Presenters-0670: Difference between revisions

From CSDMS
m Add youtube views template if missing
m Text replacement - "\|CSDMS meeting youtube views=\{\{(Youtube_[^}]+)\}\}" to "|CSDMS meeting youtube views={{#explode:{{$1}}| |0}} |CSDMS meeting youtube AverageViews={{#explode:{{$1}}| |1}}"
 
Line 14: Line 14:
In this presentation, we look at some of the research from the past few years and try to understand why the LSTM is a particularly well suited architecture for the application as rainfall-runoff model but also discuss limitations and open research questions.
In this presentation, we look at some of the research from the past few years and try to understand why the LSTM is a particularly well suited architecture for the application as rainfall-runoff model but also discuss limitations and open research questions.
|CSDMS meeting youtube code=ShTA-D6XDDE
|CSDMS meeting youtube code=ShTA-D6XDDE
|CSDMS meeting youtube views={{Youtube_ShTA-D6XDDE}}
|CSDMS meeting youtube views={{#explode:{{Youtube_ShTA-D6XDDE}}| |0}}
|CSDMS meeting youtube AverageViews={{#explode:{{Youtube_ShTA-D6XDDE}}| |1}}
|CSDMS meeting participants=0
|CSDMS meeting participants=0
}}
}}

Latest revision as of 16:34, 11 June 2025

CSDMS 2025: Exploring Earth's Surface with Models, Data & AI


Long Short-Term Memory networks for rainfall-runoff modeling



Frederik Kratzert

Google Research, Austria
kratzert@google.com


Abstract
Long Short-Term Memory networks (LSTMs) have been around since the early 90’s but only in the last few years, LSTMs gained increasing popularity in hydrological sciences. Publication counts see exponential growth and LSTMs power some of the largest-scale operational flood forecasting systems. In this presentation, we look at some of the research from the past few years and try to understand why the LSTM is a particularly well suited architecture for the application as rainfall-runoff model but also discuss limitations and open research questions.

Please acknowledge the original contributors when you are using this material. If there are any copyright issues, please let us know (CSDMSweb@colorado.edu) and we will respond as soon as possible.

Of interest for:
  • Education and Knowledge Transfer (EKT) Working Group
  • Hydrology Focus Research Group
  • Artificial Intelligence & Machine Learning Initiative
  • River Network Modeling Initiative