[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Next Article in Journal
Potential of Abandoned Agricultural Lands for New Photovoltaic Installations
Previous Article in Journal
Water Reuse: Contribution of a Decision Support Model
Previous Article in Special Issue
Water Management on Drinking Water Reservoirs in the Aspect of Climate Variability: A Case Study of the Dobromierz Dam Reservoir, Poland
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sustainability
Volume 17
Issue 2
10.3390/su17020693
sustainability-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Uncertainty-Based Industrial Water Supply and Demand Balance Pattern Recognition: A Case Study in the Yellow River Basin of Gansu Province, China

by
Mingyue Ma
1,
Junying Chu
1,*,
Zuhao Zhou
1,
Zuohuai Tang
1,2,
Yunfu Zhang
3,
Tianhong Zhou
2,
Xusheng Zhang
4 and
Ying Wang
3
1
State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources & Hydropower Research, Beijing 100038, China
2
School of Environment and Municipal Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
3
China Construction Eco-Environmental Group Co., Ltd., Beijing 100037, China
4
Gansu Water Resources and Hydropower Survey and Design Research Institute Co., Ltd., Lanzhou 730000, China
*
Author to whom correspondence should be addressed.
Sustainability 2025, 17(2), 693; https://doi.org/10.3390/su17020693
Submission received: 9 November 2024 / Revised: 13 January 2025 / Accepted: 14 January 2025 / Published: 17 January 2025
(This article belongs to the Special Issue Development in Sustainable Water Management: Processes, Barriers, Protection and Future Perspectives)
Browse Figures
Figure 1
<p>Framework for pattern recognition of supply and demand balance under uncertainty.</p> "> Figure 2
<p>Pattern I (excessive supply amid weak industrial water demand).</p> "> Figure 3
<p>Pattern II (balance of water supply and demand).</p> "> Figure 4
<p>Pattern III (insufficient supply amid strong industrial water demand).</p> "> Figure 5
<p>Prefecture-level city in the Yellow River Basin, Gansu Province.</p> "> Figure 6
<p>Predicted water demand range at different confidence levels in Lanzhou.</p> "> Figure 7
<p>Pattern I recognition.</p> "> Figure 7 Cont.
<p>Pattern I recognition.</p> "> Figure 8
<p>Pattern II recognition.</p> "> Figure 8 Cont.
<p>Pattern II recognition.</p> "> Figure 9
<p>Pattern III recognition.</p> ">
Versions Notes

Abstract

:
The balance between water supply and demand is essential for industrial growth, affecting economic, social, and environmental sustainability. Our research employs a Gaussian process regression for demand prediction. Additionally, it takes into account water limits and policy thresholds when determining the supply, thereby defining a range of uncertainty for both the industrial demand and the supply. A pattern recognition method matches this trade-off range, identifying three patterns to support water management. The study focuses on the analysis of industrial water supply and demand dynamics under uncertain conditions in nine cities (Baiyin, Dingxi, Gannan, Lanzhou, Linxia, Pingliang, Qingyang, Tianshui, and Wuwei) in Gansu Province of China’s Yellow River Basin in 2030. The results of the study show that industrial water use in Baiyin, Linxia, Dingxi, and Tianshui cities falls into Pattern I, providing water resources to support industrial development. Industrial water use in Wuwei, Pingliang, Qingyang, and Gannan cities represents Pattern II, which maintains a balance between supply and demand while allowing flexibility in water demand. Finally, the industrial water use in Lanzhou city is characterized by Pattern III, which requires optimization through structural, technological, and management improvements to mitigate the negative impacts of water scarcity on the sustainable development of the economy and society. The results of the research can be used as a reference for policy making in water resources planning and management in the basin.

