scholarly journals The use of band similarity in urban water demand forecasting as a new method

2021 ◽  
Author(s):  
V. Yılmaz
Keyword(s):  
Water Consumption ◽  
Optimization Algorithm ◽  
Water Demand ◽  
Demand Forecasting ◽  
New Method ◽  
Urban Water ◽  
Artificial Bee Colony Optimization ◽  
Urban Water Demand ◽  
Demand Models ◽  
Similarity Method

Abstract Water consumptions and demands by persons vary from time to time and from location to location depending on countless factors, notably, population, socio-economic and climatic variables. Today, studies which create models on water consumption of persons, using numerous methods including artificial neural networks and regression models in this regard and ensure that projections are made are ongoing. In this study; parameters affecting water consumption were examined within the scope of the study area, and the parameter reduction was realized with the help of the Factor Analysis. Then, as a new method, the Band Similarity method was used together with the Artificial Bee Colony optimization algorithm, and urban water demand models were produced and the temporal dependence of the relevant variables was examined. As a result of the study, it was seen that the Band Similarity method improved the results obtained with the optimization algorithm and helped to understand the temporal dependencies of the variables. The fact that the Band Similarity method, which was put forward for the first time in its field, worked successfully and produced results, can be said to be the main contribution of this study to the knowledge.

Prediction of urban water demand on the basis of Engel's coefficient and Hoffmann index: case studies in Beijing and Jinan, China

2010 ◽  
Vol 62 (2) ◽  
pp. 410-418 ◽  
Author(s):  
Zhang Zhi-guo ◽  
Shao Yi-sheng ◽  
Xu Zong-xue
Keyword(s):  
Water Consumption ◽  
Water Demand ◽  
Urban Water ◽  
Industrial Water ◽  
Demand Model ◽  
Urban Water Demand ◽  
Model Based ◽  
Demand Models ◽  
Two Cities ◽  
Water Uses

Domestic and industrial water uses are the most important segment of urban water consumption. Traditional urban water demand models are usually based on water consumption quotas or statistical relationships, which usually overestimate urban water demands. The efficiency of domestic and industrial water uses is associated with living standards and levels of industrialization. The correlation coefficient between per capita water consumption and Engel's Coefficient in Beijing and Jinan is 0.62 and 0.53, respectively. These values are much smaller than the correlation between added industrial value and the Hoffmann Index in Beijing (0.95) and Jinan (0.90). Demand models for urban water consumption, including a domestic water demand model based on Engel's Coefficient and an industrial water demand model based on the Hoffmann Index, were developed in this study to predict urban water demand in Beijing and Jinan for 2020. The results show that the models can effectively capture the trends of urban water demand. Urban water consumption in these two cities from 1995 to 2007 was used to calibrate the models. The coefficients of determination for residential and industrial water uses were 0.93 and 0.68 in Beijing, and 0.79 and 0.64 in Jinan. Social, economic and climate scenarios for Beijing and Jinan in 2020 were generated according to the Urban Master Plans for these two cities, and they formed the basis for predictions of water consumption in 2020. The results show that total water consumption will increase by 67.6% in Jinan and 33.0% in Beijing when compared with consumption from 2007.

scholarly journals A Comparative Assessment of Variable Selection Methods in Urban Water Demand Forecasting

Water ◽  
2018 ◽  
Vol 10 (4) ◽  
pp. 419 ◽  
Author(s):  
Md Haque ◽  
Ataur Rahman ◽  
Dharma Hagare ◽  
Rezaul Chowdhury
Keyword(s):  
Variable Selection ◽  
Water Demand ◽  
Demand Forecasting ◽  
Comparative Assessment ◽  
Urban Water ◽  
Selection Methods ◽  
Water Demand Forecasting ◽  
Urban Water Demand

scholarly journals Artificial Neural Networks for Urban Water Demand Forecasting: A Case Study

2019 ◽  
Vol 1284 ◽  
pp. 012004 ◽  
Author(s):  
Leandro L Lorente-Leyva ◽  
Jairo F Pavón-Valencia ◽  
Yakcleem Montero-Santos ◽  
Israel D Herrera-Granda ◽  
Erick P Herrera-Granda ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Water Demand ◽  
Demand Forecasting ◽  
Urban Water ◽  
Water Demand Forecasting ◽  
Urban Water Demand ◽  
Artificial Neural

scholarly journals Forecasting Urban Water Demand Using Cellular Automata

Water ◽  
2020 ◽  
Vol 12 (7) ◽  
pp. 2038
Author(s):  
Laís Marques de Oliveira ◽  
Samíria Maria Oliveira da Silva ◽  
Francisco de Assis de Souza Filho ◽  
Taís Maria Nunes Carvalho ◽  
Renata Locarno Frota
Keyword(s):  
Cellular Automata ◽  
Water Consumption ◽  
Water Demand ◽  
Water Resource Management ◽  
Transition Probability ◽  
Management Strategies ◽  
Weight Of Evidence ◽  
Annual Growth Rate ◽  
Urban Water ◽  
Urban Water Demand

