Water Demand Prediction Research Articles

Multi-objective optimal allocation of water resources in Shule River Basin of Northwest China based on climate change scenarios

The optimal allocation of water resources is crucial for addressing regional water scarcity, adapting to climate change, and promoting sustainable development. This study focused on the Shule River Basin and considered three climate scenarios (SSP1–2.6, SSP2–4.5, SSP5–8.5), which is combinations of Shared Socioeconomic Pathways (SSPs) and Representative Concentration Pathways (RCPs). A water resources optimal allocation model including water supply and demand prediction, multi-objective optimization, decision-making and analysis on optimal water allocation schemes was constructed. This model aims to analyze the optimal allocation of water resources in the Shule River Basin over three planning years (2025, 2030, 2035), considering guarantee rates of 50 % and 75 % under various climate scenarios. The obtained results indicate that: (1) An increasing trend in water demand in the planning year. For instance, under the SSP1–2.6 scenario, the basin's water demand is projected to reach 1.920×10^9 m3, 2.037×10^9 m3, and 2.103×10^9 m3 in 2025, 2030, and 2035, respectively. (2) The total water supply with a guarantee rate of 50 % (75 %) in the planning years is projected to be 1.939 (1.483)×10^9, 1.957(1.502) ×10^9, and 1.974 (1.519) ×10^9 m3, respectively. (3) In the three scenarios of SSP1–2.6, SSP2–4.5, and SSP5–8.5, the water demand for domestic and ecology is met in each planning year. There is a slight water shortage in the industrial sector, with a shortage rate ranging from 0 % to 13.41 %. The agricultural sector experiences the highest water shortage, with a rate of 1.93–44.77 %. (4) The water supply structure of each optimal allocation scheme of water resources was optimized. The economic benefits mainly depend on the industrial and ecological sectors. These findings offer valuable insights for optimizing the distribution of regional water resources in response to changing climatic conditions.

Enhancing accuracy and interpretability of multi-steps water demand prediction through prior knowledge integration in neural network architecture

In the field of water supply management, multi-steps water demand forecasting plays a crucial role. While there have been many studies related to multi-steps water demand forecasting based on deep learning, little attention has been paid to the interpretability of forecasting models. Aiming to improve both the forecasting accuracy and interpretability of the model, a novel urban water demand forecasting neural network (UWDFNet) was presented in this paper. Compared with traditional deep learning models, it innovatively considered domain-specific prior knowledge from water supply management and incorporated the correlation relationship between different input variables into the design of the neural network structure, and verified the consistency between the knowledge learned by the model and prior knowledge through interpretability analysis. Additionally, a systematic performance evaluation was conducted and proved that UWDFNet possesses better accuracy and stability compared to other baseline models(e.g., gated recurrent unit network (GRUN), GRUN with a corrected Network (GRUN+CORRNet), GRUN+PID, GRUN+Kmeans).

Analysis of Clean Water Quality and Quantity for Domestic Needs in Rutong

This study evaluates the quality and quantity of clean water available for domestic needs in Rutong Village, South Leitimur District, Ambon City. This study uses a quantitative descriptive research approach to provide a comprehensive overview of the clean water situation in the area. The population of this study comprises the residents of Rutong Village, with samples randomly selected from 10 households using Water Waihula and Water Cabang Dua or Saplaring. Data collection techniques include observation, documentation, and interviews. Quality analysis of clean water involves laboratory tests covering physical, biological, and chemical measurements. Quantity analysis is conducted through water flow rate calculations while predicting water demand utilizing equations based on population and standard water requirements per individual. Test results indicate that the quality of clean water in Rutong Village meets the standards set by Permenkes No. 32 of 2017. All physical, chemical, and biological parameters comply with permissible maximum standards, including odour, taste, TDS, turbidity, temperature, colour, iron, hardness, chloride, zinc, and coliform bacteria. However, despite meeting quality standards, it was found that the quantity of clean water available still needs to meet the community's needs sufficiently. On average, residents can only use 120 litres of water per day, indicating a need for improvement in the clean water supply to adequately meet the community's needs.

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.