1. Introduction

The balance between water supply and demand is essential for the sustainable development and utilization of water resources. Scholars have extensively studied the factors influencing this balance, as well as the application of models and algorithms in this area [1,2,3,4]. Currently, most research focuses on: (i) scenarios with redline constraints [5], which include (a) controlling the development and use of water resources, (b) improving the efficiency of water use, and (c) restricting the discharge of pollutants within water functional zones; (ii) supply–demand analyses of water resources [6,7]; (iii) management strategies [8,9]; (iv) water resource spatial equilibrium [10,11]; (v) and water resource utilization efficiency [12].
While existing research offers valuable insights for balancing water supply and demand, as well as for analyzing water resource patterns, the methods for predicting water demand remain relatively limited. These methods are primarily based on statistical and machine learning techniques. In contrast to the predominant focus on the variability of water demand, there is a paucity of studies addressing the variability in water availability. This includes not only fluctuations caused by climatic or seasonal changes but also factors such as infrastructure limitations, policy or regulatory constraints, water rights allocations, and unexpected disruptions like natural disasters or industrial accidents. Existing research often develops frameworks or models to categorize various scenarios, primarily addressing uncertainties on the demand side [13,14,15,16,17]. Under conditions of uncertain water demand, studies on water allocation have largely targeted agriculture, ecology, and industry, with limited attention to pattern recognition for both water supply and demand range [8,13,18].
Gaussian Process Regression (GPR), a machine learning algorithm, demonstrates strong generalization capabilities and excels at modeling complex, non-linear relationships [19]. These attributes make it superior to traditional probabilistic prediction methods. By accurately identifying water supply and demand patterns, we can enhance the efficiency of water resource allocation, support regional development, optimize water supply benefits under limited resource conditions, and meet the water needs of various users, including domestic consumers, agricultural sectors, industrial enterprises, and those involved in recreational activities. This research provides a scientific basis for governments to design effective water allocation programs and policies.
Industrial water refers to water used for industrial purposes, including manufacturing, processing, cooling, and equipment maintenance [20]. The specific applications under this category vary by country and region, but they generally include industries such as mining, energy production, textile manufacturing, and food processing. In developed countries, industrial water demand often competes with urban and domestic water use, especially in densely populated areas. In developing countries, agriculture remains a dominant consumer of water resources, creating significant competition between agricultural irrigation and industrial water use. In China, industrial water consumption, despite often being overshadowed by the prominence of agricultural water use, remains a critical area of focus [21].
Gansu serves as a vital industrial hub in the upper reaches of the Yellow River. The Yellow River Basin within Gansu Province encompasses nine cities: Wuwei, Lanzhou, Baiyin, Dingxi, Linxia, Tianshui, Pingliang, Qingyang, and Gannan. In 2022, within the Yellow River Basin in Gansu Province, agricultural water consumption accounted for 63.60% of the total, residential water consumption for 18.03%, industrial water consumption for 9.44%, and environmental water consumption for 8.93%. However, the water consumption efficiency for agriculture was 74.00%, while it reached 91.3% for heavy industry and 37.8% for general industry. Industrial water use is a significant consumer of water resources, and improving its efficiency is essential for maintaining economic stability and fostering sustainable growth. The study of industrial supply and demand balance focuses on mass balance [18], balance index [22], and water supply and demand balance [23,24], through which the sustainable use of water resources can be achieved through the study of water supply and demand balance.
Traditional supply–demand balance methods, such as the Systems–Dynamic (SD) model [1,4], typically utilize deterministic models to generate various scenarios for both the demand and supply aspects. These methods typically rely on point predictions, with demand-side projections based on deterministic techniques and supply-side targets allocated directly. The analysis is focused on balancing the scenarios through point prediction outcomes. Previous water demand range prediction methods emphasize uncertainty-based approaches, such as probabilistic prediction [15,16,25], machine learning [25,26], deep learning [26,27], integrated water resources planning [14], and multi-objective optimization [16]. These methods aim to account for variability and provide a range of potential outcomes rather than single-point estimates.
In the context of environmental protection and high-quality development in the Yellow River Basin, this research introduces a method to identify supply and demand balance patterns under conditions of uncertainty. The year 2030 is an important milestone in many of the country’s regional and national sustainable development plans related to water resources management. Specifically, the Yellow River Basin has several ongoing initiatives and policy frameworks aiming to achieve specific water–related goals by this year. The research employs the GPR algorithm to predict the range of industrial water demand for the nine cities in the Yellow River Basin of Gansu Province—Gannan, Linxia, Wuwei, Lanzhou, Baiyin, Dingxi, Tianshui, Pingliang, and Qingyang—in 2030 and to calculate the corresponding range of industrial water supply. Based on this analysis, the study conducts a pattern recognition of industrial water use across the cities, with the aim of providing a reference for promoting environmental protection and high-quality development in the Yellow River Basin of Gansu Province.

