Automatically Detected Field Boundaries in Canada, 2023

OneSoil employs a proprietary machine learning (ML) model based on state-of-the-art instance segmentation to detect field boundaries. Utilizing raw Sentinel-2 data aggregated according to local vegetation season maps and an additional upscaling module to enhance boundary accuracy, we ensure precise results. OneSoil’s data preprocessing involves the utilization of their cloud detector module and local season mapping.

Data and Resources

Additional Info

Field	Value
Last Updated	April 17, 2026, 20:39 (UTC)
Created	April 17, 2026, 20:39 (UTC)
contact_email	agri-geomatics-agrog@agr.gc.ca
contact_person	{"en": "Government of Canada; Agriculture and Agri-Food Canada; Science and Technology Branch,,agri-geomatics-agrog@agr.gc.ca", "fr": "Gouvernement du Canada; Agriculture et Agroalimentaire Canada; direction générale des sciences et de la technologie,agri-geomatics-agrog@agr.gc.ca"}
criticality_level	[]
data_dictionary	EPSG:3857,http://www.epsg-registry.org,8.1.4
geographic_scope	[]
open_canada_collection	fgp
open_canada_date_published	2024-09-12 00:00:00
open_canada_keywords	{"en": ["Farmlands", "Remote sensing", "Boundaries"], "fr": ["Terre agricole", "Télédétection", "Frontière"]}
open_canada_subject	["agriculture", "economics_and_industry", "form_descriptors", "government_and_politics", "nature_and_environment"]
sensitivity_level	unrestricted
title_fr	Limites des champs détectées automatiquement au Canada, 2023
update_frequency	not_planned