Water Demand Prediction Research Articles

Climate Change Impacts on Agricultural and Industrial Water Demands in the Beijing–Tianjin–Hebei Region Using Statistical Downscaling Model (SDSM)

As a politically and culturally important city cluster, the Beijing–Tianjin–Hebei (BTH) region is the most prominent area in China where the imbalance between the supply and demand of water resources restricts the sustainable and healthy development of the regional social economy. In the context of global warming, research into water demand prediction that takes climate change into consideration would be more in line with the strategic goal of the low-carbon sustainable development of future cities. At the same time, the prediction of agricultural water demands against a background of climate change is urgently needed, while industrial water consumption is weakly correlated with climate change, an investigation of the statistical relationship between the two is needed. Thus, in this paper, future climate data from the BTH region under the scenarios RCP2.6, RCP4.5 and RCP8.5 were generated using a statistical downscaling model, and then coupled with agricultural and industrial water demand prediction models to simulate and analyze the impact of climate change on the agricultural and industrial water demands, respectively. The results show that during the forecast period (2020–2035), the reference crop evapotranspiration (ET0) growth rates in the Beijing, Tianjin and Hebei areas under the RCP2.6 scenario are 1.438 mm·a−1, 1.393 mm·a−1 and 2.059 mm·a−1, respectively. Under the RCP4.5 scenario, they are 2.252 mm·a−1, 2.310 mm·a−1 and 2.827 mm·a−1, respectively. Under the RCP8.5 scenario, they are 3.123 mm·a−1, 2.310 mm·a−1 and 2.141 mm·a−1, respectively. Furthermore, under each climate scenario, the increase in evapotranspiration in the Hebei area is the largest, followed by that in the Tianjin area, and that in the Beijing area is the smallest. For water consumption per CNY 10,000 of industrial added value during the forecast period, under the three different climate scenarios, a downward trend is seen in the Beijing area, with rates of 0.158, 0.153 and 0.110, respectively, but in the Tianjin area, there is an upward trend, with an upward tendency in rates of 0.170, 0.087 and 0.071, and an upward trend in the Hebei area, with an upward tendency in rates of 0.254, 0.071 and 0.036, respectively. This study will help the BTH region to rationally allocate agricultural and industrial water against the background of future climate change, and strengthen the coordination and cooperation between the different regions to promote the healthy and sustainable development of the cities.

A Study on Developing an AI-Based Water Demand Prediction and Classification Model for Gurye Intake Station

Drought has significant impacts on both society and the environment, but it is a gradual and comprehensive process that affects a region over time. Therefore, non-structural measures are necessary to prepare and respond to the damage caused by drought in a flexible manner according to the stage of drought. In this study, an AI-based water demand prediction model was developed using deep neural network (DNN) and long short-term memory (LSTM) models. The model was trained from 2004 to 2015 and verified from 2016 to 2021. Model accuracy was evaluated using data, with the LSTM model achieving a correlation coefficient (CC) of 0.95 and normalized root mean square error (NRMSE) of 8.38, indicating excellent performance. The probability of the random variable X falling within the interval [a,b], as described by the probability density function f(x), was calculated using the water demand data. The cumulative distribution function was used to calculate the probability of the random variable being less than or equal to a specific value. These calculations were used to establish the criteria for each stage of the crisis alert system. Decision tree (DT) and random forest (RF) models, based on AI-based classification, were used to predict water demand at the Gurye intake station. The models took into account the impact of water demand from the previous day, as well as the effects of rainfall, maximum temperature, and average temperature. Daily water demand data from the Gurye intake station and the previous day’s rainfall, maximum temperature, and average temperature data from a nearby observatory were collected from 2004 to 2021. The models were trained on data from 2004 to 2015 and validated on data from 2016 to 2021. Model accuracy was evaluated using the F1-score, with the random forest model achieving a score of 0.88, indicating excellent performance.

