A deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration

Climate change is reshaping vulnerable ecosystems, leading to uncertain effects on ecosystem dynamics, including evapotranspiration (ET) and ecosystem respiration (Reco). However, accurate es...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	J. Chen, B. Dafflon, A. P. Tran, N. Falco, S. S. Hubbard
Formato:	article
Lenguaje:	EN
Publicado:	Copernicus Publications 2021
Materias:	Technology T Environmental technology. Sanitary engineering TD1-1066 Geography. Anthropology. Recreation G Environmental sciences GE1-350
Acceso en línea:	https://doaj.org/article/0d3aabba789948d6bab8d4dbcfe62560
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0d3aabba789948d6bab8d4dbcfe62560
record_format	dspace
spelling	oai:doaj.org-article:0d3aabba789948d6bab8d4dbcfe625602021-11-25T10:45:18ZA deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration10.5194/hess-25-6041-20211027-56061607-7938https://doaj.org/article/0d3aabba789948d6bab8d4dbcfe625602021-11-01T00:00:00Zhttps://hess.copernicus.org/articles/25/6041/2021/hess-25-6041-2021.pdfhttps://doaj.org/toc/1027-5606https://doaj.org/toc/1607-7938<p>Climate change is reshaping vulnerable ecosystems, leading to uncertain effects on ecosystem dynamics, including evapotranspiration (ET) and ecosystem respiration (<span class="inline-formula"><i>R</i><sub>eco</sub></span>). However, accurate estimation of ET and <span class="inline-formula"><i>R</i><sub>eco</sub></span> still remains challenging at sparsely monitored watersheds, where data and field instrumentation are limited. In this study, we developed a hybrid predictive modeling approach (HPM) that integrates eddy covariance measurements, physically based model simulation results, meteorological forcings, and remote-sensing datasets to estimate ET and <span class="inline-formula"><i>R</i><sub>eco</sub></span> in high space–time resolution. HPM relies on a deep learning algorithm and long short-term memory (LSTM) and requires only air temperature, precipitation, radiation, normalized difference vegetation index (NDVI), and soil temperature (when available) as input variables. We tested and validated HPM estimation results in different climate regions and developed four use cases to demonstrate the applicability and variability of HPM at various FLUXNET sites and Rocky Mountain SNOTEL sites in Western North America. To test the limitations and performance of the HPM approach in mountainous watersheds, an expanded use case focused on the East River Watershed, Colorado, USA. The results indicate HPM is capable of identifying complicated interactions among meteorological forcings, ET, and <span class="inline-formula"><i>R</i><sub>eco</sub></span> variables, as well as providing reliable estimation of ET and <span class="inline-formula"><i>R</i><sub>eco</sub></span> across relevant spatiotemporal scales, even in challenging mountainous systems. The study documents that HPM increases our capability to estimate ET and <span class="inline-formula"><i>R</i><sub>eco</sub></span> and enhances process understanding at sparsely monitored watersheds.</p>J. ChenB. DafflonA. P. TranA. P. TranN. FalcoS. S. HubbardCopernicus PublicationsarticleTechnologyTEnvironmental technology. Sanitary engineeringTD1-1066Geography. Anthropology. RecreationGEnvironmental sciencesGE1-350ENHydrology and Earth System Sciences, Vol 25, Pp 6041-6066 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Technology T Environmental technology. Sanitary engineering TD1-1066 Geography. Anthropology. Recreation G Environmental sciences GE1-350
spellingShingle	Technology T Environmental technology. Sanitary engineering TD1-1066 Geography. Anthropology. Recreation G Environmental sciences GE1-350 J. Chen B. Dafflon A. P. Tran A. P. Tran N. Falco S. S. Hubbard A deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration
description	<p>Climate change is reshaping vulnerable ecosystems, leading to uncertain effects on ecosystem dynamics, including evapotranspiration (ET) and ecosystem respiration (<span class="inline-formula"><i>R</i><sub>eco</sub></span>). However, accurate estimation of ET and <span class="inline-formula"><i>R</i><sub>eco</sub></span> still remains challenging at sparsely monitored watersheds, where data and field instrumentation are limited. In this study, we developed a hybrid predictive modeling approach (HPM) that integrates eddy covariance measurements, physically based model simulation results, meteorological forcings, and remote-sensing datasets to estimate ET and <span class="inline-formula"><i>R</i><sub>eco</sub></span> in high space–time resolution. HPM relies on a deep learning algorithm and long short-term memory (LSTM) and requires only air temperature, precipitation, radiation, normalized difference vegetation index (NDVI), and soil temperature (when available) as input variables. We tested and validated HPM estimation results in different climate regions and developed four use cases to demonstrate the applicability and variability of HPM at various FLUXNET sites and Rocky Mountain SNOTEL sites in Western North America. To test the limitations and performance of the HPM approach in mountainous watersheds, an expanded use case focused on the East River Watershed, Colorado, USA. The results indicate HPM is capable of identifying complicated interactions among meteorological forcings, ET, and <span class="inline-formula"><i>R</i><sub>eco</sub></span> variables, as well as providing reliable estimation of ET and <span class="inline-formula"><i>R</i><sub>eco</sub></span> across relevant spatiotemporal scales, even in challenging mountainous systems. The study documents that HPM increases our capability to estimate ET and <span class="inline-formula"><i>R</i><sub>eco</sub></span> and enhances process understanding at sparsely monitored watersheds.</p>
format	article
author	J. Chen B. Dafflon A. P. Tran A. P. Tran N. Falco S. S. Hubbard
author_facet	J. Chen B. Dafflon A. P. Tran A. P. Tran N. Falco S. S. Hubbard
author_sort	J. Chen
title	A deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration
title_short	A deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration
title_full	A deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration
title_fullStr	A deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration
title_full_unstemmed	A deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration
title_sort	deep learning hybrid predictive modeling (hpm) approach for estimating evapotranspiration and ecosystem respiration
publisher	Copernicus Publications
publishDate	2021
url	https://doaj.org/article/0d3aabba789948d6bab8d4dbcfe62560
work_keys_str_mv	AT jchen adeeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT bdafflon adeeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT aptran adeeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT aptran adeeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT nfalco adeeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT sshubbard adeeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT jchen deeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT bdafflon deeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT aptran deeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT aptran deeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT nfalco deeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration AT sshubbard deeplearninghybridpredictivemodelinghpmapproachforestimatingevapotranspirationandecosystemrespiration
_version_	1718413541140070400

A deep learning hybrid predictive modeling (HPM) approach for estimating evapotranspiration and ecosystem respiration

Ejemplares similares