{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T22:55:59Z","timestamp":1762642559556,"version":"build-2065373602"},"reference-count":72,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T00:00:00Z","timestamp":1623283200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Horizon 2020","award":["820852"],"award-info":[{"award-number":["820852"]}]},{"name":"LIFE20PRE","award":["LIFE20PRE\/IT\/000007"],"award-info":[{"award-number":["LIFE20PRE\/IT\/000007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The present study focuses on the use of Convolutional Neural Networks (CNN or ConvNet) to classify a multi-seasonal dataset of Sentinel-2 images to discriminate four grassland habitats in the \u201cMurgia Alta\u201d protected site. To this end, we compared two approaches differing only by the first layer machinery, which, in one case, is instantiated as a fully-connected layer and, in the other case, results in a ConvNet equipped with kernels covering the whole input (wide-kernel ConvNet). A patchwise approach, tessellating training reference data in square patches, was adopted. Besides assessing the effectiveness of ConvNets with patched multispectral data, we analyzed how the information needed for classification spreads to patterns over convex sets of pixels. Our results show that: (a) with an F1-score of around 97% (5 \u00d7 5 patch size), ConvNets provides an excellent tool for patch-based pattern recognition with multispectral input data without requiring special feature extraction; (b) the information spreads over the limit of a single pixel: the performance of the network increases until 5 \u00d7 5 patch sizes are used and then ConvNet performance starts decreasing.<\/jats:p>","DOI":"10.3390\/rs13122276","type":"journal-article","created":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T21:34:38Z","timestamp":1623360878000},"page":"2276","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Sentinel-2 Remote Sensed Image Classification with Patchwise Trained ConvNets for Grassland Habitat Discrimination"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3290-2618","authenticated-orcid":false,"given":"Paolo","family":"Fazzini","sequence":"first","affiliation":[{"name":"Institute of Atmospheric Pollution Research (IIA), National Research Council (CNR), Via Salaria Km 29 300, 00015 Monterotondo, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7377-4563","authenticated-orcid":false,"given":"Giuseppina","family":"De Felice Proia","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering and Computer Science Engineering, University of Rome \u201cTor Vergata\u201d, Via del Politecnico 1, 00133 Rome, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3030-4884","authenticated-orcid":false,"given":"Maria","family":"Adamo","sequence":"additional","affiliation":[{"name":"Institute of Atmospheric Pollution Research (IIA), National Research Council (CNR), c\/o Interateneo Physics Department, Via Amendola 173, 70126 Bari, Italy"}]},{"given":"Palma","family":"Blonda","sequence":"additional","affiliation":[{"name":"Institute of Atmospheric Pollution Research (IIA), National Research Council (CNR), c\/o Interateneo Physics Department, Via Amendola 173, 70126 Bari, Italy"}]},{"given":"Francesco","family":"Petracchini","sequence":"additional","affiliation":[{"name":"Institute of Atmospheric Pollution Research (IIA), National Research Council (CNR), Via Salaria Km 29 300, 00015 Monterotondo, Italy"}]},{"given":"Luigi","family":"Forte","sequence":"additional","affiliation":[{"name":"Department of Biology\u2014Botanical Garden Museum, University of Bari, Via Orabona 4, 70125 Bari, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3304-5355","authenticated-orcid":false,"given":"Cristina","family":"Tarantino","sequence":"additional","affiliation":[{"name":"Institute of Atmospheric Pollution Research (IIA), National Research Council (CNR), c\/o Interateneo Physics Department, Via Amendola 173, 70126 Bari, Italy"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1080\/01431160600746456","article-title":"A survey of image classification methods and techniques for improving classification performance","volume":"28","author":"Lu","year":"2007","journal-title":"Int. J. Remote Sens."