Study on the Optimal Allocation of Water Resources Based on the Perspective of Water Rights Trading

Water rights trading plays an important role in the market mechanism to optimize the allocation of water resources. This study takes Luxian county of Sichuan province as the research area. Based on the prediction of water supply and demand, this study aims to achieve minimum water shortage and maximum economic benefits for regional water distribution, and introduces a water-saving reward and water price punishment mechanism to construct a two-layer collaborative regulation model of water rights trading for water users. The self-improved elite strategy and cogenetic algorithm (NSGA II-S) are used to solve the optimization model, and the optimal allocation of water resources and water rights trading in different towns in the planning year (2025 and 2030) under different flat and dry scenarios is studied. The results show that there would be an obvious problem in the uneven distribution of water resources between supply and demand in 2025 and 2030. The overall water shortage rates in the flat and dry scenario areas in 2025 are 13.71% and 31.99%, respectively, and the overall water shortage rates in the flat and dry scenario areas in 2030 are 11.55% and 31.94%, respectively. Water rights trading can increase the economic benefit value, with the economic benefit increasing by an average of CNY 614 million in all scenarios, an average increase of 8.68%. The research results could be helpful in alleviating the contradiction between the supply and demand of regional water resources and provide a theoretical basis for optimizing water resource allocation by means of water rights trading in the region.

Crop Water Requirement Prediction Method Based on EEMD-Attention-LSTM Model

Crop water demand prediction is an important part of Precision agriculture. Due to the nonlinear relationship between input variables (weather data, soil moisture, and crop type) and output variables (crop water demand), it is difficult to accurately predict crop water demand. This article proposes a method for predicting crop water demand based on the EEMD Attention LSTM model. The model combines the ensemble empirical mode decomposition (EEMD), attention mechanism (Attention), and Long short-term memory (LSTM) neural networks to capture the changes in different scales of input variables. It selectively focuses on the relevant parts of the input sequence when making predictions. The performance of the EEMD attention LSTM model was evaluated on the historical crop water demand data set and compared with other prediction models such as RNN, LSTM, and EMD-LSTM. It shows that the model is superior to other methods in terms of Mean squared error and mean absolute error. When the relationship between input variables and output variables is nonlinear, the EEMD-attention-LSTM model is a powerful tool for crop water demand prediction.

Integrated dynamic multi-threshold pattern recognition with graph attention long short-term neural memory network for water distribution network losses prediction: An automated expert system

Water loss is a common and critical problem in water distribution networks, resulting in a decrease in wastewater and user experience. In this research, prediction-classification framework based on deep learning (i.e., graph attention long short-term neural memory network (GA-LSTM)) is proposed. Dynamic multi-threshold pattern recognition (DMTPR) was developed to identify and classify losses. To improve the model's reliability, we performed hyperparameter optimisation, trained and verified using one year's operation data of a real pipe network, and compared it with the previous methods. In addition, the influence of different aggregation ranges on the accuracy and stability of the model was analysed. The results showed that the GA-LSTM-DMTPR framework can be used as a reliable tool for practical applications because it provides high-precision and high-stability water demand prediction and realises accurate loss identification and classification. This is owing the potential of the model to aggregate the spatial and temporal multi-dimensional information.

A Machine Learning Framework for Enhancing Short-Term Water Demand Forecasting Using Attention-BiLSTM Networks Integrated with XGBoost Residual Correction

