Bed Topography Inference from Velocity Field Using Deep Learning
Measuring bathymetry has always been a major scientific and technological challenge. In this work, we used a deep learning technique for inferring bathymetry from the depth-averaged velocity field. The training of the neural network is based on 5742 laboratory data using a gravel-bed flume and recon...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/23/4055 |
| _version_ | 1797399473765220352 |
|---|---|
| author | Mehrdad Kiani-Oshtorjani Christophe Ancey |
| author_facet | Mehrdad Kiani-Oshtorjani Christophe Ancey |
| author_sort | Mehrdad Kiani-Oshtorjani |
| collection | DOAJ |
| description | Measuring bathymetry has always been a major scientific and technological challenge. In this work, we used a deep learning technique for inferring bathymetry from the depth-averaged velocity field. The training of the neural network is based on 5742 laboratory data using a gravel-bed flume and reconstructed velocity fields, namely the topographies were obtained from real-world experiments, and the velocity fields were estimated using a statistical model. To examine the predictive power of the proposed neural network model for bathymetry inference, we applied the model to flume experiments, numerical simulations, and field data. The results showed the model properly estimates topography, leading to a model for riverine bathymetry estimation with a 31.3% maximum relative error for the case study (confluence of the Kaskaskia River with the Copper Slough in east-central Illinois state, USA). |
| first_indexed | 2024-03-09T01:40:48Z |
| format | Article |
| id | doaj.art-2418ada76545464c90f629e2e34e4c02 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-09T01:40:48Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-2418ada76545464c90f629e2e34e4c022023-12-08T15:28:15ZengMDPI AGWater2073-44412023-11-011523405510.3390/w15234055Bed Topography Inference from Velocity Field Using Deep LearningMehrdad Kiani-Oshtorjani0Christophe Ancey1Environmental Hydraulics Laboratory, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, SwitzerlandEnvironmental Hydraulics Laboratory, École Polytechnique Fédérale de Lausanne, 1015 Lausanne, SwitzerlandMeasuring bathymetry has always been a major scientific and technological challenge. In this work, we used a deep learning technique for inferring bathymetry from the depth-averaged velocity field. The training of the neural network is based on 5742 laboratory data using a gravel-bed flume and reconstructed velocity fields, namely the topographies were obtained from real-world experiments, and the velocity fields were estimated using a statistical model. To examine the predictive power of the proposed neural network model for bathymetry inference, we applied the model to flume experiments, numerical simulations, and field data. The results showed the model properly estimates topography, leading to a model for riverine bathymetry estimation with a 31.3% maximum relative error for the case study (confluence of the Kaskaskia River with the Copper Slough in east-central Illinois state, USA).https://www.mdpi.com/2073-4441/15/23/4055bathymetry estimationdeep learningU-net architectureentropy-based modelsinverse modelinggravel-bed flume/river |
| spellingShingle | Mehrdad Kiani-Oshtorjani Christophe Ancey Bed Topography Inference from Velocity Field Using Deep Learning Water bathymetry estimation deep learning U-net architecture entropy-based models inverse modeling gravel-bed flume/river |
| title | Bed Topography Inference from Velocity Field Using Deep Learning |
| title_full | Bed Topography Inference from Velocity Field Using Deep Learning |
| title_fullStr | Bed Topography Inference from Velocity Field Using Deep Learning |
| title_full_unstemmed | Bed Topography Inference from Velocity Field Using Deep Learning |
| title_short | Bed Topography Inference from Velocity Field Using Deep Learning |
| title_sort | bed topography inference from velocity field using deep learning |
| topic | bathymetry estimation deep learning U-net architecture entropy-based models inverse modeling gravel-bed flume/river |
| url | https://www.mdpi.com/2073-4441/15/23/4055 |
| work_keys_str_mv | AT mehrdadkianioshtorjani bedtopographyinferencefromvelocityfieldusingdeeplearning AT christopheancey bedtopographyinferencefromvelocityfieldusingdeeplearning |