A Water Demand Forecasting Model Based on Generative Adversarial Networks and Multivariate Feature Fusion

Accurate long-term water demand forecasting is beneficial to the sustainable development and management of cities. However, the randomness and nonlinear nature of water demand bring great challenges to accurate long-term water demand forecasting. For accurate long-term water demand forecasting, the models currently in use demand the input of extensive datasets, leading to increased costs for data gathering and higher barriers to entry for predictive projects. This situation underscores the pressing need for an effective forecasting method that can operate with a smaller dataset, making long-term water demand predictions more feasible and economically sensible. This study proposes a framework to delineate and analyze long-term water demand patterns. A forecasting model based on generative adversarial networks and multivariate feature fusion (the water demand forecast-mixer, WDF-mixer) is designed to generate synthetic data, and a gradient constraint is introduced to overcome the problem of overfitting. A multi-feature fusion method based on temporal and channel features is then derived, where a multi-layer perceptron is used to capture temporal dependencies and non-negative matrix decomposition is applied to obtain channel dependencies. After that, an attention layer receives all those features associated with the water demand forecasting, guiding the model to focus on important features and representing correlations across them. Finally, a fully connected network is constructed to improve the modeling efficiency and output the forecasting results. This approach was applied to real-world datasets. Our experimental results on four water demand datasets show that the proposed WDF-mixer model can achieve high forecasting accuracy and robustness. In comparison to the suboptimal models, the method introduced in this study demonstrated a notable enhancement, with a 62.61% reduction in the MSE, a 46.85% decrease in the MAE, and a 69.15% improve in the R2 score. This research could support decision makers in reducing uncertainty and increasing the quality of water resource planning and management.

Optimization model of water-fertilizer coupling in garden plant cultivation based on big data analysis

This study is dedicated to the development of an Internet of Things (IoT)-based water-fertilizer coupling optimization model for landscape plant cultivation using big data analysis technology to solve the problems of resource wastage and unstable plant growth quality in traditional water-fertilizer management. Through real-time monitoring of soil, climate and plant physiological indicators, combined with autoregressive moving average model and other prediction means, to achieve accurate prediction of plant water and fertilizer demand and dynamic coupling management. The model is able to customize personalized water and fertilizer supply strategies according to plant species, growth stages and environmental conditions, thus enhancing the efficiency of water and fertilizer utilization, promoting healthy plant growth, and enhancing the effect of urban greening.

Short-term water demand prediction based on decomposition technique optimization and a multihead attention mechanism

ABSTRACT Short-term water demand prediction is crucial for real-time optimal scheduling and leakage control in water distribution systems. This paper proposes a new deep learning-based method for short-term water demand prediction. The proposed method consists of four main parts: the variational mode decomposition method, the golden jackal optimization algorithm, the multihead attention mechanism, and the bidirectional gated recurrent unit (BiGRU) model. Furthermore, a seq2seq strategy was adopted for multistep prediction to avoid the error accumulation problem. Hourly water demand data collected from a real-world water distribution system were applied to investigate the potential of the proposed method. The results show that the proposed method can yield remarkably accurate and stable forecasts in single-step prediction (i.e., the mean absolute percentage error (MAPE) reaches 0.45%, and the root mean squared error (RMSE) is 25 m3/h). Moreover, the proposed method still achieves credible performance in 24-step prediction (i.e., the MAPE reaches 2.12%, and the RMSE is 126 m3/h). In general, for both single-step prediction and multistep prediction, the proposed method consistently outperforms other BiGRU-based methods. These findings suggest that the proposed method can provide a reliable alternative for short-term water demand prediction.

Long-term water demand forecasting using artificial intelligence models in the Tuojiang River basin, China.

Accurate forecasts of water demand are a crucial factor in the strategic planning and judicious use of finite water resources within a region, underpinning sustainable socio-economic development. This study aims to compare the applicability of various artificial intelligence models for long-term water demand forecasting across different water use sectors. We utilized the Tuojiang River basin in Sichuan Province as our case study, comparing the performance of five artificial intelligence models: Genetic Algorithm optimized Back Propagation Neural Network (GA-BP), Extreme Learning Machine (ELM), Gaussian Process Regression (GPR), Support Vector Regression (SVR), and Random Forest (RF). These models were employed to predict water demand in the agricultural, industrial, domestic, and ecological sectors using actual water demand data and relevant influential factors from 2005 to 2020. Model performance was evaluated based on the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE), with the most effective model used for 2025 water demand projections for each sector within the study area. Our findings reveal that the GPR model demonstrated superior results in predicting water demand for the agricultural, domestic, and ecological sectors, attaining R2 values of 0.9811, 0.9338, and 0.9142 for the respective test sets. Also, the GA-BP model performed optimally in predicting industrial water demand, with an R2 of 0.8580. The identified optimal prediction model provides a useful tool for future long-term water demand forecasting, promoting sustainable water resource management.

