2025 CSDMS meeting-027: Difference between revisions
From CSDMS
Created page with "{{CSDMS meeting personal information template-2025 |CSDMS meeting first name=Mohamed Fathi |CSDMS meeting last name=Said |CSDMS meeting institute=Florida Gulf Coast University |CSDMS meeting city=Fort Myers |CSDMS meeting country=United States |CSDMS meeting state=Florida |CSDMS meeting email address=m.fathi.said0@gmail.com |CSDMS meeting phone=4845819234 }} {{CSDMS meeting select clinics1 2025 |CSDMS_meeting_select_clinics1_2025=4) Get lazy with LLMs }} {{CSDMS meeting..." |
No edit summary |
||
| Line 19: | Line 19: | ||
}} | }} | ||
{{CSDMS meeting abstract yes no 2025 | {{CSDMS meeting abstract yes no 2025 | ||
|CSDMS meeting abstract submit 2025= | |CSDMS meeting abstract submit 2025=Yes | ||
}} | |||
{{CSDMS meeting abstract poster Epub 2025 | |||
|CSDMS meeting poster Epub submit 2025=Poster | |||
}} | |||
{{CSDMS meeting abstract title temp2025 | |||
|CSDMS meeting abstract title=Accelerate Bed-Change Simulations Using Spatiotemporal Deep Learning Framework | |||
|Working_group_member_WG_FRG=Hydrology Focus Research Group, Geodynamics Focus Research Group | |||
}} | |||
{{CSDMS meeting authors template | |||
|CSDMS meeting coauthor first name abstract=Virginia | |||
|CSDMS meeting coauthor last name abstract=Smith | |||
|CSDMS meeting coauthor institute / Organization=Villanova University | |||
|CSDMS meeting coauthor town-city=Villanova | |||
|CSDMS meeting coauthor country=United States | |||
|State=Pennsylvania | |||
|CSDMS meeting coauthor email address=virginia.smith@villanova.edu | |||
}} | |||
{{CSDMS meeting authors template | |||
|CSDMS meeting coauthor first name abstract=Zihan | |||
|CSDMS meeting coauthor last name abstract=Liu | |||
|CSDMS meeting coauthor institute / Organization=Villanova University | |||
|CSDMS meeting coauthor town-city=Villanova | |||
|CSDMS meeting coauthor country=United States | |||
|State=Pennsylvania | |||
|CSDMS meeting coauthor email address=zliu5@villanova.edu | |||
}} | |||
{{CSDMS meeting authors template | |||
|CSDMS meeting coauthor first name abstract=Anjali M. | |||
|CSDMS meeting coauthor last name abstract=Fernandes | |||
|CSDMS meeting coauthor institute / Organization=Denison University | |||
|CSDMS meeting coauthor town-city=Granville | |||
|CSDMS meeting coauthor country=United States | |||
|State=Ohio | |||
|CSDMS meeting coauthor email address=fernandesa@denison.edu | |||
}} | |||
{{CSDMS meeting authors template | |||
|CSDMS meeting coauthor first name abstract=Michael T. | |||
|CSDMS meeting coauthor last name abstract=Hren | |||
|CSDMS meeting coauthor institute / Organization=University of Connecticut | |||
|CSDMS meeting coauthor town-city=Storrs | |||
|CSDMS meeting coauthor country=United States | |||
|State=Connecticut | |||
|CSDMS meeting coauthor email address=michael.hren@uconn.edu | |||
}} | |||
{{CSDMS meeting authors template | |||
|CSDMS meeting coauthor first name abstract=Dennis O. | |||
|CSDMS meeting coauthor last name abstract=Terry | |||
|CSDMS meeting coauthor institute / Organization=Temple University | |||
|CSDMS meeting coauthor town-city=Philadelphia | |||
|CSDMS meeting coauthor country=United States | |||
|State=Pennsylvania | |||
|CSDMS meeting coauthor email address=dennis.terry@temple.edu | |||
}} | |||
{{CSDMS meeting authors template | |||
|CSDMS meeting coauthor first name abstract=C. | |||
|CSDMS meeting coauthor last name abstract=Nataraj | |||
|CSDMS meeting coauthor institute / Organization=Villanova University | |||
|CSDMS meeting coauthor town-city=Villanova | |||
|CSDMS meeting coauthor country=United States | |||
|State=Pennsylvania | |||
|CSDMS meeting coauthor email address=c.nataraj@villanova.edu | |||
}} | |||
{{CSDMS meeting abstract template 2025 | |||
