology | Year: 2014

Practice experience reveals that prediction interval is more reliable and informative compared to single simulation, as it indicates the precision of the forecast. However, traditional ways to implement the construction of prediction interval is very difficult. This paper proposed a novel method for constructing prediction interval based on a hydrological model ensemble. The excellent multi-objective shuffled complex differential evolution algorithm was introduced to calibrate the parameters of hydrological models so as to construct an ensemble of hydrological models, which ensures a maximum of the observed data to fall within the estimated prediction interval, and whose width is also minimized simultaneously. Meanwhile, the mean of the hydrological model ensemble can be used as single simulation. The proposed method was applied to a real world case study in order to identify the effectiveness of the construction of prediction interval for the Leaf River Watershed. The results showed that the proposed method is able to construct prediction interval appropriately and efficiently. Meanwhile, the ensemble mean can be used as single simulation because it maintains comparative forecasting accuracy as the traditional single hydrological model. © 2014 Elsevier B.V.


Zhou J.,Huazhong University of Science and Technology | Zhou J.,Hubei Key Laboratory of Digital Valley Science and Technology | Pan L.,Huazhong University of Science and Technology | Pan L.,Hubei Key Laboratory of Digital Valley Science and Technology | Ge M.,Sias International University
2013 3rd International Conference on Consumer Electronics, Communications and Networks, CECNet 2013 - Proceedings | Year: 2013

With the development and wide application of virtual reality in various industries, three-dimensional virtual visual simulation technique has become an important presentation manner in water conservancy project information management. After the relevant support technologies such as GIS, Remote sense, computer graphics and water rendering are deeply researched, this paper presents a development framework about three-dimensional virtual visual simulation system (3D VVSS) of large-scale urban lakes. Combining with the large-scale ecological water network scheduling project of Dong Lake in Wuhan city of Hubei province and OpenSceneGraph platform, a 3D VVSS of urban lakes is constructed, which can provide virtual roaming, information query, real time monitor information of water quality displaying, etc. Finally, some optimized measures are discussed to improve running speed and efficiency of the VVSS. © 2013 IEEE.


Zhao Y.,Huazhong University of Science and Technology | Zhao Y.,Hubei Key Laboratory of Digital Valley Science and Technology | Zhou J.,Huazhong University of Science and Technology | Zhou J.,Hubei Key Laboratory of Digital Valley Science and Technology | And 6 more authors.
Shuikexue Jinzhan/Advances in Water Science | Year: 2013

Existing physical habitat models could only be available and efficient for the rivers which have abundant monitoring data. To overcome this shortcoming, a new physical habitat simulation method by applying fuzzy logic inference was presented. Based on precise flow field simulation results, the proposed fuzzy habitat model linked these data to the expert knowledge base to compute habitat suitability indexes of each unit by using fuzzy logic reasoning. At last, the weighted usable area and highly suitable proportion of habitat at different river discharges were calculated to study the ecological water requirement. By using the proposed method, Chinese sturgeon spawning habitat on the downstream of the Gezhouba Dam was simulated. The results indicate that the suitable ecological flow range for Chinese sturgeon propagation is about 10000-17000 m3/s. The proposed method which is weak dependence on monitoring data by considering expert knowledge and experience is feasible and available. This research could be helpful to ecological protection and river management for the rivers which are lack of field-measured data, and could also provide a reference for the application of fuzzy mathematics in water ecology.


Guo J.,Huazhong University of Science and Technology | Guo J.,Hubei Key Laboratory of Digital Valley Science and Technology | Guo J.,Hunan Electric Power Test and Research Institute | Zhou J.,Huazhong University of Science and Technology | And 6 more authors.
Water Resources Management | Year: 2013

Practice experience suggests that the traditional calibration of hydrological models with single objective cannot properly measure all of the behaviors of the hydrological system. To circumvent this problem, in recent years, a lot of studies have looked into calibration of hydrological models with multi-objective. In this paper, we propose a novel multi-objective evolution algorithm entitled multi-objective shuffled complex differential evolution (MOSCDE) algorithm, which is an extension of the famous single objective algorithm, shuffled complex evolution (SCE-UA) algorithm, to the multi-objective framework. This new proposed algorithm replaces the simplex search used in SCE-UA with the differential evolution (DE) algorithm and can more thoroughly utilize the information of the individuals in the evolutionary population and improve the search ability of the algorithm. Meanwhile, the Cauchy mutation (CM) operator is employed to prevent the algorithm from falling into the local optimal region of the feasible space. Moreover, two types of archive sets are employed to further improve the performance of the algorithm. The efficacy of the MOSCDE algorithm is first tested on five benchmark problems. After achieving satisfactory performance on the test problems, the MOSCDE is applied to multi-objective parameter optimization of a hydrological model for daily runoff forecasting. The results show that the MOSCDE algorithm can be a viable alternative for multi-objective parameter optimization of hydrological model. © 2013 Springer Science+Business Media Dordrecht.


