Machine Learning Modeling of Climate Variability Impact on River Runoff
The hypothesis of this study was one of existence of spatially organized links between the time series of river runoff and climate variability indices, describing the oscillations in the atmosphere–ocean system: ENSO (El Niño–Southern Oscillation), PDO (Pacific Decadal Oscillation), AMO (Atlantic Mu...
Published in: | Water |
---|---|
Main Authors: | , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/w13091177 |
id |
ftmdpi:oai:mdpi.com:/2073-4441/13/9/1177/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2073-4441/13/9/1177/ 2023-08-20T04:08:23+02:00 Machine Learning Modeling of Climate Variability Impact on River Runoff Mateusz Norel Krzysztof Krawiec Zbigniew W. Kundzewicz agris 2021-04-24 application/pdf https://doi.org/10.3390/w13091177 EN eng Multidisciplinary Digital Publishing Institute Hydrology https://dx.doi.org/10.3390/w13091177 https://creativecommons.org/licenses/by/4.0/ Water; Volume 13; Issue 9; Pages: 1177 river runoff climate variability machine learning Text 2021 ftmdpi https://doi.org/10.3390/w13091177 2023-08-01T01:34:43Z The hypothesis of this study was one of existence of spatially organized links between the time series of river runoff and climate variability indices, describing the oscillations in the atmosphere–ocean system: ENSO (El Niño–Southern Oscillation), PDO (Pacific Decadal Oscillation), AMO (Atlantic Multidecadal Oscillation), and NAO (North Atlantic Oscillation). The global river flow reconstructions (ERA-20-CM-R) for 18 study areas on six continents and climate variability indices for the period 1901–2010 were used. The split-sample approach was applied, with the period 1901–2000 used for training and 2001–2010 used for testing. The quality measures used in this paper were mean absolute error, dynamic time warping, and top extreme events error. We demonstrated that a machine learning approach (convolution neural network, CNN) trained on climate variability indices can model the river runoff better than the long-term monthly mean baseline, both in univariate (per-cell) and multivariate (multi-cell, regionalized) settings. We compared the models to the baseline in the form of heatmaps and presented results of ablation experiments (test time ablation, i.e., jackknifing, and training time ablation), which suggested that ENSO is the primary determinant among the considered indices. Text North Atlantic North Atlantic oscillation MDPI Open Access Publishing Pacific Water 13 9 1177 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
river runoff climate variability machine learning |
spellingShingle |
river runoff climate variability machine learning Mateusz Norel Krzysztof Krawiec Zbigniew W. Kundzewicz Machine Learning Modeling of Climate Variability Impact on River Runoff |
topic_facet |
river runoff climate variability machine learning |
description |
The hypothesis of this study was one of existence of spatially organized links between the time series of river runoff and climate variability indices, describing the oscillations in the atmosphere–ocean system: ENSO (El Niño–Southern Oscillation), PDO (Pacific Decadal Oscillation), AMO (Atlantic Multidecadal Oscillation), and NAO (North Atlantic Oscillation). The global river flow reconstructions (ERA-20-CM-R) for 18 study areas on six continents and climate variability indices for the period 1901–2010 were used. The split-sample approach was applied, with the period 1901–2000 used for training and 2001–2010 used for testing. The quality measures used in this paper were mean absolute error, dynamic time warping, and top extreme events error. We demonstrated that a machine learning approach (convolution neural network, CNN) trained on climate variability indices can model the river runoff better than the long-term monthly mean baseline, both in univariate (per-cell) and multivariate (multi-cell, regionalized) settings. We compared the models to the baseline in the form of heatmaps and presented results of ablation experiments (test time ablation, i.e., jackknifing, and training time ablation), which suggested that ENSO is the primary determinant among the considered indices. |
format |
Text |
author |
Mateusz Norel Krzysztof Krawiec Zbigniew W. Kundzewicz |
author_facet |
Mateusz Norel Krzysztof Krawiec Zbigniew W. Kundzewicz |
author_sort |
Mateusz Norel |
title |
Machine Learning Modeling of Climate Variability Impact on River Runoff |
title_short |
Machine Learning Modeling of Climate Variability Impact on River Runoff |
title_full |
Machine Learning Modeling of Climate Variability Impact on River Runoff |
title_fullStr |
Machine Learning Modeling of Climate Variability Impact on River Runoff |
title_full_unstemmed |
Machine Learning Modeling of Climate Variability Impact on River Runoff |
title_sort |
machine learning modeling of climate variability impact on river runoff |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2021 |
url |
https://doi.org/10.3390/w13091177 |
op_coverage |
agris |
geographic |
Pacific |
geographic_facet |
Pacific |
genre |
North Atlantic North Atlantic oscillation |
genre_facet |
North Atlantic North Atlantic oscillation |
op_source |
Water; Volume 13; Issue 9; Pages: 1177 |
op_relation |
Hydrology https://dx.doi.org/10.3390/w13091177 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/w13091177 |
container_title |
Water |
container_volume |
13 |
container_issue |
9 |
container_start_page |
1177 |
_version_ |
1774720614925336576 |