|CSDMS meeting abstract=Traditional sediment transport models are constrained by their spatial and/or temporal resolution, requiring high computational power and consuming extensive processing time. This limitation poses a substantial challenge in modeling two-dimensional landscape evolution over long-term scales and in predicting the impacts of system dynamics, such as climate change. To address this shortcoming, we introduce a novel Deep Learning (DL) framework that integrates Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) to capture the spatiotemporal morphodynamics of rivers in response to flooding events. This framework combines three models to simulate essential hydrodynamic and morphodynamic features: water depth, flow velocity, and bed change, which operate in a continuous loop to ensure dynamic updates to bed topography. The proposed framework was trained and evaluated using a dataset generated by HEC-RAS, a physics-based model, for a 22 km segment of Ninnescah River in Kansas. The hydrodynamic results demonstrate proficiency in capturing the flood dynamics, where the average Root Mean Square Error (RMSE) across the testing dataset is 0.19 m and 0.04 m/s for water depth and flow velocity, respectively. These hydrodynamic features are essential for the bed-change model, which exhibits high accuracy with a normalized RMSE and an R2 of 27% and 0.93, respectively, at the end of the testing dataset. Furthermore, the trained framework can generate predictions 4700 times faster than HEC-RAS. This work signifies a paradigm shift in the long-term simulation of river evolution and sets the stage for exploring new frontiers in fluvial morphodynamic modeling. | |||
}} | }} | ||
{{blank line template}} | {{blank line template}} | ||
Latest revision as of 11:09, 22 March 2025
(if you haven't already)
Log in (or create account for non-CSDMS members)
Forgot username? Search or email:CSDMSweb@colorado.edu
Browse abstracts
Accelerate Bed-Change Simulations Using Spatiotemporal Deep Learning Framework
Mohamed Fathi Said,
Florida Gulf Coast University Fort Myers Florida, United States. m.fathi.said0@gmail.com
Virginia Smith, Villanova University Villanova Pennsylvania, United States. virginia.smith@villanova.edu
Zihan Liu, Villanova University Villanova Pennsylvania, United States. zliu5@villanova.edu
Anjali M. Fernandes, Denison University Granville Ohio, United States. fernandesa@denison.edu
Michael T. Hren, University of Connecticut Storrs Connecticut, United States. michael.hren@uconn.edu
Dennis O. Terry, Temple University Philadelphia Pennsylvania, United States. dennis.terry@temple.edu
C. Nataraj, Villanova University Villanova Pennsylvania, United States. c.nataraj@villanova.edu
Traditional sediment transport models are constrained by their spatial and/or temporal resolution, requiring high computational power and consuming extensive processing time. This limitation poses a substantial challenge in modeling two-dimensional landscape evolution over long-term scales and in predicting the impacts of system dynamics, such as climate change. To address this shortcoming, we introduce a novel Deep Learning (DL) framework that integrates Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) to capture the spatiotemporal morphodynamics of rivers in response to flooding events. This framework combines three models to simulate essential hydrodynamic and morphodynamic features: water depth, flow velocity, and bed change, which operate in a continuous loop to ensure dynamic updates to bed topography. The proposed framework was trained and evaluated using a dataset generated by HEC-RAS, a physics-based model, for a 22 km segment of Ninnescah River in Kansas. The hydrodynamic results demonstrate proficiency in capturing the flood dynamics, where the average Root Mean Square Error (RMSE) across the testing dataset is 0.19 m and 0.04 m/s for water depth and flow velocity, respectively. These hydrodynamic features are essential for the bed-change model, which exhibits high accuracy with a normalized RMSE and an R2 of 27% and 0.93, respectively, at the end of the testing dataset. Furthermore, the trained framework can generate predictions 4700 times faster than HEC-RAS. This work signifies a paradigm shift in the long-term simulation of river evolution and sets the stage for exploring new frontiers in fluvial morphodynamic modeling.
