13 Sep 2022
13 Sep 2022
Status: this preprint is currently under review for the journal ESSD.

AI4Boundaries: an open AI-ready dataset to map field boundaries with Sentinel-2 and aerial photography

Raphaël d'Andrimont1, Martin Claverie1, Pieter Kempeneers1, Davide Muraro1, Momchil Yordanov1, Devis Peressutti2, Matej Batič2, and François Waldner1 Raphaël d'Andrimont et al.
  • 1European Commission Joint Research Centre (JRC), Ispra, Italy
  • 2Sinergise, Ljubljana, Slovenia

Abstract. Field boundaries are at the core of many agricultural applications and are a key enabler for operational monitoring of agricultural production to support food security. Recent scientific progress in deep learning methods has highlighted the capacity to extract field boundaries from satellite and aerial images with a clear improvement from object-based image analysis (e.g., multiresolution segmentation) or conventional filters (e.g., Sobel filters). However, these methods need labels to be trained on. So far, no standard data set exists to easily and robustly benchmark models and progress the state of the art. The absence of such benchmark data further impedes proper comparison against existing methods. Besides, there is no consensus on which evaluation metrics should be reported (both at the pixel and field levels). As a result, it is currently impossible to compare and benchmark new and existing methods. To fill these gaps, we introduce AI4Boundaries, a data set of images and labels readily usable to train and compare models on the task of field boundary detection. AI4Boundaries includes two specific data sets: (i) a 10-m Sentinel-2 monthly composites for large-scale analyses in retrospect, (ii) a 1-m orthophoto data set for regional-scale analyses such as the automatic extraction of Geospatial Aid Application (GSAA). All labels have been sourced from GSAA data that have been made openly available (Austria, Catalonia, France, Luxembourg, the Netherlands, Slovenia, and Sweden) for 2019 representing 14.8 M parcels covering 376 km2. Data were selected following a stratified random sampling drawn based on two landscape fragmentation metrics, the perimeter/area ratio and the area covered by parcels, thus taking into account the diversity of the agricultural landscapes. The resulting “AI4Boundaries” dataset consists of 7,831 samples of 256 by 256 pixels for the 10-m Sentinel-2 dataset and of 512 by 512 pixels for the 1-m aerial orthophoto. Both datasets are provided with the corresponding vector ground-truth parcel delineation (2.5 M parcels covering 47,105 km2) and with a raster version already pre-processed and ready to use. Besides providing this open dataset to foster computer vision developments of parcel delineation methods, we discuss perspectives and limitations of the dataset for various types of applications in the agriculture domain and consider possible further improvements.

Raphaël d'Andrimont et al.

Status: open (until 08 Nov 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Raphaël d'Andrimont et al.

Data sets

AI4boundaries d'Andrimont, R., Claverie, M., Kempeneers, P., Muraro, D., Martinez Sanchez, L., and Waldner, F.

Raphaël d'Andrimont et al.


Total article views: 109 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
75 29 5 109 3 2
  • HTML: 75
  • PDF: 29
  • XML: 5
  • Total: 109
  • BibTeX: 3
  • EndNote: 2
Views and downloads (calculated since 13 Sep 2022)
Cumulative views and downloads (calculated since 13 Sep 2022)

Viewed (geographical distribution)

Total article views: 100 (including HTML, PDF, and XML) Thereof 100 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 20 Sep 2022
Short summary
AI4boundaries is an open AI-ready dataset to map field boundaries with Sentinel-2 and aerial photography provided with harmonised labels covering 7 countries and 2.5 M parcels in Europe.