山东禹城站叶面积指数无线传感器网络数据集(2020)研发方法与验证结果

Development and Validation of the Wireless Sensor Network Dataset of Leaf Area Index in Shandong Yucheng of China(2020)

随着通讯技术的发展,基于无线传感器网络技术的地面测量成为获取地表参数的重要手段。无线传感器网络以其长时间、多点同步观测的优势,为遥感卫星叶面积指数产品的真实性检验提供了可靠的数据支撑。然而,意外的电池、通信故障或天气影响会导致测量数据的不稳定,这就需要从大量原始数据中处理得到能够代表地面相对真值的数据。本文针对2020年5–11月在山东禹城站布置3个节点(0803、0804、0805)运用叶面积指数传感器网络系统SBLX-034进行观测。首先选择观测时间在上午10时至下午15时的数据,筛选出有效数据的时刻。然后依据站点间的时空相关性利用时序神经网络NARX建模,剔除模型预测误差大于1的异常时刻数据,并利用LSTM神经网络对处理后的数据规律进行检验。最后对每天的数据进行平均处理得到长时间序列的LAI实测相对真值,用于为相关研究提供数据支撑。本数据集为处理后的山东禹城站0803、0804和0805站点的无线传感器网络数据,具体包括:(1)禹城站3个无线传感器网络节点的地理位置数据;(2)2020年5–11月3个节点、每日叶面积指数数据。该数据集存储为.xlsx、.shp和.kml数据格式,由10个文件组成,数据量为49.1KB(压缩为1个文件,42.5 KB)。

With the development of communication technology,ground measurement based on Wireless Sensor Network(WSN)technology has become an important method for obtaining ground surface parameters.With its advantages of long-term and multi-point simultaneous observation,WSN provides reliable data for the validation of remote sensing satellite LAI products.However,unexpected situations such as dead batteries,communication failures or weather influence will cause the measurement data to be unstable,so it is necessary to process a large amount of raw data into relatively true value representing the ground measurement.In this paper,three nodes(0803,0804 and 0805)are arranged in Yucheng Station of Shandong province of China from May to November 2020,and the LAI WSN system SBLX-034 is used for observation.First,we select the observation between 10 a.m.and 3 p.m.,and filter out invalid data for each node.Then,according to the temporal and spatial correlation between the notes,the abnormal time data with NARX model prediction error more than 1 is eliminated,and the LSTM neural network is used to test the processed data pattern.Finally,the daily data are averaged into the measured relative true value of long-term LAI,which is used to provide data support for related research.This dataset is the processed WSN data of 0803,0804 and 0805 notes in Shandong Yucheng Station,including:(1)geographical location of three WSN nodes in Yucheng Station;(2)daily LAI of three nodes from May to November in 2020.The storage format is.xlsx,.shp and.kml data formats,and consists of 10 files with a data volume of 49.1 KB(compressed into one file,42.5 KB).