Estimating Global GPP From the Plant Functional Type Perspective Using a Machine Learning Approach. Guo, R., Chen, T., Chen, X., Yuan, W., Liu, S., He, B., Li, L., Wang, S., Hu, T., Yan, Q., Wei, X., & Dai, J. Journal of Geophysical Research: Biogeosciences, 128(4):e2022JG007100, April, 2023. ![Estimating Global GPP From the Plant Functional Type Perspective Using a Machine Learning Approach [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Abstract The long‐term monitoring of gross primary production (GPP) is crucial to the assessment of the carbon cycle of terrestrial ecosystems. In this study, a well‐known machine learning model (random forest, RF) is established to reconstruct the global GPP data set named ECGC_GPP. The model distinguished nine functional plant types, including C3 and C4 crops, using eddy fluxes, meteorological variables, and leaf area index (LAI) as training data of RF model. Based on ERA5_Land and the corrected GEOV2 data, global monthly GPP data set at a 0.05° resolution from 1999 to 2019 was estimated. The results showed that the RF model could explain 74.81% of the monthly variation of GPP in the testing data set, of which the average contribution of LAI reached 41.73%. The average annual and standard deviation of GPP during 1999–2019 were 117.14 ± 1.51 Pg C yr −1 , with an upward trend of 0.21 Pg C yr −2 ( p \textless 0.01). By using the plant functional type classification, the underestimation of cropland is improved. Therefore, ECGC_GPP provides reasonable global spatial pattern and long‐term trend of annual GPP. , Plain Language Summary Accurate estimation of gross primary production (GPP) is critical for understanding the terrestrial ecosystem carbon cycle. There are a variety of GPP data sets based on different methods, but huge differences validated by the GPP measured values of flux observation towers still exist. At present, a large amount of GPP measured data provides us with the opportunity to use machine learning models to estimate global GPP. This paper presents a new global GPP data set (ECGC_GPP) with 0.05° and monthly scales from 1999 to 2019. This GPP data set is based on random forest model and driven by remote sensing data from GEOV2 and climate data from ERA5_Land. In ECGC_GPP, site‐level training models are constructed based on plant functional types (especially C3 and C4 crops) to improve accuracy. All these improvements are aimed at improving the lack of interannual fluctuations and the underestimation of cropland in current machine learning data set. , Key Points The accuracy of gross primary production (GPP) estimation can be improved by distinguishing plant functional types, especially for C3 and C4 crops Significant increasing trend is found in this random forest‐based data set Leaf area index plays a leading role in both the average state and long‐term trend of GPP
@article{guo_estimating_2023,
title = {Estimating {Global} {GPP} {From} the {Plant} {Functional} {Type} {Perspective} {Using} a {Machine} {Learning} {Approach}},
volume = {128},
issn = {2169-8953, 2169-8961},
url = {https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2022JG007100},
doi = {10.1029/2022JG007100},
abstract = {Abstract
The long‐term monitoring of gross primary production (GPP) is crucial to the assessment of the carbon cycle of terrestrial ecosystems. In this study, a well‐known machine learning model (random forest, RF) is established to reconstruct the global GPP data set named ECGC\_GPP. The model distinguished nine functional plant types, including C3 and C4 crops, using eddy fluxes, meteorological variables, and leaf area index (LAI) as training data of RF model. Based on ERA5\_Land and the corrected GEOV2 data, global monthly GPP data set at a 0.05° resolution from 1999 to 2019 was estimated. The results showed that the RF model could explain 74.81\% of the monthly variation of GPP in the testing data set, of which the average contribution of LAI reached 41.73\%. The average annual and standard deviation of GPP during 1999–2019 were 117.14 ± 1.51 Pg C yr
−1
, with an upward trend of 0.21 Pg C yr
−2
(
p
{\textless} 0.01). By using the plant functional type classification, the underestimation of cropland is improved. Therefore, ECGC\_GPP provides reasonable global spatial pattern and long‐term trend of annual GPP.
,
Plain Language Summary
Accurate estimation of gross primary production (GPP) is critical for understanding the terrestrial ecosystem carbon cycle. There are a variety of GPP data sets based on different methods, but huge differences validated by the GPP measured values of flux observation towers still exist. At present, a large amount of GPP measured data provides us with the opportunity to use machine learning models to estimate global GPP. This paper presents a new global GPP data set (ECGC\_GPP) with 0.05° and monthly scales from 1999 to 2019. This GPP data set is based on random forest model and driven by remote sensing data from GEOV2 and climate data from ERA5\_Land. In ECGC\_GPP, site‐level training models are constructed based on plant functional types (especially C3 and C4 crops) to improve accuracy. All these improvements are aimed at improving the lack of interannual fluctuations and the underestimation of cropland in current machine learning data set.