},{"key":"ref_2","first-page":"25","article-title":"Grassland habitat mapping by intra-annual time series analysis\u2013Comparison of RapidEye and TerraSAR-X satellite data","volume":"34","author":"Schuster","year":"2015","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1093\/jpe\/rtw005","article-title":"Satellite remote sensing of grasslands: From observation to management","volume":"9","author":"Ali","year":"2016","journal-title":"J. Plant Ecol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.jnc.2012.02.001","article-title":"Assessment of grassland use intensity by remote sensing to support conservation schemes","volume":"20","author":"Franke","year":"2012","journal-title":"J. Nat. Conserv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"6163","DOI":"10.3390\/rs6076163","article-title":"Combined use of Multi-temporal optical and radar satellite images for grassland monitoring","volume":"6","author":"Dusseux","year":"2014","journal-title":"Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.rama.2018.11.007","article-title":"The Classification of Grassland Types Based on Object-Based Image Analysis with Multisource Data","volume":"72","author":"Xu","year":"2019","journal-title":"Rangel. Ecol. Manag."},{"key":"ref_7","first-page":"46","article-title":"Object-based random forest classification of Landsat ETM+ and worldview-2 satellite imagery for mapping lowland native grassland communities in Tasmania, Australia","volume":"66","author":"Melville","year":"2018","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_8","first-page":"83","article-title":"Using information layers for mapping grassland habitat distribution at local to regional scales","volume":"37","author":"Buck","year":"2015","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"8056","DOI":"10.3390\/rs6098056","article-title":"Categorizing Grassland Vegetation with Full-Waveform Airborne Laser Scanning: A Feasibility Study for Detecting Natura 2000 Habitat Types","volume":"6","author":"Zlinszky","year":"2014","journal-title":"Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Marcinkowska-Ochtyra, A., Gryguc, K., Ochtyra, A., Kope\u0107, D., Jarocinska, A., and S\u0142awik, L. (2019). Multitemporal Hyperspectral Data Fusion with Topographic Indices\u2014Improving Classification of Natura 2000 Grassland Habitats. Remote Sens., 11.","DOI":"10.3390\/rs11192264"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.rse.2019.01.018","article-title":"Evaluation of Sentinel-2 time-series for mapping floodplain grassland plant communities","volume":"223","author":"Rapinel","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"111536","DOI":"10.1016\/j.rse.2019.111536","article-title":"Prediction of plant diversity in grasslands using Sentinel-1 and -2 satellite image time-series","volume":"237","author":"Fauvel","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tarantino, C., Forte, L., Blonda, P., Vicario, S., Tomaselli, V., Beierkuhnlein, C., and Adamo, M. (2021). Intra-Annual Sentinel-2 Time-Series Supporting Grassland Habitat Discrimination. Remote Sens., 13.","DOI":"10.3390\/rs13020277"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1080\/01431160701294661","article-title":"Multispectral land use classification using neural networks and support vector machines: One or the other, or both?","volume":"29","author":"Dixon","year":"2008","journal-title":"Int. J. Rem. Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1080\/014311697218719","article-title":"Strategies and best practice for neural network image classification","volume":"18","author":"Kanellopoulos","year":"2010","journal-title":"Int. J. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"959","DOI":"10.1016\/S0098-3004(96)00034-9","article-title":"The sensitivity of a neural network for classifying remotely sensed imagery","volume":"22","author":"Jarvis","year":"1996","journal-title":"Comput. Geosci."},{"key":"ref_17","first-page":"12","article-title":"An Assessment of Internal Neural Network Parameters Affecting Image Classification Accuracy","volume":"77","author":"Zhou","year":"2011","journal-title":"Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1109\/ACCESS.2014.2325029","article-title":"Big Data Deep Learning: Challenges and Perspectives","volume":"2","author":"Chen","year":"2014","journal-title":"IEEE Access"},{"key":"ref_19","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_20","unstructured":"Zhang, J., and Zhang, Y. (2014, January 27\u201330). Classification of hyperspectral image based on deep belief networks. Proceedings of the 2014 IEEE International Conference on Image Processing (ICIP), Paris, France."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"14680","DOI":"10.3390\/rs71114680","article-title":"Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery","volume":"7","author":"Hu","year":"2015","journal-title":"Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2448","DOI":"10.1109\/LGRS.2015.2483680","article-title":"Multiview Deep Learning for Land-Use Classification","volume":"12","author":"Luus","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_23","first-page":"100394","article-title":"Land cover classification in Thailand\u2019s Eastern Economic Corridor (EEC) using convolutional neural network on satellite images","volume":"20","author":"Hongkarnjanakul","year":"2020","journal-title":"Remote Sens. Appl. Soc. Environ."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/j.isprsjprs.2020.05.022","article-title":"Land-cover classification of multispectral LiDAR data using CNN with optimized hyper-parameters","volume":"166","author":"Pan","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_25","first-page":"102086","article-title":"A multi-level context-guided classification method with object-based convolutional neural network for land cover classification using very high resolution remote sensing images","volume":"88","author":"Zhang","year":"2020","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.isprsjprs.2019.04.015","article-title":"Deep learning in remote sensing applications: A meta-analysis and review","volume":"152","author":"Ma","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.isprsjprs.2019.09.009","article-title":"Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images","volume":"157","author":"Yoo","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_28","first-page":"100326","article-title":"Inland water\u2019s trophic status classification based on machine learning and remote sensing data","volume":"19","author":"Watanabe","year":"2020","journal-title":"Remote Sens. Appl. Soc. Environ."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1017\/S037689291300043X","article-title":"Using spatial simulations of habitat modification for adaptive management of protected areas: Mediterranean grassland modification by woody plant encroachment","volume":"41","author":"Mairota","year":"2013","journal-title":"Environ. Conserv."},{"key":"ref_30","first-page":"83","article-title":"Le praterie a Stipa austroitalica Martinovsky ssp. austroitalica dell\u2019Alta Murgia (Puglia) e della Murgia Materana (Basilicata)","volume":"42","author":"Forte","year":"2005","journal-title":"Fitosociologia"},{"key":"ref_31","unstructured":"(2019, June 26). Council Directive 2009\/147\/EEC. Available online: https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/?uri=CELEX%3A32009L0147."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1139\/z98-018","article-title":"Avifaunal and habitat changes resulting from conversion of native prairie to crested wheat grass:Patterns at songbird community and species levels","volume":"76","author":"Sutter","year":"1998","journal-title":"Can. J. Zool."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1111\/j.1365-2699.2004.01195.x","article-title":"Colonization of dynamic Mediterranean landscapes: Where do birds come from after fire?","volume":"32","author":"Brotons","year":"2005","journal-title":"J. Biogeogr."},{"key":"ref_34","first-page":"100","article-title":"Very high resolution Earth observation features for monitoring plant and animal community structure across multiple spatial scales in protected areas","volume":"37","author":"Mairota","year":"2015","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.isprsjprs.2018.11.013","article-title":"Ailanthus altissima mapping from multi-temporal very high resolution satellite images","volume":"147","author":"Tarantino","year":"2019","journal-title":"ISPRS J. Photogram. Remote Sens."},{"key":"ref_36","unstructured":"(2013, July 01). Council Directive 92\/43\/EEC. Available online: https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/?uri=celex%3A31992L0043."},{"key":"ref_37","unstructured":"Davies, C.E., and Moss, D. (2002). EUNIS Habitat Classification. Final Report to the European Topic Centre of Nature Protection and Biodiversity, European Environment Agency."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Braun-Blanquet, J. (1964). Pflanzensoziologie: Grundz\u00fcge der Vegetationskunde: Plant Sociology Basics of Vegetation Science, Springer.","DOI":"10.1007\/978-3-7091-8110-2"},{"key":"ref_39","unstructured":"EU (2013, April 01). Habitats Manual, Interpretation Manual of European Union Habitats: 1\u2013144. Available online: http:\/\/ec.europa.eu\/environment\/nature\/legislation\/habitatsdirective\/docs\/Int_Manual_EU28.pdf."},{"key":"ref_40","unstructured":"Biondi, E., Blasi, C., Burrascano, S., Casavecchia, S., Copiz, R., Del Vico, E., Galdenzi, D., Gigante, D., Lasen, C., and Spampinato, G. (2007, December 01). Manuale Italiano di Interpretazione Degli Habitat Della Direttiva 92\/43\/CEE. MATTM-DPN, SBI. Available online: http:\/\/vnr.unipg.it\/habitat\/index.jsp."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Whittaker, R.H. (1978). The Braun-Blanquet Approach. Classification of Plant Communities, Junk.","DOI":"10.1007\/978-94-009-9183-5"},{"key":"ref_42","first-page":"5","article-title":"Diagnosis and syntaxonomic interpretation of Annex I Habitats (Dir. 92\/43\/ EEC) in Italy at the alliance level","volume":"49","author":"Biondi","year":"2012","journal-title":"Plant Sociol."},{"key":"ref_43","unstructured":"Biondi, E., and Blasi, C. (2015, March 01). Prodromo della Vegetazione Italiana 2015. Ministero dell\u2019Ambiente e della Tutela del Territorio e del Mare. Available online: http:\/\/www.prodromo-vegetazione-italia.org\/."},{"key":"ref_44","unstructured":"(2018, May 09). USGS Portal, Available online: https:\/\/earthexplorer.usgs.gov\/."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Anagnostis, A., Asiminari, G., Papageorgiou, E., and Bochtis, D. (2020). A Convolutional Neural Networks Based Method for Anthracnose Infected Walnut Tree Leaves Identification. NATO Adv. Sci. Inst. Ser. E Appl. Sci., 10.","DOI":"10.3390\/app10020469"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Hasan, M., Ullah, S., Khan, M.J., and Khurshid, K. (2019, January 10\u201314). Comparative analysis of svm, ann and cnn for classifying vegetation species using hyperspectral thermal infrared data. Proceedings of the ISPRS Geospatial Week 2019 (Volume XLII-2\/W13), Enschede, The Netherlands.","DOI":"10.5194\/isprs-archives-XLII-2-W13-1861-2019"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1985). Learning Internal Representations by Error Propagation, Institute for Cognitive Science. Available online: https:\/\/apps.dtic.mil\/sti\/pdfs\/ADA164453.pdf.","DOI":"10.21236\/ADA164453"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.neucom.2015.09.116","article-title":"Deep learning for visual understanding: A review","volume":"187","author":"Guo","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1016\/j.procs.2018.10.342","article-title":"Deep AlexNet with Reduced Number of Trainable Parameters for Satellite Image Classification","volume":"143","author":"Unnikrishnan","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"ref_50","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_51","unstructured":"Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., and Darrell, T. (2014, January 21\u201326). DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition. Proceedings of the International Conference on Machine Learning, PMLR, Beijing, China."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Sharif Razavian, A., Azizpour, H., Sullivan, J., and Carlsson, S. (2014, January 24\u201327). CNN Features Off-the-Shelf: An Astounding Baseline for Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Columbus, OH, USA.","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref_53","unstructured":"Yosinski, J., Clune, J., Bengio, Y., and Lipson, H. (2014). How transferable are features in deep neural networks?. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Penatti, O.A.B., Nogueira, K., and dos Santos, J.A. (2015, January 7\u201312). Do Deep Features Generalize From Everyday Objects to Remote Sensing and Aerial Scenes Domains?. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Boston, MA, USA.","DOI":"10.1109\/CVPRW.2015.7301382"},{"key":"ref_55","unstructured":"Castelluccio, M., Poggi, G., Sansone, C., and Verdoliva, L. (2015). Land Use Classification in Remote Sensing Images by Convolutional Neural Networks. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Lyu, H., Lu, H., and Mou, L. (2016). Learning a Transferable Change Rule from a Recurrent Neural Network for Land Cover Change Detection. Remote Sens., 8.","DOI":"10.3390\/rs8060506"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","article-title":"Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning","volume":"35","author":"Shin","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_58","first-page":"025010","article-title":"Using convolutional neural network to identify irregular segmentation objects from very high-resolution remote sensing imagery","volume":"12","author":"Fu","year":"2018","journal-title":"JARS"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"2237","DOI":"10.1063\/1.4825984","article-title":"Satellite image classification using convolutional learning","volume":"1558","author":"Nguyen","year":"2013","journal-title":"AIP Conf. Proc."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1109\/LGRS.2015.2499239","article-title":"Deep Learning Earth Observation Classification Using Image Net Pretrained Networks","volume":"13","author":"Marmanis","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"2149","DOI":"10.1080\/01431161.2016.1171928","article-title":"Using convolutional features and a sparse autoencoderfor land-use scene classification","volume":"37","author":"Othman","year":"2016","journal-title":"Int. J. Remote Sens."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.neunet.2017.07.017","article-title":"A patch-based convolutional neural network for remote sensing image classification","volume":"95","author":"Sharma","year":"2017","journal-title":"Neural Netw."},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Lv, X., Ming, D., Lu, T., Zhou, K., Wang, M., and Bao, H. (2018). A New Method for Region-Based Majority Voting CNNs for Very High Resolution Image Classification. Remote Sens., 10.","DOI":"10.3390\/rs10121946"},{"key":"ref_64","unstructured":"(2020, December 31). CS231n Convolutional Neural Networks for Visual Recognition. Available online: https:\/\/cs231n.github.io\/convolutional-networks\/."},{"key":"ref_65","unstructured":"Arunava (2020, December 31). Convolutional Neural Network\u2014Towards Data Science. Towards Data Science, 25 December 2018. Available online: https:\/\/towardsdatascience.com\/convolutional-neural-network-17fb77e76c05."},{"key":"ref_66","unstructured":"Dansbecker (2021, April 01). Rectified Linear Units (ReLU) in Deep Learning. Kaggle. 7 May 2018. Available online: https:\/\/kaggle.com\/dansbecker\/rectified-linear-units-relu-in-deep-learning."},{"key":"ref_67","unstructured":"Wood, T. (2021, April 01). Softmax Function. DeepAI. 17 May 2019. Available online: https:\/\/deepai.org\/machine-learning-glossary-and-terms\/softmax-layer."},{"key":"ref_68","unstructured":"Budhiraja, A. (2020, December 31). Dropout in (Deep) Machine Learning\u2014Amar Budhiraja\u2014Medium. Medium, 15 December 2016. Available online: https:\/\/medium.com\/@amarbudhiraja\/https-medium-com-amarbudhiraja-learning-less-to-learn-better-dropout-in-deep-machine-learning-74334da4bfc5."},{"key":"ref_69","unstructured":"Keras Team (2021, February 15). Layer Weight Initializers. Available online: https:\/\/keras.io\/api\/layers\/initializers\/#glorotuniform-class."},{"key":"ref_70","unstructured":"Keras Team (2021, February 15). Keras: The Python Deep Learning API. Available online: https:\/\/keras.io\/."},{"key":"ref_71","unstructured":"Brownlee, J. (2020, December 31). A Gentle Introduction to k-Fold Cross-Validation. 22 May 2018. Available online: https:\/\/machinelearningmastery.com\/k-fold-cross-validation\/."},{"key":"ref_72","unstructured":"Shung, K.P. (2020, December 31). Accuracy, Precision, Recall or F1?\u2014Towards Data Science. Towards Data Science, 15 March 2018. Available online: https:\/\/towardsdatascience.com\/accuracy-precision-recall-or-f1-331fb37c5cb9."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/12\/2276\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:13:02Z","timestamp":1760163182000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/12\/2276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,10]]},"references-count":72,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["rs13122276"],"URL":"https:\/\/doi.org\/10.3390\/rs13122276","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2021,6,10]]}}}