{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T06:25:50Z","timestamp":1768803950111,"version":"3.49.0"},"reference-count":49,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T00:00:00Z","timestamp":1656288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41971379"],"award-info":[{"award-number":["41971379"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Satellite hyperspectral remote sensing has gradually become an important means of Earth observation, but the existence of various types of noise seriously limits the application value of satellite hyperspectral images. With the continuous development of deep learning technology, breakthroughs have been made in improving hyperspectral image denoising algorithms based on supervised learning; however, these methods usually require a large number of clean\/noisy training pairs, a target that is difficult to meet for real satellite hyperspectral imagery. In this paper, we propose a self-supervised learning-based algorithm, 3S-HSID, for denoising real satellite hyperspectral images without requiring external data support. The 3S-HSID framework can perform robust denoising of a single satellite hyperspectral image in all bands simultaneously. It first conducts a Bernoulli sampling of the input data, then uses the Bernoulli sampling results to construct the training pairs. Furthermore, the global spectral consistency and minimum local variance are used in the loss function to train the network. We use the training model to predict different Bernoulli sampling results, and the average of multiple predicted values is used as the denoising result. To prevent overfitting, we adopt a dropout strategy during training and testing. The results of denoising experiments on the simulated hyperspectral data show that the denoising performance of 3S-HSID is better than most state-of-the-art algorithms, especially in terms of maintaining the spectral characteristics of hyperspectral images. The denoising results for different types of real satellite hyperspectral data also demonstrate the reliability of the proposed method. The 3S-HSID framework provides a new technical means for real satellite hyperspectral image preprocessing.<\/jats:p>","DOI":"10.3390\/rs14133083","type":"journal-article","created":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:07:02Z","timestamp":1656374822000},"page":"3083","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Self-Supervised Denoising for Real Satellite Hyperspectral Imagery"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4773-0695","authenticated-orcid":false,"given":"Jinchun","family":"Qin","sequence":"first","affiliation":[{"name":"Department of Civil Engineering, Tsinghua University, Beijing 100084, China"},{"name":"State Key Laboratory of Geo-Information Engineering, Xi\u2019an 710054, China"}]},{"given":"Hongrui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, Tsinghua University, Beijing 100084, China"}]},{"given":"Bing","family":"Liu","sequence":"additional","affiliation":[{"name":"PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,6,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Transon, J., D\u2019Andrimont, R., Maugnard, A., and Defourny, P. (2018). Survey of Hyperspectral Earth Observation Applications from Space in the Sentinel-2 Context. Remote Sens., 10.","DOI":"10.3390\/rs10020157"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"106188","DOI":"10.1016\/j.compag.2021.106188","article-title":"Deep learning-based crop mapping in the cloudy season using one-shot hyperspectral satellite imagery","volume":"186","author":"Meng","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1949","DOI":"10.1080\/10106049.2020.1805031","article-title":"New spectral indices for detection of urban built-up surfaces and its sub-classes in AVIRIS-NG hyperspectral imagery","volume":"37","author":"Pandey","year":"2020","journal-title":"Geocarto Int."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Niroumand-Jadidi, M., Bovolo, F., and Bruzzone, L. (2020). Water Quality Retrieval from PRISMA Hyperspectral Images: First Experience in a Turbid Lake and Comparison with Sentinel-2. Remote Sens., 12.","DOI":"10.3390\/rs12233984"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Xie, Y., Sha, Z., and Mesev, V. (2018). Remote Sensing of Sustainable Ecosystems. J. Sens., 2018.","DOI":"10.1155\/2018\/9683415"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.1109\/TCYB.2017.2677944","article-title":"Denoising Hyperspectral Image with Non-i.i.d. Noise Structure","volume":"48","author":"Chen","year":"2018","journal-title":"IEEE Trans. Cybern."