001046797 001__ 1046797
001046797 005__ 20251202203134.0
001046797 0247_ $$2doi$$a10.1109/CVPRW67362.2025.00225
001046797 037__ $$aFZJ-2025-03964
001046797 1001_ $$0P:(DE-HGF)0$$aBlumenstiel, Benedikt$$b0$$eCorresponding author
001046797 1112_ $$a2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)$$cNashville$$d2025-06-11 - 2025-06-12$$wTN
001046797 245__ $$aTerramesh: A Planetary Mosaic of Multimodal Earth Observation Data
001046797 260__ $$bIEEE$$c2025
001046797 300__ $$an/a
001046797 3367_ $$2ORCID$$aCONFERENCE_PAPER
001046797 3367_ $$033$$2EndNote$$aConference Paper
001046797 3367_ $$2BibTeX$$aINPROCEEDINGS
001046797 3367_ $$2DRIVER$$aconferenceObject
001046797 3367_ $$2DataCite$$aOutput Types/Conference Paper
001046797 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1764676848_15938
001046797 520__ $$aLarge-scale foundation models in Earth Observation can learn versatile, label-efficient representations by leveraging massive amounts of unlabeled data. However, existing public datasets are often limited in scale, geographic coverage, or sensor variety. We introduce TerraMesh, a new globally diverse, multimodal dataset combining optical, synthetic aperture radar, elevation, and land-cover modalities in an Analysis-Ready Data format. TerraMesh includes over 9 million samples with eight spatiotemporal aligned modalities, enabling large-scale pre-training and fostering robust cross-modal correlation learning. The dataset spans nearly all terrestrial ecosystems and is stored with Zarr to facilitate efficient, HPC-friendly loading at scale. We provide detailed data processing steps, comprehensive statistics, and empirical evidence demonstrating improved model performance when pre-trained on TerraMesh. The dataset will be made publicly available with a permissive license.
001046797 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001046797 536__ $$0G:(ESA-Grant)D/564/67338791$$aAI Foundation - AI Foundation Models for EO (AIFM4EO, FAST-EO) (D/564/67338791)$$cD/564/67338791$$x1
001046797 588__ $$aDataset connected to CrossRef Conference
001046797 7001_ $$0P:(DE-HGF)0$$aFraccaro, Paolo$$b1
001046797 7001_ $$0P:(DE-HGF)0$$aMarsocci, Valerio$$b2
001046797 7001_ $$0P:(DE-HGF)0$$aJakubik, Johannes$$b3
001046797 7001_ $$0P:(DE-Juel1)204210$$aMaurogiovanni, Stefano$$b4$$ufzj
001046797 7001_ $$0P:(DE-HGF)0$$aCzerkawski, Mikolaj$$b5
001046797 7001_ $$0P:(DE-Juel1)178695$$aSedona, Rocco$$b6$$ufzj
001046797 7001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b7$$ufzj
001046797 7001_ $$0P:(DE-HGF)0$$aBrunschwiler, Thomas$$b8
001046797 7001_ $$0P:(DE-HGF)0$$aBernabe-Moreno, Juan$$b9
001046797 7001_ $$0P:(DE-HGF)0$$aLongépé, Nicolas$$b10
001046797 773__ $$a10.1109/CVPRW67362.2025.00225
001046797 8564_ $$uhttp://doi.org/10.1109/CVPRW67362.2025.00225
001046797 8564_ $$uhttps://juser.fz-juelich.de/record/1046797/files/_CVPR_EV__TerraMesh.pdf$$yRestricted
001046797 909CO $$ooai:juser.fz-juelich.de:1046797$$pVDB
001046797 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)204210$$aForschungszentrum Jülich$$b4$$kFZJ
001046797 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178695$$aForschungszentrum Jülich$$b6$$kFZJ
001046797 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b7$$kFZJ
001046797 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001046797 9141_ $$y2025
001046797 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001046797 980__ $$acontrib
001046797 980__ $$aVDB
001046797 980__ $$aI:(DE-Juel1)JSC-20090406
001046797 980__ $$aUNRESTRICTED