Urban Water Demand Prediction Research Articles

Research on urban water demand prediction based on machine learning and feature engineering

ABSTRACT Urban water demand prediction is not only the foundation of water resource planning and management, but also an important component of water supply system optimization and scheduling. Therefore, predicting future water demand is of great significance. For univariate time series data, the issue of outliers can be solved through data preprocessing. Then, the data input dimension is increased through feature engineering, and finally, the LightGBM (Light Gradient Boosting Machine) model is used to predict future water demand. The results demonstrate that cubic polynomial interpolation outperforms the Prophet model and the linear method in the context of missing value interpolation tasks. In terms of predicting water demand, the LightGBM model demonstrates excellent forecasting performance and can effectively predict future water demand trends. The evaluation indicators MAPE (mean absolute percentage error) and NSE (Nash–Sutcliffe efficiency coefficient) on the test dataset are 4.28% and 0.94, respectively. These indicators can provide a scientific basis for short-term prediction of water supply enterprises.

Urban Water Demand Prediction Based on Attention Mechanism Graph Convolutional Network-Long Short-Term Memory

Urban Water Demand Prediction Based on Attention Mechanism Graph Convolutional Network-Long Short-Term Memory

Performance of TANN, NARX, and GMDHT Models for Urban Water Demand Forecasting: A Case Study in a Residential Complex in Qom, Iran

To keep the balance between demand and supply, methods based on the average per capita consumption were usually applied to predict water demand. More complicated models such as linear regression and time series models were developed for this purpose. However, after the introduction of artificial neural networks (ANNs), different applications of this method were used in the field of water supply management, especially for urban water demand prediction. In this study, multiple types of ANNs were studied to understand their suitability for a residential complex water demand prediction in the city of Qom, Iran. The results indicated that time series ANN (TANN), nonlinear autoregressive network with exogenous inputs (NARX), group method of data handling time series (GMDHT), and their wavelet counterparts (i.e., w-TANN and w-NARX) exhibited varying degrees of performance. Among the aforementioned models, w-NARX performed the best (based on the average overall error) with the test set root mean squared error (MSE) of 49.5 (m3 /h) and R of 0.93, followed by the GMDHT model with the test set MSE of 104 (m3 /h) and R of 0.97 and w-TANN with the test set MSE of 68.8 (m3 /h) and R of 0.91. In addition, the feedback connection in NARX compared to TANN demonstrated overall performance improvement.

A Water Evaluation and Planning-based framework for the long-term prediction of urban water demand and supply

Increased usage and non-efficient management of limited resources has created the risk of water resource scarcity. Due to climate change, urbanization, and lack of effective water resource management, countries like Pakistan are facing difficulties coping with the increasing water demand. Rapid urbanization and non-resilient infrastructures are the key barriers in sustainable urban water resource management. Therefore, there is an urgent need to address the challenges of urban water management through effective means. We propose a workflow for the modeling and simulation of sustainable urban water resource management and develop an integrated framework for the evaluation and planning of water resources in a typical urban setting. The proposed framework uses the Water Evaluation and Planning system to evaluate current and future water demand and the supply gap. Our simulation scenarios demonstrate that the demand–supply gap can effectively be dealt with by dynamic resource allocation, in the presence of assumptions, for example, those related to population and demand variation with the change of weather, and thus work as a tool for informed decisions for supply management. In the first scenario, 23% yearly water demand is reduced, while in the second scenario, no unmet demand is observed due to the 21% increase in supply delivered. Similarly, the overall demand is fulfilled through 23% decrease in water demand using water conservation. Demand-side management not only reduces the water usage in demand sites but also helps to save money, and preserve the environment. Our framework coupled with a visualization dashboard deployed in the water resource management department of a metropolitan area can assist in water planning and effective governance.

Hybridised Artificial Neural Network Model with Slime Mould Algorithm: A Novel Methodology for Prediction of Urban Stochastic Water Demand

Urban water demand prediction based on climate change is always challenging for water utilities because of the uncertainty that results from a sudden rise in water demand due to stochastic patterns of climatic factors. For this purpose, a novel combined methodology including, firstly, data pre-processing techniques were employed to decompose the time series of water and climatic factors by using empirical mode decomposition and identifying the best model input via tolerance to avoid multi-collinearity. Second, the artificial neural network (ANN) model was optimised by an up-to-date slime mould algorithm (SMA-ANN) to predict the medium term of the stochastic signal of monthly urban water demand. Ten climatic factors over 16 years were used to simulate the stochastic signal of water demand. The results reveal that SMA outperforms a multi-verse optimiser and backtracking search algorithm based on error scale. The performance of the hybrid model SMA-ANN is better than ANN (stand-alone) based on the range of statistical criteria. Generally, this methodology yields accurate results with a coefficient of determination of 0.9 and a mean absolute relative error of 0.001. This study can assist local water managers to efficiently manage the present water system and plan extensions to accommodate the increasing water demand.

Urban Water Demand Prediction for a City That Suffers from Climate Change and Population Growth: Gauteng Province Case Study

The proper management of a municipal water system is essential to sustain cities and support the water security of societies. Urban water estimating has always been a challenging task for managers of water utilities and policymakers. This paper applies a novel methodology that includes data pre-processing and an Artificial Neural Network (ANN) optimized with the Backtracking Search Algorithm (BSA-ANN) to estimate monthly water demand in relation to previous water consumption. Historical data of monthly water consumption in the Gauteng Province, South Africa, for the period 2007–2016, were selected for the creation and evaluation of the methodology. Data pre-processing techniques played a crucial role in the enhancing of the quality of the data before creating the prediction model. The BSA-ANN model yielded the best result with a root mean square error and a coefficient of efficiency of 0.0099 mega liters and 0.979, respectively. Moreover, it proved more efficient and reliable than the Crow Search Algorithm (CSA-ANN), based on the scale of error. Overall, this paper presents a new application for the hybrid model BSA-ANN that can be successfully used to predict water demand with high accuracy, in a city that heavily suffers from the impact of climate change and population growth.

