arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.05912q-bio.QMcs.LGphysics.data-anstat.ML
收藏

生物物理参数时间序列的多输出高斯过程间隙填充

Gap Filling of Biophysical Parameter Time Series with Multi-Output Gaussian Processes

1 Image Processing Laboratory (IPL). Universitat de Val\`encia, Spain. 2 Dep. Física de la Terra i Termodinàmica, Universitat de Val\`encia, Spain.

Anna Mateo-Sanchis, Jordi Munoz-Mari, Manuel Campos-Taberner, Javier Garcia-Haro, Gustau Camps-Valls

摘要:

在这项工作中,我们评估多输出(MO)高斯过程(GP)模型的基础上的线性模型coregionalization(LMC)的生物物理参数变量估计下的间隙填充设置。特别是,我们专注于LAI和fAPAR水稻地区。我们展示了这个问题如何无法用标准的单输出(SO)GP模型来解决,以及所提出的MO-GP模型如何通过隐式地执行跨域信息传输,即使在高缺失数据制度下也能够成功地预测这些变量。

英文摘要:

In this work we evaluate multi-output (MO) Gaussian Process (GP) models based on the linear model of coregionalization (LMC) for estimation of biophysical parameter variables under a gap filling setup. In particular, we focus on LAI and fAPAR over rice areas. We show how this problem cannot be solved with standard single-output (SO) GP models, and how the proposed MO-GP models are able to successfully predict these variables even in high missing data regimes, by implicitly performing an across-domain information transfer.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