{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:48:27Z","timestamp":1774964907092,"version":"3.50.1"},"reference-count":59,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T00:00:00Z","timestamp":1720742400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of Qinghai Province of China","award":["2021-ZJ-913"],"award-info":[{"award-number":["2021-ZJ-913"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The unique geographic environment, diverse ecosystems, and complex landforms of the Qinghai\u2013Tibet Plateau make accurate land cover classification a significant challenge in plateau earth sciences. Given advancements in machine learning and satellite remote sensing technology, this study investigates whether emerging ensemble learning classifiers and submeter-level stereoscopic images can significantly improve land cover classification accuracy in the complex terrain of the Qinghai\u2013Tibet Plateau. This study utilizes multitemporal submeter-level GF-7 stereoscopic images to evaluate the accuracy of 11 typical ensemble learning classifiers (representing bagging, boosting, stacking, and voting strategies) and 3 classification datasets (single-temporal, multitemporal, and feature-optimized datasets) for land cover classification in the loess hilly area of the Eastern Qinghai\u2013Tibet Plateau. The results indicate that compared to traditional single strong classifiers (such as CART, SVM, and MLPC), ensemble learning classifiers can improve land cover classification accuracy by 5% to 9%. The classification accuracy differences among the 11 ensemble learning classifiers are generally within 1% to 3%, with HistGBoost, LightGBM, and AdaBoost-DT achieving a classification accuracy comparable to CNNs, with the highest overall classification accuracy (OA) exceeding 93.3%. All ensemble learning classifiers achieved better classification accuracy using multitemporal datasets, with the classification accuracy differences among the three classification datasets generally within 1% to 3%. Feature selection and feature importance evaluation show that spectral bands (e.g., the summer near-infrared (NIR-S) band), topographic factors (e.g., the digital elevation model (DEM)), and spectral indices (e.g., the summer resident ratio index (RRI-S)) significantly contribute to the accuracy of each ensemble learning classifier. Using feature-optimized datasets, ensemble classifiers can improve classification efficiency. This study preliminarily confirms that GF-7 images are suitable for land cover classification in complex terrains and that using ensemble learning classifiers and multitemporal datasets can improve classification accuracy.<\/jats:p>","DOI":"10.3390\/rs16142556","type":"journal-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T11:28:03Z","timestamp":1720783683000},"page":"2556","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Ensemble Learning for the Land Cover Classification of Loess Hills in the Eastern Qinghai\u2013Tibet Plateau Using GF-7 Multitemporal Imagery"],"prefix":"10.3390","volume":"16","author":[{"given":"Feifei","family":"Shi","sequence":"first","affiliation":[{"name":"School of Geographical Science, Qinghai Normal University, Xining 810008, China"},{"name":"Institute of Qinghai Meteorological Science Research, Xining 810008, China"},{"name":"Ministry of Education Key Laboratory of Tibetan Plateau Land Surface Processes and Ecological Conservation, Xining 810008, China"},{"name":"Qinghai Province Key Laboratory of Physical Geography and Environmental Process, Xining 810008, China"},{"name":"Qinghai Province Key Laboratory of Disaster Prevention and Mitigation, Xining 810008, China"}]},{"given":"Xiaohong","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Geographical Science, Qinghai Normal University, Xining 810008, China"},{"name":"Ministry of Education Key Laboratory of Tibetan Plateau Land Surface Processes and Ecological Conservation, Xining 810008, China"},{"name":"Qinghai Province Key Laboratory of Physical Geography and Environmental Process, Xining 810008, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4296-6869","authenticated-orcid":false,"given":"Runxiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Geographical Science, Qinghai Normal University, Xining 810008, China"},{"name":"Ministry of Education Key Laboratory of Tibetan Plateau Land Surface Processes and Ecological Conservation, Xining 810008, China"},{"name":"Qinghai Province Key Laboratory of Physical Geography and Environmental Process, Xining 810008, China"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Geographical Science, Qinghai Normal University, Xining 810008, China"},{"name":"Ministry of Education Key Laboratory of Tibetan Plateau Land Surface Processes and Ecological Conservation, Xining 810008, China"},{"name":"Qinghai Province Key Laboratory of Physical Geography and Environmental Process, Xining 810008, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s11273-016-9500-4","article-title":"Land use and land cover change analysis in predominantly man-made coastal wetlands: Towards a methodological framework","volume":"25","author":"Camilleri","year":"2017","journal-title":"Wetl. Ecol. Manag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1146\/annurev.environ.33.020107.113339","article-title":"Terrestrial vegetation in the coupled human-earth system: Contributions of remote sensing","volume":"33","author":"Defries","year":"2008","journal-title":"Ann. Rev. Environ. Resour."