Snow depth estimation and historical data reconstruction over China based on a random forest machine learning approach
We investigated the potential capability of the random forest (RF) machine learning (ML) model to estimate snow depth in this work. Four combinations composed of critical predictor variables were used to train the RF model. Then, we utilized three validation datasets from out-of-bag (OOB) samples, a...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2020
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-14-1763-2020 https://noa.gwlb.de/receive/cop_mods_00051674 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00051330/tc-14-1763-2020.pdf https://tc.copernicus.org/articles/14/1763/2020/tc-14-1763-2020.pdf |
id |
ftnonlinearchiv:oai:noa.gwlb.de:cop_mods_00051674 |
---|---|
record_format |
openpolar |
spelling |
ftnonlinearchiv:oai:noa.gwlb.de:cop_mods_00051674 2023-05-15T18:32:33+02:00 Snow depth estimation and historical data reconstruction over China based on a random forest machine learning approach Yang, Jianwei Jiang, Lingmei Luojus, Kari Pan, Jinmei Lemmetyinen, Juha Takala, Matias Wu, Shengli 2020-06 electronic https://doi.org/10.5194/tc-14-1763-2020 https://noa.gwlb.de/receive/cop_mods_00051674 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00051330/tc-14-1763-2020.pdf https://tc.copernicus.org/articles/14/1763/2020/tc-14-1763-2020.pdf eng eng Copernicus Publications The Cryosphere -- ˜Theœ Cryosphere -- http://www.bibliothek.uni-regensburg.de/ezeit/?2393169 -- http://www.the-cryosphere.net/ -- 1994-0424 https://doi.org/10.5194/tc-14-1763-2020 https://noa.gwlb.de/receive/cop_mods_00051674 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00051330/tc-14-1763-2020.pdf https://tc.copernicus.org/articles/14/1763/2020/tc-14-1763-2020.pdf https://creativecommons.org/licenses/by/4.0/ uneingeschränkt info:eu-repo/semantics/openAccess CC-BY article Verlagsveröffentlichung article Text doc-type:article 2020 ftnonlinearchiv https://doi.org/10.5194/tc-14-1763-2020 2022-02-08T22:36:18Z We investigated the potential capability of the random forest (RF) machine learning (ML) model to estimate snow depth in this work. Four combinations composed of critical predictor variables were used to train the RF model. Then, we utilized three validation datasets from out-of-bag (OOB) samples, a temporal subset, and a spatiotemporal subset to verify the fitted RF algorithms. The results indicated the following: (1) the accuracy of the RF model is greatly influenced by geographic location, elevation, and land cover fractions; (2) however, the redundant predictor variables (if highly correlated) slightly affect the RF model; and (3) the fitted RF algorithms perform better on temporal than spatial scales, with unbiased root-mean-square errors (RMSEs) of ∼4.4 and ∼7.3 cm, respectively. Finally, we used the fitted RF2 algorithm to retrieve a consistent 32-year daily snow depth dataset from 1987 to 2018. This product was evaluated against the independent station observations during the period 1987–2018. The mean unbiased RMSE and bias were 7.1 and −0.05 cm, respectively, indicating better performance than that of the former snow depth dataset (8.4 and −1.20 cm) from the Environmental and Ecological Science Data Center for West China (WESTDC). Although the RF product was superior to the WESTDC dataset, it still underestimated deep snow cover (>20 cm), with biases of −10.4, −8.9, and −34.1 cm for northeast China (NEC), northern Xinjiang (XJ), and the Qinghai–Tibetan Plateau (QTP), respectively. Additionally, the long-term snow depth datasets (station observations, RF estimates, and WESTDC product) were analyzed in terms of temporal and spatial variations over China. On a temporal scale, the ground truth snow depth presented a significant increasing trend from 1987 to 2018, especially in NEC. However, the RF and WESTDC products displayed no significant changing trends except on the QTP. The WESTDC product presented a significant decreasing trend on the QTP, with a correlation coefficient of −0.55, whereas there were no significant trends for ground truth observations and the RF product. For the spatial characteristics, similar trend patterns were observed for RF and WESTDC products over China. These characteristics presented significant decreasing trends in most areas and a significant increasing trend in central NEC. Article in Journal/Newspaper The Cryosphere Niedersächsisches Online-Archiv NOA The Cryosphere 14 6 1763 1778 |
institution |
Open Polar |
collection |
Niedersächsisches Online-Archiv NOA |
op_collection_id |
ftnonlinearchiv |
language |
English |
topic |
article Verlagsveröffentlichung |
spellingShingle |