Wang X.-M.,Huazhong University of Science and Technology | Zhou J.-Z.,Huazhong University of Science and Technology | Zhou J.-Z.,Hubei Key Laboratory of Digital Valley Science and Technology | Ou Yang S.,Huazhong University of Science and Technology | And 2 more authors.
Shuili Xuebao/Journal of Hydraulic Engineering | Year: 2013

The optimal ecological flow of Yichang station is determined as ecological benefit evaluation standard based on monthly frequency computation method and ecology elements of the Yangtze River. An eco-friendly generation multi-objective optimal dispatch model of cascade reservoir is proposed according to the major ecology problems and the specific engineering practice in the Three Gorges Cascade (TGC). A dual-subpopulation multi-objective differential evolution algorithm with external archive, elitist selection and chaotic migration is presented to solve the optimal dispatch model. The results reveales that a lot of non-dominated and uniformly dispatch schemes for decision-making can be generated in short time.


Wang C.,Huazhong University of Science and Technology | Wang X.,Huazhong University of Science and Technology | Zhou J.,Hubei Key Laboratory of Digital Valley Science and Technology | Zhang C.,Huazhong University of Science and Technology
Proceedings - 2015 International Conference on Control, Automation and Robotics, ICCAR 2015 | Year: 2015

This paper focus on the ecological optimization operation problem of the Three Gorges reservoir in flood recession. In this season, the primary goal of the reservoir is impounding to get the maximum economic benefit. As people increasing concern about their environment, impact of the reservoir operation to the aquatic habitat at the downstream area becomes an increasing important factor. The conflict between economic benefit and habitat conservation makes the dispatch a multi-objective problem. In this paper, stored energy at the end of dispatch period is proposed to be the economic objective and the weighted usable area (WUA) of the habitat is used to represent the environmental demand. The multi-objective differential evolution (MODE) and a particular constraint handling strategy proposed in this paper are used to solve this problem. Simulation results show that the proposed constraint handling strategy improves the performance of MODE in solving this problem. More importantly, the Pareto optimal front of different operating condition shows that the conflict between economic benefit and environmental benefit is sharp, especially in low flow years. The degree of conflict relates to the value of average inflow. So it is necessary to consider the habitat conservation while operating. And this work provides a support to aquatic organism protection and ecological operation of the Three Gorges reservoir. © 2015 IEEE.


Zhang H.,Huazhong University of Science and Technology | Zhang H.,Hubei Key Laboratory of Digital Valley Science and Technology | Zhou J.,Huazhong University of Science and Technology | Zhou J.,Hubei Key Laboratory of Digital Valley Science and Technology | And 5 more authors.
Water Resources Management | Year: 2015

It is widely accepted that Prediction Interval (PI) can provide more accurate and precise information than deterministic forecast when the uncertainty level increases in flood forecasting. Coverage probability and PI width are two main criteria used to assess the constructed PI, rarely has there been an index to quantify the symmetry between target value and PI. This study extends a newly proposed PI estimation method called Lower Upper Bound Estimation (LUBE) method, which adopts an Artificial Neural Network (ANN) with two outputs to directly generate the upper and lower bounds of PI without making any assumption about the data distribution. A new Prediction Interval Symmetry (PIS) index is introduced and a new objective function is developed for the comprehensive evaluation of PI considering their coverage probability, width and symmetry. Furthermore, Shuffled Complex Evolution algorithm (SCE-UA) is used to minimize the objective function and optimize ANN parameters in the LUBE method. The proposed method is applied to a real world flood forecasting case study of the upper Yangtze River Watershed. The result shows that the SCE-UA based LUBE method with new objective function is very efficient, meanwhile, the midpoint forecasting of the PI obtains excellent performance by evidently improving the symmetry of PI. © 2015, Springer Science+Business Media Dordrecht.


Xue X.M.,Huazhong University of Science and Technology | Zhou J.Z.,Huazhong University of Science and Technology | Zhou J.Z.,Hubei Key Laboratory of Digital Valley Science and Technology | Zhang Y.C.,Huazhong University of Science and Technology | And 3 more authors.
Applied Mechanics and Materials | Year: 2013

The end effects is a serious problem in the applications of the empirical mode decomposition (EMD) method. To deal with this problem, an extrema extension method based on the support vector regression (SVR) is proposed in this paper. In each iterating process of the EMD method, the SVR method is employed to predict one maximum and a minimum point respectively at the both ends of the original data series to form the relatively true upper and lower envelope, thus the end effects can be restrained effectively. The prediction of an extrema point includes two parts, the forecast of the extreme value and location. In contrast with other traditional extrema extension methods, such as the extrema mirror extension and linear fitting extension method, the decomposed results from the simulation and actual signals demonstrated that this proposed method has a better performance in eliminating the end effects related to the empirical mode decomposition. © (2013) Trans Tech Publications, Switzerland.

Loading Hubei Key Laboratory of Digital Valley Science and Technology collaborators
Loading Hubei Key Laboratory of Digital Valley Science and Technology collaborators