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2607","DOI":"10.1080\/01431161.2012.748992","article-title":"Finer resolution observation and monitoring of global land cover: First mapping results with Landsat TM and ETM+ data","volume":"34","author":"Gong","year":"2013","journal-title":"Int. J. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liu, F., Zhang, G., and Wang, J. (2024). Response of the Normalized Difference Vegetation Index (NDVI) to Snow Cover Changes on the Qinghai\u2013Tibet Plateau. Remote Sens., 16.","DOI":"10.3390\/rs16122140"},{"key":"ref_5","first-page":"3","article-title":"Protection and construction of the national ecological security shelter zone on Tibetan Plateau","volume":"67","author":"Sun","year":"2012","journal-title":"Acta Geogr. Sin."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2865","DOI":"10.1360\/TB-2019-0046","article-title":"Spatial and temporal characteristics of land use and cover changes in the Tibetan Plateau","volume":"64","author":"Zhang","year":"2019","journal-title":"Chin. Sci. Bull."},{"key":"ref_7","first-page":"1907","article-title":"The settlement intention of floating population and the factors in Qinghai-Tibet Plateau: An analysis from the perspective of short-distance and long-distance migrants","volume":"76","author":"Liu","year":"2022","journal-title":"Acta Geogr. Sin."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Shi, F., Zhou, B., Zhou, H., Zhang, H., Li, H., Li, R., Guo, Z., and Gao, X. (2022). Spatial Autocorrelation Analysis of Land Use and Ecosystem Service Value in the Huangshui River Basin at the Grid Scale. Plants, 11.","DOI":"10.3390\/plants11172294"},{"key":"ref_9","unstructured":"Tang, M. (2020). Land Use\/Land Cover Information Extraction from SPOT6 Imagery with Object-Oriented and Random Forest Methods in the Huangshui River Basin. [Master\u2019s Thesis, Qinghai Normal University]."},{"key":"ref_10","unstructured":"Li, J. (2013). Research on Land Use\/Land Cover Classification in Complex Terrain Areas. [Master\u2019s Thesis, Qinghai Normal University]."},{"key":"ref_11","unstructured":"Jia, W. (2015). Research on Object-Oriented Land Use Information Extraction in Complex Terrain Areas. [Master\u2019s Thesis, Qinghai Normal University]."},{"key":"ref_12","unstructured":"Gu, X. (2018). Research on Land Use\/Land Cover Classification in Huangshui Basin Based on Machine Learning. [Master\u2019s Thesis, Qinghai Normal University]."},{"key":"ref_13","unstructured":"Ma, H. (2018). Land Use\/Land Cover Change Detection in Huangshui River Basin Based on Random Forest. [Master\u2019s Thesis, Qinghai Normal University]."},{"key":"ref_14","unstructured":"Shen, Z. (2020). Land Use\/Land Cover Classification and Accuracy Assessment in Huangshui Basin Based on GEE\u2019s Landsat Image Long-Term Series Data. [Master\u2019s Thesis, Qinghai Normal University]."},{"key":"ref_15","unstructured":"Li, R. (2020). Research on Land Cover Classification Based on Ensemble Learning\u2014A Case Study of the Huangshui River Basin in the Northeast of Qinghai-Tibet Plateau. [Master\u2019s Thesis, Qinghai Normal University]."},{"key":"ref_16","first-page":"4","article-title":"Superpixel-based and Spatially-regularized Diffusion Learning for Unsupervised Hyperspectral Image Clustering","volume":"5","author":"Cui","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Maung, W.S., Tsuyuki, S., and Guo, Z. (2024). Improving Land Use and Land Cover Information of Wunbaik Mangrove Area in Myanmar Using U-Net Model with Multisource Remote Sensing Datasets. Remote Sens., 16.","DOI":"10.3390\/rs16010076"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lam, C.-N., Niculescu, S., and Bengoufa, S. (2023). Monitoring and Mapping Floods and Floodable Areas in the Mekong Delta (Vietnam) Using Time-Series Sentinel-1 Images, Convolutional Neural Network, Multi-Layer Perceptron, and Random Forest. Remote Sens., 15.","DOI":"10.3390\/rs15082001"},{"key":"ref_19","first-page":"749","article-title":"Research on land cover classification of images with different spatial resolutions based on CNN","volume":"35","author":"Li","year":"2020","journal-title":"Remote Sens. Technol. Appl."},{"key":"ref_20","unstructured":"Li, H. (2021). Research on Land Cover Classification of Sentinel-2 Multi-Seasonal Data Based on Gradient Boosting Tree and Random Forest. [Master\u2019s Thesis, Qinghai Normal University]."