2. Methods

This research adopts a probabilistic prediction approach to analyze water demand, incorporates supply-side uncertainties, and proposes a pattern to identify the supply and demand balance of industrial water in the Yellow River Basin of Gansu Province based on the range of water demand and the range of water supply. Figure 1 shows the framework for pattern recognition of supply and demand balance under uncertainty.
On the demand side, the GPR algorithm is used to calculate the range of water demand in 2030 [28]. The GPR algorithm is employed to estimate the industrial water demand within the specified confidence range of 30%, 70%, and 90%. The squared exponential (SE) covariance function was chosen to transform complex non-linear problems into more manageable linear ones. Mean Absolute Percentage Error (MAPE) and Coverage Probability (CP) were used to assess the accuracy of the range. Industrial water demand is usually influenced by many factors, such as economy, policy, science and technology, and production level [29,30,31,32]. The GPR algorithm is employed to estimate the range of industrial water demand across various confidence levels. Based on error analysis, the water demand range corresponding to each confidence level is then selected.
On the supply side, surface water availability and total water resources are determined based on relevant plans, leading to projections of water availability and red line thresholds that define the range of water resources. The amount of water allocated for industrial use is defined as the share allocated for regional industrial production based on available water allocation programs or planning allocations, ensuring essential water use to maintain environmental health in rivers and lakes.
Surface water availability is determined according to valid legal documents, such as existing water allocation programs, historical water-sharing agreements, or related agreements. Control indicators based on detailed metrics for tributaries, branch streams, and municipalities are used to establish local surface water availability. In the Yellow River Basin, where water consumption is a control indicator, conversion from water use to water consumption indicators is necessary. The calculation of groundwater availability is primarily based on the results of the latest national water resources survey and assessment, groundwater utilization and protection plans, and related water supply plans, combined with economic and social development plans. For unconventional water sources, which include (a) treated wastewater, (b) sea, saline, and brackish water, and (c) harvested rainwater, water availability is calculated according to national water conservation actions, water pollution prevention and control programs, and related plans. The minimum control quantity or proportion is determined by each local prefecture–level administrative region.
The quantity of surface water is determined through the application of Equation (1). Building upon this, the calculation of total water availability is accomplished using Equation (2). Equation (3) is then employed to specifically compute the industrial water availability based on the foundation laid by the previous two equations. In summary, the formula for calculating industrial water availability can be presented as follows:
W i , t   s u r f a c e = ∑ n = i n Q i , t ∆
W i , t   t o t a l = W i , t   s u r f a c e + W i , t   g r o u n d + W i , t   u n c o n v e n t i o n a l
W i , t   I n d u s t r i a l = W i , t   t o t a l × β
where W i , t   s u r f a c e is the available surface water quantity for city i at time t, in 100 M m3; n is the number of cities; Q i , t is the water consumption indicator for city i at time t, in 100 Mm3; Δ is the water consumption coefficient, with a value range of (0, 1); W i , t   t o t a l is the total available water quantity for city i at time t, in 100 Mm3; W i , t   g r o u n d is the available groundwater quantity for city i at time t, in 100 Mm3; W i , t   u n c o n v e n t i o n a l is the available unconventional water quantity, in 100 Mm3; W i , t   I n d u s t r i a l is the available industrial water quantity for city i at time t, in 100 Mm3; β is the coefficient of available industrial water quantity, with a value range of (0, 1).
Three kinds of patterns between the industrial water demand range and the industrial water supply range are recognized based on the supply and demand balance (Figure 2, Figure 3 and Figure 4):
(i)
Pattern I (excessive supply amid weak industrial water demand): If the range of water supply is higher than the range of water demand, it indicates that the supply exceeds the demand, and the range of water demand is weak. There is still considerable potential for growth in this pattern; however, it remains essential to strengthen market access and adhere to the principle of ‘innovation-driven, green leadership’. Efforts should center on enhancing efficiency, promoting the industry’s transformation towards green, high-end, and intelligent development, and establishing a sustainable, innovative, and efficient industrial framework.
(ii)
Pattern II (balance of water supply and demand): When the water supply consumption range is within the water demand range, it indicates that the balance of supply and demand is basically maintained, and there is a certain elasticity of development space. The industrial structure should be reasonably adjusted, continue to promote water-saving technologies and related water resource management measures, improve the efficiency of water resource utilization, reduce unreasonable demand, and realize the matching of supply and demand, and the industrial economy will continue to develop steadily and in a good direction.
(iii)
Pattern III (insufficient supply amid strong industrial water demand): When the range of water supply is below the range of water demand, it indicates that there is insufficient supply against strong demand. At this time, industrial development is constrained by water resources. Based on the comprehensive measures of structure, technology, and management, on the one hand, the industrial scale should be reasonably controlled and compressed to minimize the threat of water shortage to economic and social development; on the other hand, following the basic principles of real need, ecological safety, and sustainability, the industry and economy should be promoted on the basis of high-level protection through the adjustment of indexes or the optimization of water resources allocation projects on the basis of full selection. High-quality economic and social development is based on a high level of protection.

