{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T20:01:12Z","timestamp":1774641672689,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,8]],"date-time":"2021-06-08T00:00:00Z","timestamp":1623110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>New, accurate and generalizable methods are required to transform the ever-increasing amount of raw hyperspectral data into actionable knowledge for applications such as environmental monitoring and precision agriculture. Here, we apply advances in generative deep learning models to produce realistic synthetic hyperspectral vegetation data, whilst maintaining class relationships. Specifically, a Generative Adversarial Network (GAN) is trained using the Cram\u00e9r distance on two vegetation hyperspectral datasets, demonstrating the ability to approximate the distribution of the training samples. Evaluation of the synthetic spectra shows that they respect many of the statistical properties of the real spectra, conforming well to the sampled distributions of all real classes. Creation of an augmented dataset consisting of synthetic and original samples was used to train multiple classifiers, with increases in classification accuracy seen under almost all circumstances. Both datasets showed improvements in classification accuracy ranging from a modest 0.16% for the Indian Pines set and a substantial increase of 7.0% for the New Zealand vegetation. Selection of synthetic samples from sparse or outlying regions of the feature space of real spectral classes demonstrated increased discriminatory power over those from more central portions of the distributions.<\/jats:p>","DOI":"10.3390\/rs13122243","type":"journal-article","created":{"date-parts":[[2021,6,8]],"date-time":"2021-06-08T21:16:58Z","timestamp":1623187018000},"page":"2243","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Generative Adversarial Network Synthesis of Hyperspectral Vegetation Data"],"prefix":"10.3390","volume":"13","author":[{"given":"Andrew","family":"Hennessy","sequence":"first","affiliation":[{"name":"School of Biological Sciences, The University of Adelaide, Adelaide 5000, Australia"}]},{"given":"Kenneth","family":"Clarke","sequence":"additional","affiliation":[{"name":"School of Biological Sciences, The University of Adelaide, Adelaide 5000, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1203-6281","authenticated-orcid":false,"given":"Megan","family":"Lewis","sequence":"additional","affiliation":[{"name":"School of Biological Sciences, The University of Adelaide, Adelaide 5000, Australia"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Hennessy, A., Clarke, K., and Lewis, M. (2020). Hyperspectral Classification of Plants: A Review of Waveband Selection Generalisability. Remote Sens., 12.","DOI":"10.3390\/rs12010113"},{"key":"ref_2","unstructured":"JPL\/NASA (2021, May 28). ECOSTRESS, Available online: https:\/\/ecostress.jpl.nasa.gov\/."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5789","DOI":"10.1109\/JSTARS.2020.3025117","article-title":"The SPECCHIO Spectral Information System","volume":"13","author":"Hueni","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_4","unstructured":"Taylor, L., and Nitschke, G. (2020, November 12). Improving Deep Learning Using Generic Data Augmentation. Available online: https:\/\/arxiv.org\/abs\/1708.06020."},{"key":"ref_5","unstructured":"Wang, K. (2020, December 08). Synthetic DATA Generation and Adaptation for Object Detection in Smart Vending Machines. Available online: https:\/\/arxiv.org\/abs\/1904.12294."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"4818","DOI":"10.1109\/JSTARS.2017.2758964","article-title":"DIRSIG5: Next-Generation Remote Sensing Data and Image Simulation Framework","volume":"10","author":"Goodenough","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Bissoto, A., Perez, F.V.M., Valle, E., and Avila, S. (2018). Skin Lesion Synthesis with Generative Adversarial Networks. Transactions on Petri Nets and Other Models of Concurrency XV, Springer Science and Business Media LLC.","DOI":"10.1007\/978-3-030-01201-4_32"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, G., Kang, W., Wu, Q., Wang, Z., and Gao, J. (2018, January 10\u201313). Generative Adversarial Network (GAN) Based Data Augmentation for Palmprint Recognition. Proceedings of the 2018 Digital Image Computing: Techniques and Applications (DICTA), Canberra, Australia.","DOI":"10.1109\/DICTA.2018.8615782"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wen, Q., Sun, L., Yang, F., Song, X., Gao, J., Wang, X., and Xu, H. (2020, November 09). Time Series Data Augmentation for Deep Learning: A Survey. Available online: https:\/\/arxiv.org\/abs\/2002.12478.","DOI":"10.24963\/ijcai.2021\/631"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"S56","DOI":"10.1016\/j.rse.2008.01.026","article-title":"PROSPECT+SAIL models: A review of use for vegetation characterization","volume":"113","author":"Jacquemoud","year":"2009","journal-title":"Remote Sens. Environ."