RaVÆn: unsupervised detection of changes in extreme events using on-board ML satellites

  • Bello, OM & Aina, YA Satellite remote sensing as a tool for disaster management and sustainable development: towards a synergistic approach. Process. Soc. Sci behavior. 120365–373 (2014).

    Article

    Google Scholar

  • Huyck, C., Verrucci, E. & Bevington, J. Remote sensing for disaster response: A rapid image-based perspective. In Seismic hazard, risks and disasters 1–24 (Elsevier, 2014).

    Google Scholar

  • Mas, J.-F. Monitoring land cover changes: a comparison of change detection techniques. Int. J. Telesens. 20139-152 (1999).

    Article

    Google Scholar

  • Coppin, P., Jonckheere, I., Nackaerts, K., Muys, B. & Lambin, E. Review article Numerical change detection methods in ecosystem monitoring: A review. Int. J. Telesens. 251565-1596 (2004).

    Article

    Google Scholar

  • Yang, XX Urban remote sensing: monitoring, synthesis and modeling in urban areas (Wiley, 2021).

    Book

    Google Scholar

  • Fritz, S. et al. A comparison of global agricultural monitoring systems and current gaps. Agric. System 168258-272 (2019).

    Article

    Google Scholar

  • Kothari, V., Liberis, E. & Lane, ND The Final Frontier: Deep Learning in Space. In Proceedings of the 21st International Workshop on Mobile Computing Systems and Applications45–49 (2020).

  • Selva, D. & Krejci, D. A survey and assessment of the capabilities of cubesats for Earth observation. Acta Astron. 7450–68 (2012).

    Article

    Google Scholar

  • Boucheret, M.-L., Mortensen, I. & Favaro, H. Fast convolution filter banks for satellite payloads with on-board processing. IEEE J. Select. Common areas. 17238-248 (1999).

    Article

    Google Scholar

  • Velazco, R., Cheynet, P., Muller, J., Ecoffet, R. & Buchner, S. Robustness of artificial neural network for on-board satellite image processing: results from disturbance simulations and ground tests . IEEE Trans. Nucl. Science. 442337–2344 (1997).

    ADS
    Article

    Google Scholar

  • Griggin, M., Burke, H., Mandl, D. & Miller, J. Cloud cover detection algorithm for EO-1 Hyperion imagery. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2003), flight. 1, 86–89. https://doi.org/10.1109/IGARSS.2003.1293687 (2003).

  • Giuffrida, G. et al. CloudScout: a deep neural network for embedded cloud detection on hyperspectral images. Telesens. 122205 (2020).

    ADS
    Article

    Google Scholar

  • Mateo Garcia, G. et al. Towards a global mapping of floods on board low cost satellites with machine learning. Science. representing 117249 (2021).

    CASE
    Article

    Google Scholar

  • Hintz, R. et al. Eo-alert: on-board satellite processing based on machine learning for nowcasting very low latency convective storms. In EMCWF-ESA Workshop (2020).

  • Kingma, DP & Welling, M. Self-encoding Variational Bayes (2013). arXiv:1312.6114.

  • Drush, M. et al. Sentinel-2: ESA’s high-resolution optical mission for gmes operational services. Remote Sensing Approx. 12025–36 (2012).

    ADS
    Article

    Google Scholar

  • Angerhausen, D., Bickel, VT, and Adam, L. Unsupervised distribution learning for lunar surface technosignature detection. Earth Sp. Sci. Open arch. 201 (2020).

    Google Scholar

  • Merrill, N. & Eskandarian, A. Modified autoencoder training and scoring for robust unsupervised anomaly detection in deep learning. IEEE Access (2020).

  • Reed, IS & Yu, X. Adaptive multiband cfar detection of an optical pattern with an unknown spectral distribution. IEEE Trans. Acoustic. Voice signal process. 381760–1770 (1990).

    ADS
    Article

    Google Scholar

  • Caye Daudt, R., Le Saux, B. & Boulch, A. Fully convolutional Siamese networks for change detection. 2018 25th IEEE International Conference on Image Processing (ICIP) (2018).

  • Ruzicka, V., D’Aronco, S., Wegner, JD & Schindler, K. Deep active learning in remote sensing for efficient data change detection. In Proceedings of MACLEAN: MACHine Learning for EARth ObservatioN Workshop (ECML/PKDD 2020), flight. 2766 (2020).

  • Çelik, T. Unsupervised change detection in satellite images using principal component analysis and (k)-means grouping. IEEE Geosci. Remote sensing Lett. 2020 (2009).

