Learning Global Evapotranspiration Dataset Corrections from a Water Cycle Closure Supervision. Hascoet, T., Pellet, V., Aires, F., & Takiguchi, T. Remote Sensing, 16(1):170, December, 2023. ![Learning Global Evapotranspiration Dataset Corrections from a Water Cycle Closure Supervision [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Evapotranspiration (E) is one of the most uncertain components of the global water cycle (WC). Improving global E estimates is necessary to improve our understanding of climate and its impact on available surface water resources. This work presents a methodology for deriving monthly corrections to global E datasets at 0.25∘ resolution. A principled approach is proposed to firstly use indirect information from the other water components to correct E estimates at the catchment level, and secondly to extend this sparse catchment-level information to global pixel-level corrections using machine learning (ML). Several E satellite products are available, each with its own errors (both random and systematic). Four such global E datasets are used to validate the proposed approach and highlight its ability to extract seasonal and regional systematic biases. The resulting E corrections are shown to accurately generalize WC closure constraints to unseen catchments. With an average deviation of 14% from the original E datasets, the proposed method achieves up to 20% WC residual reduction on the most favorable dataset.
@article{hascoet_learning_2023,
title = {Learning {Global} {Evapotranspiration} {Dataset} {Corrections} from a {Water} {Cycle} {Closure} {Supervision}},
volume = {16},
copyright = {https://creativecommons.org/licenses/by/4.0/},
issn = {2072-4292},
url = {https://www.mdpi.com/2072-4292/16/1/170},
doi = {10.3390/rs16010170},
abstract = {Evapotranspiration (E) is one of the most uncertain components of the global water cycle (WC). Improving global E estimates is necessary to improve our understanding of climate and its impact on available surface water resources. This work presents a methodology for deriving monthly corrections to global E datasets at 0.25∘ resolution. A principled approach is proposed to firstly use indirect information from the other water components to correct E estimates at the catchment level, and secondly to extend this sparse catchment-level information to global pixel-level corrections using machine learning (ML). Several E satellite products are available, each with its own errors (both random and systematic). Four such global E datasets are used to validate the proposed approach and highlight its ability to extract seasonal and regional systematic biases. The resulting E corrections are shown to accurately generalize WC closure constraints to unseen catchments. With an average deviation of 14\% from the original E datasets, the proposed method achieves up to 20\% WC residual reduction on the most favorable dataset.},
language = {en},
number = {1},
urldate = {2024-11-15},
journal = {Remote Sensing},
author = {Hascoet, Tristan and Pellet, Victor and Aires, Filipe and Takiguchi, Tetsuya},
month = dec,
year = {2023},
pages = {170},
}
Downloads: 0
{"_id":"tPodbvjZfFrSfsav2","bibbaseid":"hascoet-pellet-aires-takiguchi-learningglobalevapotranspirationdatasetcorrectionsfromawatercycleclosuresupervision-2023","author_short":["Hascoet, T.","Pellet, V.","Aires, F.","Takiguchi, T."],"bibdata":{"bibtype":"article","type":"article","title":"Learning Global Evapotranspiration Dataset Corrections from a Water Cycle Closure Supervision","volume":"16","copyright":"https://creativecommons.org/licenses/by/4.0/","issn":"2072-4292","url":"https://www.mdpi.com/2072-4292/16/1/170","doi":"10.3390/rs16010170","abstract":"Evapotranspiration (E) is one of the most uncertain components of the global water cycle (WC). Improving global E estimates is necessary to improve our understanding of climate and its impact on available surface water resources. This work presents a methodology for deriving monthly corrections to global E datasets at 0.25∘ resolution. A principled approach is proposed to firstly use indirect information from the other water components to correct E estimates at the catchment level, and secondly to extend this sparse catchment-level information to global pixel-level corrections using machine learning (ML). Several E satellite products are available, each with its own errors (both random and systematic). Four such global E datasets are used to validate the proposed approach and highlight its ability to extract seasonal and regional systematic biases. The resulting E corrections are shown to accurately generalize WC closure constraints to unseen catchments. With an average deviation of 14% from the original E datasets, the proposed method achieves up to 20% WC residual reduction on the most favorable dataset.","language":"en","number":"1","urldate":"2024-11-15","journal":"Remote Sensing","author":[{"propositions":[],"lastnames":["Hascoet"],"firstnames":["Tristan"],"suffixes":[]},{"propositions":[],"lastnames":["Pellet"],"firstnames":["Victor"],"suffixes":[]},{"propositions":[],"lastnames":["Aires"],"firstnames":["Filipe"],"suffixes":[]},{"propositions":[],"lastnames":["Takiguchi"],"firstnames":["Tetsuya"],"suffixes":[]}],"month":"December","year":"2023","pages":"170","bibtex":"@article{hascoet_learning_2023,\n\ttitle = {Learning {Global} {Evapotranspiration} {Dataset} {Corrections} from a {Water} {Cycle} {Closure} {Supervision}},\n\tvolume = {16},\n\tcopyright = {https://creativecommons.org/licenses/by/4.0/},\n\tissn = {2072-4292},\n\turl = {https://www.mdpi.com/2072-4292/16/1/170},\n\tdoi = {10.3390/rs16010170},\n\tabstract = {Evapotranspiration (E) is one of the most uncertain components of the global water cycle (WC). Improving global E estimates is necessary to improve our understanding of climate and its impact on available surface water resources. This work presents a methodology for deriving monthly corrections to global E datasets at 0.25∘ resolution. A principled approach is proposed to firstly use indirect information from the other water components to correct E estimates at the catchment level, and secondly to extend this sparse catchment-level information to global pixel-level corrections using machine learning (ML). Several E satellite products are available, each with its own errors (both random and systematic). Four such global E datasets are used to validate the proposed approach and highlight its ability to extract seasonal and regional systematic biases. The resulting E corrections are shown to accurately generalize WC closure constraints to unseen catchments. With an average deviation of 14\\% from the original E datasets, the proposed method achieves up to 20\\% WC residual reduction on the most favorable dataset.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2024-11-15},\n\tjournal = {Remote Sensing},\n\tauthor = {Hascoet, Tristan and Pellet, Victor and Aires, Filipe and Takiguchi, Tetsuya},\n\tmonth = dec,\n\tyear = {2023},\n\tpages = {170},\n}\n\n\n\n\n\n\n\n","author_short":["Hascoet, T.","Pellet, V.","Aires, F.","Takiguchi, T."],"key":"hascoet_learning_2023","id":"hascoet_learning_2023","bibbaseid":"hascoet-pellet-aires-takiguchi-learningglobalevapotranspirationdatasetcorrectionsfromawatercycleclosuresupervision-2023","role":"author","urls":{"Paper":"https://www.mdpi.com/2072-4292/16/1/170"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/tereno","dataSources":["cq3J5xX6zmBvc2TQC"],"keywords":[],"search_terms":["learning","global","evapotranspiration","dataset","corrections","water","cycle","closure","supervision","hascoet","pellet","aires","takiguchi"],"title":"Learning Global Evapotranspiration Dataset Corrections from a Water Cycle Closure Supervision","year":2023}