The EuroCropsML time series benchmark dataset for few-shot crop type classification in Europe

2024-07-24

Scientific Data

AI Summary

This paper addresses the few-shot learning challenge in cross-national agricultural parcel crop-type classification. We introduce EuroCropsML—the first open, fine-grained (176 classes), time-series remote sensing benchmark for few-shot learning across multiple European countries. Built upon the open-source EuroCrops parcel boundaries and labels, EuroCropsML integrates Sentinel-2 L1C imagery to extract pixel-level median time-series profiles, yielding an analysis-ready dataset of 706,683 labeled parcels. Hosted on Zenodo, it enables standardized evaluation of few-shot temporal models across national borders, years, and crop categories. EuroCropsML is the first benchmark to support reproducible, fair, and comparable few-shot time-series modeling in fine-grained, multi-country agricultural remote sensing—thereby filling a critical gap in the field.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

We introduce EuroCropsML, an analysis-ready remote sensing dataset based on the open-source EuroCrops collection, for machine learning (ML) benchmarking of time series crop type classification in Europe. It is the first time-resolved remote sensing dataset designed to benchmark transnational few-shot crop type classification algorithms that supports advancements in algorithmic development and research comparability. It comprises 706683 multi-class labeled data points across 176 crop classes. Each data point features a time series of per-parcel median pixel values extracted from Sentinel-2 L1C data and precise geospatial coordinates. EuroCropsML is publicly available on Zenodo.

Problem

• Benchmark few-shot crop classification across Europe
• Provide time-series Sentinel-2 data for agriculture
• Enable standardized algorithm comparison with 706K samples

Innovation

• Time series crop classification using Sentinel-2 data
• Few-shot learning for transnational crop classification
• Public benchmark dataset with 706k multi-class labels