    Google Scholar

  • Çelik, T. & Curtis, CV Selective detection of resolution changes in satellite images. In ICASSP (2010).

  • Cheng, Y., Li, H., Çelik, T. & Zhang, F. Improved Frft-based algorithm for unsupervised change detection in SAR images via PCA and k-means clustering. In IGARSS (2013).

  • Radke, RJ, Andra, S., Al-Kofahi, O. & Roysam, B. Image Change Detection Algorithms: A Systematic Investigation. IEEE Trans. Image process. 14294–307 (2005).

    ADS
    MathSciNet
    Article

    Google Scholar

  • Gong, P. Change detection using principal component analysis and fuzzy set theory. Box. J. Telesens. 1922–29 (1993).

    ADS
    Article

    Google Scholar

  • de Jong, KL & Bosman, AS Unsupervised change detection in satellite images using convolutional neural networks. In IJCNN (IEEE, 2019).

  • Kerner, HR et al. Towards generalized detection of changes on planetary surfaces with convolutional autoencoders and transfer learning. IEEE J. Select. High. Appl. Earth observation. Telesens. 123900–3918 (2019).

    ADS
    Article

    Google Scholar

  • Giuffrida, G. et al. The (phi)-mission sat-1: The first on-board deep neural network demonstrator for Earth observation by satellite. IEEE Trans. Geosci. Telesens. 601–14 (2021).

    Article

    Google Scholar

  • Wagstaff, KL et al. Enable on-board detection of events of scientific interest for the Europa Clipper spacecraft. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining2191-2201 (2019).

  • Cogliati, S. et al. The PRISMA imaging spectroscopy mission: Presentation and first performance analysis. Remote Sensing Approx. 262112499. https://doi.org/10.1016/j.rse.2021.112499 (2021).

    ADS
    Article

    Google Scholar

  • Copernicus Emergency Management System. Accessed 4.11.2021.

  • s2cloudless: Sentinel hub cloud detector for Sentinel-2 imagery. Accessed 4.11.2021.

  • Brown, CF et al. Dynamic world, global mapping of land cover at 10 m in near real time. Science. Data 91–17 (2022).

    Article

    Google Scholar

  • Saha, S. & Zhu, XX Unsupervised patch-level planetary change detection. IEEE Geosci. Remote sensing Lett. 191–5 (2021).

    Google Scholar

  • Ballé, J., Laparra, V. & Simoncelli, EP End-to-end optimized image compression. arXiv:1611.01704 (2016).

  • BLUE BOOK. Lossless and Near Lossless Low Complexity Multispectral and Hyperspectral Image Compression (2019).

  • Schelkens, P. et al. The jpeg 2000 family of standards. Wavelet Applications in Industrial Processing VI Flight. 7248 724802 (SPIE, 2009).

    Chapter

    Google Scholar

  • Ruzicka, V. et al. Unsupervised detection of extreme event changes using ML On-board. In Workshop on Artificial Intelligence for Humanitarian Aid and Disaster Response (NeurIPS 2021), Vancouver, Canada (2021). arXiv: 2111.02995.

  • Odena, A., Dumoulin, V. & Olah, C. Deconvolution and checkerboard artifacts. Distill 1e3 (2016).

    Article

    Google Scholar

  • Wang, S.-Y., Wang, O., Zhang, R., Owens, A. & Efros, AA The Cnn-generated images are surprisingly easy to spot…yet. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition8695–8704 (2020).

  • Rapuano, E. et al. An fpga-based hardware accelerator for cnns inference onboard satellites: benchmarking with a myriad 2-based solution for the cloudscout case study. Telesens. 131518 (2021).

    ADS
    Article

    Google Scholar

  • Mikolov, T., Chen, K., Corrado, G. & Dean, J. Efficient estimation of word representations in vector space. arXiv:1301.3781 (2013).

  • Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A Simple Framework for Contrastive Learning of Visual Representations. In International Conference on Machine Learning1597-1607 (PMLR, 2020).

  • McInnes, L., Healy, J. & Melville, J. Umap: Approximation and Uniform Variety Projection for Dimension Reduction. arXiv:1802.03426 (2018).

  • Saha, S., Bovolo, F. & Bruzzone, L. Change detection in image time series using unsupervised lstm. IEEE Geosci. Remote sensing Lett. 2020 (2020).

    Google Scholar

  • Manas, O., Lacoste, A., Giró-i Nieto, X., Vazquez, D. & Rodriguez, P. Seasonal contrast: unsupervised pre-training from uncurated remote sensing data. In Proceedings of the IEEE/CVF International Conference on Computer Vision9414–9423 (2021).

  • Comments are closed.