Associating the dynamic spatial modeling based on the theory of cellular automata with remote sensing and geoprocessing technologies, this article analyzes what would be the per capita consumption behavior of Fortaleza-CE, located in the Northeast of Brazil, in 2017, had there not been a period of water scarcity between 2013 and 2017, and estimates the future urban water demand for the years 2021 and 2025. The weight of evidence method was applied to produce a transition probability map, that shows which areas will be more subject to consumption class change. For that, micro-measured water consumption data from 2009 and 2013 were used. The model was validated by the evaluation of diffuse similarity indices. A high level of similarity was found between the simulated and observed data (0.99). Future scenarios indicated an increase in water demand of 6.45% and 10.16% for 2021 and 2025, respectively, compared to 2017. The simulated annual growth rate was 1.27%. The expected results of urban water consumption for the years 2021 and 2025 are essential for local water resources management professionals and scientists, because, based on our results, these professionals will be able to outline future water resource management strategies.

scholarly journals Water demand forecasting using extreme learning machines

2016 ◽  
Vol 28 (1) ◽  
pp. 37-52 ◽  
Author(s):  
Mukesh Tiwari ◽  
Jan Adamowski ◽  
Kazimierz Adamowski
Keyword(s):  
Water Demand ◽  
Demand Forecasting ◽  
Urban Water ◽  
Demand Model ◽  
Demand Prediction ◽  
Learning Machines ◽  
Water Demand Forecasting ◽  
Urban Water Demand ◽  
Learning Machine ◽  
Similar Accuracy

AbstractThe capacity of recently-developed extreme learning machine (ELM) modelling approaches in forecasting daily urban water demand from limited data, alone or in concert with wavelet analysis (W) or bootstrap (B) methods (i.e., ELM, ELMW, ELMB), was assessed, and compared to that of equivalent traditional artificial neural network-based models (i.e., ANN, ANNW, ANNB). The urban water demand forecasting models were developed using 3-year water demand and climate datasets for the city of Calgary, Alberta, Canada. While the hybrid ELMBand ANNBmodels provided satisfactory 1-day lead-time forecasts of similar accuracy, the ANNWand ELMWmodels provided greater accuracy, with the ELMWmodel outperforming the ANNWmodel. Significant improvement in peak urban water demand prediction was only achieved with the ELMWmodel. The superiority of the ELMWmodel over both the ANNWor ANNBmodels demonstrated the significant role of wavelet transformation in improving the overall performance of the urban water demand model.

Application of Time Series-Exponential Smoothing Model on Urban Water Demand Forecasting

2011 ◽  
Vol 183-185 ◽  
pp. 1158-1162 ◽  
Author(s):  
Jun Liang Liu ◽  
Xu Chen ◽  
Tie Jian Zhang
Keyword(s):  
Time Series ◽  
Water Demand ◽  
Demand Forecasting ◽  
Original Data ◽  
Exponential Smoothing ◽  
Forecasting Model ◽  
Urban Water ◽  
Analysis Software ◽  
Urban Water Demand ◽  
Statistical Analysis Software

Based on the traditional time series methods, this paper researched a time series-exponential smoothing model that is built by SPSS statistical analysis software. In the application of the model, the original data of water consumption were in processed by a particular smoothing method first.Secondly, the processed data were used to build a time series-exponential smoothing model. On error test, we found that this forecasting model has advantages of better effect, high precision and minor error on urban water demand forecasing.

scholarly journals Hybrid regression model for near real-time urban water demand forecasting

2017 ◽  
Vol 309 ◽  
pp. 532-541 ◽  
Author(s):  
Bruno M. Brentan ◽  
Edevar Luvizotto Jr. ◽  
Manuel Herrera ◽  
Joaquín Izquierdo ◽  
Rafael Pérez-García
Keyword(s):  
Regression Model ◽  
Real Time ◽  
Water Demand ◽  
Demand Forecasting ◽  
Urban Water ◽  
Water Demand Forecasting ◽  
Urban Water Demand
Sign in / Sign up

Export Citation Format

Share Document