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.     

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.     

Assessment of predictive uncertainty within the framework of water demand forecasting using the Model Conditional Processor (MCP)

This paper presents an application of the Model Conditional Processor (MCP), originally proposed by Todini (2008) within the hydrological framework, to assess the predictive uncertainty in water demand forecasting related to water distribution systems. The MCP enables us to assess the probability distribution of the future water demand conditional on the forecasts provided by two or more deterministic forecasting models. In the numerical application described here, where two years of hourly water demand data for a town in northern Italy are considered, two forecasting models are applied in order to forecast hourly water demands from 1 to 24 hours ahead: the first model has a modular structure comprising a periodic component which reflects the long-term effects and a persistence component which represents the short-term memory of the process; the latter is based on neural networks. The results highlight the effectiveness of the approach, provided that the data set used for the MCP parameterization is properly selected so as to be actually representative of the accuracy of the real-time water demand forecasting models.     

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.     

Elasticity estimation and forecasting: An analysis of residential electricity demand in Brazil

Spatiotemporal models to estimate electricity demand are scarce in the existing literature. In this paper, we compare three models to estimate elasticities and forecast demand for residential electricity in Brazil. The Dynamic Spatial Durbin Model presented the best goodness of fit, with results that confirm the need to consider spatial dependence in the Brazilian regions. The results showed temporal inertia, inelasticity of demand concerning price and income, and a significant impact of the temperature and the number of households connected to the grid. We conclude that omitting the spatiotemporal dynamic could lead to bias in the models used by Brazilian utilities.     

Managing water demand by contract: a survey of conservation outsourcing in China

The research was to gain insight into the characteristics, driving forces and barriers, specifications, and other issues of water conservation outsourcing contracts (OSCs) in China. Our analysis is based on information obtained from a pre-coded questionnaire, an assessment of OSC documents, and project on-site visits and interviews. The result shows that both parties of the OSCs lack knowledge and experience in preparing contracts. All eight contract documents are underspecified, which is the key reason for the existing disputes found in all OSCs studied. Recommendations are provided by this research to improve China's OSCs in the future.     

Presentation of machine learning methods to determine the most important factors affecting road traffic accidents on rural roads

The purpose of this research was to develop statistical and intelligent models for predicting the severity of road traffic accidents (RTAs) on rural roads. Multiple Logistic Regression (MLR) was used to predict the likelihood of RTAs. For more accurate prediction, Multi-Layer Perceptron (MLP) and Radius Basis Function (RBF) neural networks were applied. Results indicated that in MLR, the model obtained from the backward method with the correct percent of 84.7% and R² value of 0.893 was the best method for predicting the likelihood of RTAs. Also, MLR showed that the variables of not paying attention to the front not paying attention to the frontroad ahead, followed byand then vehicle-motorcycle/bike accidents were the greatest problems. Among the models, MLP had a better performance, so that the prediction accuracy of MLR, MLP, and RBF were 84.7%, 96.7%, and 92.1%, respectively. MLP model, due to higher accuracy, showed that the variable of reason of accident had the highest effect on the prediction of accidents, and considering MLR results, the variables of not paying attention to the front and then vehicle-motorcycle/bike accidents had the most influence on the occurrence of accidents. Therefore, motorcyclists and cyclists are more prone to accidents, and appropriate solutions should be adopted to enhance their safety.     

Predicting and quantifying the effect of variations in long-term water demand on micro-hydropower energy recovery in water supply networks

To improve water supply energy efficiency micro-hydropower turbines can be installed within networks at locations of excess pressure. However, future changes in flow rates and pressures at these locations could render an installed turbine unsuitable. It is therefore important that long term changes in flow conditions at potential turbine locations be considered at initial feasibility/design stages.

Using historical data over a ten-year period, this paper predicts the effects of changes in water flow rates at potential turbine locations in Ireland and the UK. Results show that future flow rates at these locations could be predicted with an R² of up to 66% using multivariate linear regression and up to 93% using artificial neural networks. Flow rates were shown to vary with population, economic activity and climate factors. Changes in flow rate were shown to have a significant impact on power output within the design life of a typical hydropower turbine.     

A sustainable framework for water resources management in an urban watershed: the case of Volos,Greece

The implementation of sustainable development principles in water resources management refers to an integrated management and coordination of the entirety of the actions and interventions that concern the water ecosystem, or parts of it, within a watershed. This procedure is accomplished through the development and application of an overall management plan at a hydrological basin level. This concept was followed by the water resources management plan of the city of Volos' watershed, which is presented in this paper. The main objective is the choice of the best set, among others, of hydraulic projects, which will be able to re-establish the balance in the basin's deficient water budget, satisfying at the same time future urban water demand. Decision making was carried out using a GIS tool and involved traditional water capture hydraulic projects on the one hand and sustainable water saving measures on the other. The whole procedure is being developed in an area with serious environmental problems, concerning mainly the groundwater resources. The particularity here is that the alternative solutions strongly depend on administrative agreement and consensus between relevant authorities.     