A Novel Methodology for Prediction Urban Water Demand by Wavelet Denoising and Adaptive Neuro-Fuzzy Inference System Approach

Accurate and reliable urban water demand prediction is imperative for providing the basis to design, operate, and manage water system, especially under the scarcity of the natural water resources. A new methodology combining discrete wavelet transform (DWT) with an adaptive neuro-fuzzy inference system (ANFIS) is proposed to predict monthly urban water demand based on several intervals of historical water consumption. This ANFIS model is evaluated against a hybrid crow search algorithm and artificial neural network (CSA-ANN), since these methods have been successfully used recently to tackle a range of engineering optimization problems. The study outcomes reveal that (1) data preprocessing is essential for denoising raw time series and choosing the model inputs to render the highest model performance; (2) both methodologies, ANFIS and CSA-ANN, are statistically equivalent and capable of accurately predicting monthly urban water demand with high accuracy based on several statistical metric measures such as coefficient of efficiency (0.974, 0.971, respectively). This study could help policymakers to manage extensions of urban water system in response to the increasing demand with low risk related to a decision.

A hybrid model based on stacking and multi-correction mechanisms for urban water demand prediction

Water demand prediction is the key link for the effective operation of urban intelligent water supply system. Since the non-linearity and complex variability of water consumption, it is difficult for traditional water demand prediction models to guarantee high accuracy for a long period. Different holiday types and even tiny changes in temperatures can affect urban water demand seriously. This paper proposes a Stacking-based hybrid model which integrates multi-correction mechanisms to address these problems. A better stacking model is proposed to minimize the generalization error. The stability and reliability of predictions are improved through the design of multi-correction mechanisms such as high temperature weather compensation feature, holiday-type correction model and water quantity fluctuation correction model. Comparing different models before and after stacking also before and after correcting, the prediction accuracy of the proposed hybrid model is much higher and the predictions are more stable and reliable.

A distributed model for urban water demand prediction

The prediction of urban water demand is likely to play a significant role in the planning of urban water supply and drainage pipe network. The traditional water demand forecasting methods, including the water index method and the fuzzy water demand prediction model, are widely used with some deficiencies. The water demand prediction results varied among different water quantity indexes with subjectivity. The prediction results by fuzzy water demand prediction model, with fuzzy model structure, are lack of spatial distribution. Meanwhile, the process of urban water demand is closely related to the land use of urban unit. The difference of intensity and characteristic of water demand is obvious among different land use types. In this paper, a distributed urban water demand prediction model was established based on the relationship of water demand process, considering of the eight types of urban construction land use data and three types of major water demand data. In this model, we assumed the linear relationship between water demand and land use unit, ignored the fire water demand because with more randomness than other water demand process. The distributed model for urban water demand prediction was applied in Xiamen. We obtained the land use data and water demand data in 2004–2014 of Xiamen from official statistics. The monolayer construction area and the number of building stories in the residential units obtained by the high definition satellite image and the actual measurement were used to calculated the area of residential land unit, while the area of other land unit was obtained from official land planning in 2020 of Xiamen. The water demand parameters of every urban construction land unit were calibrated by PEST, and the rationality of parameters was analyzed. We observed the stability of the water demand parameters in the model while the results showed great similarity with different calibration period in the same validation period. The water demand of Xiamen and its spatial distribution in 2020 were predicted by the distributed water demand prediction model. The results showed that the water demand of Xiamen in 2020 will reach to 366.57 million tons, which will increase by 24.2% than that in 2014; the water demand intensity of residential land and industrial land will be greater than other types of construction land; the water demand intensity of residential land in Xiamen Island will be greater than the other residential land. The simulation results proved that the spatial distribution of water demand has positive correlation with population density in urban area. We observed the great difference of water demand intensity among different types land use with great difference in the process of urban water demand. The results also showed the excellent performance of the distributed model for urban water demand prediction both in calibration and validation when applied in Xiamen urban water demand prediction. Compared with the traditional urban water demand prediction model, the distributed water demand prediction model, with bright application prospect, can obtain the distributed urban water demand data with relatively stable parameters which can be determined by water demand data and land use data in the past years.

Water demand forecasting using extreme learning machines

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 Urban Water Demand Prediction Model by Using Particle Swarm Algorithm Based on Simulated Annealing

Water demand prediction is a complicated multifactor, multi-level non-linear system influenced by the urban population, industrial and economic level. The results of the prediction accuracy have a greater uncertainty and ambiguity. As a new cluster intelligent evolutionary algorithms, particle swarm optimization (PSO) is easy to understand, easy to implement ,and it is very suitable for non-linear model parameters fitting problems. At the same time, we will introduce the simulated annealing mechanism into particle swarm optimization algorithm, constructed the optimization algorithm of simulated annealing particle swarm (SA-PSO). In the paper, the optimization algorithm of simulated annealing particle swarm (SA-PSO) is applied to the field of water demand prediction. Example show that compared with the particle swarm algorithm, simulated annealing particle swarm optimization achieves a high prediction accuracy for urban water demand prediction, and it is strong applicability in the water demand forecast.

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

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.