Accurate short-term water demand forecasting assumes a pivotal role in optimizing water supply control strategies, constituting a cornerstone of effective water management. In recent times, the rise of machine learning technologies has ushered in hybrid models that exhibit superior performance in this domain. Given the intrinsic non-linear fluctuations and variations in short-term water demand sequences, achieving precise forecasts presents a formidable challenge. Against this backdrop, this study introduces an innovative machine learning framework for short-term water demand prediction. The maximal information coefficient (MIC) is employed to select high-quality input features. A deep learning architecture is devised, featuring an Attention-BiLSTM network. This design leverages attention weights and the bidirectional information in historical sequences to highlight influential factors and enhance predictive capabilities. The integration of the XGBoost algorithm as a residual correction module further bolsters the model’s performance by refining predicted results through error simulation. Hyper-parameter configurations are fine-tuned using the Keras Tuner and random parameter search. Through rigorous performance comparison with benchmark models, the superiority and stability of this method are conclusively demonstrated. The attained results unequivocally establish that this approach outperforms other models in terms of predictive accuracy, stability, and generalization capabilities, with MAE, RMSE, MAPE, and NSE values of 544 m3/h, 915 m3/h, 1.00%, and 0.99, respectively. The study reveals that the incorporation of important features selected by the MIC, followed by their integration into the attention mechanism, essentially subjects these features to a secondary filtration. While this enhances model performance, the potential for improvement remains limited. Our proposed forecasting framework offers a fresh perspective and contribution to the short-term water resource scheduling in smart water management systems.

Real-time water demand pattern estimation using an optimized extended Kalman filter

This study presents a hybrid approach for the estimation of real-time water demand multipliers using the Kalman filter (KF) and extended Kalman filter (EKF). Multiple Linear Regression (MLR) and Nonlinear Regression (NLR) models were applied to predict water demand multipliers at each time step with historical flow data. The estimation performance of EKF is highly affected by the state noise covariance matrix (Q) and the measurement noise covariance matrix (R). An inappropriate value ofQandRsignificantly degrades the EKF’s performance and makes the filter diverge. So, the particle swarm optimization algorithm (PSO) was used to tune the noise covariance matricesQandRat each time step of EKF. Then the optimal values of noise covariance matrices are inserted in the real-time water demand multiplier estimation process. To find the optimal values ofQandR, the mean absolute percentage error (MAPE) between measured and simulated pressure was minimized. The proposed method was evaluated in Net1 and Net3 benchmark networks. The root means square error (RMSE) of EKF-PSO estimated water demand multiplier for Net1 and Net3 were 0.063 and 0.198, respectively. The simulation results indicated that the EKF-PSO algorithm was more accurate than the conventional EKF algorithm. Moreover, the KF-PSO performed poorly when dealing with nonlinear hydraulic systems.

An interval water demand prediction method to reduce uncertainty: A case study of Sichuan Province, China

Effective prediction of water demand is a prerequisite for decision makers to achieve reliable management of water supply. Currently, the research on water demand prediction focuses on point prediction method. In this study, we constructed a GA-BP-KDE hybrid interval water demand prediction model by combining non-parametric estimation and point prediction. Multiple metaheuristic algorithms were used to optimize the Back-Propagation Neural Network (BP) and Kernel Extreme Learning Machine (KELM) network structures. The performance of the water demand point prediction models was compared by the Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), Kling-Gupta Efficiency (KGE), computation time, and fitness convergence curves. The kernel density estimation method (KDE) and the normal distribution method were used to fit the distribution of errors. The probability density function with the best fitting degree was selected based on the index G. The shortest confidence interval under 95% confidence was calculated according to the asymmetry of the error distribution. We predicted the impact indicator values for 2025 using the exponential smoothing method, and obtained water demand prediction intervals for various water use sectors. The results showed that the GA-BP model was the optimal model as it exhibited the highest computational efficiency, algorithmic stability, and prediction accuracy. The three prediction intervals estimated after adjusting the KDE bandwidth parameter covered most of the sample points in the test set. The prediction intervals of the four water use sectors were evaluated as F values of 1.6845, 1.3294, 1.6237, and 1.3600, which indicates high accuracy and quality of the prediction intervals. The mixed water demand interval prediction based on GA-BP-KDE reduces the uncertainty of the point prediction results and can provide a basis for water resource management by decision makers.

