Simulation of Flood Control by Rainwater Storage Facilities in Urbanized Watershed

Suharyanto, Agus; Sugio, Satoru; Deguchi, Chikashi; Kunitake, Masato

doi:10.2208/jscej.1997.572_95

Cited by 3 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the mechanical modeling approach, floods are simulated accurately based on hydraulic equations so no supervisory data is required. Several types of mechanical modeling have been carried out to suit the target environment: Xanthopoulos et al carried out a 2D flooding analysis using a diffusion wave equation [12], Fennema et al carried out surface flooding analysis using a dynamic wave equation [13], and Suharyanto et al carried out slope flooding analysis using a kinematic wave equation [14]. For urban flood analysis, an integrated flood analysis model that combines multiple mechanical models is used to simulate water movements on the ground surface and in sewer pipelines [15].…”

Section: Mechanical Modeling Approachmentioning

confidence: 99%

Machine Learning Framework Supervised by Hydraulic Mechanical Models for Real-time Pluvial Flood Prediction

Kondo

Narusue

et al. 2023

Journal of Information Processing

View full text Add to dashboard Cite

Real-time flood prediction in urban areas is an important tool for city emergency planning. Earlier studies suggest two approaches to predict flooding: a supervised machine learning approach based on observed data and a modeling approach for urban environments based on hydraulics. However, the first approach can only be applied in areas where there is sufficient data on flooding and is not accurate enough for prediction. The second approach can provide accurate predictions even for cities that have never experienced flooding, but models of complex urban environments are not suitable for real-time prediction owing to significant computational complexity. Therefore, we propose a third approach, machine learning supervised by a program. This approach consists of training a lightweight neural network using an integrated flood analysis program composed of multiple hydrologically based models. We demonstrate that this trained neural network is 19.8 times faster and and has accuracy comparable to that of the previous modeling approaches.

show abstract