{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T16:05:05Z","timestamp":1791648305106,"version":"4.3.4"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T00:00:00Z","timestamp":1687824000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T00:00:00Z","timestamp":1687824000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","award":["PID2019-109026RB-I00, ERDF"],"award-info":[{"award-number":["PID2019-109026RB-I00, ERDF"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Cognitive cloud computing in space (3CS) describes a new frontier of space innovation powered by Artificial Intelligence, enabling an explosion of new applications in observing our planet and enabling deep space exploration. In this framework, machine learning (ML) payloads\u2014isolated software capable of extracting high level information from onboard sensors\u2014are key to accomplish this vision. In this work we demonstrate, in a satellite deployed in orbit, a ML payload called \u2018WorldFloods\u2019 that is able to send compressed flood maps from sensed images. In particular, we perform a set of experiments to: (1) compare different segmentation models on different processing variables critical for onboard deployment, (2) show that we can produce, onboard, vectorised polygons delineating the detected flood water from a full Sentinel-2 tile, (3) retrain the model with few images of the onboard sensor downlinked to Earth and (4) demonstrate that this new model can be uplinked to the satellite and run on new images acquired by its camera. Overall our work demonstrates that ML-based models deployed in orbit can be updated if new information is available, paving the way for agile integration of onboard and onground processing and \u201con the fly\u201d continuous learning.<\/jats:p>","DOI":"10.1038\/s41598-023-34436-w","type":"journal-article","created":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T06:03:28Z","timestamp":1687845808000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["In-orbit demonstration of a re-trainable machine learning payload for processing optical imagery"],"prefix":"10.1038","volume":"13","author":[{"given":"Gonzalo","family":"Mateo-Garcia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josh","family":"Veitch-Michaelis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cormac","family":"Purcell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Longepe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Reid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alice","family":"Anlind","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fredrik","family":"Bruhn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Parr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pierre Philippe","family":"Mathieu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,27]]},"reference":[{"key":"34436_CR1","unstructured":"Etten, A.\u00a0V. & Hogan, D. The SpaceNet multi-temporal urban development challenge. CoRRarXiv:2102.11958 (2021)."},{"key":"34436_CR2","unstructured":"Sirko, W. et\u00a0al. Continental-scale building detection from high resolution satellite imagery (2021). arXiv:2107.12283."},{"key":"34436_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3233\/AIS-210610","volume":"13","author":"Y Wang","year":"2021","unstructured":"Wang, Y. et al. Machine learning-based ship detection and tracking using satellite images for maritime surveillance. J. Amb. Intell. Smart Environ. 13, 1\u201311. https:\/\/doi.org\/10.3233\/AIS-210610 (2021).","journal-title":"J. Amb. Intell. Smart Environ."},{"key":"34436_CR4","doi-asserted-by":"publisher","first-page":"897","DOI":"10.3390\/rs14040897","volume":"14","author":"I Maduako","year":"2022","unstructured":"Maduako, I. et al. Automated school location mapping at scale from satellite imagery based on deep learning. Remote Sens. 14, 897. https:\/\/doi.org\/10.3390\/rs14040897 (2022).","journal-title":"Remote Sens."},{"key":"34436_CR5","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-021-03957-7","volume":"598","author":"L Kruitwagen","year":"2021","unstructured":"Kruitwagen, L. et al. A global inventory of photovoltaic solar energy generating units. Nature 598, 604\u2013610. https:\/\/doi.org\/10.1038\/s41586-021-03957-7 (2021).","journal-title":"Nature"},{"key":"34436_CR6","doi-asserted-by":"publisher","first-page":"100413","DOI":"10.1016\/j.rsase.2020.100413","volume":"20","author":"R Yang","year":"2020","unstructured":"Yang, R., Ahmed, Z. U., Schulthess, U. C., Kamal, M. & Rai, R. Detecting functional field units from satellite images in smallholder farming systems using a deep learning based computer vision approach: A case study from bangladesh. Remote Sens. Appl. Soc. Environ. 20, 100413. https:\/\/doi.org\/10.1016\/j.rsase.2020.100413 (2020).","journal-title":"Remote Sens. Appl. Soc. Environ."},{"key":"34436_CR7","first-page":"702","volume":"33","author":"T Rudner","year":"2019","unstructured":"Rudner, T. et al. Multi3net: segmenting flooded buildings via fusion of multiresolution, multisensor, and multitemporal satellite imagery. Proc. AAAI Conf. Artif. Intell. 33, 702\u2013709 (2019).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"34436_CR8","doi-asserted-by":"publisher","first-page":"2532","DOI":"10.3390\/rs12162532","volume":"12","author":"E Nemni","year":"2020","unstructured":"Nemni, E., Bullock, J., Belabbes, S. & Bromley, L. Fully convolutional neural network for rapid flood segmentation in synthetic aperture radar imagery. Remote Sens. 12, 2532. https:\/\/doi.org\/10.3390\/rs12162532 (2020).","journal-title":"Remote Sens."