Harnessing Administrative Data Inventories to Create a Reliable Transnational Reference Database for Crop Type Monitoring

TL;DR

This paper presents EURO C ROPS, a harmonized transnational reference dataset for crop type classification, addressing the scarcity of reliable large-scale ground-truth data for machine learning in Earth observation.

Contribution

It introduces a novel approach to aggregate and harmonize administrative data across countries to create a reliable, large-scale reference database for crop monitoring.

Findings

EURO C ROPS enables improved crop type classification accuracy.

The dataset demonstrates successful transnational interoperability.

It provides a scalable solution for high-quality reference data sourcing.

Abstract

With leaps in machine learning techniques and their applicationon Earth observation challenges has unlocked unprecedented performance across the domain. While the further development of these methods was previously limited by the availability and volume of sensor data and computing resources, the lack of adequate reference data is now constituting new bottlenecks. Since creating such ground-truth information is an expensive and error-prone task, new ways must be devised to source reliable, high-quality reference data on large scales. As an example, we showcase E URO C ROPS, a reference dataset for crop type classification that aggregates and harmonizes administrative data surveyed in different countries with the goal of transnational interoperability.