IAMAP: Unlocking Deep Learning in QGIS for non-coders and limited computing resources
We introduce IAMAP, a user-friendly plugin for the geographic information system QGIS that allows users to (1) tile raster images and feed them into pre-trained deep learning model to extract image features; (2) reduce feature dimensionality; (3) perform clustering on features or their reduced representations; (4) generate feature similarity maps; (5) calibrate and validate supervised machine learning models to create maps.By enabling non-AI specialists to leverage the high-quality features provided by foundation models without requiring GPU capacity or extensive reference datasets, IAMAP contributes to the democratization of these computationally efficient and energy-conscious methods.Development of the plugin is opensource on GitHub.Documentation and tutorials are available on Read the Docs.
Authors
- Anthony Malkassian (ORCID: https://orcid.org/0000-0001-9603-4448)
- Paul Tresson (ORCID: https://orcid.org/0000-0002-1275-4673)
- Pierre Le Coz (ORCID: https://orcid.org/0000-0002-7391-6955)
- Hadrien Tulet (ORCID: https://orcid.org/0009-0004-8139-2380)
- Maxime Réjou Méchain
Institutions
- Centre National de la Recherche Scientifique (FR)
- Centre de Coopération Internationale en Recherche Agronomique pour le Développement (FR)
- Université de Montpellier (FR)
- University of Reunion Island (RE)
- Institut Agro Montpellier (FR)
- Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement (FR)
- UMR Botanique et Modélisation de l’Architecture des Plantes et des végétations (FR)
- Peuplements végétaux et bioagresseurs en milieu tropical (RE)
- Institut de Recherche pour le Développement (FR)
- Chiang Mai University (TH)
Publication Details
- Journal
- The Journal of Open Source Software
- Published
- 2026-06-25
- DOI
- https://doi.org/10.21105/joss.10329
- Primary Topic
- Remote-Sensing Image Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.00