{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/m3fusion-a-deep-learning-architecture-for","title":"M3Fusion: A Deep Learning Architecture for Multi-{Scale/Modal/Temporal} satellite data fusion","arxiv_id":"1803.01945","date":"2018-03-05","proceeding":null,"authors":["P. Benedetti","D. Ienco","R. Gaetano","K. Osé","R. Pensa","S. Dupuy"],"abstract":"Modern Earth Observation systems provide sensing data at different temporal\nand spatial resolutions. Among optical sensors, today the Sentinel-2 program\nsupplies high-resolution temporal (every 5 days) and high spatial resolution\n(10m) images that can be useful to monitor land cover dynamics. On the other\nhand, Very High Spatial Resolution images (VHSR) are still an essential tool to\nfigure out land cover mapping characterized by fine spatial patterns.\nUnderstand how to efficiently leverage these complementary sources of\ninformation together to deal with land cover mapping is still challenging. With\nthe aim to tackle land cover mapping through the fusion of multi-temporal High\nSpatial Resolution and Very High Spatial Resolution satellite images, we\npropose an End-to-End Deep Learning framework, named M3Fusion, able to leverage\nsimultaneously the temporal knowledge contained in time series data as well as\nthe fine spatial information available in VHSR information. Experiments carried\nout on the Reunion Island study area asses the quality of our proposal\nconsidering both quantitative and qualitative aspects.","url_abs":"http://arxiv.org/abs/1803.01945v1","url_pdf":"http://arxiv.org/pdf/1803.01945v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"m3fusion-a-deep-learning-architecture-for","repo_url":"https://github.com/remicres/otbtf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"earth-observation","task_name":"Earth Observation"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}