天津市行洪河道管理信息系统

针对天津市河道防洪资料的不系统性,管理和利用的不科学性,设计并开发了天津市行洪河道管理信息系统.系统首次建立了天津市19条一级行洪河道的数字地图、网络空间数据库、属性数据库,并开发了以WEBGIS为平台的行洪河道信息查询系统,为天津市水利管理部门提供了行洪河道管理信息共享的网络化平台,从而对减灾和管理决策提供准确、及时的技术支持.     

Prediction of river discharge and surface water quality using an integrated geographical information system approach

A methodology is developed for the prediction of river discharge and surface water quality (indexed by nitrogen loading) of a predominantly rural catchment using simple models in an integrated Geographical Information System (GIS). River discharge is predicted using the Soil Conservation Service (SCS) runoff Curve Number model, and surface water quality by the export coefficient model. Main input variable to these models is information on land-use along with ancillary information such as soils. Land-use is an important parameter that affects both discharge and water quality, and it can be derived from classification of remotely sensed images. Unlike conventional models, the models employed here do not require large amounts of data on several hydro-meteorological variables. The models are applied to a rural catchment in eastern England where major land-use changes have occurred in the recent past. Historical land-use data are derived from a variety of sources including maps, aerial photographs and remotely sensed satellite images for various dates ranging from 1931 to 1989. A GIS is a valuable means to enable large amounts of spatial data to be integrated, and to facilitate data manipulation for the specific application of the models. Results are validated using observed runoff and water quality records, and it is shown that the model predictions are of acceptable accuracy. This study demonstrated an application of a GIS to employ simple models to predict river discharge and water quality.     

An application of pruning in the design of neural networks for real time flood forecasting

We propose the application of pruning in the design of neural networks for hydrological prediction. The basic idea of pruning algorithms, which have not been used in water resources problems yet, is to start from a network which is larger than necessary, and then remove the parameters that are less influential one at a time, designing a much more parameter-parsimonious model. We compare pruned and complete predictors on two quite different Italian catchments. Remarkably, pruned models may provide better generalization than fully connected ones, thus improving the quality of the forecast. Besides the performance issues, pruning is useful to provide evidence of inputs relevance, removing measuring stations identified as redundant (30–40% in our case studies) from the input set. This is a desirable property in the system exercise since data may not be available in extreme situations such as floods; the smaller the set of measuring stations the model depends on, the lower the probability of system downtimes due to missing data. Furthermore, the Authority in charge of the forecast system may decide for real-time operations just to link the gauges of the pruned predictor, thus saving costs considerably, a critical issue in developing countries.

Neural network forecasting of an opening cash price index

The study investigates the information content of SGX-DT Nikkei 225 futures prices during the non-cash-trading (NCT) period using an artificial neural network model. The cash market closing index, the futures prices from a period in the same trading day and on the following trading day are utilized to determine the appropriate input nodes of a back propagation neural network model in forecasting the opening cash price index. Sensitivity analysis is first employed to address and solve the issue of finding the appropriate network topology. Extensive studies are then performed on the robustness of the constructed network by using different training and testing sample sizes. The effectiveness of the method is demonstrated on data from a 6-month historical record (1998-99). Analytic results demonstrate that the proposed neural network model outperforms a neural network model with the previous day's closing index as the input node and the random walk model forecasts. It, therefore, indicates that there is valuable information involved in futures prices during the NCT period that can be used to forecast the opening cash market price index.     

Analysis of radar images for rainfall forecasting using neural networks

This paper describes a new approach to the analysis of weather radar data for short-range rainfall forecasting based on a neural network model. This approach consists in extracting synthetic information from radar images using the approximation capabilities of multilayer neural networks. Each image in a sequence is approximated using a modified radial basis function network trained by a competitive mechanism. Prediction of the rain field evolution is performed by analysing and extrapolating the time series of weight values. This method has been compared to the conventional cross-correlation technique and the persistence method for three different rainfall events, showing significant improvement in 30 and 60 min ahead forecast accuracy.     

Neural cryptography using optimal structure of neural networks

Applied Intelligence - The asymmetric cryptography method is typically used to transfer the key via an insecure channel while creating a key between two parties. However, since the methods using...     

Neural networks for steady state modelling of an extruder

The inherent complexities of the extrusion process have made the development of both mechanistic and parametric models problematic. This contribution addresses the issues involved in developing a realistic model of an industrial reactive plasticating extruder to enable prediction of extrudate viscosity, which provides a good measure of product quality for the process. The complex nonlinearities associated with the process input-output mapping suggest that neural networks could be an appropriate modelling paradigm. However, the large number of parameters that had to be used caused problems during model identification, since only a limited data set was available. Resampling techniques were therefore used for model identification and validation, due to their efficient use of data and their ability to provide realistic inference of the true error rate associated with the identified models. The statistics obtained are utilised for network structure selection, outlier detection and the derivation of a distribution for model prediction errors. A final network model is presented with fixed confidence bounds, the weights of this network are analysed and an input-output mapping of the process is generated.     

Reconstruction of 2D river beds by appropriate interpolation of 1D cross-sectional information for flood simulation

The 2D numerical simulation of river flow requires a large amount of topographic data to build an accurate Digital Terrain Model which must cover the main river channel and the area likely to be flooded. DTMs for large floodplains are often generated by LiDAR flights. However, it is often impossible to obtain LiDAR data of permanently inundated river beds. These areas are often surveyed and discrete cross-sections of the river channel are obtained. This work presents an algorithm to generate the missing information for the areas between cross-sections. The algorithm allows to generate a river bed which preserves important morphological features such as meanders and thalweg trajectory. Two benchmark cases are studied: a synthetic river-floodplain system and a real case application on a reach of the Ebro river in Spain. The cases are analyzed from a geometry and hydrodynamics perspective by performing 2D simulations with good results.     

基于遗传算法的WNN在电力负荷短期预测中的应用

提出将小波神经网络和遗传算法相结合,用于电力系统短期负荷预测的新方法。具体是充分利用遗传算法的优越性,对小波神经网络的权值进行优化,然后利用优化得到的权值,对原始数据进行W N N训练。通过仿真,该种方法比传统利用神经网络进行负荷预测具有更高的精度。     

Neural networks for estimation of discharge capacity of triangular labyrinth side-weir located on a straight channel

Side-weirs are flow diversion devices widely used in irrigation, land drainage, and urban sewage systems. It is essential to correctly predict the discharge coefficient for hydraulic engineers involved in the technical and economical design of side-weirs. In this study, the discharge capacity of triangular labyrinth side-weirs is estimated by using artificial neural networks (ANN). Two thousand five hundred laboratory test results are used for determining discharge coefficient of triangular labyrinth side-weirs. The performance of the ANN model is compared with multi nonlinear regression models. Root mean square errors (RMSE), mean absolute errors (MAE) and correlation coefficient (R) statistics are used as comparing criteria for the evaluation of the models’ performances. Based on the comparisons, it was found that the neural computing technique could be employed successfully in modelling discharge coefficient from the available experimental data. There were good agreements between the measured values and the values obtained using the ANN model. It was found that the ANN model with RMSE of 0.0674 in validation stage is superior in estimation of discharge coefficient than the multiple nonlinear and linear regression models with RMSE of 0.1019 and 0.1507, respectively.     

Neural networks for load torque monitoring of an induction motor

In this paper, the possibility to use neural networks for the monitoring of the load torque of induction motors is investigated. In particular, unsupervised neural networks are used to detect possible torque anomalies and supervised neural networks are used to identify the average value of steady-state load torque. These networks are trained and validated on the data gathered from a 1.5 kW three-phase squirrel-cage induction motor. Their generalisation abilities have been tested through the data collected with a 3 kW induction motor.     

A new learning method using prior information of neural networks

In this paper, we present a new learning method using prior information for three-layer neural networks. Usually when neural networks are used for identification of systems, all of their weights are trained independently, without considering interrelated weights values. Thus, the training results are usually not good. The reason for this in that each parameter has its influence on others during learning. To overcome this problem, we first give an exact mathematical equation that describes the relation between weight values given a set of data conveying prior information. The we present a new learning method that trains part of the weights and calculates the others using these exact mathematical equations. This method often a priori keeps the given mathematical structure exactly the same during learning; in other words, training is done so that the network follows a predetermined trajectory. Numerical computer simulation results are provided to support this approach. This work was presented, in part, at the Fourth International Symposium on Artificial Life and Robotics, Oita, Japan, January 19–22, 1999.     

A new learning method using prior information of neural networks

In this paper, we present a new learning method using prior information for three-layered neural networks. Usually when neural networks are used for identification of systems, all of their weights are trained independently, without considering their interrelation of weight values. Thus the training results are not usually good. The reason for this is that each parameter has its influence on others during the learning. To overcome this problem, first, we give an exact mathematical equation that describes the relation between weight values given by a set of data conveying prior information. Then we present a new learning method that trains a part of the weights and calculates the others by using these exact mathematical equations. In almost all cases, this method keeps prior information given by a mathematical structure exactly during the learning. In addition, a learning method using prior information expressed by inequality is also presented. In any case, the degree of freedom of networks (the number of     

Technological information extraction of free form surfaces using neural networks

The aim of this paper is to show how to predict the accurate machining technology for the particular free form NURBS or B-spline surface. Since that kind of a surface is very hard to describe in an analytical manner, the topological and geometrical information about the surface was acquired with the help of self-organized neural networks (NNs) and first- or second-order statistic parameters. It is proved that the most significant parameter in this process is the curvature, especially when rapid changes of curvature on a free form surface occurred. As the Gaussian distribution of surface curvatures and slope gradient data were presumed, the mean and variance was used for one-dimensional data presentation, and the Hebbian output data vector was used to assess probability, density function and distribution of the presented data. For collecting the maximum amount of surface information, the principal component analysis method inside the Hebbian NN was used.     

Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications

Artificial Neural Networks (ANNs) are being used increasingly to predict and forecast water resources variables. In this paper, the steps that should be followed in the development of such models are outlined. These include the choice of performance criteria, the division and pre-processing of the available data, the determination of appropriate model inputs and network architecture, optimisation of the connection weights (training) and model validation. The options available to modellers at each of these steps are discussed and the issues that should be considered are highlighted. A review of 43 papers dealing with the use of neural network models for the prediction and forecasting of water resources variables is undertaken in terms of the modelling process adopted. In all but two of the papers reviewed, feedforward networks are used. The vast majority of these networks are trained using the backpropagation algorithm. Issues in relation to the optimal division of the available data, data pre-processing and the choice of appropriate model inputs are seldom considered. In addition, the process of choosing appropriate stopping criteria and optimising network geometry and internal network parameters is generally described poorly or carried out inadequately. All of the above factors can result in non-optimal model performance and an inability to draw meaningful comparisons between different models. Future research efforts should be directed towards the development of guidelines which assist with the development of ANN models and the choice of when ANNs should be used in preference to alternative approaches, the assessment of methods for extracting the knowledge that is contained in the connection weights of trained ANNs and the incorporation of uncertainty into ANN models.     

Univariate modeling and forecasting of monthly energy demand time series using abductive and neural networks

Neural networks have been widely used for short-term, and to a lesser degree medium and long-term, demand forecasting. In the majority of cases for the latter two applications, multivariate modeling was adopted, where the demand time series is related to other weather, socio-economic and demographic time series. Disadvantages of this approach include the fact that influential exogenous factors are difficult to determine, and accurate data for them may not be readily available. This paper uses univariate modeling of the monthly demand time series based only on data for 6 years to forecast the demand for the seventh year. Both neural and abductive networks were used for modeling, and their performance was compared. A simple technique is described for removing the upward growth trend prior to modeling the demand time series to avoid problems associated with extrapolating beyond the data range used for training. Two modeling approaches were investigated and compared: iteratively using a single next-month forecaster, and employing 12 dedicated models to forecast the 12 individual months directly. Results indicate better performance by the first approach, with mean percentage error (MAPE) of the order of 3% for abductive networks. Performance is superior to naı¨ve forecasts based on persistence and seasonality, and is better than results quoted in the literature for several similar applications using multivariate abductive modeling, multiple regression, and univariate ARIMA analysis. Automatic selection of only the most relevant model inputs by the abductive learning algorithm provides better insight into the modeled process and allows constructing simpler neural network models with reduced data dimensionality and improved forecasting performance.     

落差指数法在大湟江口水文站流量在线监测的探讨

河流水能资源梯级开发对水文站水文监测造成了较大的影响,水位流量关系变得散乱,在洪水涨落过程或水利工程回水影响期,现用的综合水位流量关系法推算的实时流量可能出现较大偏差。为应对受水利工程回水等因素影响下的水文监测难题,探讨用落差指数法对受影响水文站水位流量关系进行单值化处理,用实测水位信息推算出实时流量,从而实现流量在线监测。以珠江流域西江干流大湟江口水文站为例,用该站 2017 年以来的实测资料,对落差指数法有关参数进行率定,以单值化关系推算流量。分析结果表明：所推算流量的精度满足规范要求,基本解决大湟江口水文站受影响后的流量实时在线监测和水文资料整编定线难题,可为开展西江干流浔江河段水情预警、生态流量监控、水文分析评价提供良好的实时流量信息支撑。     

顾及局部特性的CNN在遥感影像分类的应用

深度学习的方法在图像识别和自然语言处理等方面展示了优异的性能。将卷积神经网络（Convolution Neural Network,CNN）用于高分辨率遥感影像分类。针对CNN用于遥感影像分类使用固定大小窗口遍历时,影像采样窗口数量过多,导致的分类效率低下问题,提出一种基于影像区域特性的采样窗口确定方法,提高分类效率。影像分类包括两个阶段：首先,利用卷积神经网络得到的特征对影像进行分类;然后,采用支撑向量机对第一步分类由于特征区分性不足造成的错分地物类别进行再分类。采用具有不同特性的遥感影像对所提方法进行了验证,实验结果表明,同现有的特征表示和分类方法相比,该方法的性能有明显改善。