Reference : Procedural generation of flood-sensitive urban layouts
Scientific journals : Article
Engineering, computing & technology : Civil engineering
http://hdl.handle.net/2268/229124
Procedural generation of flood-sensitive urban layouts
English
Mustafa, Ahmed Mohamed El Saeid mailto [Université de Liège - ULiège > Département ArGEnCo > LEMA (Local environment management and analysis) >]
Zhang, Xiao Wei [Purdue University, USA > > > >]
Aliaga [Purdue University, USA > > > >]
Bruwier, Martin mailto [Université de Liège - ULiège > Département ArGEnCo > Hydraulics in Environmental and Civil Engineering >]
Nishida, Gen [Purdue University, USA > > > >]
Dewals, Benjamin mailto [Université de Liège - ULiège > Département ArGEnCo > Hydraulics in Environmental and Civil Engineering >]
Erpicum, Sébastien mailto [Université de Liège - ULiège > > Scientifiques attachés au Doyen (Sc.appliquées) >]
Archambeau, Pierre mailto [Université de Liège - ULiège > Département ArGEnCo > HECE (Hydraulics in Environnemental and Civil Engineering) >]
Pirotton, Michel mailto [Université de Liège - ULiège > Département ArGEnCo > HECE (Hydraulics in Environnemental and Civil Engineering) >]
Teller, Jacques mailto [Université de Liège - ULiège > Département ArGEnCo > Urbanisme et aménagement du territoire >]
In press
Environment and Planning B: Urban Analytics and City Science
Sage Publications Ltd.
Yes (verified by ORBi)
International
2399-8083
2399-8091
London
United Kingdom
[en] Inverse procedural modeling ; urban layout ; urban flooding ; neural network ; Markov Chain Monte Carlo
[en] Aside from modeling geometric shape, three-dimensional (3D) urban procedural modeling has shown its value in understanding, predicting and/or controlling effects of shape on design and urban planning. In this paper, instead of the construction of flood resistant measures, we create a procedural generation system for designing urban layouts that passively reduce water depth during a flooding scenario. Our tool enables exploring designs that passively lower flood depth everywhere or mostly in chosen key areas. Our approach tightly integrates a hydraulic model and a parameterized urban generation system with an optimization engine so as to find the least cost modification to an initial urban layout design. Further, due to the computational cost of a fluid simulation, we train neural networks to assist with accelerating the design process. We have applied our system to several real-world locations and have obtained improved 3D urban models in just a few seconds.
Urban and Environmental Engineering
FloodLand
Researchers ; Professionals
http://hdl.handle.net/2268/229124
10.1177/2399808318812458

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Restricted access
Mustafa_2018_EPB_Proof.pdfPublisher postprint2.71 MBRequest copy

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.