Dataset of Sentinel 2 Image Time Series for Multi-annual Crop Type Classification in Perú

This repository contains multi-annual crop classification data for the Chugay district, Peru. The main dataset, s2_cube.nc, contains processed Sentinel-2 imagery (August 2021–December 2024) used to generate crop classifications. The imagery was retrieved from Google Earth Engine collections: COPERNICUS/S2_SR, COPERNICUS/S2_CLOUD_PROBABILITY, and GOOGLE/CLOUD_SCORE_PLUS/V1/S2_HARMONIZED and processed using the Python function export_s2_images from the s2_gee_utils module in the Github repository https://github.com/kundun14/multi-annual-crop-classification-with-phenological-features. Additional datasets include: aoi.gpkg – Area of interest of the study region. FIELDS_v2_REFINED_YEARLYCLASS_97_V3.gpkg – Cropland boundaries for 189 fields sampled in 2022 and 2024, including dominant crop types and sowing/harvest dates. MO_SAMPLES.xlsx – Soil physical-chemical data from 189 composite soil samples collected at 0–24 cm depth, analyzed for pH, EC, SOC, CEC, exchangeable cations, particle size, and δ¹⁵N. zonal_NDVI_s2_fields.rds/ – Tabular dataset containing NDVI and EVI time series, alongside a quality flag for each observation. The data are extracted from a sequence of Sentinel-2 surface reflectance images processed in Google Earth Engine. After preliminary cloud masking and pixel quality tests, NDVI and EVI are calculated on a per-field basis, aggregating the statistics in zonal summaries per crop type and season. results/ – Folder containing intermediate and final outputs from crop classification analyses. Reference for code and methodology:The Sentinel-2 image processing and crop classification workflow is available at: https://github.com/kundun14/multi-annual-crop-classification-with-phenological-features. Acknowledgments:This research was funded by the Sustainable Farming CGIAR Science Program and the Deutsche Gesellschaft für Internationale Zusammenarbeit (GIZ) through the fund for the promotion of innovation in agriculture (i4Ag), Agreement 543 N◦: 81275993; and as part of the CGIAR Initiative on Excellence in Agronomy, now integrated into the CGIAR Sustainable Farming Science Program. CGIAR research is supported by contributions to the CGIAR Trust Fund. Authors:Marcelo Bueno — https://orcid.org/0000-0003-2377-0430Hildo Loayza — https://orcid.org/0000-0002-4145-5453