3. Study Area

Gansu is located in the upper reaches of the Yellow River and is the third province through which the Yellow River flows. It holds a very important position in China’s economic and social development and ecological security. The Yellow River Basin of Gansu Province covers an area of 142,700 km2, accounting for 33% of the land area of Gansu Province, specifically including nine prefecture-level cities of Gannan, Linxia, Wuwei, Lanzhou, Baiyin, Dingxi, Tianshui, Pingliang, and Qingyang (Figure 5). The Yellow River Basin of Gansu Province is an important comprehensive energy base in China, and the current traditional industries such as petrochemical, metallurgy and non-ferrous metals, equipment manufacturing, etc., account for a relatively high proportion in the industrial structure and are the pillars of the province’s industrial development. According to the Gansu development yearbook 2023 [33] and 2022 Gansu Water Resources Bulletin [34], the industrial water consumption in the Yellow River Basin of Gansu Province has shown a decreasing trend year by year since 2010, from 1.061 Gm3 in 2010 to 375 Mm3 in 2022, a decrease of 64.66%; the proportion of industrial water to the total water consumption has decreased from 23.11% since 2010 to 9.44% in 2022.
In 2022, the gross regional product of the Yellow River Basin in Gansu Province was 763.17 G¥, of which the primary, secondary, and tertiary industries were 83.69, 256.73, and 422.74 G¥, respectively, and the added value of industry was 208.806 G¥ [33,34].

3.1. Uncertainty of Industrial Water Demand Prediction

The industrial added value and water usage per ¥10,000 of industrial added value for 2030 are predicted based on historical data, and these are used as the foundational data for the industrial water demand prediction for 2030 [33,34].
As the capital of Gansu Province, Lanzhou serves as a relatively representative example of the region’s unique characteristics and plays an important role in illustrating the broader social, economic, and cultural aspects of northwestern China. To verify the prediction performance, historical data from 2013 to 2022 for Lanzhou were selected for training, which provided the range of industrial water demand at 30%, 70%, and 90% confidence levels (Figure 6). The results show that the GPR algorithm achieved a MAPE of 16.8% and CP of 90%, 90%, and 80% for the confidence levels of 30%, 70%, and 90%, respectively. Considering the error analysis in its entirety, the prediction result at the 30% confidence level was adopted. The prediction of industrial water demand for the Yellow River Basin in Gansu Province in 2030 is shown in Table 1. The results show that at the 30% confidence level, the industrial water demand ranges from 472 Mm3 to 839 Mm3.

3.2. Uncertainty of Industrial Water Supply Prediction

The surface water consumption index of the Yellow River Basin allocated to Gansu Province before the South-to-North Water Diversion Project takes effect is 3040 Mm3. The water consumption coefficient is 0.72, and the total water consumption of surface water in the Yellow River Basin of Gansu Province in 2030 will be 3956 Mm3. The total water consumption of groundwater in the Yellow River Basin of Gansu Province in 2030 will be 350 Mm3. The total water availability of unconventional water sources in 2030 will be 316 Mm3. The red line of water consumption in the Yellow River Basin of Gansu Province in 2030 will be 5.479 Gm3. The ratio of water supply for industry and the red line of water consumption of each city in the Yellow River Basin of Gansu Province in the total water supply and the red line of water consumption will be 3.956 Gm3.
The proportion of water supply and the red line of total water consumption is mainly determined according to the relevant planning and management requirements of each city, with the value of available water consumption ranging from 10 to 15% and the value of the red line of industrial water consumption ranging from 10 to 12%. Under the constraint of the red line of water use, the lower limit of water availability and the upper limit of the red line of water use are taken as the water supply range, and if the range of water availability exceeds the range of the red line of water use (i.e., the upper limit of the red line of water use is smaller than the lower limit of water availability), the range of the red line of water use is taken as the water supply range. In summary, the industrial supply water range of the Yellow River Basin in Gansu Province in 2030 is 457–558 Mm3 (Table 2).