Prediction of railway track geometry deterioration using artificial neural networks: a case study for Turkish state railways

The main goal of this paper is to model track geometry deterioration using a comprehensive field investigation gathered over a period of 2 years on approximately 180 km of railway line. Artificial neural networks (ANNs) were adapted for this research. The railway line was divided into analytical segments (ASs). For each AS, the following data were collected: track structure, traffic characteristics, track layout, environmental factors, track geometry, and maintenance and renewal data. ANN models were developed for the main track geometry parameters and produced significant relationships between the variables. In addition, sensitivity analyses were performed to compute the importance of each predictor in determining the neural network. The obtained results proved that ANN may be an alternative method for predicting track geometry deterioration.     

Using the bimonthly water balance of a non-fully monitored water distribution network with seasonal water demand peaks to define its actual NRW level: the case of Kos town,Greece

Water losses in pipe networks are usually the biggest ‘water use’ due to the high leakage occurring. The need for conservative water use is today more pressing than ever due to the stressful climate change conditions, forcing water utilities to consider applying effective Non Revenue Water reduction strategies. The assessment of a network's current operating status based on the IWA water balance (WB) is a good start. Although IWA suggests the WB to be annually assessed, this is not ideal for networks experiencing seasonal demand peaks, like in Kos town, capital of Kos Island in Greece. The WB for Kos town network was assessed on a bimonthly basis, following the water billing period used by the local water utility. The results revealed that higher real loss rates occur during the lower water demand periods due to the higher operating pressures. The annual WB can not reveal water loss peak timing.     

Context driven policy design in urban water management. A case study of Windhoek,Namibia

Urban water management in the southern cities of Namibia is composed through both a formal and an informal system. In the formal system, controlling demand is the key issue, and in the informal system, an improved accessibility to water is fundamental. The main issue raised in this paper is how authorities can support an ever-increasing poor population with water and at the same time keep demand among households with private water connections at a reasonable level. To decrease the demand for water in Windhoek, a thorough water demand management strategy (WDM) was launched in 1994. Water managers showed a high level of adaptability to the alarming water situation. One of the lessons learned from the implementation in Windhoek is that dedicated people with active involvement and vision are important for successful WDM. The budget must be allocated on a continuous basis for the implementation of certain WDM measures and a degree of flexibility among water users is important for the strategy to be successful. The dual situation experienced in cities in the South where both a need to expand services, and at the same time control demand, calls for a new approach in urban water management. Strategies need to be socially specific and flexible to changing pre-conditions. Therefore, a context driven policy design is advocated.     

The transformation of the agroforestry landscape in the nineteenth century: a case study in southern Quebec (Canada)

Although recent landscape changes have been extensively studied, we possess very little information about the nature and extent of changes before aerial photographs were available. To contribute to this knowledge, we propose to explore the information within the Canadian censuses of the nineteenth century, documentary sources still very underused in landscape dynamics studies. The importance of these data lies in the fact that information is provided at the scale of each lot between 1842 and 1871, and at the township scale for subsequent years (1881–1951). In this study, nominative data provided for a rural township (139 km²) located in southern Quebec were coupled with detailed information about geomorphologic features using GIS.The analyses indicated two main phenomena. First, characterization of global landscape dynamics revealed the extent and rapidity of change. The evolution of land-use shows an increase of about 40% in improved areas between 1842 and 1871. while cumulative data show improved areas occupying nearly 83% of the total areas in 1891. These results contrast with recent landscape dynamics (1958–1993) which display relatively minor changes. Second, at the landscape type scale as well as at the surface deposit scale, analysis of nominative data failed to show any clear relationship between landscape dynamics and the spatial entities considered, whereas recent land-use patterns are closely linked to surface deposits. Thus, constant fluctuation in the agroforestry landscape and the lack of influence of abiotic characteristics on land-use dynamics represent two specific characteristics of this nineteenth century landscape.     

The role of water utilities in urban greening: A case study of Melbourne,Australia

Melbourne's “Greening the West” (GTW) initiative is a successful example of water utilities actively supporting urban greening through facilitating collaboration between stakeholders. GTW was convened by City West Water in 2011, to bring together 23 partner organisations to protect and enhance urban greening to support community wellbeing. This research involved interviews to determine how GTW works, its challenges, factors for success, achievements, areas for improvement, future directions, and implications. It is found that the existence of GTW has resulted in an additional one million trees planted in Melbourne's western suburbs, and has caused a significant cultural shift within local government.     

