Hybrid Artificial Neural Network-Geostatistics Model for Urban Water Consumption Prediction. A Case Study: Osku City مدل ترکيبي شبکه عصبي مصنوعي- زمين آمار براي پيش‌بيني مصرف آب شهري: مطالعه موردي: شهر اسکو

Journal Title: آب و فاضلاب - Year 2018, Vol 29, Issue 5

Abstract

Abstract The prediction of water consumption in urban basins is of immense importance for the management of water resources, especially in arid and semiarid countries. The lack of strong predictive tools, or perhaps the lack of experienced users to those tools, may contribute to problems in data interpretation and failure to reach consensus about the need for key water management actions. Therefore, it is extremely important to comprehend the spatiotemporal variations of the water demand for the management of water in such urban areas. In this paper, a hybrid, artificial neural network – geostatistics, model is presented for spatiotemporal prediction of water consumptions. The proposed model contains two individual stages. In the first stage, an artificial neural network is trained for each station for time series modeling of water demands, so that the model can predict the water demands in the next month. At the second stage, the predicted values of water demands at different stations are imposed to a calibrated geostatistics model in order to estimate water demands at any desired point in the city. This methodology is applied for the Osku city, in East Azerbaijan Province, Iran. The most appropriate set of input variables to the model are selected through a combination of domain knowledge and available data series. The results suggested that the hybrid model is a good choice for predicting water demands in the study area.

Authors and Affiliations

Rezagoli Ejlali

Keywords

Related Articles

Numerical Kinetic and Hydrodynamic Study of Advanced Oxidation Process for a Dye Degradation in a Fluidized Bed Reactor مطالعه عددي سينتيکي و هيدروديناميکي فرايند اکسايش پيشرفته براي حذف ماده رنگزا در راکتور بسترسيال

Abstract Organic contaminants in industrial wastewater are mostly non-biodegradable, so advanced oxidation processes (AOPs) should be used as a promising alternative for conventional treatment processes. In this investi...

مشارکت خصوصي در بخش عمومي آب و فاضلاب: هزينه‌هاي مبادله، ضد انحصار و تعرفه‌گذاري غيرخطي

Public-Private Partnership in Water and Wastewater Industry Transaction Costs, Antitrust, and Nonlinear Pricing Adopting a long-term horizon in planning for investment in water and wastewater projects is especially impor...

مطالعه جذب سطحي حذف رنگزاي مالاخيت سبز با استفاده از گاما آلوميناي عامل‌دار شده

Adsorption of Malachite Green Dye Using Modified γ-Alumina Modified γ-Alumina was used for the adsorption of the cationic dye malachite green (MG) from aqueous solutions. The properties of the modified particles were init...

بررسي عملكرد نانوذرات آهن در كاهش بار آلي فاضلاب

Performance of Iron Nanoparticles in Removing BOD from Wastewater Nanotechnology has nowadays found applications in a wide variety of fields including industrial effluent treatment. In this study, iron nanoparticles wer...

عوامل مؤثر بر گرفتگي غشاء در راکتور زيستي غشايي

Factors Influencing Membrane fouling in the MBR Proces Biological processes of wastewater treatmnent have found wide applications due to their lower costs and higher efficiency. Membrane bioreactors (MBR’s) form one grou...

Download PDF file
  • EP ID EP463346
  • DOI 10.22093/wwj.2017.6731.1481
  • Views 79
  • Downloads 0

How To Cite

Rezagoli Ejlali (2018). Hybrid Artificial Neural Network-Geostatistics Model for Urban Water Consumption Prediction. A Case Study: Osku City مدل ترکيبي شبکه عصبي مصنوعي- زمين آمار براي پيش‌بيني مصرف آب شهري: مطالعه موردي: شهر اسکو. آب و فاضلاب, 29(5), 99-111. https://europub.co.uk/articles/-A-463346