4. Results and Discussions

Based on the prediction of industrial water demand in the future period under uncertainty and the calculation of industrial water supply, an analysis of the supply and demand balance pattern in the Yellow River Basin of Gansu Province under uncertainty is carried out. The results show that there are mainly three typical supply and demand balance patterns in the cities of the Yellow River Basin in Gansu Province.
Pattern I of supply and demand balance in the Yellow River Basin in Gansu Province is mainly distributed in Baiyin, Linxia, Dingxi, and Tianshui, and the pattern recognition is shown in Figure 7. It can be seen that in 2030, the water supply range in the region is above the water demand range, and the supply and demand balance pattern is a Pattern I. In the future period, Baiyin and Dingxi belong to the Longzhong region, and Tianshui belongs to the Longdong region, and water resources have not yet brought strong constraints on the industrial development of the region, but it is still necessary to focus on the improvement of efficiency, strengthen the industrial water-saving access, and realize the transformation of industry to greening and ecologization. Comparatively speaking, Linxia is located in the upper reaches of the Yellow River Basin and should adhere to the priority of environmental protection and water conservation, give full play to the industrial advantages combined with national characteristics, strengthen industrial water-saving management and the application of water-saving technology, promote the optimization of the scale and layout of industrial development, and promote high-quality industrial development with the sustainable use of water resources.
Pattern II of supply and demand balance in the Yellow River Basin in Gansu Province is mainly distributed in Wuwei, Pingliang, Qingyang, and Gannan, and the pattern recognition is shown in Figure 8. It can be seen that in 2030, the water supply range in the region is between the water demand range, and the supply and demand balance pattern is a Pattern II. In the future period, Wuwei belongs to the Longzhong region, Pingliang and Qingyang belong to the Longdong region, and Gannan belongs to the upper reaches of the Yellow River Basin, and it is necessary to further release the elasticity space of the region’s industrial water demand on the basis of maintaining the balance of supply and demand and to realize the coordinated development of the industrial economy and water resources.
Pattern III of the supply and demand balance in the Yellow River Basin of Gansu Province is mainly found in Lanzhou, as presented in Figure 9. In 2030, the water supply range in Lanzhou is below the water demand range, and the industrial water supply can no longer satisfy the lower limit of the water demand, and the water resources play a strong constraining role on the scale, layout, and water use efficiency of the industrial development. In 2030, the lower limit of industrial water demand range of Lanzhou exceeds the upper limit of water supply range by 316 Mm3. Lanzhou is located in the Longzhong region, which is the key industrial development area in Gansu province. The region can promote adaptive management on both the supply and demand sides, specifically: on the demand side, further strengthen water conservation, scientifically deploy water metering facilities, strengthen water use monitoring of key users, establish a water use efficiency evaluation system, strengthen the research and development and application of non-conventional water utilization technologies, and formulate economic incentive policies for non-conventional water utilization such as price and tax; on the supply side, the basic principles of ‘real need, ecological safety and sustainability’ should be followed, and the impact of water shortage on sustainable industrial development should be reduced through measures such as adjusting targets or planning water resources optimization and allocation projects on the basis of adequate comparison.
On the demand side, the GPR algorithm was introduced to accurately calculate the range of water demand, providing an advanced scientific basis for the quantitative analysis of the demand side.
On the supply side, through in-depth analysis of relevant plans, the available surface water amount and total water resources were systematically determined. An effective method for predicting the available water resources amount and the red line critical value was constructed, thereby precisely defining the range of water resources amount, laying a solid foundation for the resource assessment and planning of the supply side.
Based on the research results of both the water demand and supply sides, the water resources supply–demand balance pattern in the Yellow River Basin of Gansu Province under uncertain conditions was deeply analyzed. Three typical supply–demand balance patterns mainly presented by cities in the basin were identified, providing valuable reference and strategic guidance for regional water resources management and decision-making.

5. Conclusions

The case study examines uncertainties on both the demand and supply sides, proposing an uncertainty-based approach to identify supply and demand balance patterns and classifying regions into Pattern I, Pattern II, and Pattern III. The supply and demand balance patterns were recognized for each city and prefecture in the Yellow River Basin of Gansu Province, resulting in three typical patterns. Among them, Baiyin, Linxia, Dingxi, and Tianshui belong to Pattern I; Wuwei, Pingliang, Qingyang, and Gannan belong to Pattern II, while Lanzhou falls under Pattern III. These different patterns of regions should implement differentiated water resource management strategies, with particular attention to ensuring industrial water needs are met while balancing agricultural, ecological, and domestic water uses to promote high-quality economic and social development through sustainable water resource utilization.
In the future, the amount of surface water in the arid region of Northwest China is likely to remain at a high state of fluctuation [35]. Studies utilizing hybrid models such as WEP-L combined with Random Forest to identify non-perennial river reaches provide valuable insights into water management in such regions, including industrial water supply planning [36]. With the development of the economy and society, further research and discussion can focus on the impact of different incoming water frequency conditions, climate change, and other factors on the balance between supply and demand of water resources. This includes fostering coordination among industrial, agricultural, domestic, and ecological water use sectors to achieve sustainable and equitable water resource allocation. Considering regional differences, management strategies will be continuously refined to support precise and efficient water resource management for both industrial and non-industrial uses across different areas of the Yellow River Basin in Gansu Province in the future.

Author Contributions

Writing—original draft, M.M. and Z.T.; writing—review and editing, J.C., Z.Z., Y.Z. and Y.W.; data curation, M.M., X.Z. and T.Z.; funding acquisition, J.C., Z.Z. and Y.Z. All authors have read and agreed to the published version of the manuscript.

Funding

This research was funded by the Major Science and Technology Project of the Ministry of Water Resources: SKS-2022070; the Academy of Chinese Engineering S & T Strategy for development of Gansu province: GS2022ZDI02; the project of key technology for ecological restoration of rivers and lakes: CSCEC-2022-K-36.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

The original contributions presented in the study are included in the article, further inquiries can be directed to the corresponding author.