Daily streamflow modelling using autoregressive moving average and artificial neural networks models: case study of Çoruh basin,Turkey

Streamflow modelling is a quite important issue for water resources system planning and management projects, such as dam construction, reservoir operation and flood control. This study demonstrates the application of artificial neural networks (ANN) and autoregressive moving average (ARMA) models for modelling daily streamflow in Çoruh basin, Turkey, where there are numerous highly critical power plants either under construction or being projected. Daily streamflow records from nine gauging stations located in the basin were used in this study. In the first phase of our study, ANN and ARMA models were obtained using daily streamflow. In the second phase, 100 synthetic streamflow series were generated using previously determined ANN and ARMA models in order to ensure the preservation of main statistical characteristics of the historical time series. The results have showed that the historical time series have similar statistical parameters to those of the generated time series at 95% confidence level.     

Achieving ambidexterity in large,complex engineering projects: a case study of the Sutong Bridge project

Complex engineering projects typically face unique challenges that demand both exploring innovative solutions and exploiting existing capabilities. However, it is difficult to manage both exploitation and exploration in the same organizational unit owing to the different organizational support required for each. The solutions to managing the tension involve separating the two approaches into separate organizational units—structural separation, or separating by time—temporal separation, or by creating an organizational context that empowers employees to pursue both. Structural separation may not work because of the predominant need for integration at project level due to the fragmented nature of the construction industry and the co-location of project team. Instead, temporal separation could be an effective mechanism of separation. Creating the appropriate project context could facilitate project ambidexterity. Extant studies on ambidexterity focus on the organizational level which may not apply at project level. This study examines the effects of the above three antecedents to project ambidexterity. The key findings are that ambidexterity can be achieved during the limited lifespan of a complex engineering project through: (1) partitioning the two approaches in different project phases and then integrating the two; (2) implementing policies and financial support aiming at facilitating contextual ambidexterity both at and above project level.     

An artificial neural network model for the prediction of critical submergence for intake in a stratified fluid medium

Density differences may occur because of temperature differentials, suspended sediments, dissolved salts or other chemicals. Most of the large surface reservoirs are stably stratified throughout most, or all, of the year. One of the means of assisting the management is to allow a selective withdrawal from the reservoir. And while an intake is used for withdrawal (from the lower layer), a maximum discharge is required not allowing the uptake of the upper layer fluids. The value of the intake's vertical distance from the upper layer elevation (submergence) when the upper layer fluids begin to be drawn into the intake is known as ‘critical submergence’. In this study, the critical submergence for a circular intake pipe in a stratified body (which has different layer thickness) is investigated. Experiments were conducted on a vertically flowing downward intake pipe in a still-water reservoir. Artificial neural network (ANN) models and formulas, which are found by the theoretical analysis of critical spherical sink surface (CSSS), are used for the analysis of experimental results. The CSSS has the same centre and discharge as the intake. The ANN model and CSSS results are compared with the experimental results.     

Impact of urbanization on the quality of water in a natural reservoir: a case study with the Deepor Beel in Guwahati city,India

The Deepor Beel is a natural, freshwater wetland in the south-west corner of Guwahati, India. The Beel harbours a large number of migratory aquatic birds, especially in winter, and is a Ramsar site since 2002. The wetland provides livelihood to the people of the surrounding villages through collection and sale of fish, nymphaea nuts and flower, ornamental fish, orchids, medicinal plants, etc. The water quality of the Beel is threatened by excessive fishing, hunting of water birds, pollution from pesticides and fertilizers and infestation by water hyacinth. The present work reports on the water quality of the wetland by continuous monitoring from February to July, covering the dry, temperate period and the wet, hot and humid period. Sampling was carried out at 10 sites for physical and aggregate properties, metallic and nonmetallic constituents, organic contaminants and microbiological parameters.     

Ecological network analysis of an urban water metabolic system: Model development, and a case study for Beijing

Using ecological network analysis, we analyzed the network structure and ecological relationships in an urban water metabolic system. We developed an ecological network model for the system, and used Beijing as an example of analysis based on the model. We used network throughflow analysis to determine the flows among components, and measured both indirect and direct flows. Using a network utility matrix, we determined the relationships and degrees of mutualism among six compartments - 1) local environment, 2) rainwater collection, 3) industry, 4) agriculture, 5) domestic sector, and 6) wastewater recycling - which represent producer, consumer, and reducer trophic levels. The capacity of producers to provide water for Beijing decreased from 2003 to 2007, and consumer demand for water decreased due to decreasing industrial and agricultural demand; the recycling capacity of reducers also improved, decreasing the discharge pressure on the environment. The ecological relationships associated with the local environment or the wastewater recycling sector changed little from 2003 to 2007. From 2003 to 2005, the main changes in the ecological relationships among components of Beijing's water metabolic system mostly occurred between the local environment, the industrial and agricultural sectors, and the domestic sector, but by 2006 and 2007, the major change was between the local environment, the agricultural sector, and the industrial sector. The other ecological relationships did not change during the study period. Although Beijing's mutualism indices remained generally stable, the ecological relationships among compartments changed greatly. Our analysis revealed ways to further optimize this system and the relationships among compartments, thereby optimizing future urban water resources development.