Developing a hybrid model for accurate short-term water demand prediction under extreme weather conditions: a case study in Melbourne, Australia

Accurate prediction of short-term water demand, especially, in the case of extreme weather conditions such as flood, droughts and storms, is crucial information for the policy makers to manage the availability of freshwater. This study develops a hybrid model for the prediction of monthly water demand using the database of monthly urban water consumption in Melbourne, Australia. The dataset consisted of minimum, maximum, and mean temperature (°C), evaporation (mm), rainfall (mm), solar radiation (MJ/m2), maximum relative humidity (%), vapor pressure (hpa), and potential evapotranspiration (mm). The dataset was normalized using natural logarithm and denoized then by employing the discrete wavelet transform. Principle component analysis was used to determine which predictors were most reliable. Hybrid model development included the optimization of ANN coefficients (its weights and biases) using adaptive guided differential evolution algorithm. Post-optimization ANN model was trained using eleven different leaning algorithms. Models were trained several times with different configuration (nodes in hidden layers) to achieve better accuracy. The final optimum learning algorithm was selected based on the performance values (regression; mean absolute, relative and maximum error) and Taylor diagram.

利用线性回归分析、BP 神经网络与随机森林的枣树灌溉系统设计

This paper evaluates linear regression analysis, BP neural network, and a random forest prediction model for the prediction of jujube water demand. The results highlight that the R2 of the random forest is 0.941 and the residual distribution is the most stable. Hence, the random forest is more suitable for prediction, and therefore, an intelligent irrigation system is established employing random forest, where the cloud server is the upper computer and a Raspberry Pi is the lower computer, and at the same time, a PC and a mobile interface was built to present various information about the developed irrigation system.

Unraveling the Impact of COVID-19 Pandemic Dynamics on Commercial Water-Use Variation

Water use was impacted significantly by the COVID-19 pandemic. Although previous studies quantitatively investigated the effects of COVID-19 on water use, the relationship between water-use variation and COVID-19 dynamics (i.e., the spatial-temporal characteristics of COVID-19 cases) has received less attention. This study developed a two-step methodology to unravel the impact of COVID-19 pandemic dynamics on water-use variation. First, using a water-use prediction model, the water-use change percentage (WUCP) indicator, which was calculated as the relative difference between modeled and observed water use, i.e., water-use variation, was used to quantify the COVID-19 effects on water use. Second, two indicators, i.e., the number of existing confirmed cases (NECC) and the spatial risk index (SRI), were applied to characterize pandemic dynamics, and the quantitative relationship between WUCP and pandemic dynamics was examined by means of regression analysis. We collected and analyzed 6-year commercial water-use data from smart meters of Zhongshan District in Dalian City, Northeast China. The results indicate that commercial water use decreased significantly, with an average WUCP of 59.4%, 54.4%, and 45.7%during the three pandemic waves, respectively, in Dalian. Regression analysis showed that there was a positive linear relationship between water-use changes (i.e., WUCP) and pandemic dynamics (i.e., NECC and SRI). Both the number of COVID-19 cases and their spatial distribution impacted commercial water use, and the effects were weakened by restriction strategy improvement, and the accumulation of experience and knowledge about COVID-19. This study provides an in-depth understanding of the impact of COVID-19 dynamics on commercial water use. The results can be used to help predict water demand under during future pandemic periods or other types of natural and human-made disturbance.

Clean Water Demand Prediction Model Using The Long Short Term Memory (LSTM) Method

Cities or districts as population centers with various service facilities, really need the provision of clean water. The agency that handles clean water in Indonesia is the Regional Drinking Water Company (PDAM). PDAMs were established in every city and district in Indonesia as agencies that serve the community's need for clean water. One of them is the Regional Public Company (Perumda) Tirta Pakuan and as time goes by the number of customers will definitely increase so that the need for clean water will also increase. The purpose of this research is to create a Clean Water Demand Prediction Model using the Long Short Term Memory (LSTM) Method to find the most optimal modeling. The data in this study were obtained from data reports is from Perumda Tirta Pakuan. The prediction model development process is carried out through Visual Studio Code tools. To find a model with the smallest error rate using various ratios, namely 80:20, 70:30, 60:40, and 50:50, then testing is also carried out based on the number of different hyperparameter values in batch sizes 5, 10, 15, 20, 25 and max epoch 50, 100, 150, 200, 250. From all the experiments that have been carried out, the most optimal is batch size 5 and epoch 50 with a ratio of 60:40 for water production to get RMSE 0.4862 and MAPE 2.5252% while for the amount of water use with a ratio of 50:50 get RMSE 0.4674 and MAPE of 2.5163%.