Conflicts of Interest

Authors Yunfu Zhang and Ying Wang were employed by the company China Construction Eco-Environmental Group Co., Ltd. Author Xusheng Zhang was employed by the company Gansu Water Resources and Hydropower Survey and Design Research Institute Co., Ltd. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

References

  1. Li, T.; Yang, S.; Tan, M. Simulation and optimization of water supply and demand balance in Shenzhen: A system dynamics approach. J. Clean. Prod. 2019, 207, 882–893. [Google Scholar] [CrossRef]
  2. Han, C.; Zheng, J.; Guan, J.; Yu, D.; Lu, B. Evaluating and simulating resource and environmental carrying capacity in arid and semiarid regions: A case study of Xinjiang, China. J. Clean. Prod. 2022, 338, 130646. [Google Scholar] [CrossRef]
  3. Guo, W.; Liu, T.; Dai, F.; Xu, P. An improved whale optimization algorithm for forecasting water resources demand. Appl. Soft Comput. 2020, 86, 105925. [Google Scholar] [CrossRef]
  4. Lindqvist, A.N.; Fornell, R.; Prade, T.; Khalil, S.; Tufvesson, L.; Kopainsky, B. Impacts of future climate on local water supply and demand–A socio-hydrological case study in the Nordic region. J. Hydrol. Reg. Stud. 2022, 41, 101066. [Google Scholar] [CrossRef]
  5. Yan, B.; Jiang, H.; Zou, Y.; Liu, Y.; Mu, R.; Wang, H. An integrated model for optimal water resources allocation under “3 Redlines” water policy of the upper Hanjiang river basin. J. Hydrol. Reg. Stud. 2022, 42, 101167. [Google Scholar] [CrossRef]
  6. Karamouz, M.; Mohammadpour, P.; Mahmoodzadeh, D. Assessment of sustainability in water supply-demand considering uncertainties. Water Resour. Manag. 2017, 31, 3761–3778. [Google Scholar] [CrossRef]
  7. Zhang, F.; Wu, Z.; Di, D.; Wang, H. Water resources allocation based on water resources supply-demand forecast and comprehensive values of water resources. J. Hydrol. Reg. Stud. 2023, 47, 101421. [Google Scholar] [CrossRef]
  8. Blanco-Gutiérrez, I.; Varela-Ortega, C.; Purkey, D.R. Integrated assessment of policy interventions for promoting sustainable irrigation in semi-arid environments: A hydro-economic modeling approach. J. Environ. Manag. 2013, 128, 144–160. [Google Scholar] [CrossRef]
  9. Liu, Y.; Gupta, H.; Springer, E.; Wagener, T. Linking science with environmental decision making: Experiences from an integrated modeling approach to supporting sustainable water resources management. Environ. Model. Softw. 2008, 23, 846–858. [Google Scholar] [CrossRef]
  10. He, Y.; Wang, Y.; Chen, X. Spatial patterns and regional differences of inequality in water resources exploitation in China. J. Clean. Prod. 2019, 227, 835–848. [Google Scholar] [CrossRef]
  11. Bian, D.; Yang, X.; Lu, Y.; Chen, H.; Sun, B.; Wu, F.; Chen, Y.; Xiang, W. Analysis of the spatiotemporal patterns and decoupling effects of China’s water resource spatial equilibrium. Environ. Res. 2023, 216, 114719. [Google Scholar] [CrossRef] [PubMed]
  12. Song, M.; Tao, W.; Shang, Y.; Zhao, X. Spatiotemporal characteristics and influencing factors of China’s urban water resource utilization efficiency from the perspective of sustainable development. J. Clean. Prod. 2022, 338, 130649. [Google Scholar] [CrossRef]
  13. Graveline, N.; Aunay, B.; Fusillier, J.L.; Rinaudo, J.D. Coping with urban & agriculture water demand uncertainty in water management plan design: The interest of participatory scenario analysis. Water Resour. Manag. 2014, 28, 3075–3093. [Google Scholar]
  14. Safavi, H.R.; Golmohammadi, M.H.; Sandoval-Solis, S. Scenario analysis for integrated water resources planning and management under uncertainty in the Zayandehrud river basin. J. Hydrol. 2016, 539, 625–639. [Google Scholar] [CrossRef]
  15. Greve, P.; Kahil, T.; Mochizuki, J.; Schinko, T.; Satoh, Y.; Burek, P.; Fischer, G.; Tramberend, S.; Burtscher, R.; Langan, S.; et al. Global assessment of water challenges under uncertainty in water scarcity projections. Nat. Sustain. 2018, 1, 486–494. [Google Scholar] [CrossRef]
  16. Basupi, I.; Kapelan, Z. Flexible water distribution system design under future demand uncertainty. J. Water Resour. Plan. Manag. 2015, 141, 04014067. [Google Scholar] [CrossRef]