,
Key Points
The accuracy of gross primary production (GPP) estimation can be improved by distinguishing plant functional types, especially for C3 and C4 crops
Significant increasing trend is found in this random forest‐based data set
Leaf area index plays a leading role in both the average state and long‐term trend of GPP},
language = {en},
number = {4},
urldate = {2024-11-15},
journal = {Journal of Geophysical Research: Biogeosciences},
author = {Guo, Renjie and Chen, Tiexi and Chen, Xin and Yuan, Wenping and Liu, Shuci and He, Bin and Li, Lin and Wang, Shengzhen and Hu, Ting and Yan, Qingyun and Wei, Xueqiong and Dai, Jie},
month = apr,
year = {2023},
pages = {e2022JG007100},
}
Downloads: 0
{"_id":"hJn6zqpggc9dYjKPj","bibbaseid":"guo-chen-chen-yuan-liu-he-li-wang-etal-estimatingglobalgppfromtheplantfunctionaltypeperspectiveusingamachinelearningapproach-2023","author_short":["Guo, R.","Chen, T.","Chen, X.","Yuan, W.","Liu, S.","He, B.","Li, L.","Wang, S.","Hu, T.","Yan, Q.","Wei, X.","Dai, J."],"bibdata":{"bibtype":"article","type":"article","title":"Estimating Global GPP From the Plant Functional Type Perspective Using a Machine Learning Approach","volume":"128","issn":"2169-8953, 2169-8961","url":"https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2022JG007100","doi":"10.1029/2022JG007100","abstract":"Abstract The long‐term monitoring of gross primary production (GPP) is crucial to the assessment of the carbon cycle of terrestrial ecosystems. In this study, a well‐known machine learning model (random forest, RF) is established to reconstruct the global GPP data set named ECGC_GPP. The model distinguished nine functional plant types, including C3 and C4 crops, using eddy fluxes, meteorological variables, and leaf area index (LAI) as training data of RF model. Based on ERA5_Land and the corrected GEOV2 data, global monthly GPP data set at a 0.05° resolution from 1999 to 2019 was estimated. The results showed that the RF model could explain 74.81% of the monthly variation of GPP in the testing data set, of which the average contribution of LAI reached 41.73%. The average annual and standard deviation of GPP during 1999–2019 were 117.14 ± 1.51 Pg C yr −1 , with an upward trend of 0.21 Pg C yr −2 ( p \\textless 0.01). By using the plant functional type classification, the underestimation of cropland is improved. Therefore, ECGC_GPP provides reasonable global spatial pattern and long‐term trend of annual GPP. , Plain Language Summary Accurate estimation of gross primary production (GPP) is critical for understanding the terrestrial ecosystem carbon cycle. There are a variety of GPP data sets based on different methods, but huge differences validated by the GPP measured values of flux observation towers still exist. At present, a large amount of GPP measured data provides us with the opportunity to use machine learning models to estimate global GPP. This paper presents a new global GPP data set (ECGC_GPP) with 0.05° and monthly scales from 1999 to 2019. This GPP data set is based on random forest model and driven by remote sensing data from GEOV2 and climate data from ERA5_Land. In ECGC_GPP, site‐level training models are constructed based on plant functional types (especially C3 and C4 crops) to improve accuracy. All these improvements are aimed at improving the lack of interannual fluctuations and the underestimation of cropland in current machine learning data set. , Key Points The accuracy of gross primary production (GPP) estimation can be improved by distinguishing plant functional types, especially for C3 and C4 crops Significant increasing trend is found in this random forest‐based data set Leaf area index plays a leading role in both the average state and long‐term trend of GPP","language":"en","number":"4","urldate":"2024-11-15","journal":"Journal of Geophysical Research: Biogeosciences","author":[{"propositions":[],"lastnames":["Guo"],"firstnames":["Renjie"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Tiexi"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Xin"],"suffixes":[]},{"propositions":[],"lastnames":["Yuan"],"firstnames":["Wenping"],"suffixes":[]},{"propositions":[],"lastnames":["Liu"],"firstnames":["Shuci"],"suffixes":[]},{"propositions":[],"lastnames":["He"],"firstnames":["Bin"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Lin"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Shengzhen"],"suffixes":[]},{"propositions":[],"lastnames":["Hu"],"firstnames":["Ting"],"suffixes":[]},{"propositions":[],"lastnames":["Yan"],"firstnames":["Qingyun"],"suffixes":[]},{"propositions":[],"lastnames":["Wei"],"firstnames":["Xueqiong"],"suffixes":[]},{"propositions":[],"lastnames":["Dai"],"firstnames":["Jie"],"suffixes":[]}],"month":"April","year":"2023","pages":"e2022JG007100","bibtex":"@article{guo_estimating_2023,\n\ttitle = {Estimating {Global} {GPP} {From} the {Plant} {Functional} {Type} {Perspective} {Using} a {Machine} {Learning} {Approach}},\n\tvolume = {128},\n\tissn = {2169-8953, 2169-8961},\n\turl = {https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2022JG007100},\n\tdoi = {10.1029/2022JG007100},\n\tabstract = {Abstract\n \n The long‐term monitoring of gross primary production (GPP) is crucial to the assessment of the carbon cycle of terrestrial ecosystems. In this study, a well‐known machine learning model (random forest, RF) is established to reconstruct the global GPP data set named ECGC\\_GPP. The model distinguished nine functional plant types, including C3 and C4 crops, using eddy fluxes, meteorological variables, and leaf area index (LAI) as training data of RF model. Based on ERA5\\_Land and the corrected GEOV2 data, global monthly GPP data set at a 0.05° resolution from 1999 to 2019 was estimated. The results showed that the RF model could explain 74.81\\% of the monthly variation of GPP in the testing data set, of which the average contribution of LAI reached 41.73\\%. The average annual and standard deviation of GPP during 1999–2019 were 117.14 ± 1.51 Pg C yr\n −1\n , with an upward trend of 0.21 Pg C yr\n −2\n (\n p\n {\\textless} 0.01). By using the plant functional type classification, the underestimation of cropland is improved. Therefore, ECGC\\_GPP provides reasonable global spatial pattern and long‐term trend of annual GPP.\n \n , \n Plain Language Summary\n Accurate estimation of gross primary production (GPP) is critical for understanding the terrestrial ecosystem carbon cycle. There are a variety of GPP data sets based on different methods, but huge differences validated by the GPP measured values of flux observation towers still exist. At present, a large amount of GPP measured data provides us with the opportunity to use machine learning models to estimate global GPP. This paper presents a new global GPP data set (ECGC\\_GPP) with 0.05° and monthly scales from 1999 to 2019. This GPP data set is based on random forest model and driven by remote sensing data from GEOV2 and climate data from ERA5\\_Land. In ECGC\\_GPP, site‐level training models are constructed based on plant functional types (especially C3 and C4 crops) to improve accuracy. All these improvements are aimed at improving the lack of interannual fluctuations and the underestimation of cropland in current machine learning data set.\n , \n Key Points\n \n \n \n The accuracy of gross primary production (GPP) estimation can be improved by distinguishing plant functional types, especially for C3 and C4 crops\n \n \n Significant increasing trend is found in this random forest‐based data set\n \n \n Leaf area index plays a leading role in both the average state and long‐term trend of GPP},\n\tlanguage = {en},\n\tnumber = {4},\n\turldate = {2024-11-15},\n\tjournal = {Journal of Geophysical Research: Biogeosciences},\n\tauthor = {Guo, Renjie and Chen, Tiexi and Chen, Xin and Yuan, Wenping and Liu, Shuci and He, Bin and Li, Lin and Wang, Shengzhen and Hu, Ting and Yan, Qingyun and Wei, Xueqiong and Dai, Jie},\n\tmonth = apr,\n\tyear = {2023},\n\tpages = {e2022JG007100},\n}\n\n\n\n\n\n\n\n","author_short":["Guo, R.","Chen, T.","Chen, X.","Yuan, W.","Liu, S.","He, B.","Li, L.","Wang, S.","Hu, T.","Yan, Q.","Wei, X.","Dai, J."],"key":"guo_estimating_2023","id":"guo_estimating_2023","bibbaseid":"guo-chen-chen-yuan-liu-he-li-wang-etal-estimatingglobalgppfromtheplantfunctionaltypeperspectiveusingamachinelearningapproach-2023","role":"author","urls":{"Paper":"https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2022JG007100"},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/tereno","dataSources":["cq3J5xX6zmBvc2TQC"],"keywords":[],"search_terms":["estimating","global","gpp","plant","functional","type","perspective","using","machine","learning","approach","guo","chen","chen","yuan","liu","he","li","wang","hu","yan","wei","dai"],"title":"Estimating Global GPP From the Plant Functional Type Perspective Using a Machine Learning Approach","year":2023}