{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T09:36:50Z","timestamp":1769852210008,"version":"3.49.0"},"reference-count":47,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2021,7,31]],"date-time":"2021-07-31T00:00:00Z","timestamp":1627689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of China","award":["No. 41772352"],"award-info":[{"award-number":["No. 41772352"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Landslide inventories could provide fundamental data for analyzing the causative factors and deformation mechanisms of landslide events. Considering that it is still hard to detect landslides automatically from remote sensing images, endeavors have been carried out to explore the potential of DCNNs on landslide detection, and obtained better performance than shallow machine learning methods. However, there is often confusion as to which structure, layer number, and sample size are better for a project. To fill this gap, this study conducted a comparative test on typical models for landside detection in the Wenchuan earthquake area, where about 200,000 secondary landslides were available. Multiple structures and layer numbers, including VGG16, VGG19, ResNet50, ResNet101, DenseNet120, DenseNet201, UNet\u2212, UNet+, and ResUNet were investigated with different sample numbers (100, 1000, and 10,000). Results indicate that VGG models have the highest precision (about 0.9) but the lowest recall (below 0.76); ResNet models display the lowest precision (below 0.86) and a high recall (about 0.85); DenseNet models obtain moderate precision (below 0.88) and recall (about 0.8); while UNet+ also achieves moderate precision (0.8) and recall (0.84). Generally, a larger sample set can lead to better performance for VGG, ResNet, and DenseNet, and deeper layers could improve the detection results for ResNet and DenseNet. This study provides valuable clues for designing models\u2019 type, layers, and sample set, based on tests with a large number of samples.<\/jats:p>","DOI":"10.3390\/s21155191","type":"journal-article","created":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T21:44:32Z","timestamp":1627854272000},"page":"5191","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Valuable Clues for DCNN-Based Landslide Detection from a Comparative Assessment in the Wenchuan Earthquake Area"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5229-8158","authenticated-orcid":false,"given":"Chang","family":"Li","sequence":"first","affiliation":[{"name":"Three Gorges Research Center for Geo-Hazard, Ministry of Education, China University of Geosciences, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bangjin","family":"Yi","sequence":"additional","affiliation":[{"name":"Yunnan Institute of Geological Science, Kuming 650051, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Earth and Ocean Sciences, University of North Carolina, Wilmington, NC 28403, USA"},{"name":"Department of Geography, University of South Carolina, 709 Bull St., Columbia, SC 29208, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Earth Sciences, China University of Geosciences, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jixing","family":"Sun","sequence":"additional","affiliation":[{"name":"Yunnan Institute of Geological Science, Kuming 650051, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueye","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Urban Land Resources Monitoring and Simulation, MNR, Shenzhen 518034, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Three Gorges Research Center for Geo-Hazard, Ministry of Education, China University of Geosciences, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,7,31]]},"reference":[{"key":"ref_1","unstructured":"China Geological Survey (2021, May 22). National Geological Disasters Bulletin, Available online: https:\/\/www.cgs.gov.cn\/."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/s10346-013-0400-x","article-title":"Delineating and defining the boundaries of an active landslide in the rainforest of Puerto Rico using a combination of airborne and terrestrial lidar data","volume":"10","author":"Wang","year":"2013","journal-title":"Landslides"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40677-014-0006-1","article-title":"Support vector machine modeling of earthquake-induced landslides susceptibility in Central Part of Sichuan Province China","volume":"2","author":"Zhou","year":"2015","journal-title":"Geoenviron. Disasters"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.5194\/nhess-17-1159-2017","article-title":"Prediction of the area affected by earthquake-induced landsliding based on seismological parameters","volume":"17","author":"Marc","year":"2017","journal-title":"Nat. Hazards Eatrh Syst. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.earscirev.2012.02.001","article-title":"Landslide inventory maps: New tools for an old problem","volume":"112","author":"Guzzetti","year":"2012","journal-title":"Earth Sci. Rev."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1080\/01431161.2019.1672904","article-title":"Landslide mapping with remote sensing: Challenges and opportunities","volume":"41","author":"Zhong","year":"2020","journal-title":"Int. J. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"8026","DOI":"10.3390\/rs6098026","article-title":"Automated spatiotemporal landslide mapping over large areas using RapidEye time series data","volume":"6","author":"Behling","year":"2014","journal-title":"Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ramos-Berna, R., V\u00e1zquez-Jim\u00e9nez, R., Romero-Calcerrada, R., Arrogante-Funes, P., and Novillo, C. (2018). Evaluation of unsupervised change detection methods applied to landslide inventory mapping using ASTER imagery. Remote Sens., 10.","DOI":"10.3390\/rs10121987"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3741","DOI":"10.1080\/01431161.2014.915438","article-title":"Semi-automatic approach for identifying locations of shallow debrisslides\/flows based on lidar-derived morphological features","volume":"35","author":"Deng","year":"2014","journal-title":"Int. J. Remote Sens."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.cageo.2014.10.007","article-title":"Contour connection method for automated identification and classification of landslide deposits","volume":"74","author":"Leshchinsky","year":"2015","journal-title":"Comput. Geosci."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.1007\/s10346-015-0660-8","article-title":"Detection of geohazards in the Bailong river basin using synthetic aperture radar interferometry","volume":"13","author":"Zhang","year":"2016","journal-title":"Landslides"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1080\/01431160512331330481","article-title":"Remote Sensing image thresholding methods for determining landslide activity","volume":"26","author":"Rosin","year":"2005","journal-title":"Int. J. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.cageo.2016.12.007","article-title":"A new technique for landslide mapping from a large-scale remote sensed image: A case study of central Nepal","volume":"100","author":"Yu","year":"2017","journal-title":"Comput. Geosci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.rse.2016.10.008","article-title":"Landslide mapping from aerial photographs using change detection-based Markov random field","volume":"187","author":"Li","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1758","DOI":"10.1109\/JSTARS.2017.2661802","article-title":"Postearthquake landslides mapping from landsat-8 data for the 2015 Nepal earthquake using a pixel-based change detection method","volume":"10","author":"Zhao","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhong, C., Wang, C., Li, H., Chen, W., and Hou, Y. (2018). Mapping inter-annual land cover variations automatically based on a novel sample transfer method. Remote Sens., 10.","DOI":"10.3390\/rs10091457"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1038\/ngeo1154","article-title":"Mass wasting triggered by the 2008 Wenchuan earthquake is greater than orogenic growth","volume":"4","author":"Parker","year":"2011","journal-title":"Nat. Geosci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1080\/19475705.2014.898702","article-title":"Rule-based semi-automated approach for the detection of landslides induced by 18 September 2011 Sikkim Himalaya earthquake using IRS LISS3 satellite images","volume":"7","author":"Siyahghalati","year":"2016","journal-title":"Geomat. Nat. Hazards Risk"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1029","DOI":"10.3390\/rs10071029","article-title":"Improving landslide detection from airborne laser scanning data using optimized dempster\u2013shafer","volume":"10","author":"Mustafa","year":"2018","journal-title":"Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.rse.2016.10.006","article-title":"Detecting seasonal landslide movement within the cascade landslide complex (Washington) using time-series SAR imagery","volume":"187","author":"Hu","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2915","DOI":"10.1007\/s11629-020-6080-9","article-title":"Rapid identification of landslide collapse and crack based on low-altitude remote sensing image of UAV","volume":"17","author":"Lian","year":"2020","journal-title":"J. Mt. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A fast learning algorithm for deep belief nets","volume":"18","author":"Geoffrey","year":"2006","journal-title":"Neural Comput."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large-scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"111425","DOI":"10.1016\/j.rse.2019.111425","article-title":"Deep learning-based fusion of landsat-8 and sentinel-2 images for a harmonized surface reflectance product","volume":"235","author":"Shao","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhang, R., Shao, Z., Huang, X., Wang, J., and Li, D. (2020). Object detection in UAV images via global density fused convolutional network. Remote Sens., 12.","DOI":"10.3390\/rs12193140"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e3998","DOI":"10.1002\/ett.3998","article-title":"Review on remote sensing methods for landslide detection using machine and deep learning","volume":"32","author":"Mohan","year":"2020","journal-title":"Trans. Emerg. Telecommun. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ghorbanzadeh, O., Meena, S.R., Blaschke, T., and Aryal, J. (2019). UAV-based slope failure detection using deep-learning convolutional neural networks. Remote Sens., 11.","DOI":"10.3390\/rs11172046"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ghorbanzadeh, O., Blaschke, T., Gholamnia, K., Sansar, R.M., Tiede, D., and Aryal, J. (2019). Evaluation of different machine learning methods and deep-learning convolutional neural networks for landslide detection. Remote Sens., 11.","DOI":"10.3390\/rs11020196"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"114363","DOI":"10.1109\/ACCESS.2019.2935761","article-title":"Landslide detection using residual networks and the fusion of spectral and topographic information","volume":"7","author":"Sameen","year":"2019","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.1007\/s10346-020-01353-2","article-title":"Landslide detection from an open satellite imagery and digital elevation model dataset using attention boosted convolutional neural networks","volume":"17","author":"Ji","year":"2020","journal-title":"Landslides"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Prakash, I., Manconi, A., and Loew, S. (2020). Mapping landslides on EO data: Performance of deep learning models vs. traditional machine learning models. Remote Sens., 12.","DOI":"10.5194\/egusphere-egu2020-11876"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"6166","DOI":"10.1109\/JSTARS.2020.3028855","article-title":"A new deep-learning-based approach for earthquake-triggered landslide detection from single-temporal RapidEye satellite imagery","volume":"13","author":"Yi","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4654","DOI":"10.1109\/TGRS.2020.3015826","article-title":"Landslide recognition by deep convolutional neural network and change detection","volume":"59","author":"Shi","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3799","DOI":"10.1109\/JSTARS.2021.3064981","article-title":"A new mask R-CNN-based method for improved landslide detection","volume":"14","author":"Ullo","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"2611","DOI":"10.1002\/esp.4210","article-title":"Perturbation of fluvial sediment fluxes following the 2008 Wenchuan earthquake: Fluvial sediment fluxes following large-magnitude earthquake","volume":"42","author":"Wang","year":"2017","journal-title":"Earth Surf. Process. Landf."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1016\/j.gsf.2014.03.004","article-title":"Preparation of earthquake-triggered landslide inventory maps using remote sensing and GIS technologies: Principles and case studies","volume":"6","author":"Xu","year":"2015","journal-title":"Geosci. Front."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2325","DOI":"10.1007\/s10346-018-1054-5","article-title":"Spatio-temporal evolution of mass wasting after the 2008 mw 7.9 Wenchuan earthquake revealed by a detailed multi-temporal inventory","volume":"15","author":"Fan","year":"2018","journal-title":"Landslides"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"35","DOI":"10.5194\/essd-11-35-2019","article-title":"Two multi-temporal datasets that track the enhanced landsliding after the 2008 Wenchuan earthquake","volume":"11","author":"Fan","year":"2019","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_39","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"1","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst. NIPS"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhang, L., Shao, Z., Liu, J., and Cheng, Q. (2019). Deep learning-based retrieval of forest aboveground biomass from combined lidar and Landsat 8 data. Remote Sens., 11.","DOI":"10.3390\/rs11121459"},{"key":"ref_41","unstructured":"He, L., Zhang, X., Ren, S., and Sun, J. (2020). Deep Residual learning for image recognition. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Gao, H., Zhuang, L., and Weinberger, L. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the CVPR 2017, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/JSTARS.2019.2961634","article-title":"Multilabel remote sensing image retrieval based on fully convolutional network","volume":"13","author":"Shao","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-Net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_45","unstructured":"Lucas, S., Helen, D., and Carlos, G. (2020). Landslide segmentation with U-Net: Evaluating different sampling methods and patch sizes. arXiv."},{"key":"ref_46","first-page":"674","article-title":"Remote sensing research on Daguangbao gigantic rock-Slide triggered by Wenchuan earthquake","volume":"19","author":"Yin","year":"2011","journal-title":"Q. J. Eng. Geol. Hydrogeol."},{"key":"ref_47","unstructured":"Simonyan, K., and Zisserman, A. (2020). Very deep convolutional networks for large-scale image recognition. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/15\/5191\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:38:02Z","timestamp":1760164682000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/15\/5191"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,31]]},"references-count":47,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["s21155191"],"URL":"https:\/\/doi.org\/10.3390\/s21155191","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,31]]}}}