摘要
由机器人与机器学习每日新闻的新闻记者兼新闻编辑-研究人员详细介绍了人工智能的新数据。根据Ne wsRx编辑从加州伯克利发回的新闻报道，研究表明：“太阳诱导的叶绿素荧光(SIF)在估算初级生产力方面仍然具有优势，尽管lac k保持稳定关系。基于卫星的二级SIF测量提供了全面的全球覆盖范围，并且几乎可以实时获得。”我们的新闻编辑引用了劳伦斯·伯克利国家实验室的研究：“然而，这些测量往往受到空间和空间稀疏性以及不连续性的限制。这些限制主要来自不完整的卫星轨道。此外，云层覆盖的变异性和仪器特有的周期性问题会损害数据质量。已经发展了两类方法来解决数据不连续性问题：(1)基于马赫ine学习的间隙填充技术和(2)地质统计学技术(各种形式的克里金)。前者利用辅助数据和SIF之间的关系，而后者通常依赖于现有的SIF数据记录及其协方差结构来提供未抽样位置的估计值。在本研究中，我们通过在具有外部漂移的Kriging保护伞下对两种方法进行Hybr化，创建了一种SIF缺口填充的综合方法。我们对2019年全年的OCO-2 SIF检索总量进行了留一交叉验证，比较了三种方法：普通Kriging，使用辅助数据的基于ML的估计，以及具有外部漂移的克里格法。发现ML、普通克里格法和混合方法的平均Abso Lute误差(MAE)分别为0.1399、0.1318和0.1183 mW m2 SR-1 nm-1.
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in artific ial intelligence. According to news reporting out of Berkeley, California, by Ne wsRx editors, research stated, “Sun-induced chlorophyll fluorescence (SIF) has p roven to be advantageous in estimating gross primary production, despite the lac k of a stable relationship. Satellite-based SIF measurements at Level 2 offer co mprehensive global coverage and are available in near real time.” Our news editors obtained a quote from the research from Lawrence Berkeley Natio nal Laboratory: “However, these measurements are often limited by spatial and te mporal sparsity, as well as discontinuities. These limitations primarily arise f rom incomplete satellite trajectories. Additionally, variability in cloud cover and periodic issues specific to the instruments can compromise data quality. Two families of methods have been developed to address data discontinuity: (1) mach ine learning-based gap-filling techniques and (2) geostatistical techniques (var ious forms of kriging). The former techniques utilize the relationships between ancillary data and SIF, while the latter usually rely on the available SIF data recordings and their covariance structure to provide estimates at unsampled loca tions. In this study, we create a synthetic approach for SIF gap filling by hybr idizing the two approaches under the umbrella of kriging with external drift. We performed leave-one-out cross-validation of the OCO-2 SIF retrieval aggregates for the entire year of 2019, comparing three methods: ordinary kriging, ML-based estimation using ancillary data, and kriging with external drift. The Mean Abso lute Error (MAE) for ML, ordinary kriging, and the hybrid approach was found to be 0.1399, 0.1318, and 0.1183 mW m2 sr-1 nm-1, respectively.”
NETL
NSTL