Water resource utilization and future supply–demand scenarios in energy cities of semi-arid regions

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 10, 2025

Analyzing the characteristics of water resource utilization and forecasting future supply–demand dynamics are great practical significance for planning allocation. This study focuses on challenges in energy cities located semi-arid regions, using Qingyang City as a case study. The demand various sectors was simulated projected, balance under different socioeconomic climate scenarios analyzed Shared Socioeconomic Pathways framework combined with model data. research addresses gap existing literature concerning analysis structures change provides scientific support regional sustainable development. results show that: (1) Over past 20 years, supply have exhibited significant growth trends, agricultural use continuously increasing, industrial fluctuating, domestic remaining stable, ecological growing significantly; (2) From 2024 to 2035, is projected substantially, being highly sensitive scenario configurations; (3) Under high economic scenarios, likely face severe shortages.

Language: Английский

---

Monitoring the Industrial waste polluted stream - Integrated analytics and machine learning for water quality index assessment

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 450, P. 141877 - 141877

Published: March 28, 2024

Language: Английский

---

Stacked hybridization to enhance the performance of artificial neural networks (ANN) for prediction of water quality index in the Bagh river basin, India

Heliyon, Journal Year: 2024, Volume and Issue: 10(10), P. e31085 - e31085

Published: May 1, 2024

Water quality assessment is paramount for environmental monitoring and resource management, particularly in regions experiencing rapid urbanization industrialization. This study introduces Artificial Neural Networks (ANN) its hybrid machine learning models, namely ANN-RF (Random Forest), ANN-SVM (Support Vector Machine), ANN-RSS Subspace), ANN-M5P (M5 Pruned), ANN-AR (Additive Regression) water the rapidly urbanizing industrializing Bagh River Basin, India. The Relief algorithm was employed to select most influential input parameters, including Nitrate (NO

Language: Английский

---

Evaluation and Prediction of Agricultural Water Use Efficiency in the Jianghan Plain Based on the Tent-SSA-BPNN Model

Agriculture, Journal Year: 2025, Volume and Issue: 15(2), P. 140 - 140

Published: Jan. 9, 2025

The Jianghan Plain (JHP) is a key agricultural area in China where efficient water use (AWUE) vital for sustainable management, food security, environmental sustainability, and economic growth. This study introduces novel AWUE prediction model the JHP, combining BP neural network with Sparrow Search Algorithm (SSA) an improved Tent Mixing (Tent-SSA-BPNN). hybrid addresses limitations of traditional methods by enhancing forecast accuracy stability. By integrating historical data factors, provides detailed understanding AWUE’s spatial temporal variations. Compared to networks other methods, Tent-SSA-BPNN significantly improves stability, achieving (ACC) 96.218%, root mean square error (RMSE) 0.952, coefficient determination (R2) 0.9939, surpassing previous models. results show that (1) from 2010 2022, average JHP fluctuated within specific range, exhibiting decrease 0.69%, significant differences distributions across various cities; (2) was (R²) value 0.9939. (3) those preoptimization model, ACC, RMSE, R² values terms clearly indicating efficacy optimization. (4) reveal proportion consumption has impact on AWUE. These provide actionable insights optimizing resource allocation, particularly water-scarce regions, guide policymakers management strategies, supporting development.

Language: Английский

---

The Optimization of River Network Water Pollution Control Based on Hydrological Connectivity Measures

Water, Journal Year: 2025, Volume and Issue: 17(2), P. 197 - 197

Published: Jan. 13, 2025

Urbanization, driven by socio-economic development, has significantly impacted river ecosystems, particularly in plain city regions, leading to disruptions network structure and function. These changes have exacerbated hydrological fluctuations ecological degradation. This study focuses on the central urban area of Changzhou using a MIKE11 model assess effects four connectivity strategies—water diversion scheduling, connectivity, dredging, sluice connectivity—across 13 different scenarios. The results show that water diversion, scenarios provide greatest improvements environmental capacity, with maximum increases 54.76%, 41.97%, 25.62%, respectively. spatial distribution reveals significant regional variation, some areas, Tianning Zhonglou districts, experiencing declines capacity under river-connectivity In addition, Lao Zaogang River is identified as crucial for improving overall quality network. Based multi-objective evaluation, combining economic factors, recommends optimizing scheduling at sluices (Weicun, Zaogang, Xiaohe) flow rates between 20–40 m3/s, enhancing key hubs, focusing management efforts Xinmeng rivers strengthen linkages within

Language: Английский

---

Harnessing Deep Learning for Real-Time Water Quality Assessment: A Sustainable Solution

