This is a Preprint and has not been peer reviewed. This is version 3 of this Preprint.
Downloads
Authors
Abstract
A deep learning rainfall-runoff model can take multiple meteorological forcing products as inputs and learn to combine them in spatially and temporally dynamic ways. This is demonstrated using Long Short Term Memory networks (LSTMs) trained over basins in the continental US using the CAMELS data set. Using multiple precipitation products (NLDAS, Maurer, DayMet) in a single LSTM significantly improved simulation accuracy relative to using only individual precipitation products. A sensitivity analysis showed that the LSTM learned to utilize different precipitation products in different ways in different basins and for simulating different parts of the hydrograph in individual basins.
DOI
https://doi.org/10.31223/osf.io/pjm5a
Subjects
Earth Sciences, Hydrology, Physical Sciences and Mathematics
Keywords
machine learning, Deep learning, hydrology, modeling, Rainfall-Runoff
Dates
Published: 2020-05-08 21:31
There are no comments or no comments have been made public for this article.