Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production

It is significant to simulate grassland gross primary production (GPP) to understand the terrestrial carbon budget over Inner Mongolia (IMG), China. Nevertheless, there is not sufficient <italic>in situ</italic> GPP data over this region. In this study, we proposed a novel model-based tr...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruiyang Yu, Yunjun Yao, Qingxin Tang, Xueyi Zhang, Changliang Shao, Joshua B. Fisher, Jiquan Chen, Xiaotong Zhang, Yufu Li, Jia Xu, Lu Liu, Zijing Xie, Jing Ning, Jiahui Fan, Luna Zhang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10923714/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731049050865664
author Ruiyang Yu
Yunjun Yao
Qingxin Tang
Xueyi Zhang
Changliang Shao
Joshua B. Fisher
Jiquan Chen
Xiaotong Zhang
Yufu Li
Jia Xu
Lu Liu
Zijing Xie
Jing Ning
Jiahui Fan
Luna Zhang
author_facet Ruiyang Yu
Yunjun Yao
Qingxin Tang
Xueyi Zhang
Changliang Shao
Joshua B. Fisher
Jiquan Chen
Xiaotong Zhang
Yufu Li
Jia Xu
Lu Liu
Zijing Xie
Jing Ning
Jiahui Fan
Luna Zhang
author_sort Ruiyang Yu
collection DOAJ
description It is significant to simulate grassland gross primary production (GPP) to understand the terrestrial carbon budget over Inner Mongolia (IMG), China. Nevertheless, there is not sufficient <italic>in situ</italic> GPP data over this region. In this study, we proposed a novel model-based transfer learning (MTL) approach with generative adversarial networks-long short-term memory (GAN-LSTM) and light use efficiency (LUE) models to derive grassland GPP over IMG, China. We first used 25 grassland eddy covariance sites over the conterminous United States to establish the GAN-LSTM model and then fine-tuned it with six sites over IMG to estimate water constraints that were embedded into the LUE model to predict GPP. We then compared it with instance-based transfer learning and nontransfer learning approaches. Against the six IMG EC sites, the GPP estimates of MTL-LUE outperformed the other approaches with a lower root-mean-square error median (1.35 g C m<sup>&#x2212;2</sup> d<sup>&#x2212;1</sup>) and a higher Kling-Gupta efficiency of 0.54. An innovation of this approach is that MTL-LUE mitigates the effect of limited training samples on the machine learning-based LUE hybrid model for GPP estimates over IMG.
format Article
id doaj-art-b09c2b08f6aa452b83dc20fe316e0c94
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-b09c2b08f6aa452b83dc20fe316e0c942025-08-20T03:08:40ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01189738975410.1109/JSTARS.2025.354937310923714Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary ProductionRuiyang Yu0https://orcid.org/0000-0001-5000-0779Yunjun Yao1https://orcid.org/0000-0003-3803-8170Qingxin Tang2Xueyi Zhang3Changliang Shao4Joshua B. Fisher5Jiquan Chen6https://orcid.org/0000-0003-0761-9458Xiaotong Zhang7https://orcid.org/0000-0002-8397-2096Yufu Li8Jia Xu9https://orcid.org/0000-0001-7688-5050Lu Liu10Zijing Xie11Jing Ning12Jiahui Fan13https://orcid.org/0009-0006-0251-1420Luna Zhang14State Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing, ChinaState Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing, ChinaSchool of Geography and Environment, Liaocheng University, Liaocheng, ChinaKey Laboratory for Meteorological Disaster Monitoring and Early Warning and Risk Management of Characteristic Agriculture in Arid Regions, CMA, Yinchuan, ChinaState Key Laboratory of Efficient Utilization of Arid and Semi-arid Arable Land in Northern China, National Hulunber Grassland Ecosystem Observation and Research Station, Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing, ChinaSchmid College of Science and Technology, Chapman University,University Drive, Orange, CA, USADepartment of Geography, Environment, and Spatial Sciences, Michigan State University, East Lansing, MI, USAState Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing, ChinaJincheng Meteorological Administration, Jincheng, ChinaDepartment of Infrastructure Engineering, Faculty of Engineering &amp; IT, University of Melbourne, Melbourne, VIC, AustraliaState Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing, ChinaState Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing, ChinaState Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing, ChinaState Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing, ChinaState Key Laboratory of Remote Sensing and Digital Earth, Faculty of Geographical Science, Beijing Normal University, Beijing, ChinaIt is significant to simulate grassland gross primary production (GPP) to understand the terrestrial carbon budget over Inner Mongolia (IMG), China. Nevertheless, there is not sufficient <italic>in situ</italic> GPP data over this region. In this study, we proposed a novel model-based transfer learning (MTL) approach with generative adversarial networks-long short-term memory (GAN-LSTM) and light use efficiency (LUE) models to derive grassland GPP over IMG, China. We first used 25 grassland eddy covariance sites over the conterminous United States to establish the GAN-LSTM model and then fine-tuned it with six sites over IMG to estimate water constraints that were embedded into the LUE model to predict GPP. We then compared it with instance-based transfer learning and nontransfer learning approaches. Against the six IMG EC sites, the GPP estimates of MTL-LUE outperformed the other approaches with a lower root-mean-square error median (1.35 g C m<sup>&#x2212;2</sup> d<sup>&#x2212;1</sup>) and a higher Kling-Gupta efficiency of 0.54. An innovation of this approach is that MTL-LUE mitigates the effect of limited training samples on the machine learning-based LUE hybrid model for GPP estimates over IMG.https://ieeexplore.ieee.org/document/10923714/Grassland gross primary production (GPP)light use efficiency (LUE)remote sensingtransfer learning (TL)
spellingShingle Ruiyang Yu
Yunjun Yao
Qingxin Tang
Xueyi Zhang
Changliang Shao
Joshua B. Fisher
Jiquan Chen
Xiaotong Zhang
Yufu Li
Jia Xu
Lu Liu
Zijing Xie
Jing Ning
Jiahui Fan
Luna Zhang
Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Grassland gross primary production (GPP)
light use efficiency (LUE)
remote sensing
transfer learning (TL)
title Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production
title_full Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production
title_fullStr Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production
title_full_unstemmed Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production
title_short Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production
title_sort transfer learning in junction with a light use efficiency model for estimating grassland gross primary production
topic Grassland gross primary production (GPP)
light use efficiency (LUE)
remote sensing
transfer learning (TL)
url https://ieeexplore.ieee.org/document/10923714/
work_keys_str_mv AT ruiyangyu transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT yunjunyao transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT qingxintang transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT xueyizhang transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT changliangshao transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT joshuabfisher transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT jiquanchen transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT xiaotongzhang transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT yufuli transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT jiaxu transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT luliu transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT zijingxie transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT jingning transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT jiahuifan transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction
AT lunazhang transferlearninginjunctionwithalightuseefficiencymodelforestimatinggrasslandgrossprimaryproduction