{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T21:54:45Z","timestamp":1772142885419,"version":"3.50.1"},"reference-count":55,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T00:00:00Z","timestamp":1623196800000},"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>Land use (LU) and land cover (LC) are two complementary pieces of cartographic information used for urban planning and environmental monitoring. In the context of New Caledonia, a biodiversity hotspot, the availability of up-to-date LULC maps is essential to monitor the impact of extreme events such as cyclones and human activities on the environment. With the democratization of satellite data and the development of high-performance deep learning techniques, it is possible to create these data automatically. This work aims at determining the best current deep learning configuration (pixel-wise vs. semantic labelling architectures, data augmentation, image prepossessing, \u2026), to perform LULC mapping in a complex, subtropical environment. For this purpose, a specific data set based on SPOT6 satellite data was created and made available for the scientific community as an LULC benchmark in a tropical, complex environment using five representative areas of New Caledonia labelled by a human operator: four used as training sets, and the fifth as a test set. Several architectures were trained and the resulting classification was compared with a state-of-the-art machine learning technique: XGboost. We also assessed the relevance of popular neo-channels derived from the raw observations in the context of deep learning. The deep learning approach showed comparable results to XGboost for LC detection and over-performed it on the LU detection task (61.45% vs. 51.56% of overall accuracy). Finally, adding LC classification output of the dedicated deep learning architecture to the raw channels input significantly improved the overall accuracy of the deep learning LU classification task (63.61% of overall accuracy). All the data used in this study are available on line for the remote sensing community and for assessing other LULC detection techniques.<\/jats:p>","DOI":"10.3390\/rs13122257","type":"journal-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T14:16:04Z","timestamp":1623248164000},"page":"2257","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["Assessment of Deep Learning Techniques for Land Use Land Cover Classification in Southern New Caledonia"],"prefix":"10.3390","volume":"13","author":[{"given":"Guillaume","family":"Rousset","sequence":"first","affiliation":[{"name":"ESPACE-DEV, Univ New Caledonia, Univ Montpellier, IRD, Univ Antilles, Univ Guyane, Univ R\u00e9union, 98800 New Caledonia, France"},{"name":"ISEA, Univ New Caledonia, 98800 New Caledonia, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5581-7323","authenticated-orcid":false,"given":"Marc","family":"Despinoy","sequence":"additional","affiliation":[{"name":"ESPACE-DEV, Univ New Caledonia, Univ Montpellier, IRD, Univ Antilles, Univ Guyane, Univ R\u00e9union, 98800 New Caledonia, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3172-9246","authenticated-orcid":false,"given":"Konrad","family":"Schindler","sequence":"additional","affiliation":[{"name":"Photogrammetry and Remote Sensing, ETH Zurich, 8093 Zurich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4146-3784","authenticated-orcid":false,"given":"Morgan","family":"Mangeas","sequence":"additional","affiliation":[{"name":"Institut de Recherche pour le D\u00e9veloppement, UMR 9220 ENTROPIE (Institut de Recherche pour le D\u00e9veloppement, Universit\u00e9 de la R\u00e9union, IFREMER, Universit\u00e9 de la Nouvelle-Cal\u00e9donie, Centre National de la Recherche Scientifique), 98800 New Caledonia, France"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0167-8809(01)00199-2","article-title":"Predicting land-use change","volume":"85","author":"Veldkamp","year":"2001","journal-title":"Agric. Ecosyst. Environ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/S0034-4257(03)00084-1","article-title":"Evaluating environmental influences of zoning in urban ecosystems with remote sensing","volume":"86","author":"Wilson","year":"2003","journal-title":"Remote Sens. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.gsf.2015.07.003","article-title":"Machine learning in geosciences and remote sensing","volume":"7","author":"Lary","year":"2015","journal-title":"Geosci. Front."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.isprsjprs.2009.06.004","article-title":"Object based image analysis for remote sensing","volume":"65","author":"Blaschke","year":"2010","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"123","DOI":"10.2307\/2999756","article-title":"Research on New Caledonian Terrestrial Fauna: Achievements and Prospects","volume":"1","author":"Chazeau","year":"1993","journal-title":"Biodivers. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s11104-016-2910-5","article-title":"How did the ultramafic soils shape the flora of the New Caledonian hotspot?","volume":"403","author":"Isnard","year":"2016","journal-title":"Plant Soil"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.marpolbul.2010.06.013","article-title":"Developing erosion models for integrated coastal zone management: A case study of The New Caledonia west coast","volume":"61","author":"Dumas","year":"2010","journal-title":"Mar. Pollut. Bull."