  17. Seifollahi-Aghmiuni, S.; Haddad, O.B.; Omid, M.H.; Mariño, M.A. Long-term efficiency of water networks with demand uncertainty. Proc. Inst. Civ. Eng. Water Manag. 2011, 164, 147–159. [Google Scholar] [CrossRef]
  18. Pham, T.T.; Mai, T.D.; Pham, T.D.; Hoang, M.T.; Nguyen, M.K.; Pham, T.T. Industrial water mass balance as a tool for water management in industrial parks. Water Resour. Ind. 2016, 13, 14–21. [Google Scholar] [CrossRef]
  19. Seeger, M. Gaussian processes for machine learning. Int. J. Neural Syst. 2004, 14, 69–106. [Google Scholar] [CrossRef]
  20. Klemeš, J.J. Industrial water recycle/reuse. Curr. Opin. Chem. Eng. 2012, 1, 238–245. [Google Scholar] [CrossRef]
  21. Zhou, Z.; Wu, H.; Song, P. Measuring the resource and environmental efficiency of industrial water consumption in China: A non-radial directional distance function. J. Clean. Prod. 2019, 240, 118169. [Google Scholar] [CrossRef]
  22. Karamouz, M.; Rahimi, R.; Ebrahimi, E. Uncertain water balance-based sustainability index of supply and demand. J. Water Resour. Plan. Manag. 2021, 147, 04021015. [Google Scholar] [CrossRef]
  23. Le, T.M.; Kujawa-Roeleveld, K.; Tran, D.T.; Rijnaarts, H.H. Data envelopment analysis as a tool to assess the water demand minimization potential in industrial zones in the Vietnamese Delta. Water Resour. Ind. 2022, 28, 100181. [Google Scholar] [CrossRef]
  24. Zhang, L.; Chen, S. Carbon peaks of water systems in Chinese cities under varying water demand dynamics and energy transition pathways. J. Clean. Prod. 2022, 379, 134695. [Google Scholar] [CrossRef]
  25. Lopez Farias, R.; Puig, V.; Rodriguez Rangel, H.; Flores, J.J. Multi-model prediction for demand forecast in water distribution networks. Energies 2018, 11, 660. [Google Scholar] [CrossRef]
  26. Huang, H.; Zhang, Z.; Song, F. An ensemble-learning-based method for short-term water demand forecasting. Water Resour. Manag. 2021, 35, 1757–1773. [Google Scholar] [CrossRef]
  27. Kavya, M.; Mathew, A.; Shekar, P.R.; Sarwesh, P. Short term water demand forecast modelling using artificial intelligence for smart water management. Sustain. Cities Soc. 2023, 95, 104610. [Google Scholar] [CrossRef]
  28. Xue, H.; Jia, Y.; Wen, P.; Farkoush, S.G. Using of improved models of Gaussian Processes in order to Regional wind power forecasting. J. Clean. Prod. 2020, 262, 121391. [Google Scholar] [CrossRef]
  29. Abbott, M.; Cohen, B. Productivity and efficiency in the water industry. Util. Policy 2009, 17, 233–244. [Google Scholar] [CrossRef]
  30. Vásquez-Lavín, F.; Vargas, L.; Hernández, J.I.; Oliva, R.D.P. Water demand in the Chilean manufacturing industry: Analysis of the economic value of water and demand elasticities. Water Resour. Econ. 2020, 32, 100159. [Google Scholar] [CrossRef]
  31. Revollo-Fernández, D.A.; Rodríguez-Tapia, L.; Morales-Novelo, J.A. Economic value of water in the manufacturing industry located in the Valley of Mexico Basin, Mexico. Water Resour. Econ. 2020, 30, 100138. [Google Scholar] [CrossRef]
  32. Willet, J.; Wetser, K.; Vreeburg, J.; Rijnaarts, H.H. Review of methods to assess sustainability of industrial water use. Water Resour. Ind. 2019, 21, 100110. [Google Scholar] [CrossRef]
  33. Gansu Development Yearbook Editorial Committee. Gansu Development Yearbook 2023; China Statistics Press: Beijing, China, 2023.
  34. Gansu Water Resources Department. 2022 Gansu Water Resources Bulletin; Gansu Water Resources Department: Lanzhou, China, 2023.
  35. Chen, Y.; Li, Z.; Fan, Y.; Wang, H.; Deng, H. Progress and prospects of climate change impacts on hydrology in the arid region of northwest China. Environ. Res. 2015, 139, 11–19. [Google Scholar] [CrossRef] [PubMed]
  36. Yuan, K.; Chu, J.; Zhou, Z.; Liu, J.; Chen, Y.; Wang, Y.; Tang, Z. Identifying Non-Perennial River Reaches: A Hybrid Model Combining WEP-L and Random Forest. Sustainability 2024, 16, 10543. [Google Scholar] [CrossRef]
Sustainability 17 00693 g001
Figure 1. Framework for pattern recognition of supply and demand balance under uncertainty.