Comparison of deep learning approaches for forecasting urban short-term water demand a Greater Sydney Region case study

Accurate water demand forecasting is essential for water utilities for effective water planning and pump scheduling. To conduct effective water planning and pump scheduling, Sydney Water needs a reliable method for predicting water demand. Short-term water demand forecasting deep learning- based models have been applied to different datasets collected from various water plants in the Greater Sydney region. This paper uses correlation analysis, the attention mechanism and a deep convolutional neural network to identify and study the importance of n number of factors that inform water prediction in the Greater Sydney region. The aim of this study is to develop, evaluate and compare multi- variate input deep learning-based models to predict water demand in various locations in the Greater Sydney region. This paper investigates five models — the recurrent neural network (RNN), long short- term memory networks (LSTM), bidirectional long short-term memory networks (BiLSTM), gated recurrent unit (GRU), and the deep convolutional neural network (CNN). The results of this study demonstrate that all the proposed models achieved a superior forecasting performance with accuracy hits of 97% using water consumption and climate factors as input data.

Assessing the energy storage potential of electric hot water cylinders with stochastic model-based control

ABSTRACT As electric hot water cylinders (HWCs) have a large capacity for thermal storage, they are well-suited for Demand Side Management (DSM). This paper compares different methods of HWC temperature control and presents a methodology to assess the amount of thermal storage available in HWCs for demand side management based on use behaviour in different household types. Simple stochastic methods for domestic hot water (DHW) demand prediction were employed to design a smart controller that produced lower rates of unmet DHW demand and higher available storage than setpoint and ripple controllers. The average storage available for DSM from the use of this smart controller is predicted to be between 3.63 and 7.20 kWh per household. These results indicate the use of HWCs for thermal storage is a low-cost viable option for peak-shaving of power system load and could decrease power system greenhouse gas (GHG) emissions in countries such as Aotearoa New Zealand, where GHG-emitting electricity generation is primarily used to meet peak loads.

MACLA-LSTM: A Novel Approach for Forecasting Water Demand

Sustainable and effective management of urban water supply is a key challenge for the well-being and security of current society. Urban water supply systems have to deal with a huge amount of data, and it is difficult to develop efficient intervention mechanisms by relying on the human experience. Deep learning methods make it possible to predict water demand in real-time; however, deep learning methods have a large number of hyperparameters, and the selection of hyperparameters can easily affect the accuracy of prediction. Within this context, a novel framework of short-term water demand forecast is proposed, in which a forecasting method clouded leopard algorithm based on multiple adaptive mechanisms—long short-term memory networks (MACLA-LSTM)—is developed to improve the accuracy of water demand predictions. Specifically, LSTM networks are used to predict water demand and the MACLA is utilized to optimize the input parameters of the LSTM. The MACLA-LSTM model is evaluated on a real dataset sampled from water distribution systems. In comparison with other methods, the MACLA-LSTM achieved MAE values of 1.12, 0.89, and 1.09; MSE values of 2.22, 1.21, and 2.38; and R2 values of 99.51%, 99.44%, and 99.01%. The results show the potential of the MACLA-LSTM model for water demand forecasting tasks and also demonstrate the positive effect of the MACLA on forecasting tasks by comparing results with LSTM variant models. The proposed MACLA-LSTM can provide a resilient, sustainable, and low-cost management strategy for water supply systems.