Water, Journal Year: 2024, Volume and Issue: 16(23), P. 3380 - 3380

Published: Nov. 24, 2024

This study presents an innovative approach utilizing artificial intelligence (AI) for the prediction and classification of water quality parameters based on physico-chemical measurements. The primary objective was to enhance accuracy, speed, accessibility monitoring. Data collected from various samples in Algeria were analyzed determine key such as conductivity, turbidity, pH, total dissolved solids (TDS). These measurements integrated into deep neural networks (DNNs) predict indices sodium adsorption ratio (SAR), magnesium hazard (MH), percentage (SP), Kelley’s (KR), potential salinity (PS), exchangeable (ESP), well Water Quality Index (WQI) Irrigation (IWQI). DNNs model, optimized through selection activation functions hidden layers, demonstrated high precision, with a correlation coefficient (R) 0.9994 low root mean square error (RMSE) 0.0020. AI-driven methodology significantly reduces reliance traditional laboratory analyses, offering real-time assessments that are adaptable local conditions environmentally sustainable. provides practical solution resource managers, particularly resource-limited regions, efficiently monitor make informed decisions public health agricultural applications.

Language: Английский

---

A novel approach for quantifying the influence intensity of urban water and greenery resources on microclimate for efficient utilization

Sustainable Cities and Society, Journal Year: 2024, Volume and Issue: 112, P. 105597 - 105597

Published: June 20, 2024

Climate changes have led to increasing global energy consumption, detrimental the sustainable development of society. Urban blue-green infrastructure (UBGI) can improve urban microclimate. However, influence intensity UBGI on microclimate has not been quantified deeply use efficiency water and greenery resources. To solve research deficiencies, this study numerically simulated for 44 scenarios with different resource configurations (various body areas coverages) in summer. Based simulations, developed novel mathematical models thermo-environment (BGTE) quantify UBGI. The results indicated that daytime synergies first increased then decreased time. significance time (t), area (Sw), tree coverage rate (TCR), shrub (SCR), grassland (GLCR) synergy was by artificial neural network: t (39.4%), Sw (22.6%), TCR (22.0%), SCR (13.2%), GLCR (2.8%). make overall effect relatively efficient, should be less than 10000 m2, greater 65%, close 15%. This provides practical ideas efficient

Language: Английский

---

Machine Learning for Smart Irrigation in Agriculture: How Far along Are We?

Information, Journal Year: 2024, Volume and Issue: 15(6), P. 306 - 306

Published: May 24, 2024

The management of water resources is becoming increasingly important in several contexts, including agriculture. Recently, innovative agricultural practices, advanced sensors, and Internet Things (IoT) devices have made it possible to improve the efficiency use. However, application control strategies based on machine learning techniques that enables adoption smart irrigation scheduling immediate economic, social, environmental benefits. This challenging research area has attracted attention many researchers worldwide, who proposed technological methodological solutions. Unfortunately, results these scientific efforts not yet been categorized a thematic survey, making difficult understand how far we are from optimal learning. paper fills this gap by focusing systems with an emphasis More specifically, generic structure agriculture system presented, existing available datasets discussed. Furthermore, open issues identified, especially processing long-term data, also due lack corresponding annotated datasets. Finally, some interesting future directions be pursued order build scalable, domain-independent approaches proposed.

Language: Английский

---

Explainable Artificial Intelligence for Reliable Water Demand Forecasting to Increase Trust in Predictions

Water Research, Journal Year: 2024, Volume and Issue: 268, P. 122779 - 122779

Published: Nov. 9, 2024

Language: Английский

---

Deep learning and smart energy-based lightweight urban power load forecasting model for sustainable urban growth

Frontiers in Sustainable Cities, Journal Year: 2025, Volume and Issue: 6

Published: Jan. 15, 2025

Introduction Urban power load forecasting is essential for smart grid planning but hindered by data imbalance issues. Traditional single-model approaches fail to address this effectively, while multi-model methods mitigate splitting datasets incur high costs and risk losing shared distribution characteristics. Methods A lightweight urban model (DLUPLF) proposed, enhancing LSTM networks with contrastive loss in short-term sampling, a difference compensation mechanism, feature extraction layer reduce costs. The adjusts predictions learning differences employs dynamic class-center regularization. Its performance was evaluated through parameter tuning comparative analysis. Results DLUPLF demonstrated improved accuracy imbalanced reducing computational It preserved characteristics outperformed traditional efficiency prediction accuracy. Discussion effectively addresses complexity challenges, making it promising solution forecasting. Future work will focus on real-time applications broader systems.

Language: Английский

---