径向基函数神经网络预测城市用水量模型及应用

以城市用水人口和城市生产总值作为输入向量,年用水量数据作为目标向量,建立了径向基函数神经网络并对城市用水量进行预测。采用不同的扩展速度,预测误差不同。当扩展速度spread=1时,预测数据与实际数据的相对误差均小于0.05%,取得了很好的预测效果,说明采用径向基函数神经网络模型预测城市用水量的方法是可行的。     

城市供水水量预测模型研究及案例分析

从分析城市用水量的变化规律着手,给出了城市用水量预测的常用模型,并以此为基础分析了选择用水量预测模型时所需考虑的影响因素,然后以铜陵市日用水量预测为例,建立了三阶自回归预测模型,最后分析了铜陵节假日用水量预测模型,为供水系统管理的良好调度提供了数据依据。     

城市供水规划中人均综合用水量指标取值讨论

根据同一城市人均综合用水量与生活用水量之间相对稳定的比例关系建立人均综合用水量指标模型，采用该方法对广东某城区新一轮规划的城市人均综合用水量指标进行了预测，其结果与目前居住小区规划中使用的数据相吻合，说明这一方法是比较合理的。     

基于灰色RBF组合模型的城市用水量预测

为解决城市用水量预测中单一方法预测精度不高的问题,建立了灰色径向基（RBF）神经网络组合模型。对比实验结果表明,灰色GM（1,1）模型、RBF神经网络模型和灰色RBF神经网络组合模型的平均相对误差分别为2．1222％,1．2562％和0．6821％。与灰色GM（1,1）模型和RBF神经网络相比,灰色RBF神经网络组合模型充分发挥了灰色系统的贫乏数据建模和RBF神经网络的高度非线性映射能力的双重优势,具有较高的预测精度,更适合用于城市用水量预测。     

应用GM（1,1）模型预测城市中长期用水量

阐述了GM（1,1）模型的建模思路以及模型模拟预测精度的检验方法,应用所建立的GM（1,1）模型对某市的中长期规划用水量进行了预测,结果表明,模型模拟预测精度为一级,预测效果良好。     

城市水资源优化配置模型研究

结合某市新区发展特性,建立了城市分质供水水资源优化配置数学模型,对新区中水、雨水与自来水等水资源进行了优化配置仿真计算。结果表明,水资源的综合优化配置有利于社会经济的协调发展,实现水资源的可持续利用,具有良好的经济、社会和环境效益。     

Multi-criteria spatial decision analysis for forecasting urban water requirements: a case study of Dehradun city, India

A uniform spatial water distribution system will help in distributing domestic water equally to all places with proper pressure. It will avoid the probable risk of failure in the complete distribution system and can make the system cost effective. In the present study a scientific approach has been adopted to compute drinking water requirements at present and in the near future in a spatial environment using multi-criteria decision analysis techniques. Drinking water problems in the city of Dehradun, India, have been studied and causes of drinking water scarcity have been analysed. Different thematic layers required for the study such as, road network map, landuse/landcover, have been prepared in a Geographic Information System environment using very high-resolution digital data of IKONOS satellite coupled with the field data. Future drinking water demand areas have been identified considering numerous variables such as: distance from the main city, road distance, topographic slopes, landuse/landcover, present population density, soils, floodplains, and the existing water supply system. A questionnaire has been conducted to compute the weights for these variables. Additional supplies that have to be provided for the next two decades have been computed and analysed with the present supply system. A spatial future water demand map has been prepared to produce more thorough and accurate means of assessing city development, and allow the planning and construction of optimum and efficient water supply system.     

Using water consumption smart metering for water loss assessment in a DMA: a case study

ABSTRACT

In this study we analyse the benefits that may be gained from using a smart metering system to assess water losses at a district level with reference to a real case. Consumptions of all the users of this district metered area (DMA) were monitored at an hourly time step by means of electromagnetic meters. Assuming that information on water consumption was available for only a portion of users, we then estimated the water consumption of the entire DMA and calculated the error committed in this estimation as the number of available users varied. Finally, as the simultaneous hourly pattern of inflow into the DMA was also available, we used the water balance method to assess water losses. The results obtained show that monitoring even only 60% of users makes it possible to achieve an error of less than 2% in the estimation of daily consumption across the entire DMA.     

