您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

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

文献类型： 外文期刊

作者： Yu, Ruiyang 1 ; Yao, Yunjun 1 ; Tang, Qingxin 2 ; Zhang, Xueyi 3 ; Shao, Changliang 4 ; Fisher, Joshua B. 5 ; Chen, Jiquan 6 ; Zhang, Xiaotong 1 ; Li, Yufu 7 ; Xu, Jia 8 ; Liu, Lu 1 ; Xie, Zijing 1 ; Ning, Jing 1 ; Fan, Jiahui 1 ; Zhang, Luna 1 ;

作者机构： 1.Beijing Normal Univ, Fac Geog Sci, State Key Lab Remote Sensing & Digital Earth, Beijing 100875, Peoples R China

2.Liaocheng Univ, Sch Geog & Environm, Liaocheng 252000, Peoples R China

3.CMA, Key Lab Meteorol Disaster Monitoring & Early Warni, Yinchuan 750002, Peoples R China

4.Chinese Acad Agr Sci, Inst Agr Resources & Reg Planning, State Key Lab Efficient Utilizat Arid & Semiarid A, Natl Hulunber Grassland Ecosyst Observat & Res Stn, Beijing 100081, Peoples R China

5.Chapman Univ, Schmid Coll Sci & Technol, Univ Dr, Orange, CA 92866 USA

6.Michigan State Univ, Dept Geog Environm & Spatial Sci, E Lansing, MI 48823 USA

7.Jincheng Meteorol Adm, Jincheng 048026, Peoples R China

8.Univ Melbourne, Fac Engn & IT, Dept Infrastruct Engn, Melbourne, Vic 3010, Australia

关键词： Grasslands; Training; Long short term memory; Logic gates; Transfer learning; Remote sensing; Predictive models; Land surface temperature; Data models; Normalized difference vegetation index; Grassland gross primary production (GPP); light use efficiency (LUE); remote sensing; transfer learning (TL)

期刊名称：IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING （ 影响因子：5.3； 五年影响因子：5.6 ）

ISSN： 1939-1404

年卷期： 2025 年 18 卷

页码：

收录情况： SCI

摘要： 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 in situ 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(-2) d(-1)) 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.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台