基于通量观测网的华北平原农田蒸散发数据集（2001-2015）

华北平原是中国最重要的产粮基地之一，然而该地区水资源缺乏、供需矛盾突出。 在全球气候变化及用水需求日益增加的背景下， 该地区水循环过程变得愈加脆弱。 因此如何准确估算蒸散发、 掌握蒸散发的时空变化规律， 进而合理配置水资源、提高农业用水效率、维持粮食产量是迫在眉睫的问题。
本研究利用支持向量回归模型，基于华北平原及周边的8个通量站点，并结合气象及遥感数据，对华北平原农田区域的蒸散发进行估算，并生产了年限为2001-2015年，空间分辨率为1km，时间分辨率为8天的蒸散发数据集。该模型在交叉验证试验中表现良好， 说明其空间泛化能力较强，适用于区域蒸散发模拟。

The North China Plain is one of the most important grain production bases in China. However, this region suffers from severe water shortages and prominent contradictions between water supply and demand. Against the backdrop of global climate change and increasing water demand, the water cycle processes in this region have grown increasingly fragile. Therefore, accurately estimating evapotranspiration, grasping its spatiotemporal variation patterns, and then rationally allocating water resources, improving agricultural water use efficiency, and maintaining grain production have become extremely pressing issues.

This study adopted the Support Vector Regression (SVR) model to estimate evapotranspiration over the cropland areas of the North China Plain, using data from 8 flux stations located in and around the plain, combined with meteorological and remote sensing datasets. We developed an evapotranspiration dataset spanning the period from 2001 to 2015, with a spatial resolution of 1 km and a temporal resolution of 8 days. This model exhibited excellent performance in cross-validation experiments, demonstrating its strong spatial generalization capability and suitability for regional evapotranspiration simulation.