Data, R Scripts and Random Forest Models for Winter Catch Crop Monitoring from Sentinel-2 NDVI Time Series in Germany

The data contains a zip-file with the following folders: a) data (agricultural parcels, filled and unfilled NDVI time series tables, feature extraction tables and prediction results) (csv, shp), b) model (random forest models for catch crop prediction) (rds), and c) R (R script files for Random Forest model training and prediction with RStudio) (r).

The algorithms and models developed for this study were implemented via virtual Docker containers into the timeStamp software prototype which allows for large-scale automatized catch crop analysis on the parcel-level (www.timestamp.lup-umwelt.de). timeStamp saves Sentinel-2 raster data as parcel-wise clipped image time series into a PostGIS database. All further processing steps were performed with the statistical computing language R (RStudio Team, 2020). For raster data manipulation within the PostGIS database and downloading NDVI time series, we used the packages rpostgis (Bucklin and Basille, 2019) and RPostgreSQL (Conway et al., 2017). For time series filling and predictors calculation, we used the packages zoo (Zeileis et al., 2020), hydroGOF (Zambrano-Bigiarini, 2020), tsoutliers (de Lacalle, 2019), and changepoint (Killick et al., 2016). For RF modelling, we used the package caret (Kuhn et al., 2020).

The original data for NDVI time series calculation is from the GFZ Time Series System for Sentinel-2 by the German Research Centre for Geosciences, 2020 (https://gitext.gfz-potsdam.de/gts2). The predictors for Random Forest modelling calculated from the NDVI time series are described in the article in the reference section.

For further information, we refer to the following article: Schulz, C.; Holtgrave, A.; Kleinschmit, B.: Large-scale winter catch crop monitoring with Sentinel-2 time series and machine learning–An alternative to on-site controls?, Computers and Electronics in Agriculture, Volume 186, 2021, 106173, ISSN 0168-1699, https://doi.org/10.1016/j.compag.2021.106173.

本数据集包含一个压缩包，内含三类文件夹：a) data（数据）文件夹，存储农业地块的归一化差分植被指数（Normalized Difference Vegetation Index, NDVI）时序表格（含已填充与未填充数据）、特征提取表格及预测结果文件，格式涵盖csv与shp；b) model（模型）文件夹，存放用于填闲作物预测的随机森林（Random Forest, RF）模型，文件格式为rds；c) R脚本文件夹，包含依托RStudio开展随机森林模型训练与预测的R脚本文件，格式为r。

本研究开发的算法与模型通过Docker虚拟容器集成至timeStamp软件原型中，该原型可实现地块级别的大规模自动化填闲作物分析（访问地址：www.timestamp.lup-umwelt.de）。timeStamp将Sentinel-2栅格数据裁剪为地块级时序影像，并存储至PostGIS数据库中。后续所有处理步骤均通过统计计算语言R（RStudio Team, 2020）完成。针对PostGIS数据库内的栅格数据操作与NDVI时序数据下载，本研究使用了rpostgis（Bucklin与Basille, 2019）及RPostgreSQL（Conway等, 2017）工具包；针对时序数据填充与预测因子计算，使用了zoo（Zeileis等, 2020）、hydroGOF（Zambrano-Bigiarini, 2020）、tsoutliers（de Lacalle, 2019）及changepoint（Killick等, 2016）工具包；针对随机森林建模，则使用了caret工具包（Kuhn等, 2020）。

用于NDVI时序计算的原始数据源自德国地球科学研究中心2020年发布的Sentinel-2时间序列系统（GFZ Time Series System for Sentinel-2，访问地址：https://gitext.gfz-potsdam.de/gts2）。由NDVI时序计算得到的随机森林建模预测因子已在本文参考文献章节中详细说明。

如需获取更多信息，请参阅以下论文：Schulz, C.; Holtgrave, A.; Kleinschmit, B.：基于Sentinel-2时序数据与机器学习的大规模冬季填闲作物监测——替代田间核查的可行方案？, 《农业计算机与电子学》（Computers and Electronics in Agriculture）, 第186卷, 2021年, 文章编号106173, ISSN 0168-1699, https://doi.org/10.1016/j.compag.2021.106173.