Application of machine learning-based surrogate models for urban flood depth modeling in Ho Chi Minh City, Vietnam

Applied Soft Computing, Journal Year: 2023, Volume and Issue: 150, P. 111031 - 111031

Published: Nov. 10, 2023

Language: Английский

---

On the accuracy requirement of surrogate models for adequate global sensitivity analysis of urban low-impact development model

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 133102 - 133102

Published: March 1, 2025

Language: Английский

---

Quantifying the impact of river levels on urban drainage capacity

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: April 15, 2025

When river flooding and urban waterlogging occur simultaneously, the rising water level could reduce drainage capacity of pipe network, thereby exacerbating risk. This study quantitatively analyzed impact fluctuations on network. A 1D network model was coupled with a 2D hydrodynamic to simulate different combination scenarios, based which flow coefficient formula fitted. The results indicate that is closely related outflow conditions. Under free conditions, remains largely unaffected by external levels. However, when 1 2 times (in term diameter outlet) higher than bottom outlet, phenomenon inundation begins emerge, progressively weakening capacity. exceeds twice diminishes rapidly zero, backflow may occur. Taking Beijing Sub-center as case study, findings reveal during normal levels, operates effectively, ensuring proper drainage. under high becomes limited or even ineffective. During recession phase, river's influence diminishes, leading partial recovery drainage, although it cannot be fully restored. These provide important reference for combined scheduling floods waterlogging.

Language: Английский

---

An intelligent SWMM calibration method and identification of urban runoff generation patterns

Frontiers in Environmental Science, Journal Year: 2025, Volume and Issue: 13

Published: April 4, 2025

The accuracy of urban runoff simulation using the Storm Water Management Model (SWMM) largely depends on parameter calibration. This study proposes a universal and effective method to enhance model by optimizing value ranges through an unsupervised intelligent clustering algorithm. Simulation scenarios with varying proportions pervious impervious areas are established, sensitivity analysis is conducted rank key parameters identify dominant generation patterns. results show that when area less than 10%, most sensitive Zero.Imperv, N.Imperv, Dstore-Imperv, indicating primarily originates from surfaces. As increases, shifts areas, where Unit Hydrograph Model, fewer simpler calibration process, leads higher accuracy. These findings improve reliability SWMM provide reference for setting requirements under different surface conditions.

Language: Английский

---

Enhancing 2D hydrodynamic flood models through machine learning and urban drainage integration

Journal of Hydrology, Journal Year: 2025, Volume and Issue: 659, P. 133258 - 133258

Published: April 10, 2025

Language: Английский

---

Toward Improved Urban Building Energy Modeling Using a Place-Based Approach

Energies, Journal Year: 2023, Volume and Issue: 16(9), P. 3944 - 3944

Published: May 7, 2023

Urban building energy models present a valuable tool for promoting efficiency in design and control, as well managing urban systems. However, the current often overlook importance of site-specific characteristics, spatial attributes variations within specific area city. This methodological paper moves beyond state-of-the-art modeling urban-scale by incorporating an improved place-based approach to address this research gap. allows more in-depth understanding interactions behind patterns increase number quality energy-related variables. The outlines detailed description steps required create presents sample application results each model. pre-modeling phase is highlighted critical step which geo-database used collected, corrected, integrated. We also discuss use auto-correlation geo-database, introduces new spatial-temporal relationships that describe territorial clusters complex environment study identifies redefines three primary types modeling, including process-driven, data-driven, hybrid models, context approaches. challenges associated with type are highlighted, emphasis on data requirements availability concerns. concludes crucial achieving self-sufficiency districts or cities energy-modeling studies.

Language: Английский

---

A novel and efficient method for real-time simulating spatial and temporal evolution of coastal urban pluvial flood without drainage network

Environmental Modelling & Software, Journal Year: 2023, Volume and Issue: 172, P. 105888 - 105888

Published: Nov. 22, 2023

Language: Английский

---

Machine learning-based surrogate modelling of a robust, sustainable development goal (SDG)-compliant land-use future for Australia at high spatial resolution

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 363, P. 121296 - 121296

Published: June 5, 2024

Language: Английский

---

Spatial–temporal evolution characteristics of PM2.5 and its driving mechanism: spatially explicit insights from Shanxi Province, China

Environmental Monitoring and Assessment, Journal Year: 2024, Volume and Issue: 196(7)

Published: June 19, 2024

Language: Английский

---

Layout Optimization for Stormwater Harvesting Facilities in Coal Ports Considering Stochasticity of Underlying Surface Types

Journal of Construction Engineering and Management, Journal Year: 2024, Volume and Issue: 150(10)

Published: July 29, 2024

Language: Английский

---