Study on Real-Time Water Demand Prediction of Winter Wheat–Summer Corn Based on Convolutional Neural Network–Informer Combined Modeling

The accurate prediction of crops’ water requirements is an important reference for real-time irrigation decisions on farmland. In order to achieve precise control of irrigation and improve irrigation water utilization, a real-time crop water requirement prediction model combining convolutional neural networks (CNNs) and the Informer model is presented in this paper, taking the real-time water demand of winter wheat–summer maize from 2017 to 2021 as the research object. The CNN model was used to extract the depth features of the day-by-day meteorological data of the crops, and the extracted feature values were inputted into the Informer model according to the time series for training and prediction to obtain the predicted water demand of winter wheat and summer maize. The results showed that the prediction accuracy of the constructed CNN–Informer combination model was higher compared to CNN, BP, and LSTM models, with an improvement of 1.2%, 25.1%, and 21.9% for winter wheat and 0.4%, 37.4%, and 20.3% for summer maize; based on the good performance of the model in capturing the long-term dependency relationship, the irrigation analysis using the model prediction data showed a significant water-saving effect compared with the traditional irrigation mode, with an average annual water saving of about 1004.3 m3/hm2, or 18.4%, which verified the validity of the model, and it can provide a basis for the prediction of crops’ water demand and sustainable agricultural development.

AI-Forecast: an innovative and practical tool for short-term water demand forecasting

ABSTRACT Water management is a major contemporary and future challenge. In an increasing water demand scenario related to climate change, a water distribution system must ensure equal access to water for all users. In this context, a reliable short-term water demand forecasting system is crucial for reliable water management. However, despite the abundance of studies in the scientific literature, few examples highlight complete tools for providing such models to real water utilities and water managers. This study presents AI-Forecast, an innovative tool developed to predict water demand with state-of-the-art models. Such tool is based on the data-driven logic, and it is designed to provide a complete data-driven chain that starts from the data and arrives to the short-term water demand prediction. AI-Forecast can import data, properly manage them, and assess tasks like outlier detection and missing data imputation. Eventually, it can implement state-of-the-art forecasting models and provide the forecasts. The prediction is shown through an intuitive web interface, which is designed to highlight the major information related to the prediction accuracy. Although this tool does not provide a new prediction algorithm, it proposes a complete data-driven chain that is practically designed to take such models in practice to real water utilities.

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

Quantifying the effects of future environmental changes on water supply and hydropower generation benefits of cascade reservoirs in the Yellow River Basin within the framework of reservoir water supply and demand uncertainty

Inflow and water demand prediction plays an important role in reservoir operation rulemaking. Uncertainties in meteorological and hydrological modeling increase the complexity of inflow and water demand prediction, which are not sufficiently considered in conventional inflow and water demand prediction. Thus, this study took cascade reservoirs as the research object. These cascade reservoirs were located in the mainstream of the Yellow River Basin (YRB). A three-step framework was proposed: (1) developing a distributed Soil & Water Assessment Tool (SWAT) model to determine historical and future water availability in the reservoirs; (2) constructing the AquaCrop agricultural irrigation water demand model to predict future water demand of water users at 264 nodes (reservoirs and hydrological stations) in the YRB; (3) developing an optimal regulation model of cascade reservoirs in the YRB mainstream to quantitively determine the influence of future environmental changes on hydropower generation and water supply benefits of cascade reservoirs. The results indicate that the inflow of cascade reservoirs increased in the flood season and decreased significantly during the non-flood season compared with that in the historical period (1970–2016). However, there was a slight increase in the agricultural irrigation water demand, and the contradiction became more prominent between water resource supply and demand. During the future period (2020–2050), the guaranteed rate of hydropower generation and water supply in the YRB’s lower reaches will increase significantly. Uncertainties in climate models greatly impact hydropower generation benefits and reservoir water supply, especially in the flood season. These findings can facilitate the understanding of the complexity of hydropower management and production of cascade reservoirs under future environmental changes (inflow and demand) and encourage the use of regulation models for impact assessment studies and adaptive reservoir management to mitigate climate change.