灰色模型在承德市需水预测中的应用

承德市位于河北省东北部,地处滦河和潮白河流域上游地区,为京津的重要水源地,其水环境不仅关系到承德市的用水问题,而且直接影响下游的天津市、北京市和唐山市的用水安全,因此,对其需水量进行科学预测极为重要.根据承德市历年用水资料及其与时间的变化规律,用灰色系统理论建立模型,在满足精度要求的情况下用于需水量预测.并提出灰色模型预测方法可用于对不同水平年需水量的宏观控制,也可用于近期逐年需水量的预测.     

Performance of stochastic approaches for forecasting river water quality

This study analysed water quality data collected from the river Ganges in India from 1981 to 1990 for forecasting using stochastic models. Initially the box and whisker plots and Kendall's tau test were used to identify the trends during the study period. For detecting the possible intervention in the data the time series plots and cusum charts were used. The three approaches of stochastic modelling which account for the effect of seasonality in different ways, i.e. multiplicative autoregressive integrated moving average (ARIMA) model, deseasonalised model and Thomas–Fiering model were used to model the observed pattern in water quality. The multiplicative ARIMA model having both nonseasonal and seasonal components were, in general, identified as appropriate models. In the deseasonalised modelling approach, the lower order ARIMA models were found appropriate for the stochastic component. The set of Thomas–Fiering models were formed for each month for all water quality parameters. These models were then used to forecast the future values. The error estimates of forecasts from the three approaches were compared to identify the most suitable approach for the reliable forecast. The deseasonalised modelling approach was recommended for forecasting of water quality parameters of a river.     

Large metropolitan water demand forecasting using DAN2, FTDNN,and KNN models: A case study of the city of Tehran,Iran

Efficient operation of urban water systems necessitates accurate water demand forecasting. We present daily, weekly, and monthly water demand forecasting using dynamic artificial neural network (DAN2), focused time-delay neural network (FTDNN), and K-nearest neighbor (KNN) models for the city of Tehran. The daily model investigates whether partitioning weekdays into weekends and non-weekends can improve forecast results; it did not. The weekly model yielded good results by using the summation of the daily forecast values into their corresponding weeks. The monthly results showed that partitioning the year into high and low seasons can improve forecast accuracy. All three models offer very good results for water demand forecasting. DAN2, the best model, yielded forecasting accuracies of 96%, 99%, and 98%, for daily, weekly, and monthly models respectively.     

Inter‐sector water allocation in Israel, 2011–2050: urban consumption versus farm usage

According to the Water Authority of Israel, Israel's water economy is on the brink of a crisis. Demands are increasing, exceeding the capacity of the natural sources, which are being depleted. Water, as a resource in short supply, necessitated administrative actions in order to attain its efficient utilization, in accordance with the goals set by the state. In addition, the issue of water allocation in Israel is strongly connected to internal politics and not necessarily to a clear overall policy. This article presents a simulation model which examined a large number of different scenarios and returns the possible outcomes of water allocations in a routine situation of uncertainty. The findings show that even under ideal conditions, a water shortage in Israel is inevitable and urban consumption will demand the largest allocation of water. As a result, the Israeli rural sector will be required to reorganize the water allocation system and production structure.     

Energy consumption in an urban wastewater treatment plant: the case of Murcia Region (Spain)

Of all the costs associated with the operation and maintenance of wastewater treatment plants (WWTPs), those associated with energy use tend to be the most significant. From this point of view, it is hence logical that energy efficiency and saving strategies should be one of the current focuses of debate amongst those involved with the management of WWTPs. The present study's objective is to determine the correlation between size and energy consumption for a WWTP. To this end, 90 WWTPs currently in service were analysed and their energetic impact quantified in terms of kWh/m³ of water treated. The results obtained demonstrate that energy consumption ratio increases as the size of WWTPs decreases, either in terms of treatment volume or population equivalent served.     

