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...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| 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>−2</sup> d<sup>−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 & 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>−2</sup> d<sup>−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 |