Snow water equivalent forecasting in Sub-Arctic and Arctic regions with recurrent neural networks ...
<!--!introduction!--> Snow water equivalent (SWE) expresses amount of liquid water in the snow pack. This information is crucial in many hydrological models, but the actual measurement of SWE requires a lot of labor demanding manual work. Because these in situ measurements are labor demanding...
Main Authors: | , , |
---|---|
Format: | Conference Object |
Language: | unknown |
Published: |
GFZ German Research Centre for Geosciences
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.57757/iugg23-2856 https://gfzpublic.gfz-potsdam.de/pubman/item/item_5019028 |
id |
ftdatacite:10.57757/iugg23-2856 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.57757/iugg23-2856 2023-07-23T04:17:30+02:00 Snow water equivalent forecasting in Sub-Arctic and Arctic regions with recurrent neural networks ... Malin, Miika Okkonen, Jarkko Suutala, Jaakko 2023 https://dx.doi.org/10.57757/iugg23-2856 https://gfzpublic.gfz-potsdam.de/pubman/item/item_5019028 unknown GFZ German Research Centre for Geosciences Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 Article ConferencePaper Oral 2023 ftdatacite https://doi.org/10.57757/iugg23-2856 2023-07-03T18:44:13Z <!--!introduction!--> Snow water equivalent (SWE) expresses amount of liquid water in the snow pack. This information is crucial in many hydrological models, but the actual measurement of SWE requires a lot of labor demanding manual work. Because these in situ measurements are labor demanding and often scarce, efficient, and accurate, forecasts of SWE are crucial to get reliable estimates from current and future state of the hydrological systems. In this work, we compare two different recurrent neural network (RNN) architectures: long short-term memory (LSTM) and gated recurrent unit (GRU). We show that GRU is as accurate as LSTM, but requires less computation and is thus preferred RNN architecture for SWE forecasting. We optimise the efficiency and accuracy of these RNNs with hyper parameter Bayesian optimisation, and comprehensive data preprocessing. We furthermore improve the accuracy of the forecasts by using time to vector representation of time in the RNN architecture. We also show that the RNNs ... : The 28th IUGG General Assembly (IUGG2023) (Berlin 2023) ... Conference Object Arctic DataCite Metadata Store (German National Library of Science and Technology) Arctic |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
description |
<!--!introduction!--> Snow water equivalent (SWE) expresses amount of liquid water in the snow pack. This information is crucial in many hydrological models, but the actual measurement of SWE requires a lot of labor demanding manual work. Because these in situ measurements are labor demanding and often scarce, efficient, and accurate, forecasts of SWE are crucial to get reliable estimates from current and future state of the hydrological systems. In this work, we compare two different recurrent neural network (RNN) architectures: long short-term memory (LSTM) and gated recurrent unit (GRU). We show that GRU is as accurate as LSTM, but requires less computation and is thus preferred RNN architecture for SWE forecasting. We optimise the efficiency and accuracy of these RNNs with hyper parameter Bayesian optimisation, and comprehensive data preprocessing. We furthermore improve the accuracy of the forecasts by using time to vector representation of time in the RNN architecture. We also show that the RNNs ... : The 28th IUGG General Assembly (IUGG2023) (Berlin 2023) ... |
format |
Conference Object |
author |
Malin, Miika Okkonen, Jarkko Suutala, Jaakko |
spellingShingle |
Malin, Miika Okkonen, Jarkko Suutala, Jaakko Snow water equivalent forecasting in Sub-Arctic and Arctic regions with recurrent neural networks ... |
author_facet |
Malin, Miika Okkonen, Jarkko Suutala, Jaakko |
author_sort |
Malin, Miika |
title |
Snow water equivalent forecasting in Sub-Arctic and Arctic regions with recurrent neural networks ... |
title_short |
Snow water equivalent forecasting in Sub-Arctic and Arctic regions with recurrent neural networks ... |
title_full |
Snow water equivalent forecasting in Sub-Arctic and Arctic regions with recurrent neural networks ... |
title_fullStr |
Snow water equivalent forecasting in Sub-Arctic and Arctic regions with recurrent neural networks ... |
title_full_unstemmed |
Snow water equivalent forecasting in Sub-Arctic and Arctic regions with recurrent neural networks ... |
title_sort |
snow water equivalent forecasting in sub-arctic and arctic regions with recurrent neural networks ... |
publisher |
GFZ German Research Centre for Geosciences |
publishDate |
2023 |
url |
https://dx.doi.org/10.57757/iugg23-2856 https://gfzpublic.gfz-potsdam.de/pubman/item/item_5019028 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_doi |
https://doi.org/10.57757/iugg23-2856 |
_version_ |
1772179320908808192 |