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1111\/ecog.04890","article-title":"Testing whether ensemble modelling is advantageous for maximising predictive performance of species distribution models","volume":"43","author":"Hao","year":"2020","journal-title":"Ecography"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Luo, H., Li, M., Dai, S., Li, H., Li, Y., Hu, Y., Zheng, Q., Yu, X., and Fang, J. (2022). Combinations of Feature Selection and Machine Learning Algorithms for Object-Oriented Betel Palms and Mango Plantations Classification Based on Gaofen-2 Imagery. Remote Sens., 14.","DOI":"10.3390\/rs14071757"},{"key":"ref_23","first-page":"271","article-title":"Glossary of terms: Machine learning","volume":"30","author":"Kohavi","year":"1998","journal-title":"Appl. Mach. Learn. Knowl. Discov. Process"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wen, L., and Hughes, M. (2020). Coastal Wetland Mapping Using Ensemble Learning Algorithms: A Comparative Study of Bagging, Boosting and Stacking Techniques. Remote Sens., 12.","DOI":"10.3390\/rs12101683"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3125","DOI":"10.1007\/s10994-020-05943-y","article-title":"Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-Task Network Study","volume":"111","author":"Saux","year":"2022","journal-title":"Mach. Learn."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cuypers, S., Nascetti, A., and Vergauwen, M. (2023). Land Use and Land Cover Mapping with VHR and Multi-Temporal Sentinel-2 Imagery. Remote Sens., 15.","DOI":"10.3390\/rs15102501"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Xie, G., and Niculescu, S. (2021). Mapping and Monitoring of Land Cover\/Land Use (LCLU) Changes in the Crozon Peninsula (Brittany, France) from 2007 to 2018 by Machine Learning Algorithms (Support Vector Machine, Random Forest, and Convolutional Neural Network) and by Post-classification Comparison (PCC). Remote Sens., 13.","DOI":"10.3390\/rs13193899"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez, A.-M.S., Gonz\u00e1lez-Piqueras, J., de la Ossa, L., and Calera, A. (2022). Convolutional Neural Networks for Agricultural Land Use Classification from Sentinel-2 Image Time Series. Remote Sens., 14.","DOI":"10.3390\/rs14215373"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"024525","DOI":"10.1117\/1.JRS.13.024525","article-title":"Deep convolutional neural networks for land-cover classification with Sentinel-2 images","volume":"13","author":"Kroupi","year":"2019","journal-title":"J. Appl. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MCAS.2006.1688199","article-title":"Ensemble based systems in decision making","volume":"6","author":"Polikar","year":"2006","journal-title":"IEEE Circuits Syst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhou, Z.H. (2012). Ensemble Methods: Foundations and Algorithms, CRC Press.","DOI":"10.1201\/b12207"},{"key":"ref_32","unstructured":"Qinghai Provincial Bureau of Statistics (2020). Qinghai Statistical Yearbook 2020, China Statistics Press."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Z., Cheng, Q., Duan, F., Sui, R., Huang, X., and Xu, H. (2022). UAV-Based Hyperspectral and Ensemble Machine Learning for Predicting Yield in Winter Wheat. Agronomy, 12.","DOI":"10.3390\/agronomy12010202"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1007\/s11442-014-1082-6","article-title":"Spatiotemporal characteristics, patterns, and causes of land-use changes in China since the late 1980s","volume":"24","author":"Liu","year":"2014","journal-title":"J. Geogr. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1109\/36.911126","article-title":"Enhanced algorithm performance for land cover classification from remotely sensed data using bagging and boosting","volume":"39","author":"Chan","year":"2001","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Ahn, J.M., Kim, J., and Kim, K. (2023). Ensemble Machine Learning of Gradient Boosting (XGBoost, LightGBM, CatBoost) and Attention-Based CNN-LSTM for Harmful Algal Blooms Forecasting. Toxins, 15.","DOI":"10.2139\/ssrn.4434784"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Van der Laan, M.J., Polley, E.C., and Hubbard, A.E. (2007). Super learner. Stat. Appl. Genet. Mol. Biol., 6.","DOI":"10.2202\/1544-6115.1309"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Shuai, S., Zhang, Z., Zhang, T., Luo, W., Tan, L., Duan, X., and Wu, J. (2024). Innovative Decision Fusion for Accurate Crop\/Vegetation Classification with Multiple Classifiers and Multisource Remote Sensing Data. Remote Sens., 16.","DOI":"10.3390\/rs16091579"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.1109\/TMI.2002.806569","article-title":"A Support Vector Machine Approach for Detection of Microcalcifications","volume":"21","author":"Yang","year":"2002","journal-title":"IEEE Trans. Med."