A hybrid model for refining gross primary productivity estimation by integrating multiple environmental factors

Environmental factors lead mainly to the uncertainty of gross primary productivity estimation in most light use efficiency (LUE, ε) models since the simple physical formulas are inadequate to fully express the overall constraint of diverse environmental factors on the maximum ε (εmax). In contrast,...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhilong Li, Ziti Jiao, Zheyou Tan, Chenxia Wang, Jing Guo, Sizhe Chen, Ge Gao, Fangwen Yang, Xin Dong
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:MethodsX
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2215016124005429
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849423668911800320
author Zhilong Li
Ziti Jiao
Zheyou Tan
Chenxia Wang
Jing Guo
Sizhe Chen
Ge Gao
Fangwen Yang
Xin Dong
author_facet Zhilong Li
Ziti Jiao
Zheyou Tan
Chenxia Wang
Jing Guo
Sizhe Chen
Ge Gao
Fangwen Yang
Xin Dong
author_sort Zhilong Li
collection DOAJ
description Environmental factors lead mainly to the uncertainty of gross primary productivity estimation in most light use efficiency (LUE, ε) models since the simple physical formulas are inadequate to fully express the overall constraint of diverse environmental factors on the maximum ε (εmax). In contrast, machine learning has the natural potential to detect intricate patterns and relationships among various environmental variables. Here, we presented a hybrid model (TL-CRF) that utilizes the random forest (RF) technique to incorporate various ecological stress factors into the two-leaf LUE (TL-LUE) model, meanwhile, seasonal differences in the clumping index (CI) on a global scale are considered to adjust seasonal patterns of canopy structure. The comprehensive integration of complex environmental variables based on this RF submodule is conducive to scaling theoretical εmax to actual ε as much as possible. The proposed TL-CRF model considerably improves global GPP estimation by complementing innate advantages between the process-based and data-driven models. • The seasonal CI averages in different stages of the leaf life cycle are estimated for different vegetation types on a global scale. • Various environmental stress factors are integrated via the RF technique. • The RF submodule is embedded into the TL-LUE model to establish a hybrid model.
format Article
id doaj-art-7ac766623e884ac2b99ccc286ab2d1cf
institution Kabale University
issn 2215-0161
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series MethodsX
spelling doaj-art-7ac766623e884ac2b99ccc286ab2d1cf2025-08-20T03:30:32ZengElsevierMethodsX2215-01612025-06-011410309110.1016/j.mex.2024.103091A hybrid model for refining gross primary productivity estimation by integrating multiple environmental factorsZhilong Li0Ziti Jiao1Zheyou Tan2Chenxia Wang3Jing Guo4Sizhe Chen5Ge Gao6Fangwen Yang7Xin Dong8State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China; Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China; Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China; Beijing Engineering Research Center for Global Land Remote Sensing Products, Beijing Normal University, Beijing 100875, China; Corresponding author at: State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China.State Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China; Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China; Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China; Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China; Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China; Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China; Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Beijing Normal University, Beijing 100875, China; Institute of Remote Sensing Science and Engineering, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaEnvironmental factors lead mainly to the uncertainty of gross primary productivity estimation in most light use efficiency (LUE, ε) models since the simple physical formulas are inadequate to fully express the overall constraint of diverse environmental factors on the maximum ε (εmax). In contrast, machine learning has the natural potential to detect intricate patterns and relationships among various environmental variables. Here, we presented a hybrid model (TL-CRF) that utilizes the random forest (RF) technique to incorporate various ecological stress factors into the two-leaf LUE (TL-LUE) model, meanwhile, seasonal differences in the clumping index (CI) on a global scale are considered to adjust seasonal patterns of canopy structure. The comprehensive integration of complex environmental variables based on this RF submodule is conducive to scaling theoretical εmax to actual ε as much as possible. The proposed TL-CRF model considerably improves global GPP estimation by complementing innate advantages between the process-based and data-driven models. • The seasonal CI averages in different stages of the leaf life cycle are estimated for different vegetation types on a global scale. • Various environmental stress factors are integrated via the RF technique. • The RF submodule is embedded into the TL-LUE model to establish a hybrid model.http://www.sciencedirect.com/science/article/pii/S2215016124005429Large-scale GPP estimation via combining RF technique with TL-LUE model
spellingShingle Zhilong Li
Ziti Jiao
Zheyou Tan
Chenxia Wang
Jing Guo
Sizhe Chen
Ge Gao
Fangwen Yang
Xin Dong
A hybrid model for refining gross primary productivity estimation by integrating multiple environmental factors
MethodsX
Large-scale GPP estimation via combining RF technique with TL-LUE model
title A hybrid model for refining gross primary productivity estimation by integrating multiple environmental factors
title_full A hybrid model for refining gross primary productivity estimation by integrating multiple environmental factors
title_fullStr A hybrid model for refining gross primary productivity estimation by integrating multiple environmental factors
title_full_unstemmed A hybrid model for refining gross primary productivity estimation by integrating multiple environmental factors
title_short A hybrid model for refining gross primary productivity estimation by integrating multiple environmental factors
title_sort hybrid model for refining gross primary productivity estimation by integrating multiple environmental factors
topic Large-scale GPP estimation via combining RF technique with TL-LUE model
url http://www.sciencedirect.com/science/article/pii/S2215016124005429
work_keys_str_mv AT zhilongli ahybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT zitijiao ahybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT zheyoutan ahybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT chenxiawang ahybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT jingguo ahybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT sizhechen ahybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT gegao ahybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT fangwenyang ahybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT xindong ahybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT zhilongli hybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT zitijiao hybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT zheyoutan hybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT chenxiawang hybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT jingguo hybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT sizhechen hybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT gegao hybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT fangwenyang hybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors
AT xindong hybridmodelforrefininggrossprimaryproductivityestimationbyintegratingmultipleenvironmentalfactors