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3309","DOI":"10.1098\/rstb.2008.0122","article-title":"New Caledonia: A very old Darwinian island?","volume":"363","author":"Grandcolas","year":"2008","journal-title":"Phil. Trans. R. Soc. B"},{"key":"ref_9","unstructured":"Payri, C., Richer de Forges, B., and Colin, F. (2007). Geology of the New Caledonia region and its implications for the study of the New Caledonian biodiversity. Compendium of Marine Species from New Caledonia, Documents Scientifiques et Techniques: II, IRD. [2nd ed.]. Available online: https:\/\/www.documentation.ird.fr\/hor\/fdi:010059749."},{"key":"ref_10","unstructured":"Rescigno, V., and Maletta, S. (2010). Conservation and Management of the Biodiversity in a Hotspot Characterized by Short Range Endemism and Rarity: The Challenge of New Caledonia. Biodiversity Hotspots, Nova Science Publishers."},{"key":"ref_11","unstructured":"Rolland, A.K., Cr\u00e9pin, A., Kenner, C., and Afro, P. (2020, February 02). Production de Donn\u00e9es D\u2019Occupation du sol 2010\u20132014 sur la Province Sud. Available online: http:\/\/oeil.nc\/cdrn\/index.php\/resource\/bibliographie\/view\/27689."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1561\/2000000039","article-title":"Deep Learning: Methods and Applications","volume":"7","author":"Deng","year":"2014","journal-title":"Found. Trends Signal Process."},{"key":"ref_13","first-page":"698","article-title":"On the Expressive Power of Deep Learning: A Tensor Analysis","volume":"Volume 49","author":"Feldman","year":"2016","journal-title":"29th Annual Conference on Learning Theory"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object Detection With Deep Learning: A Review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep Learning in Neural Networks: An Overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3651","DOI":"10.1080\/01431160310001647993","article-title":"An assessment of the effectiveness of atmospheric correction algorithms through the remote sensing of some reservoirs","volume":"25","author":"Hadjimitsis","year":"2004","journal-title":"Int. J. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1637","DOI":"10.1080\/01431168608948958","article-title":"Image correction for radiometric effects in remote sensing","volume":"7","author":"Teillet","year":"1986","journal-title":"Int. J. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3916","DOI":"10.1016\/j.rse.2008.06.011","article-title":"Assessment of radiometric correction techniques in analyzing vegetation variability and change using time series of Landsat images","volume":"112","author":"Lasanta","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/MGRS.2016.2540798","article-title":"Deep learning for Remote Sensing Data","volume":"4","author":"Zhang","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","article-title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","volume":"105","author":"Cheng","year":"2017","journal-title":"Proc. IEEE"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1111\/j.1523-1739.2008.00889.x","article-title":"Mining and Other Threats to the New Caledonia Biodiversity Hotspot","volume":"22","author":"Pascal","year":"2008","journal-title":"Conserv. Biol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1017\/S0030605300021487","article-title":"New Caledonia\u2014A conservation imperative for an ancient land","volume":"30","author":"Mittermeier","year":"1996","journal-title":"Oryx"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1109\/LGRS.2018.2803259","article-title":"Very High Resolution Object-Based Land Use\u2013Land Cover Urban Classification Using Extreme Gradient Boosting","volume":"15","author":"Georganos","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"357","DOI":"10.14358\/PERS.69.4.357","article-title":"Comparing texture analysis methods through classification","volume":"69","author":"Maillard","year":"2003","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_25","unstructured":"GIE OCEANIDE, J\u00e9r\u00e9my, A., Antoine, W., and OEIL (2020, March 12). L\u2019\u00e9volution des Paysages en Province sud. Available online: https:\/\/www.oeil.nc\/cdrn\/index.php\/resource\/bibliographie\/view\/2322."},{"key":"ref_26","unstructured":"Rousset, G. (2020, March 12). SPOT6 Satellite Imagery, Land Cover and Land Use Classification of 5 Areas in the South Province of New Caledonia. https:\/\/doi.org\/10.23708\/PHVOJD."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1162\/neco_a_01273","article-title":"A Survey on Deep Learning for Multimodal Data Fusion","volume":"32","author":"Gao","year":"2020","journal-title":"Neural Comput."},{"key":"ref_28","unstructured":"Heymann, Y., Steenmans, C., Croisille, G., Bossard, M., Lenco, M., Wyatt, B., Weber, J.L., O\u2019Brian, C., Cornaert, M.H., and Sifakis, N. (1994). Corine Land Cover Technical Guide, Office for Official Publications of the European Communities."