Slope Deformation Prediction Combining Particle Swarm Optimization-Based Fractional-Order Grey Model and K-Means Clustering DOI Creative Commons
Zhenzhu Meng, Yating Hu, Shan Jiang

и другие.

Fractal and Fractional, Год журнала: 2025, Номер 9(4), С. 210 - 210

Опубликована: Март 28, 2025

Slope deformation poses significant risks to infrastructure, ecosystems, and human safety, making early accurate predictions essential for mitigating slope failures landslides. In this study, we propose a novel approach that integrates fractional-order grey model (FOGM) with particle swarm optimization (PSO) determine the optimal fractional order, thereby enhancing model’s accuracy, even limited fluctuating data. Additionally, employ k-means clustering technique account both temporal spatial variations in multi-point monitoring data, which improves ability capture relationships between points increases prediction relevance. The was validated using displacement data collected from 12 on located Qinghai Province near Yellow River, China. results demonstrate proposed outperforms traditional statistical artificial neural networks, achieving significantly higher coefficient of determination R2 up 0.9998 some points. Our findings highlight maintains robust performance when confronted varying quality—a notable advantage over conventional approaches typically struggle under such conditions. Overall, offers data-efficient solution prediction, providing substantial potential warning systems risk management.

Язык: Английский

Optimization of Water Quantity Allocation in Multi-Source Urban Water Supply Systems Using Graph Theory DOI Open Access
Jinxin Zhang, Xinhai Zhang,

Hanze Li

и другие.

Water, Год журнала: 2024, Номер 17(1), С. 61 - 61

Опубликована: Дек. 29, 2024

The optimization of urban multi-source water supply systems is essential for addressing the growing challenges allocation, cost management, and system resilience in modern cities. This study introduces a graph-theory-based model to analyze structural operational dynamics systems, incorporating constraints such as quality, pressure, connectivity. Using Lishui City case study, evaluates three allocation plans meet projected 2030 demand. Advanced algorithms, including Floyd’s shortest path algorithm GA-COA-SA hybrid algorithm, were employed address pipeline quality attenuation, nonlinear flow dynamics. Results indicate 1.4% improvement cost-effectiveness compared current strategy, highlighting model’s capability enhance efficiency. Among evaluated options, Plan 2 emerges most cost-effective solution, achieving capacity 4.5920 × 105 m3/d with lowest annual 5.7015 107 yuan, improve both efficiency resilience. prioritizes cost-efficiency tailored regional challenges, distinguishing itself from prior research that emphasized redundancy analysis. findings demonstrate potential graph-theoretic approaches combined advanced techniques decision-making sustainable management.

Язык: Английский

Процитировано

6
Predicting the Dynamic of Debris Flow Based on Viscoplastic Theory and Support Vector Regression DOI Open Access
Xinhai Zhang,

Hanze Li,

Yazhou Fan

и другие.

Water, Год журнала: 2025, Номер 17(1), С. 120 - 120

Опубликована: Янв. 4, 2025

The prediction of debris flows is essential for safeguarding infrastructure and minimizing the economic losses associated with hazards. Traditional empirical theoretical models, while providing foundational insights, often struggle to capture complex nonlinear behaviors inherent in flows. This study aims enhance flow by integrating modeling data-driven approaches. We model as a viscoplastic fluid, employing Herschel–Bulkley rheological describe its behavior. By combining kinematic wave lubrication theory, we develop comprehensive framework that encapsulates mechanical physics identifies key governing parameters. Numerical solutions this are utilized generate an extensive training dataset, which subsequently used train support vector regression (SVR) model. SVR targets slide depth velocity upon impact, using explanatory variables including yield stress, material density, source area length, slope length. demonstrates high predictive accuracy, achieving coefficients determination R2 0.956 0.911 at impact. Additionally, relative residuals σ primarily distributed within range −0.05 0.05 both These results indicate proposed hybrid not only incorporates fundamental physical mechanisms but also significantly enhances performance through optimization. underscores critical advantage merging models machine learning techniques, offering robust tool improved risk assessment, can inform development more effective early warning systems mitigation measures.

