RapidAI4EO: A Corpus for Higher Spatial and Temporal Reasoning

TL;DR

RapidAI4EO develops a comprehensive, high-resolution spatiotemporal satellite dataset to enhance land monitoring, phenology analysis, and change detection for the Copernicus ecosystem.

Contribution

It introduces the densest open satellite training datasets combining open data with Planet imagery for improved land use and cover monitoring.

Findings

Creation of high-resolution daily time series datasets

Fusion of open satellite data with Planet imagery at 500,000 locations

Open sourcing datasets for the remote sensing community

Abstract

Under the sponsorship of the European Union Horizon 2020 program, RapidAI4EO will establish the foundations for the next generation of Copernicus Land Monitoring Service (CLMS) products. The project aims to provide intensified monitoring of Land Use (LU), Land Cover (LC), and LU change at a much higher level of detail and temporal cadence than it is possible today. Focus is on disentangling phenology from structural change and in providing critical training data to drive advancement in the Copernicus community and ecosystem well beyond the lifetime of this project. To this end we are creating the densest spatiotemporal training sets ever by fusing open satellite data with Planet imagery at as many as 500,000 patch locations over Europe and delivering high resolution daily time series at all locations. We plan to open source these datasets for the benefit of the entire remote sensing community.