A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning

TL;DR

This paper introduces Sen4AgriNet, a comprehensive multi-year, multi-country Sentinel-2 satellite dataset for crop classification and segmentation, enabling advanced deep learning applications in agricultural monitoring.

Contribution

It provides the first large-scale, multi-country, multi-year satellite dataset with ground-truth labels based on farmer declarations, standardizes crop taxonomy, and offers versatile sub-datasets for diverse deep learning tasks.

Findings

Sen4AgriNet contains 42.5 million parcels, surpassing existing datasets in size.

The dataset supports multiple deep learning applications through OAD and PAD sub-datasets.

Experiments demonstrate the dataset's effectiveness across different countries and years.

Abstract

In this work we introduce Sen4AgriNet, a Sentinel-2 based time series multi country benchmark dataset, tailored for agricultural monitoring applications with Machine and Deep Learning. Sen4AgriNet dataset is annotated from farmer declarations collected via the Land Parcel Identification System (LPIS) for harmonizing country wide labels. These declarations have only recently been made available as open data, allowing for the first time the labeling of satellite imagery from ground truth data. We proceed to propose and standardise a new crop type taxonomy across Europe that address Common Agriculture Policy (CAP) needs, based on the Food and Agriculture Organization (FAO) Indicative Crop Classification scheme. Sen4AgriNet is the only multi-country, multi-year dataset that includes all spectral information. It is constructed to cover the period 2016-2020 for Catalonia and France, while it can be extended to include additional countries. Currently, it contains 42.5 million parcels, which makes it significantly larger than other available archives. We extract two sub-datasets to highlight its value for diverse Deep Learning applications; the Object Aggregated Dataset (OAD) and the Patches Assembled Dataset (PAD). OAD capitalizes zonal statistics of each parcel, thus creating a powerful label-to-features instance for classification algorithms. On the other hand, PAD structure generalizes the classification problem to parcel extraction and semantic segmentation and labeling. The PAD and OAD are examined under three different scenarios to showcase and model the effects of spatial and temporal variability across different years and different countries.