article Verlagsveröffentlichung Yang, Jianwei Jiang, Lingmei Luojus, Kari Pan, Jinmei Lemmetyinen, Juha Takala, Matias Wu, Shengli Snow depth estimation and historical data reconstruction over China based on a random forest machine learning approach |
topic_facet |
article Verlagsveröffentlichung |
description |
We investigated the potential capability of the random forest (RF) machine learning (ML) model to estimate snow depth in this work. Four combinations composed of critical predictor variables were used to train the RF model. Then, we utilized three validation datasets from out-of-bag (OOB) samples, a temporal subset, and a spatiotemporal subset to verify the fitted RF algorithms. The results indicated the following: (1) the accuracy of the RF model is greatly influenced by geographic location, elevation, and land cover fractions; (2) however, the redundant predictor variables (if highly correlated) slightly affect the RF model; and (3) the fitted RF algorithms perform better on temporal than spatial scales, with unbiased root-mean-square errors (RMSEs) of ∼4.4 and ∼7.3 cm, respectively. Finally, we used the fitted RF2 algorithm to retrieve a consistent 32-year daily snow depth dataset from 1987 to 2018. This product was evaluated against the independent station observations during the period 1987–2018. The mean unbiased RMSE and bias were 7.1 and −0.05 cm, respectively, indicating better performance than that of the former snow depth dataset (8.4 and −1.20 cm) from the Environmental and Ecological Science Data Center for West China (WESTDC). Although the RF product was superior to the WESTDC dataset, it still underestimated deep snow cover (>20 cm), with biases of −10.4, −8.9, and −34.1 cm for northeast China (NEC), northern Xinjiang (XJ), and the Qinghai–Tibetan Plateau (QTP), respectively. Additionally, the long-term snow depth datasets (station observations, RF estimates, and WESTDC product) were analyzed in terms of temporal and spatial variations over China. On a temporal scale, the ground truth snow depth presented a significant increasing trend from 1987 to 2018, especially in NEC. However, the RF and WESTDC products displayed no significant changing trends except on the QTP. The WESTDC product presented a significant decreasing trend on the QTP, with a correlation coefficient of −0.55, whereas there were no significant trends for ground truth observations and the RF product. For the spatial characteristics, similar trend patterns were observed for RF and WESTDC products over China. These characteristics presented significant decreasing trends in most areas and a significant increasing trend in central NEC. |
format |
Article in Journal/Newspaper |
author |
Yang, Jianwei Jiang, Lingmei Luojus, Kari Pan, Jinmei Lemmetyinen, Juha Takala, Matias Wu, Shengli |
author_facet |
Yang, Jianwei Jiang, Lingmei Luojus, Kari Pan, Jinmei Lemmetyinen, Juha Takala, Matias Wu, Shengli |
author_sort |
Yang, Jianwei |
title |
Snow depth estimation and historical data reconstruction over China based on a random forest machine learning approach |
title_short |
Snow depth estimation and historical data reconstruction over China based on a random forest machine learning approach |
title_full |
Snow depth estimation and historical data reconstruction over China based on a random forest machine learning approach |
title_fullStr |
Snow depth estimation and historical data reconstruction over China based on a random forest machine learning approach |
title_full_unstemmed |
Snow depth estimation and historical data reconstruction over China based on a random forest machine learning approach |
title_sort |
snow depth estimation and historical data reconstruction over china based on a random forest machine learning approach |
publisher |
Copernicus Publications |
publishDate |
2020 |
url |
https://doi.org/10.5194/tc-14-1763-2020 https://noa.gwlb.de/receive/cop_mods_00051674 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00051330/tc-14-1763-2020.pdf https://tc.copernicus.org/articles/14/1763/2020/tc-14-1763-2020.pdf |
genre |
The Cryosphere |
genre_facet |
The Cryosphere |
op_relation |
The Cryosphere -- ˜Theœ Cryosphere -- http://www.bibliothek.uni-regensburg.de/ezeit/?2393169 -- http://www.the-cryosphere.net/ -- 1994-0424 https://doi.org/10.5194/tc-14-1763-2020 https://noa.gwlb.de/receive/cop_mods_00051674 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00051330/tc-14-1763-2020.pdf https://tc.copernicus.org/articles/14/1763/2020/tc-14-1763-2020.pdf |
op_rights |
https://creativecommons.org/licenses/by/4.0/ uneingeschränkt info:eu-repo/semantics/openAccess |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.5194/tc-14-1763-2020 |
container_title |
The Cryosphere |
container_volume |
14 |
container_issue |
6 |
container_start_page |
1763 |
op_container_end_page |
1778 |
_version_ |
1766216744390623232 |