Figure 1. Framework for pattern recognition of supply and demand balance under uncertainty.
Sustainability 17 00693 g001
Sustainability 17 00693 g002
Figure 2. Pattern I (excessive supply amid weak industrial water demand).
Figure 2. Pattern I (excessive supply amid weak industrial water demand).
Sustainability 17 00693 g002
Sustainability 17 00693 g003
Figure 3. Pattern II (balance of water supply and demand).
Figure 3. Pattern II (balance of water supply and demand).
Sustainability 17 00693 g003
Sustainability 17 00693 g004
Figure 4. Pattern III (insufficient supply amid strong industrial water demand).
Figure 4. Pattern III (insufficient supply amid strong industrial water demand).
Sustainability 17 00693 g004
Sustainability 17 00693 g005
Figure 5. Prefecture-level city in the Yellow River Basin, Gansu Province.
Figure 5. Prefecture-level city in the Yellow River Basin, Gansu Province.
Sustainability 17 00693 g005
Sustainability 17 00693 g006
Figure 6. Predicted water demand range at different confidence levels in Lanzhou.
Figure 6. Predicted water demand range at different confidence levels in Lanzhou.
Sustainability 17 00693 g006
Sustainability 17 00693 g007aSustainability 17 00693 g007b
Figure 7. Pattern I recognition.
Figure 7. Pattern I recognition.
Sustainability 17 00693 g007aSustainability 17 00693 g007b
Sustainability 17 00693 g008aSustainability 17 00693 g008b
Figure 8. Pattern II recognition.
Figure 8. Pattern II recognition.
Sustainability 17 00693 g008aSustainability 17 00693 g008b
Sustainability 17 00693 g009
Figure 9. Pattern III recognition.
Figure 9. Pattern III recognition.
Sustainability 17 00693 g009
Table 1. Prediction of industrial water demand in the Yellow River Basin of Gansu Province in 2030.
Table 1. Prediction of industrial water demand in the Yellow River Basin of Gansu Province in 2030.
City30% Confidence Range for Industrial Water Demand (×100 Mm3)
Lower LimitUpper Limit
Wuwei0.050.10
Lanzhou1.654.00
Baiyin0.570.89
Linxia0.130.25
Dingxi1.471.47
Tianshui0.180.36
Pingliang0.250.63
Qingyang0.400.65
Gannan0.020.05
total4.728.39
Table 2. Calculation of industrial supply water range in the Yellow River Basin of Gansu Province in 2030.
Table 2. Calculation of industrial supply water range in the Yellow River Basin of Gansu Province in 2030.
CityIndustrial Water Consumption Red Line (×100 Mm3)Industrial Water Availability (×100 Mm3)Supply Water Range (×100 Mm3)
Value10%12%10%15%
Wuwei0.110.130.090.130.090.11
Lanzhou1.621.941.321.991.321.62
Baiyin1.241.490.981.470.981.24
Linxia0.420.50.290.430.290.42
Dingxi0.530.630.580.870.530.63
Tianshui0.530.630.480.720.480.53
Pingliang0.50.60.460.680.460.5
Qingyang0.460.550.380.570.380.46
Gannan0.080.090.040.070.040.08
total5.486.584.626.934.575.58
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Ma, M.; Chu, J.; Zhou, Z.; Tang, Z.; Zhang, Y.; Zhou, T.; Zhang, X.; Wang, Y. Uncertainty-Based Industrial Water Supply and Demand Balance Pattern Recognition: A Case Study in the Yellow River Basin of Gansu Province, China. Sustainability 2025, 17, 693. https://doi.org/10.3390/su17020693

AMA Style

Ma M, Chu J, Zhou Z, Tang Z, Zhang Y, Zhou T, Zhang X, Wang Y. Uncertainty-Based Industrial Water Supply and Demand Balance Pattern Recognition: A Case Study in the Yellow River Basin of Gansu Province, China. Sustainability. 2025; 17(2):693. https://doi.org/10.3390/su17020693

Chicago/Turabian Style

Ma, Mingyue, Junying Chu, Zuhao Zhou, Zuohuai Tang, Yunfu Zhang, Tianhong Zhou, Xusheng Zhang, and Ying Wang. 2025. "Uncertainty-Based Industrial Water Supply and Demand Balance Pattern Recognition: A Case Study in the Yellow River Basin of Gansu Province, China" Sustainability 17, no. 2: 693. https://doi.org/10.3390/su17020693

APA Style

Ma, M., Chu, J., Zhou, Z., Tang, Z., Zhang, Y., Zhou, T., Zhang, X., & Wang, Y. (2025). Uncertainty-Based Industrial Water Supply and Demand Balance Pattern Recognition: A Case Study in the Yellow River Basin of Gansu Province, China. Sustainability, 17(2), 693. https://doi.org/10.3390/su17020693

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop