{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T00:19:00Z","timestamp":1760746740082,"version":"build-2065373602"},"reference-count":53,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:00:00Z","timestamp":1760659200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Classifying multiband images acquired by advanced sensors, including those mounted on satellites, is a central task in remote sensing and environmental monitoring. These sensors generate high-dimensional outputs rich in spectral and spatial information, enabling detailed analyses of Earth\u2019s surface. However, the complexity of such data presents substantial challenges to achieving both accuracy and efficiency. To address these challenges, we tested the ensemble learning framework based on ResNet50, MobileNetV2, and DenseNet201, each trained on distinct three-channel representations of the input to capture complementary features. Training is conducted on the LCZ42 dataset of 400,673 paired Sentinel-1 SAR and Sentinel-2 multispectral image patches annotated with Local Climate Zone (LCZ) labels. Experiments show that our best ensemble surpasses several recent state-of-the-art methods on the LCZ42 benchmark.<\/jats:p>","DOI":"10.3390\/a18100657","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T10:28:36Z","timestamp":1760696916000},"page":"657","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Ensembles and Multisensor Data for Global LCZ Mapping: Insights from So2Sat LCZ42"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3502-7209","authenticated-orcid":false,"given":"Loris","family":"Nanni","sequence":"first","affiliation":[{"name":"Department of Information Engineering, University of Padova, via Gradengo 6\/A, 35131 Padova, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7664-6930","authenticated-orcid":false,"given":"Sheryl","family":"Brahnam","sequence":"additional","affiliation":[{"name":"Department of Information Technology and Cybersecurity, Missouri State University, 901 S. National, Springfield, MO 65804, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Nalepa, J. (2021). Recent Advances in Multi- and Hyperspectral Image Analysis. Sensors, 21.","DOI":"10.3390\/s21186002"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Uddin, M.P., Mamun, M.A., and Hossain, M.A. (2017, January 21\u201323). Feature extraction for hyperspectral image classification. Proceedings of the 2017 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Dhaka, Bangladesh.","DOI":"10.1109\/R10-HTC.2017.8288979"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2781","DOI":"10.1109\/JSTARS.2021.3059451","article-title":"A hyperspectral image classification method using multifeature vectors and optimized KELM","volume":"14","author":"Chen","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1109\/LGRS.2019.2944970","article-title":"Unsupervised dimensionality reduction for hyperspectral imagery via local geometric structure feature learning","volume":"17","author":"Shi","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5564","DOI":"10.1109\/TGRS.2019.2900484","article-title":"Subpixel component analysis for hyperspectral image classification","volume":"57","author":"Xu","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_6","first-page":"5502210","article-title":"Spectral\u2013spatial and superpixelwise PCA for unsupervised feature extraction of hyperspectral imagery","volume":"60","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Champa, A.I., Rabbi, M.F., Hasan, S.M., Zaman, A., and Kabir, M.H. (2021, January 27\u201328). Tree-based classifier for hyperspectral image classification via hybrid technique of feature reduction. Proceedings of the 2021 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD), Dhaka, Bangladesh.","DOI":"10.1109\/ICICT4SD50815.2021.9396809"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wei, L., Huang, C., Wang, Z., Wang, Z., Zhou, X., and Cao, L. (2019). Monitoring of urban black-odor water based on Nemerow index and gradient boosting decision tree regression using UAV-borne hyperspectral imagery. Remote Sens., 11.","DOI":"10.3390\/rs11202402"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Xu, S., Liu, S., Wang, H., Chen, W., Zhang, F., and Xiao, Z. (2020). A hyperspectral image classification approach based on feature fusion and multi-layered gradient boosting decision trees. Entropy, 23.","DOI":"10.3390\/e23010020"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bazine, R., Huayi, W., and Boukhechba, K. (2019, January 29\u201331). K-NN similarity measure based on fourier descriptors for hyperspectral images classification. Proceedings of the 2019 International Conference on Video, Signal and Image Processing, Wuhan, China.","DOI":"10.1145\/3369318.3369320"},{"key":"ref_11","unstructured":"Bhavatarini, N., Akash, B., Avinash, A.R., and Akshay, H. (2023, January 5\u20137). Object detection and classification of hyperspectral images using K-NN. Proceedings of the 2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), Trichirappalli, India."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, L., Huang, D., Chen, X., Zhu, L., Xie, Z., Chen, X., Cui, G., Zhou, Y., Huang, G., and Shi, W. (2023). Discrimination between normal and necrotic small intestinal tissue using hyperspectral imaging and unsupervised classification. J. Biophotonics, 16.","DOI":"10.1002\/jbio.202300020"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"40","DOI":"10.2478\/jee-2021-0006","article-title":"Multiscale filter-based hyperspectral image classification with PCA and SVM","volume":"72","author":"Chen","year":"2021","journal-title":"J. Electr. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, S., Huang, H., Huang, Y., Cheng, D., and Huang, J. (2022). A GA and SVM classification model for pine wilt disease detection using UAV-based hyperspectral imagery. Appl. Sci., 12.","DOI":"10.3390\/app12136676"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1809","DOI":"10.1007\/s12065-021-00591-0","article-title":"Hyperspectral image classification using support vector machine: A spectral spatial feature based approach","volume":"15","author":"Pathak","year":"2022","journal-title":"Evol. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"258619","DOI":"10.1155\/2015\/258619","article-title":"Deep convolutional neural networks for hyperspectral image classification","volume":"2015","author":"Hu","year":"2015","journal-title":"J. Sens."},{"key":"ref_17","first-page":"5502205","article-title":"A fast and compact 3-D CNN for hyperspectral image classification","volume":"19","author":"Ahmad","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1109\/LGRS.2019.2918719","article-title":"HybridSN: Exploring 3-D\u20132-D CNN feature hierarchy for hyperspectral image classification","volume":"17","author":"Roy","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1109\/TGRS.2018.2860464","article-title":"Feature extraction with multiscale covariance maps for hyperspectral image classification","volume":"57","author":"He","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, T., Skidmore, A., Sun, Y., Jia, P., and Zhang, K. (2023). Integrated 1D, 2D, and 3D CNNs Enable Robust and Efficient Land Cover Classification from Hyperspectral Imagery. Remote Sens., 15.","DOI":"10.3390\/rs15194797"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Justo, J.A., Langer, D.D., Berg, S., Nieke, J., Ionescu, R.T., Kjeldsberg, P.G., and Johansen, T.A. (2025). Hyperspectral Image Segmentation for Optimal Satellite Operations: In-Orbit Deployment of 1D-CNN. Remote Sens., 17.","DOI":"10.3390\/rs17040642"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zai, C., Hu, N., Shi, L., Zhou, X., and Sun, J. (2024). Adaptive pixel attention network for hyperspectral image classification. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-73988-3"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Jain, V., and Phophalia, A. (August, January 28). Exponential weighted random forest for hyperspectral image classification. Proceedings of the IGARSS 2019\u20132019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8897862"},{"key":"ref_24","unstructured":"Kishore, K.M.S., Behera, M.K., Chakravarty, S., and Dash, S. (2020, January 26\u201327). Hyperspectral image classification using minimum noise fraction and random forest. Proceedings of the 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), Bhubaneswar, India."},{"key":"ref_25","first-page":"107","article-title":"A joint method of spatial\u2013spectral features and BP neural network for hyperspectral image classification","volume":"26","author":"Zhao","year":"2023","journal-title":"Egypt. J. Remote Sens. Space Sci."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ding, R., Shi, H., Liu, J., Yu, Q., Cao, G., and Li, X. (2024). Ensemble Network-Based Distillation for Hyperspectral Image Classification in the Presence of Label Noise. Remote Sens., 16.","DOI":"10.3390\/rs16224247"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Nalepa, J., Myller, M., Tulczyjew, L., and Kawulok, M. (2021). Deep Ensembles for Hyperspectral Image Data Classification and Unmixing. Remote Sens., 13.","DOI":"10.3390\/rs13204133"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Nanni, L., Brahnam, S., Ruta, M., Fabris, D., Boscolo Bacheto, M., and Milanello, T. (2025). Deep Ensembling of Multiband Images for Earth Remote Sensing and Foramnifera Data. Sensors, 25.","DOI":"10.3390\/s25072231"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/MGRS.2020.2964708","article-title":"So2Sat LCZ42: A Benchmark Data Set for the Classification of Global Local Climate Zones [Software and Data Sets]","volume":"8","author":"Zhu","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_31","first-page":"3","article-title":"Densely Connected Convolutional Networks","volume":"1","author":"Huang","year":"2017","journal-title":"CVPR"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L. (2018, January 18\u201323). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_33","unstructured":"Yosinski, J., Clune, J., Bengio, Y., and Lipson, H. (2014). How transferable are features in deep neural networks?. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A Comprehensive Survey on Transfer Learning","volume":"109","author":"Zhuang","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"4403014","DOI":"10.1109\/TGRS.2024.3360522","article-title":"Local climate zone mapping by coupling multilevel features with prior knowledge based on remote sensing images","volume":"62","author":"Zhong","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"5212117","DOI":"10.1109\/TGRS.2024.3399048","article-title":"Local Climate Zone Classification via Semi-Supervised Multimodal Multiscale Transformer","volume":"62","author":"Lin","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2793","DOI":"10.1109\/JSTARS.2020.2995711","article-title":"Multilevel feature fusion-based CNN for local climate zone classification from sentinel-2 images: Benchmark results on the So2Sat LCZ42 dataset","volume":"13","author":"Qiu","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1007\/s41748-023-00343-3","article-title":"Two-Speed Deep-Learning Ensemble for Classification of Incremental Land-Cover Satellite Image Patches","volume":"7","author":"Horry","year":"2023","journal-title":"Earth Syst. Environ."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"He, G., Dong, Z., Guan, J., Feng, P., Jin, S., and Zhang, X. (2023). SAR and multi-spectral data fusion for local climate zone classification with multi-branch convolutional neural network. Remote Sens., 15.","DOI":"10.3390\/rs15020434"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.isprsjprs.2023.01.014","article-title":"Current trends in deep learning for Earth Observation: An open-source benchmark arena for image classification","volume":"197","author":"Dimitrovski","year":"2023","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1109\/JSTARS.2022.3226524","article-title":"Multicascaded feature fusion-based deep learning network for local climate zone classification based on the So2Sat LCZ42 benchmark dataset","volume":"16","author":"Ji","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_42","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Nawaz, A., Yang, W., Zeng, H., Wang, Y., and Chen, J. (2025). Restricted Label-Based Self-Supervised Learning Using SAR and Multispectral Imagery for Local Climate Zone Classification. Remote Sens., 17.","DOI":"10.3390\/rs17081335"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s10791-024-09463-4","article-title":"Towards compressed and efficient CNN architectures via pruning","volume":"27","author":"Narkhede","year":"2024","journal-title":"Discov. Comput."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"e18","DOI":"10.1017\/ATSIP.2021.16","article-title":"Cross-layer knowledge distillation with KL divergence and offline ensemble for compressing deep neural network","volume":"10","author":"Chou","year":"2021","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"10558","DOI":"10.1109\/TPAMI.2024.3447085","article-title":"A survey on deep neural network pruning: Taxonomy, comparison, analysis, and recommendations","volume":"46","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1119","DOI":"10.1016\/0167-8655(94)90127-9","article-title":"Floating search methods in feature selection","volume":"5","author":"Pudil","year":"1994","journal-title":"Pattern Recognit. Lett."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T.-Y., Song, Y., and Belongie, S. (2019, January 15\u201320). Class-balanced loss based on effective number of samples. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv.","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., and Le, Q.V. (2021, January 19\u201325). Randaugment: Practical automated data augmentation with a reduced search space. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Nashville, TN, USA.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Hossain, M.B., Gong, N., and Shaban, M. (2023, January 12\u201327). An Improved Lightweight DenseNet-201 Model for Pneumonia Detection on Edge IoT. Proceedings of the 2023 IEEE 9th World Forum on Internet of Things (WF-IoT), Averio, Portigal.","DOI":"10.1109\/WF-IoT58464.2023.10539583"},{"key":"ref_53","first-page":"98","article-title":"SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation","volume":"11","author":"Wang","year":"2023","journal-title":"Comput. Sci."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/10\/657\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T10:42:03Z","timestamp":1760697723000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/10\/657"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":53,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["a18100657"],"URL":"https:\/\/doi.org\/10.3390\/a18100657","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,17]]}}}