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/34.683777","article-title":"Support Vector Machines for 3d Object Recognition","volume":"6","author":"Pontil","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Ren, J., Wang, R., Liu, G., Wang, Y., and Wu, W. (2021). An SVM-Based Nested Sliding Window Approach for Spectral-Spatial Classification of Hyperspectral Images. Remote Sens., 13.","DOI":"10.3390\/rs13010114"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1109\/72.991427","article-title":"A Comparison of Methods for Multiclass Support Vector Machines","volume":"13","author":"Hsu","year":"2002","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Chan, R.H., and Li, R. (2022). A 3-Stage Spectral-Spatial Method for Hyperspectral Image Classification. Remote Sens., 14.","DOI":"10.3390\/rs14163998"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Cheng, F., Ou, G., Wang, M., and Liu, C. (2024). Remote Sensing Estimation of Forest Carbon Stock Based on Machine Learning Algorithms. Forests, 15.","DOI":"10.3390\/f15040681"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Breiman, L., Friedman, J.H., and Olshen, R. (2017). Classification and Regression Trees, Routledge.","DOI":"10.1201\/9781315139470"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1016\/j.rse.2011.01.009","article-title":"Object-based crop identification using multiple vegetation indices, textural features and crop phenology","volume":"115","author":"Ngugi","year":"2011","journal-title":"Remote Sens. Environ."},{"key":"ref_47","first-page":"220","article-title":"Continuous field mapping of Mediterranean wetlands using sub-pixel spectral signatures and multi-temporal Landsat data","volume":"28","author":"Reschke","year":"2014","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/0034-4257(74)90033-9","article-title":"Combined spectral and spatial processing of ERTS imagery data","volume":"3","author":"Haralick","year":"1974","journal-title":"Remote Sens. Environ."},{"key":"ref_49","first-page":"1261","article-title":"Spatio-Temporal Reconstruction of MODIS NDVI by Regional Land Surface Phenology and Harmonic Analysis of Time-Series. GISci","volume":"56","author":"Padhee","year":"2019","journal-title":"Remote Sens."},{"key":"ref_50","first-page":"70","article-title":"A comparison of three feature selection methods for object-based classification of sub-decimeter resolution Ultra Cam-L imagery","volume":"15","author":"Laliberte","year":"2012","journal-title":"Int. J. Appl. Earth Obs."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.patrec.2008.08.010","article-title":"An experimental comparison of performance measures for classification","volume":"30","author":"Ferri","year":"2009","journal-title":"Pattern Recognit. Lett."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Wang, D., Huo, Z., Miao, P., and Tian, X. (2023). Comparison of Machine Learning Models to Predict Lake Area in an Arid Area. Remote Sens., 15.","DOI":"10.3390\/rs15174153"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Peppes, N., Daskalakis, E., Alexakis, T., Adamopoulou, E., and Demestichas, K. (2021). Performance of Machine Learning-Based Multi-Model Voting Ensemble Methods for Network Threat Detection in Agriculture 4.0. Sensors, 21.","DOI":"10.3390\/s21227475"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Kpienbaareh, D., Sun, X., Wang, J., Luginaah, I., Bezner Kerr, R., Lupafya, E., and Dakishoni, L. (2021). Crop Type and Land Cover Mapping in Northern Malawi Using the Integration of Sentinel-1, Sentinel-2, and PlanetScope Satellite Data. Remote Sens., 13.","DOI":"10.3390\/rs13040700"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Arrechea-Castillo, D.A., Solano-Correa, Y.T., Mu\u00f1oz-Ord\u00f3\u00f1ez, J.F., Pencue-Fierro, E.L., and Figueroa-Casas, A. (2023). Multiclass Land Use and Land Cover Classification of Andean Sub-Basins in Colombia with Sentinel-2 and Deep Learning. Remote Sens., 15.","DOI":"10.1117\/12.2664340"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Cheng, K., and Scott, G.J. (2023). Deep Seasonal Network for Remote Sensing Imagery Classification of Multi-Temporal Sentinel-2 Data. Remote Sens., 15.","DOI":"10.3390\/rs15194705"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1016\/j.rse.2005.08.011","article-title":"On the relationship between training sample size and data dimensionality: Monte Carlo analysis of broadband multi-temporal classification","volume":"98","author":"Vanniel","year":"2005","journal-title":"Remote Sens. Environ."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Ajibola, S., and Cabral, P. (2024). A Systematic Literature Review and Bibliometric Analysis of Semantic Segmentation Models in Land Cover Mapping. Remote Sens., 16.","DOI":"10.3390\/rs16122222"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Nasiri, V., Darvishsefat, A.A., Arefi, H., Griess, V.C., Sadeghi, S.M., and Borz, S.A. (2022). Modeling Forest Canopy Cover: A Synergistic Use of Sentinel-2, Aerial Photogrammetry Data, and Machine Learning. Remote Sens., 14.","DOI":"10.3390\/rs14061453"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/14\/2556\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:15:45Z","timestamp":1760109345000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/14\/2556"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,12]]},"references-count":59,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["rs16142556"],"URL":"https:\/\/doi.org\/10.3390\/rs16142556","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,12]]}}}