},{"key":"34436_CR9","unstructured":"Koh, P.\u00a0W. et\u00a0al. Wilds: A benchmark of in-the-wild distribution shifts. In Proceedings of the 38th International Conference on Machine Learning, Proceedings of Machine Learning Research (eds. Meila, M. & Zhang, T.), vol. 139, 5637\u20135664 (PMLR, 2021)."},{"key":"34436_CR10","unstructured":"Kairouz, P. et\u00a0al. Advances and Open Problems in Federated Learning. arXiv e-printsarXiv:1912.04977 (2019)."},{"key":"34436_CR11","doi-asserted-by":"publisher","unstructured":"Giuffrida, G. et\u00a0al. The phi-Sat-1 mission: The first on-board deep neural network demonstrator for satellite earth observation. IEEE Transactions on Geoscience and Remote Sensing 1. https:\/\/doi.org\/10.1109\/TGRS.2021.3125567 (2021).","DOI":"10.1109\/TGRS.2021.3125567"},{"key":"34436_CR12","doi-asserted-by":"publisher","first-page":"7249","DOI":"10.1038\/s41598-021-86650-z","volume":"11","author":"G Mateo-Garcia","year":"2021","unstructured":"Mateo-Garcia, G. et al. Towards global flood mapping onboard low cost satellites with machine learning. Sci. Rep. 11, 7249. https:\/\/doi.org\/10.1038\/s41598-021-86650-z (2021).","journal-title":"Sci. Rep."},{"key":"34436_CR13","unstructured":"The Pod Manager Tool. https:\/\/podman.io\/ (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR14","unstructured":"The Docker Software Container System. https:\/\/www.docker.com\/ (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR15","unstructured":"D-Orbit Space PLC LTD. https:\/\/www.dorbit.space\/ (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR16","unstructured":"Unibap PLC LTD. https:\/\/unibap.com\/ (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR17","unstructured":"ESA $$\\phi$$-Lab. https:\/\/philab.phi.esa.int\/ (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR18","unstructured":"D-Orbit ION Satellite Carrier. https:\/\/www.dorbit.space\/launch-deployment (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR19","unstructured":"The D-Orbit D-Sense Sensor Module. https:\/\/www.dorbit.space\/d-sense (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR20","unstructured":"FDL Europe 2019. https:\/\/fdleurope.org\/fdl-europe-2019 (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR21","unstructured":"The Sentinel 2 User Handbook. https:\/\/sentinels.copernicus.eu\/documents\/247904\/685211\/Sentinel-2_User_Handbook (2022). [Online] Accessed 31 May 2022."},{"key":"34436_CR22","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1080\/01431169608948714","volume":"17","author":"SK McFeeters","year":"1996","unstructured":"McFeeters, S. K. The use of the normalized difference water index (NDWI) in the delineation of open water features. Int. J. Remote Sens. 17, 1425\u20131432 (1996).","journal-title":"Int. J. Remote Sens."},{"key":"34436_CR23","doi-asserted-by":"publisher","first-page":"3025","DOI":"10.1080\/01431160600589179","volume":"27","author":"H Xu","year":"2006","unstructured":"Xu, H. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. Int. J. Remote Sens. 27, 3025\u20133033 (2006).","journal-title":"Int. J. Remote Sens."},{"key":"34436_CR24","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, LNCS, 234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28 (Springer, 2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"34436_CR25","unstructured":"Sun, K. et\u00a0al. High-resolution representations for labeling pixels and regions. CoRRarXiv:1904.04514 (2019)."},{"key":"34436_CR26","unstructured":"ML4Floods. http:\/\/trillium.tech\/ml4floods (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR27","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1038\/nature20584","volume":"540","author":"J-F Pekel","year":"2016","unstructured":"Pekel, J.-F., Cottam, A., Gorelick, N. & Belward, A. S. High-resolution mapping of global surface water and its long-term changes. Nature 540, 418\u2013422. https:\/\/doi.org\/10.1038\/nature20584 (2016).","journal-title":"Nature"},{"key":"34436_CR28","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1038\/s41586-021-03695-w","volume":"596","author":"B Tellman","year":"2021","unstructured":"Tellman, B. et al. Satellite imaging reveals increased proportion of population exposed to floods. Nature 596, 80\u201386. https:\/\/doi.org\/10.1038\/s41586-021-03695-w (2021).","journal-title":"Nature"},{"key":"34436_CR29","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D. & Wang, J. Deep high-resolution representation learning for human pose estimation. In CVPR (2019).","DOI":"10.1109\/CVPR.2019.00584"},{"key":"34436_CR30","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X. & Wang, J. Object-contextual representations for semantic segmentation. In ECCV (2020).","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"34436_CR31","unstructured":"ML4Floods Code Repository. https:\/\/github.com\/spaceml-org\/ml4floods (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR32","doi-asserted-by":"publisher","unstructured":"Torralba, A. & Efros, A. A. Unbiased look at dataset bias. In CVPR 2011 1521\u20131528. https:\/\/doi.org\/10.1109\/CVPR.2011.5995347 (2011).","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"34436_CR33","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MGRS.2016.2548504","volume":"4","author":"D Tuia","year":"2016","unstructured":"Tuia, D., Persello, C. & Bruzzone, L. Domain adaptation for the classification of remote sensing data: An overview of recent advances. IEEE Geosci. Remote Sens. Mag. 4, 41\u201357. https:\/\/doi.org\/10.1109\/MGRS.2016.2548504 (2016).","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"34436_CR34","volume-title":"Digital Image Processing","author":"RC Gonzalez","year":"2006","unstructured":"Gonzalez, R. C. & Woods, R. E. Digital Image Processing 3rd edn. (Prentice-Hall Inc, 2006).","edition":"3"},{"key":"34436_CR35","doi-asserted-by":"publisher","first-page":"2205","DOI":"10.3390\/rs12142205","volume":"12","author":"G Giuffrida","year":"2020","unstructured":"Giuffrida, G. et al. CloudScout: A deep neural network for on-board cloud detection on hyperspectral images. Remote Sens. 12, 2205. https:\/\/doi.org\/10.3390\/rs12142205 (2020).","journal-title":"Remote Sens."},{"key":"34436_CR36","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1109\/JSTARS.2020.3031741","volume":"14","author":"G Mateo-Garc\u00eda","year":"2020","unstructured":"Mateo-Garc\u00eda, G., Laparra, V., L\u00f3pez-Puigdollers, D. & G\u00f3mez-Chova, L. Cross-sensor adversarial domain adaptation of Landsat-8 and Proba-V images for cloud detection. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 14, 747\u2013761. https:\/\/doi.org\/10.1109\/JSTARS.2020.3031741 (2020).","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"34436_CR37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2980417","author":"O Tasar","year":"2020","unstructured":"Tasar, O., Happy, S. L., Tarabalka, Y. & Alliez, P. ColorMapGAN: Unsupervised domain adaptation for semantic segmentation using color mapping generative adversarial networks. IEEE Trans. Geosci. Remote Sens.https:\/\/doi.org\/10.1109\/TGRS.2020.2980417 (2020).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"34436_CR38","unstructured":"The OpenVINO Toolkit. https:\/\/docs.openvinotoolkit.org\/latest\/index.html (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR39","unstructured":"The Intel Neural Compute Stick 2. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/neural-compute-stick\/overview.html (2022). [Online]. Accessed 31 May 2022."},{"key":"34436_CR40","doi-asserted-by":"publisher","unstructured":"GDAL\/OGR Contributors. GDAL\/OGR Geospatial Data Abstraction software Library. Open Source Geospatial Foundation. https:\/\/doi.org\/10.5281\/zenodo.5884351 (2022).","DOI":"10.5281\/zenodo.5884351"},{"key":"34436_CR41","unstructured":"Huang, B., Reichman, D., Collins, L.\u00a0M., Bradbury, K. & Malof, J.\u00a0M. Tiling and Stitching Segmentation Output for Remote Sensing: Basic Challenges and Recommendations. arXiv:1805.12219 [cs] (2019)."},{"key":"34436_CR42","unstructured":"Tkachenko, M., Malyuk, M., Shevchenko, N., Holmanyuk, A. & Liubimov, N. Label Studio: Data labeling software (2020\u20132021). Open source software available from https:\/\/github.com\/heartexlabs\/label-studio."},{"key":"34436_CR43","doi-asserted-by":"publisher","first-page":"992","DOI":"10.3390\/rs13050992","volume":"13","author":"D L\u00f3pez-Puigdollers","year":"2021","unstructured":"L\u00f3pez-Puigdollers, D., Mateo-Garc\u00eda, G. & G\u00f3mez-Chova, L. Benchmarking deep learning models for cloud detection in Landsat-8 and Sentinel-2 images. Remote Sens. 13, 992. https:\/\/doi.org\/10.3390\/rs13050992 (2021).","journal-title":"Remote Sens."},{"key":"34436_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.isprsjprs.2019.11.024","volume":"160","author":"G Mateo-Garc\u00eda","year":"2020","unstructured":"Mateo-Garc\u00eda, G., Laparra, V., L\u00f3pez-Puigdollers, D. & G\u00f3mez-Chova, L. Transferring deep learning models for cloud detection between Landsat-8 and Proba-V. ISPRS J. Photogramm. Remote Sens. 160, 1\u201317. https:\/\/doi.org\/10.1016\/j.isprsjprs.2019.11.024 (2020).","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"34436_CR45","doi-asserted-by":"publisher","DOI":"10.3390\/rs13193981","author":"M Ziaja","year":"2021","unstructured":"Ziaja, M. et al. Benchmarking deep learning for on-board space applications. Remote Sens.https:\/\/doi.org\/10.3390\/rs13193981 (2021).","journal-title":"Remote Sens."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-34436-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-34436-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-34436-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T06:15:56Z","timestamp":1687846556000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-34436-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,27]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["34436"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-34436-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-1941984\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,27]]},"assertion":[{"value":"8 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors are unaware of any competing interest that may impact this work. The corresponding author is responsible for submitting a competing interests statement on behalf of all authors of the paper. This statement must be included in the submitted article file.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10391"}}