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Nalepa, J., Myller, M., Cwiek, M., Zak, L., Lakota, T., Tulczyjew, L., and Kawulok, M. (2021). Towards On-Board Hyperspectral Satellite Image Segmentation: Understanding Robustness of Deep Learning through Simulating Acquisition Conditions. Remote Sens., 13.","DOI":"10.3390\/rs13081532"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/TGRS.2015.2452812","article-title":"Total-Variation-Regularized Low-Rank Matrix Factorization for Hyperspectral Image Restoration","volume":"54","author":"He","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","article-title":"Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering","volume":"16","author":"Dabov","year":"2007","journal-title":"IEEE Trans. Image Processing"},{"key":"ref_10","unstructured":"Buades, A., Coll, B., and Morel, J. (2005, January 20\u201325). A non-local algorithm for image denoising. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), San Diego, CA, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Gu, S., Zhang, L., Zuo, W., and Feng, X. (2014, January 23\u201328). Weighted Nuclear Norm Minimization with Application to Image Denoising. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.366"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1016\/j.neucom.2018.05.115","article-title":"Deep convolutional networks with residual learning for accurate spectral-spatial denoising","volume":"312","author":"Xie","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4729","DOI":"10.1109\/TGRS.2013.2284280","article-title":"Hyperspectral Image Restoration Using Low-Rank Matrix Recovery","volume":"52","author":"Zhang","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2335","DOI":"10.1109\/LGRS.2017.2764059","article-title":"Automatic Hyperspectral Image Restoration Using Sparse and Low-Rank Modeling","volume":"14","author":"Rasti","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1940","DOI":"10.1109\/TGRS.2017.2771155","article-title":"Joint Spatial and Spectral Low-Rank Regularization for Hyperspectral Image Denoising","volume":"56","author":"Xue","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5174","DOI":"10.1109\/TGRS.2019.2897316","article-title":"Nonlocal Low-Rank Regularized Tensor Decomposition for Hyperspectral Image Denoising","volume":"57","author":"Xue","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3660","DOI":"10.1109\/TGRS.2012.2185054","article-title":"Hyperspectral Image Denoising Employing a Spectral\u2013Spatial Adaptive Total Variation Model","volume":"50","author":"Yuan","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_18","first-page":"442","article-title":"Hyperspectral Image Denoising Using Spatio-Spectral Total Variation","volume":"13","author":"Aggarwal","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5425","DOI":"10.1109\/TGRS.2016.2564639","article-title":"Noise Removal From Hyperspectral Image With Joint Spectral\u2013Spatial Distributed Sparse Representation","volume":"54","author":"Li","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1109\/TGRS.2015.2457614","article-title":"Spectral\u2013Spatial Adaptive Sparse Representation for Hyperspectral Image Denoising","volume":"54","author":"Lu","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","first-page":"1","article-title":"Robust principal component analysis?","volume":"58","author":"Li","year":"2011","journal-title":"J. ACM"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1137\/14098154X","article-title":"Structure Tensor Total Variation","volume":"8","author":"Lefkimmiatis","year":"2015","journal-title":"SIAM J. Imaging Sci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"84156","DOI":"10.1109\/ACCESS.2021.3087916","article-title":"Total Variation Regularized Low-Rank Model With Directional Information for Hyperspectral Image Restoration","volume":"9","author":"Fei","year":"2021","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1963","DOI":"10.1109\/LGRS.2017.2743738","article-title":"Hyperspectral Imagery Denoising by Deep Learning With Trainable Nonlinearity Function","volume":"14","author":"Xie","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","article-title":"Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Processing"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.neunet.2018.08.021","article-title":"Trainable spectral difference learning with spatial starting for hyperspectral image denoising","volume":"108","author":"Xie","year":"2018","journal-title":"Neural Netw."