Sap flow characteristics and water demand prediction of cash crop in hyper-arid areas

Crop sap flow is a critical indicator of crop water demand, and predicting its variation trend is essential for adjusting agricultural planting structure and managing water resource in hyper-arid areas. Presently, research on crop sap flow in hyper-arid areas faces limitations due to inadequate meteorological data and restricted monitoring duration, leading to imprecise assessments of environmental impacts on future crop sap flow. Consequently, this hinders effective irrigation scheduling and oasis sustainable development policy. This study analyzed the sap flow changes characteristics of two economic crops (red jujube and walnut) at different time scales in the oasis in the south of Tarim Basin from 2017 to 2021 and the relationship between four environmental factors (solar radiation, temperature, relative humidity and vapor pressure deficit) and the sap flow of red jujube and walnut. By using the Random Forest (RF) model and the future climate data, the sap flow of the two economic crops from 2020 to 2100 was predicted. The results showed that: (1) walnut had a longer daily peak sap flow duration compared to red jujube, whereas red jujube showed a longer monthly peak sap flow duration; (2) in hyper-arid areas, the moisture and temperature directly influenced crop sap flow, while other environmental factor affected these two factors; (3) with the temperature increases, the water demand of red jujube and walnut in Cele Oasis will exceed local water resources carrying capacity. To achieve sustainable development of oasis, it is vital to consider future climatic changes in planning the expansion and crop structure.

Prediksi Kebutuhan dan Ketersediaan Air Bersih PDAM di Kecamatan Lubuk Begalung Kota Padang Tahun 2027

The goal of this researchis: 1) To determine the population projection in Lubuk Begalung District in the year 2027. 2) To ascertain the demand for clean water in Lubuk Begalung District based on the projectted populattion increase over the next 10 year. 3). To know the comparison between water needs and the current water availability until 2027 The type of research is Quantitative Descriptive, The data utilized consists of secondary data and secondary data encompassing population figures, PDAM customers, and clean water availability data in Lubuk Begalung District. The analytical technique employed includes the Population Projection Method, specifically the Arithmetic Method, to predict the population, along with the prediction of clean water demand in the year 2027.The outcomes of this study reveal that Lubuk Begalung District is experiencing a significant increase in population and is categorized as a "Medium City" for the next 10 years, reaching a total population of 136.896 by the year 2027. Calculations for domestik and non-domestik clean water demand in 2027 for Lubuk Begalung District amount to 234.43 L/second, with estimated water loss reaching 35.52 L/second. Furthermore, based on the population projection, it is determined that the number of people to be served by PDAM in 2027 will be 127,944, with a per capita water requirement of 213.12 L/day. The total water availability at PDAM Kota Padang is 47.328.357 m3/s. From this comparison, it can be concluded that the current water source availability is still capable of meting the netwater demand in the Lubuk Begalung diistrict area until 2027.

Hybrid approach for accurate water demand prediction using socio-economic and climatic factors with ELM optimization

This study proposes a hybrid approach for accurately predicting water demand by integrating socio-economic variables, such as population and GDP (per capita), with climatic variables, including temperature and precipitation. The prediction model utilizes an Extreme Learning Machine (ELM), effectively capturing the dynamic relationships between the input variables and water demand. The Improved Ant Nesting Algorithm is employed to fine-tune the weights and biases to optimize the network's performance. To evaluate the predictive accuracy of the model, a comprehensive dataset consisting of socio-economic and climatic factors is utilized for training and testing purposes. Performance metrics, namely Root Mean Square Error (RMSE) and Correlation Coefficients (R2), are employed as evaluation criteria. The results demonstrate that the hybrid approach achieves accurate water supply predictions, showcasing its potential to contribute significantly to effective water resource management and decision-making processes. Based on the results, IANA-ELM is considered the best model due to its high R2 values. Specifically, in the training data, the R2 values are 0.693 for population, 0.624 for GDP per capita, 0.607 for temperature, and 0.708 for rainfall. Similarly, in the test data, the R2 values are 0.672 for population, 0.608 for GDP per capita, 0.592 for temperature, and 0.708 for rainfall. This integrated approach provides a robust tool for policymakers, water utility companies, and researchers in the field of water managements, enabling them to make informed decisions based on accurate predictions of water demand.