Язык: Английский

Процитировано

0
An Analysis of the Current Situation of Ecological Flow Release from Large- and Medium-Sized Reservoirs in the Southeastern River Basins of China DOI Open Access
Yijing Chen, Hui Nie,

Gaozhan Liu

и другие.

Water, Год журнала: 2025, Номер 17(3), С. 451 - 451

Опубликована: Фев. 6, 2025

Ecological flow is a crucial determinant of river ecosystem well-being and aquatic stability. Large- medium-sized reservoirs, with flood prevention, irrigation, power generation functions, necessitate scientifically devised ecological release plan for conservation water quality amelioration. This study centered on three reservoirs in the Jiaojiang River Basin Zhejiang Province, China. Using measured outflow data, hydrological approach was initially adopted to calculate individual reservoir flows. Subsequently, entropy weight method employed ascertain most suitable flow. grade thresholds were then established formulate optimal scheme. The outcomes demonstrated that average flows Xia’an, Lishimen, Longxi 1.90 m3/s, 1.95 0.42 respectively. multi-year assurance rates 62.53%, 77.72%, 56.94%, successively. weighted downstream 2.10 2.28 0.44 m3/s. During periods when monthly rate below 60%, implemented schemes installing siphons, renovating diversion systems, using post-dam units,

Язык: Английский

Процитировано

0
Machine Learnings Integrating with Preceding Sst Patterns Allow for Skillful Forecast of Compound Dry-Hot Events DOI
Xushu Wu, Xinle Feng,

Zhaoli Wang

и другие.

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Response of the Evolution of Basin Hydrometeorological Drought to ENSO: A Case Study of the Jiaojiang River Basin in Southeast China DOI Open Access

He Qiu,

Hao Chen, Yijing Chen

и другие.

Sustainability, Год журнала: 2025, Номер 17(6), С. 2616 - 2616

Опубликована: Март 16, 2025

Drought is one of the most widespread natural disasters globally, and its spatiotemporal distribution profoundly influenced by El Niño-Southern Oscillation (ENSO). As a typical humid coastal basin, Jiaojiang River Basin in southeastern China frequently experiences hydrological extremes such as dry spells during flood seasons. This study focuses on Basin, aiming to investigate response mechanisms drought evolution ENSO regions. employs 10-day scale data from 1991 2020 driven through comprehensive framework that combines standardized indices with climate–drought correlation analysis. The results indicate Comprehensive Index (CDI), integrating advantages Standardized Precipitation (SPI) Runoff (SRI), effectively reflects basin’s combined meteorological wet-dry characteristics. A strong relationship exists between events. characteristics basin vary significantly different phases. findings can provide theoretical support for construction resilient regional water resource systems, research holds reference value sustainable development practices similar regions globally.

Язык: Английский

Процитировано

0
Slope Deformation Prediction Combining Particle Swarm Optimization-Based Fractional-Order Grey Model and K-Means Clustering DOI Creative Commons
Zhenzhu Meng, Yating Hu, Shan Jiang

и другие.

Fractal and Fractional, Год журнала: 2025, Номер 9(4), С. 210 - 210

Опубликована: Март 28, 2025

Slope deformation poses significant risks to infrastructure, ecosystems, and human safety, making early accurate predictions essential for mitigating slope failures landslides. In this study, we propose a novel approach that integrates fractional-order grey model (FOGM) with particle swarm optimization (PSO) determine the optimal fractional order, thereby enhancing model’s accuracy, even limited fluctuating data. Additionally, employ k-means clustering technique account both temporal spatial variations in multi-point monitoring data, which improves ability capture relationships between points increases prediction relevance. The was validated using displacement data collected from 12 on located Qinghai Province near Yellow River, China. results demonstrate proposed outperforms traditional statistical artificial neural networks, achieving significantly higher coefficient of determination R2 up 0.9998 some points. Our findings highlight maintains robust performance when confronted varying quality—a notable advantage over conventional approaches typically struggle under such conditions. Overall, offers data-efficient solution prediction, providing substantial potential warning systems risk management.

Язык: Английский

Процитировано

0