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1109\/TGRS.2018.2865197","article-title":"Hyperspectral Image Denoising Employing a Spatial\u2013Spectral Deep Residual Convolutional Neural Network","volume":"57","author":"Yuan","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2516","DOI":"10.1109\/TGRS.2019.2952062","article-title":"A Single Model CNN for Hyperspectral Image Denoising","volume":"58","author":"Maffei","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liu, S., Feng, J., and Tian, Z. (2021). Variational Low-Rank Matrix Factorization with Multi-Patch Collaborative Learning for Hyperspectral Imagery Mixed Denoising. Remote Sens., 13.","DOI":"10.3390\/rs13061101"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhuang, L., Ng, M.K., and Fu, X. (2021). Hyperspectral Image Mixed Noise Removal Using Subspace Representation and Deep CNN Image Prior. Remote Sens., 13.","DOI":"10.3390\/rs13204098"},{"key":"ref_31","first-page":"1","article-title":"Adaptive Hyperspectral Mixed Noise Removal","volume":"60","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","first-page":"1","article-title":"MAC-Net: Model-Aided Nonlocal Neural Network for Hyperspectral Image Denoising","volume":"60","author":"Xiong","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kan, Z., Li, S., and Zhang, Y. (2021, January 2\u20134). Attention-Based Octave Dense Network for Hyperspectral Image Denoising. Proceedings of the 2021 IEEE 4th International Conference on Big Data and Artificial Intelligence (BDAI), Qingdao, China.","DOI":"10.1109\/BDAI52447.2021.9515262"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"10348","DOI":"10.1109\/TGRS.2020.3045273","article-title":"Hyperspectral Image Denoising Using a 3-D Attention Denoising Network","volume":"59","author":"Shi","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_35","first-page":"1","article-title":"SSCAN: A Spatial\u2013Spectral Cross Attention Network for Hyperspectral Image Denoising","volume":"19","author":"Wang","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_36","first-page":"1","article-title":"Partial-DNet: A Novel Blind Denoising Model With Noise Intensity Estimation for HSI","volume":"60","author":"Yuan","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lempitsky, V., Vedaldi, A., and Ulyanov, D. (2018, January 18\u201323). Deep Image Prior. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00984"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Sidorov, O., and Hardeberg, J.Y. (2019, January 27\u201328). Deep Hyperspectral Prior: Single-Image Denoising, Inpainting, Super-Resolution. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Korea.","DOI":"10.1109\/ICCVW.2019.00477"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"9435","DOI":"10.1109\/JSTARS.2021.3111404","article-title":"Hyperspectral Mixed Noise Removal via Spatial-Spectral Constrained Unsupervised Deep Image Prior","volume":"14","author":"Luo","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Imamura, R., Itasaka, T., and Okuda, M. (2019, January 27\u201328). Zero-Shot Hyperspectral Image Denoising with Separable Image Prior. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Korea.","DOI":"10.1109\/ICCVW.2019.00178"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Fu, G., Xiong, F., Tao, S., Lu, J., Zhou, J., and Qian, Y. (2021, January 11\u201316). Learning a Model-Based Deep Hyperspectral Denoiser from a Single Noisy Hyperspectral Image. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.","DOI":"10.1109\/IGARSS47720.2021.9553257"},{"key":"ref_42","first-page":"1","article-title":"A Self-Supervised Denoising Network for Satellite-Airborne-Ground Hyperspectral Imagery","volume":"60","author":"Wang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_43","first-page":"1","article-title":"Hyperspectral Image Restoration With Self-Supervised Learning: A Two-Stage Training Approach","volume":"60","author":"Qian","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Quan, Y., Chen, M., Pang, T., and Ji, H. (2020, January 13\u201319). Self2Self with Dropout: Learning Self-Supervised Denoising from Single Image. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00196"},{"key":"ref_45","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_46","unstructured":"Gal, Y., and Ghahramani, Z. (2016). Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Maggioni, M., and Foi, A. (2012). Nonlocal Transform-Domain Denoising of Volumetric Data with Groupwise Adaptive Variance Estimation, SPIE.","DOI":"10.1117\/12.912109"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1109\/JSTARS.2020.2979801","article-title":"Hyperspectral Mixed Noise Removal By l-Norm-Based Subspace Representation","volume":"13","author":"Zhuang","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"3369","DOI":"10.1109\/TGRS.2020.3008844","article-title":"Hyperspectral Image Denoising Using SURE-Based Unsupervised Convolutional Neural Networks","volume":"59","author":"Nguyen","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/13\/3083\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:39:01Z","timestamp":1760139541000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/13\/3083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,27]]},"references-count":49,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["rs14133083"],"URL":"https:\/\/doi.org\/10.3390\/rs14133083","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,27]]}}}