Analysis of Demand and Structural Changes in China’s Water Resources over the Next 30 Years

The medium and long-term demand prediction for water resources is critical to the country’s macro-allocation of water resources and the formulation of a long-term regional economic development strategy. However, the official prediction report of China’s water resources was created ten years ago, and its results are far from accurate in practice making it difficult to direct China’s water resource planning in the coming ten years. By introducing the demand forecasting method for the first time, this study built a mathematical prediction model that integrates “data constraint + mathematical prediction + actuarial prediction”. The conclusions are as follows: (1) The new method developed in this research is more accurate than previous prediction methods and has a higher degree of matching with actual data. Despite the problem of trend extrapolation, this model can accurately understand the long-term trend. However, the amount of data must be calculated. (2) China’s consumption of total water, agricultural water, industrial water, domestic water, and ecological water will predict to be 552.9 billion m3, 319.1 billion m3, 95.7 billion m3, 95.5 billion m3 and 42.6 billion m3 in 2030, respectively, as well as 504.7 billion m3, 281.1 billion m3, 61.4 billion m3, 101.4 billion m3, and 60.8 billion m3 in 2050, respectively, indicating obvious structural changes. (3) China’s industrial structure evolves frequently; therefore, water resource forecasting must account for changes in industrial structure as well as geographical variances. In North China, agricultural water demand will fall, but ecological water investment will rise. The planning and distribution of the nation’s water resources will significantly be influenced theoretically and practically by the development of this methodology study. This method is universal and can be used for long-term prediction of future water demand in other countries.

Assessing the Benefits of Nature-Inspired Algorithms for the Parameterization of ANN in the Prediction of Water Demand

Assessing the Benefits of Nature-Inspired Algorithms for the Parameterization of ANN in the Prediction of Water Demand

An artificial intelligence approach for managing water demand in water supply systems

Water demand management is essential for water utilities, which have the critical task of supplying drinking water from water sources to end-users through the distribution network. Therefore, the water utilities have to make decisions for the current and future functioning of the water distribution system. In this context, the artificial intelligence approach with data-driven methods can be used to develop powerful tools to improve overall water management. In fact, data-driven methods can model water demands for plenty of tasks and applications such as demand forecasting or anomaly detection. In this work, we propose and discuss a practical application of an artificial neural network to model the urban water demand of a water supply system. The flexibility of the proposed method allows the prediction of water demand on different horizons. Moreover, this developed model can effectively support water utilities on different operational schedules and decision tasks.

Retracted: Intelligent Control of Agricultural Irrigation through Water Demand Prediction Based on Artificial Neural Network.

[This retracts the article DOI: 10.1155/2021/7414949.].

Influence of exogenous factors on water demand forecasting models during the COVID-19 period

Water scarcity has urged the need for adequate water demand forecasting to facilitate efficient planning of municipal infrastructure. However, the development of water consumption models is challenged by the rapid environmental and socio-economic changes, particularly during unforeseen events like the COVID-19 pandemic. This study investigated the impact of COVID-19 on the efficiency of water demand prediction models, considering the lockdown measures and various exogenous features, such as previous consumption (PC) and socio-demographic (SDF), seasonal (SF), and climatic (CF) factors. Multiple ensemble models, gradient-boosting machines (GBM), extreme-gradient-boosting (XGB), light-gradient-boosting, random forest (RF), and stack regressor (STK) were examined, compared to other machine-learning techniques, multiple-linear regression (MLR), decision trees, and neural networks. The models were tested using 3-year metering records for 128,000 consumers in Dubai. The feature importance analysis indicated that PC and SDF had a significant impact on consumption rates with correlation coefficients of 0.95 and 0.74, respectively, as opposed to SF and CF, which had negligible effect. The results showed that, before COVID, RF and STK outperformed other models with a coefficient-of-determination (R2) and root-mean-squared-error (RMSE) of 0.928 and 0.039, followed by XGB at 0.923 and 0.041, respectively. However, MLR achieved the highest prediction accuracy amid COVID with R2 and RMSE of 0.90 and 0.05, followed by GBM and XGB equally at 0.83 and 0.06, respectively. An ensemble-based error prediction model was applied, resulting in up to 9.2% improvement in predictions. Overall, this research emphasized the efficiency of ensemble models in handling fluctuating data with a high degree of nonlinearity.