Loading…
Application of deep learning to large scale riverine flow velocity estimation
Fast and reliable prediction of riverine flow velocities plays an important role in many applications, including flood risk management. The shallow water equations (SWEs) are commonly used for prediction of the riverine flow velocities. However, accurate and fast prediction with standard SWE solvers...
Saved in:
Published in: | Stochastic environmental research and risk assessment 2021-05, Vol.35 (5), p.1069-1088 |
---|---|
Main Authors: | , , , , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Fast and reliable prediction of riverine flow velocities plays an important role in many applications, including flood risk management. The shallow water equations (SWEs) are commonly used for prediction of the riverine flow velocities. However, accurate and fast prediction with standard SWE solvers remains challenging in many cases. Traditional approaches are computationally expensive and require high-resolution measurement of riverbed profile (i.e., bathymetry) for accurate predictions. As a result, they are a poor fit in situations where they need to be evaluated repetitively due, for example, to varying boundary condition (BC) scenarios, or when the bathymetry is not known with certainty. In this work, we propose a two-stage process that tackles these issues. First, using the principal component geostatistical approach we estimate the probability density function of the bathymetry from flow velocity measurements, and then we use multiple machine learning algorithms in order to obtain a fast solver of the SWEs, given augmented realizations from the posterior bathymetry distribution and the prescribed range of potential BCs. The first step of the proposed approach allows us to predict flow velocities without any direct measurement of the bathymetry. Furthermore, the augmentation of the distribution in the second stage allows incorporation of the additional bathymetry information into the flow velocity prediction for improved accuracy and generalization, even if the bathymetry changes over time. Here, we use three different forward solvers, referred to as principal component analysis-deep neural network, supervised encoder, and supervised variational encoder, and validate them on a reach of the Savannah river near Augusta, GA. Our results show that the fast solvers are capable of predicting flow velocities with variable bathymetry and BCs with good accuracy, at a computational cost that is significantly lower than the cost of solving the full boundary value problem with traditional methods. |
---|---|
ISSN: | 1436-3240 1436-3259 |
DOI: | 10.1007/s00477-021-01988-0 |