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Slavkovikj, V., Verstockt, S., De Neve, W., Van Hoecke, S., and Van de Walle, R. (2015, January 26\u201330). Hyperspectral Image Classification with Convolutional Neural Networks. Proceedings of the 23rd ACM international conference on Multimedia, Brisbane, Australia.","DOI":"10.1145\/2733373.2806306"},{"key":"ref_12","first-page":"1099609","article-title":"On data augmentation for segmenting hyperspectral images","volume":"Volume 10996","author":"Nalepa","year":"2019","journal-title":"Real-Time Image Processing and Deep Learning 2019"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"144292","DOI":"10.1109\/ACCESS.2019.2934928","article-title":"Biosignal Generation and Latent Variable Analysis with Recurrent Generative Adversarial Networks","volume":"7","author":"Harada","year":"2019","journal-title":"IEEE Access"},{"key":"ref_14","unstructured":"Donahue, C., McAuley, J., and Puckette, M. (2020, February 01). Adversarial Audio Synthesis. Available online: https:\/\/arxiv.org\/abs\/1802.04208."},{"key":"ref_15","unstructured":"Esteban, C., Hyland, S.L., and R\u00e4tsch, G. (2019, August 12). Real-Valued (Medical) Time Series Generation with Recurrent Conditional Gans. Available online: https:\/\/arxiv.org\/abs\/1706.02633."},{"key":"ref_16","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8\u201313). Generative adversarial nets. Proceedings of the 27th International Conference on Neural Information Processing Systems\u2014Volume 2 (NIPS\u201914), Cambridge, MA, USA."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Audebert, N., Le Saux, B., and Lefevre, S. (2018, January 22\u201327). Generative Adversarial Networks for Realistic Synthesis of Hyperspectral Samples. Proceedings of the IGARSS 2018\u20142018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.","DOI":"10.1109\/IGARSS.2018.8518321"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1109\/LGRS.2017.2780890","article-title":"Semisupervised Hyperspectral Image Classification Based on Generative Adversarial Networks","volume":"15","author":"Zhan","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Xu, Y., Du, B., and Zhang, L. (2018, January 22\u201327). Can We Generate Good Samples for Hyperspectral Classification?\u2014A Generative Adversarial Network Based Method. Proceedings of the IGARSS 2018\u20142018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.","DOI":"10.1109\/IGARSS.2018.8519295"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"5329","DOI":"10.1109\/TGRS.2019.2899057","article-title":"Classification of Hyperspectral Images Based on Multiclass Spatial\u2013Spectral Generative Adversarial Networks","volume":"57","author":"Feng","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5046","DOI":"10.1109\/TGRS.2018.2805286","article-title":"Generative Adversarial Networks for Hyperspectral Image Classification","volume":"56","author":"Zhu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_22","unstructured":"LeCun, Y. (2021, January 15). What Are Some Recent and Potentially Upcoming Breakthroughs in Deep Learning. Available online: https:\/\/www.quora.com\/What-are-some-recent-and-potentially-upcoming-breakthroughs-in-deep-learning."},{"key":"ref_23","unstructured":"Gui, J., Sun, Z., Wen, Y., Tao, D., and Ye, J. (2021, January 20). A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications. Available online: https:\/\/arxiv.org\/abs\/2001.06937."},{"key":"ref_24","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2019, December 08). Wasserstein GAN. Available online: https:\/\/arxiv.org\/abs\/1701.07875."},{"key":"ref_25","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., and Courville, A. (2017). Improved training of wasserstein gans. arXiv."},{"key":"ref_26","unstructured":"Bellemare, M., Danihelka, I., Dabney, W., Mohamed, S., Lakshminarayanan, B., Hoyer, S., and Munos, R. (2020, March 12). The Cramer Distance as a Solution to Biased Wasserstein Gradients. Available online: https:\/\/arxiv.org\/abs\/1705.10743."},{"key":"ref_27","unstructured":"Song, J. (2019, December 28). Cramer-Gan. Available online: https:\/\/github.com\/jiamings\/cramer-gan."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.isprsjprs.2013.01.011","article-title":"Assessing reference dataset representativeness through confidence metrics based on information density","volume":"78","author":"Mountrakis","year":"2013","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_29","unstructured":"Baumgardner, M.F., Biehl, L.L., and Landgrebe, D.A. (2018, July 06). 220 Band AVIRIS Hyperspectral Image Data Set: June 12, 1992 Indian Pine Test Site 3. Available online: https:\/\/purr.purdue.edu\/publications\/1947\/1."},{"key":"ref_30","unstructured":"McInnes, L., Healy, J., and Melville, J. (2019, July 19). UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. Available online: https:\/\/arxiv.org\/abs\/1802.03426."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/12\/2243\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:12:11Z","timestamp":1760163131000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/12\/2243"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,8]]},"references-count":30,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["rs13122243"],"URL":"https:\/\/doi.org\/10.3390\/rs13122243","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,8]]}}}