PMID- 36333429
OWN - NLM
STAT- MEDLINE
DCOM- 20221108
LR  - 20230104
IS  - 2045-2322 (Electronic)
IS  - 2045-2322 (Linking)
VI  - 12
IP  - 1
DP  - 2022 Nov 4
TI  - Unraveling the complexities of urban fluvial flood hydraulics through AI.
PG  - 18738
LID - 10.1038/s41598-022-23214-9 [doi]
LID - 18738
AB  - As urbanization increases across the globe, urban flooding is an ever-pressing 
      concern. Urban fluvial systems are highly complex, depending on a myriad of 
      interacting variables. Numerous hydraulic models are available for analyzing 
      urban flooding; however, meeting the demand of high spatial extension and finer 
      discretization and solving the physics-based numerical equations are 
      computationally expensive. Computational efforts increase drastically with an 
      increase in model dimension and resolution, preventing current solutions from 
      fully realizing the data revolution. In this research, we demonstrate the 
      effectiveness of artificial intelligence (AI), in particular, machine learning 
      (ML) methods including the emerging deep learning (DL) to quantify urban flooding 
      considering the lower part of Darby Creek, PA, USA. Training datasets comprise 
      multiple geographic and urban hydraulic features (e.g., coordinates, elevation, 
      water depth, flooded locations, discharge, average slope, and the impervious area 
      within the contributing region, downstream distance from stormwater outfalls and 
      dams). ML Classifiers such as logistic regression (LR), decision tree (DT), 
      support vector machine (SVM), and K-nearest neighbors (KNN) are used to identify 
      the flooded locations. A Deep neural network (DNN)-based regression model is used 
      to quantify the water depth. The values of the evaluation matrices indicate 
      satisfactory performance both for the classifiers and DNN model (F-1 scores- 
      0.975, 0.991, 0.892, and 0.855 for binary classifiers; root mean squared error- 
      0.027 for DNN regression). In addition, the blocked K-folds Cross Validation (CV) 
      of ML classifiers in detecting flooded locations showed satisfactory performance 
      with the average accuracy of 0.899, which validates the models to generalize to 
      the unseen area. This approach is a significant step towards resolving the 
      complexities of urban fluvial flooding with a large multi-dimensional dataset in 
      a highly computationally efficient manner.
CI  - (c) 2022. The Author(s).
FAU - Mehedi, Md Abdullah Al
AU  - Mehedi MAA
AD  - Villanova Centre of Resilient Water System, Villanova University, Villanova, PA, 
      USA. mmehedi@villanova.edu.
FAU - Smith, Virginia
AU  - Smith V
AD  - Villanova Centre of Resilient Water System, Villanova University, Villanova, PA, 
      USA.
FAU - Hosseiny, Hossein
AU  - Hosseiny H
AD  - Department of Earth and Planetary Sciences, Washington University in St. Louis, 
      St. Louis, MO, USA.
FAU - Jiao, Xun
AU  - Jiao X
AD  - Department of Electrical and Computer Engineering, Villanova University, 
      Villanova, PA, USA.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20221104
PL  - England
TA  - Sci Rep
JT  - Scientific reports
JID - 101563288
RN  - 059QF0KO0R (Water)
SB  - IM
MH  - *Artificial Intelligence
MH  - *Floods
MH  - Neural Networks, Computer
MH  - Support Vector Machine
MH  - Water
PMC - PMC9636396
COIS- The authors declare no competing interests.
EDAT- 2022/11/06 06:00
MHDA- 2022/11/09 06:00
PMCR- 2022/11/04
CRDT- 2022/11/05 00:32
PHST- 2022/04/27 00:00 [received]
PHST- 2022/10/26 00:00 [accepted]
PHST- 2022/11/06 06:00 [pubmed]
PHST- 2022/11/09 06:00 [medline]
PHST- 2022/11/05 00:32 [entrez]
PHST- 2022/11/04 00:00 [pmc-release]
AID - 10.1038/s41598-022-23214-9 [pii]
AID - 23214 [pii]
AID - 10.1038/s41598-022-23214-9 [doi]
PST - epublish
SO  - Sci Rep. 2022 Nov 4;12(1):18738. doi: 10.1038/s41598-022-23214-9.