公路水土流失预测方法研究

介绍了水土流失的危害及水土流失预测的定义,结合水土流失预测的原则、范围及时段,探讨了数学模型法这一预测方法的内容和优势及缺点,并结合其在实际工程中的应用效果,指出数学模型法准确有效,值得推广。     

多元线性回归模型预测重庆市用水量

采用多元线性回归法预测城市用水总量。通过主成分分析确定用水人口、国民生产总值、工业用水重复利用率、年降水量、建成区绿化覆盖率为有效自变量,应用Eviews软件建立数学模型,实现多元线性回归分析。根据残差图检验模型的有效性,结果表明模型回归效果良好,可为准确预测城市用水量提供参考。     

基于改进型GM(1,1)模型的城市水源水质指标预测

以武汉市主要供水水源的高锰酸盐指数为研究对象,应用经指数平滑改进后的GM(1,1)模型对9个水厂的水源水质进行预测.从预测精度来看,改进型GM(1,1)模型预测精度较常规GM(1,1)模型有所提高,5个改进型GM(1,1)模型精度高于常规型,3个持平,1个稍低.从预测结果来看,6个水厂供水水源水质预测发展趋势良好,3个水厂水源水质变化趋势较差.     

An examination of a partial least squares-based dynamic water quota model for urban industries: a case study of the Wuhan City hospital industry

The establishment of water quotas has an important practical significance in promoting urban standards for water utilization. Currently, industrial water quotas are highly arbitrary, inadequately restrictive, and impractical. This paper considers the example of the Wuhan City hospital industry. Common factors of industrial water use and major differences in water utilization structures were considered, and the principles of partial least squares (PLS) analysis were applied to establish an evaluation model for water utilization levels in this industry. Residuals were used to introduce the corresponding adjustment coefficients, and a dynamic model of water quotas in the hospital industry was constructed. Experimental results revealed that for this dynamic model, 80% of the samples examined exhibited errors of |20%| or less; thus, the dynamic approach was superior to traditional approaches for quota determination, where only 40% of samples had errors of |20%| or less.     

Urban water management strategies based on a total urban water cycle model and energy aspects – Case study for Tel Aviv

Global change pressures such as climate change, water scarcity, population growth, full urbanisation of catchments and rising energy costs may increasingly affect the urban water system of Tel Aviv. These challenges formed the incentive for a multidisciplinary Learning Alliance of water sector institutions to embark on a process to identify ways to improve sustainability of the city's water system. Sustainability indicators were identified and a whole-of-system water balance model (AquaCycle) was used to score the indicators for future scenarios and strategies. Strategies included rainwater harvesting, stormwater use, permeable pavements, and wastewater reuse. The effect of the strategies on total water imported into the city was a reduction of 10% by rainwater harvesting and 32% by wastewater reuse at cluster scale. The latter strategy reduced energy consumption from 2.89 kWh per m³ of volume of water used (import + reuse) in the current situation to 2.45 kWh per m³.     

城市供水规划的自回归分布滞后模型研究

通过对广州市年用水量的分析,考虑时间、区内生产总值、人口、对用水量的影响,运用并建立自回归分布滞后预测模型,对规划用水量进行预测,实例分析说明自回归分布滞后模型预测城市用水量是可行的,具有很高的精度。     

A decision support model to aid the management of crises in urban water supply systems (the UWC-MODEL)

The objective of this study was to develop a model for crisis management in urban water supply systems, able to assist the decision-making process to deal with the urban water crisis (UWC) by those responsible for these systems. The research methodology used for model development consisted of the following steps: (1) development of a decision support model for cases of crises in urban water supply systems (UWC-MODEL); (2) performing the sensitivity analysis of the UWC-MODEL; (3) verifying the UWC-MODEL; and (4) application of the UWC-MODEL. Different levels (socio-economic, management, urban, environmental and cultural) of the UWC problem were considered in the UWC-MODEL. It was based on the similarity between a weak UWC situation (or absence), strong UWC situation (or severe) and the actual case. Results of the application of the UWC-MODEL to the Administrative Region of Brasilia, in the Federal District of Brazil, indicated that actions related to cultural and environmental levels demonstrated a greater contribution for combating UWC. Actions such as environmental education programs, water conservation programs, and use of water saving equipment, were indicated by the UWC-MODEL to solve the UWC problem in this application to the real case.