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.isprsjprs.2013.02.003","article-title":"Shadow detection in very high spatial resolution aerial images: A comparative study","volume":"80","author":"Adeline","year":"2013","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"311","DOI":"10.3166\/ts.32.311-333","article-title":"D\u00e9tection simultan\u00e9e de l\u2019ombre et la v\u00e9g\u00e9tation sur des images a\u00e9riennes couleur en haute r\u00e9solution","volume":"32","author":"Ngo","year":"2014","journal-title":"Trait. Signal"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1109\/TGRS.1995.8746029","article-title":"The interpretation of spectral vegetation indexes","volume":"33","author":"Myneni","year":"1995","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Xu, Y., Wu, L., Xie, Z., and Chen, Z. (2018). Building Extraction in Very High Resolution Remote Sensing Imagery Using Deep Learning and Guided Filters. Remote Sens., 10.","DOI":"10.3390\/rs10010144"},{"key":"ref_33","first-page":"112","article-title":"Monitoring the vernal advancement and retrogradation (green wave effect) of natural vegetation","volume":"371","author":"Rouse","year":"1973","journal-title":"Prog. Rep. RSC 1978-1"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1016\/S0031-3203(98)00036-3","article-title":"Color-based object recognition","volume":"32","author":"Gevers","year":"1999","journal-title":"Pattern Recognit."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/0034-4257(94)90134-1","article-title":"A modified soil adjusted vegetation index","volume":"48","author":"Qi","year":"1994","journal-title":"Remote Sens. Environ."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"259","DOI":"10.13031\/2013.27838","article-title":"Color indices for weed identification under various soil, residue, and lighting conditions","volume":"38","author":"Woebbecke","year":"1994","journal-title":"Trans. ASAE"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3025","DOI":"10.1080\/01431160600589179","article-title":"Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery","volume":"27","author":"Xu","year":"2006","journal-title":"Int. J. Remote Sens."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.compag.2008.03.009","article-title":"Verification of color vegetation indices for automated crop imaging applications","volume":"63","author":"Meyer","year":"2008","journal-title":"Comput. Electron. Agric."},{"key":"ref_39","unstructured":"Chen, T., and Guestrin, C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_41","first-page":"1","article-title":"A systematic study of the class imbalance problem in convolutional neural networks","volume":"106","author":"Buda","year":"2017","journal-title":"Neural Netw."},{"key":"ref_42","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., and Weinberger, K.Q. (2016). Densely Connected Convolutional Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_46","unstructured":"Noh, H., Hong, S., and Han, B. Learning deconvolution network for semantic segmentation. Proceedings of the IEEE International Conference on Computer Vision."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Navab, N., Hornegger, J., Wells, W.M., and Frangi, A.F. (2015). U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Springer International Publishing.","DOI":"10.1007\/978-3-319-24571-3"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015). Fully convolutional networks for semantic segmentation. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016). Identity mappings in deep residual networks. Computer Vision\u2014ECCV 2016, Springer International Publishing.","DOI":"10.1007\/978-3-319-46466-4"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/JSTARS.2019.2900705","article-title":"CNN-based multilayer spatial\u2014Spectral feature fusion and sample augmentation with local and nonlocal constraints for hyperspectral image classification","volume":"12","author":"Feng","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1109\/JSTARS.2020.3041859","article-title":"Object-Scale Adaptive Convolutional Neural Networks for High-Spatial Resolution Remote Sensing Image Classification","volume":"14","author":"Wang","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"103471","DOI":"10.1016\/j.artint.2021.103471","article-title":"Using ontologies to enhance human understandability of global post-hoc explanations of black-box models","volume":"296","author":"Confalonieri","year":"2021","journal-title":"Artif. Intell."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"531","DOI":"10.5721\/EuJRS20164928","article-title":"A filter-based post-processing technique for improving homogeneity of pixel-wise classification data","volume":"49","author":"Su","year":"2016","journal-title":"Eur. J. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/12\/2257\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:12:32Z","timestamp":1760163152000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/12\/2257"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,9]]},"references-count":55,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["rs13122257"],"URL":"https:\/\/doi.org\/10.3390\/rs13122257","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,9]]}}}