Internet of things sensors and support vector machine integrated intelligent irrigation system for agriculture industry

Because there is more demand for freshwater around the world and the world’s population is growing at the same time, there is a severe lack of freshwater resources in the central part of the planet. The world’s current population of 7.2 billion people is expected to grow to over 9 billion by the year 2050. The vast majority of freshwater is used for things like cooking, cleaning, and farming. Most industrialised countries are in desperate need of smart irrigation systems, which are now a must-have because of how quickly technology is improving. In article presents IoT based Sensor integrated intelligent irrigation system for agriculture industry. IoT based humidity and soil sensors are used to collect soil related data. This data is stored in a centralized cloud. Features are selected by CFS algorithm. This will help in discarding irrelevant data. Clustering of data is performed by K means algorithm. This will help in keeping similar data together. Then classification model is build using the SVM, Random Forest and Naïve Bayes algorithm. Model is trained, validated and tested using the acquired data. Historical soil and humidity related data is also used in training the model. K-means SVM hybrid classifier is achieving better results for classification, prediction of water demand and saving fresh water by intelligent irrigation. K-means SVM hybrid classifier has achieved accuracy rate of 98.5 percent. Specificity, recall and precision of K-means SVM hybrid classifier is also higher than random forest and naïve bayes classifier.

An applied study of a technique incorporating machine learning algorithms to optimize water demand prediction

Abstract In water resource management, accurate water demand prediction is essential for developing effective water supply strategies and optimizing resource allocation. This study aims to investigate machine learning algorithms, particularly echo state network (ESN) models, to improve the accuracy and efficiency of water demand prediction. ESN models are selected for their excellent nonlinear time series processing capabilities, which address the challenges of traditional prediction methods when dealing with complex water resource systems. By optimizing the parameters of the ESN model, the study hopes to provide a more scientific and efficient method for residential domestic and agricultural water demand forecasting, thus supporting more refined water resources planning and management decisions. Residential water demand prediction and crop water demand prediction are the two parts of this study. In the prediction of residential water demand, based on the actual data of City Z, the optimized ESN model predicts the water demand in 2025, and the total water demand in the baseline scenario is 790.9 million m3, and the expected values of water demand in different scenarios combined with the economic growth rate and the change of water price range from 659.4708 million m3 to 730.448 million m3. The article’s accuracy analysis of crop water demand prediction indicates that the model’s relative errors in predicting the water demand of the three major crops are limited to 10%. The ESN model optimized using the machine learning algorithm in this paper has good potential for water demand prediction and is an efficient and accurate prediction tool for managing water resources.

The Demand Prediction of Water Capacity for Drinking Water Plant by Artificial Neural Network

With the constant progress of the times and the rapid economic and social development, the demand for water consumption in the Hexi area of Xiangtan City is continuously rising. Ensuring the safety of urban water supply has become a crucial task. In this paper, we explore the effectiveness of the artificial neural network model in predicting water demand, leveraging the operational data from a water plant in Xiangtan. Thirty-three parameters are employed in this study to forecast water capacity. The results of our analysis reveal that the back propagation (BP) neural network model offers a more accurate and reliable prediction of water demand. This model, through its iterative learning process, is able to capture the complex relationships and patterns inherent in the water demand data. By adjusting its weights and thresholds based on the error between predicted and actual values, the BP neural network continuously improves its predictive accuracy. The application of the BP neural network in water demand prediction not only enhances the precision of forecasts but also contributes to better water resource management and allocation. It enables authorities to make informed decisions regarding water supply planning, ensuring the reliability and sustainability of the urban water system. The BP neural network model demonstrates its potential in accurately predicting water demand in Xiangtan’s Hexi area, thus contributing to the safety and efficiency of the urban water supply system.

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.

Analysis and prediction of urban household water demand with uncertain time series

Analysis and prediction of urban household water demand with uncertain time series