{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T04:27:32Z","timestamp":1772252852907,"version":"3.50.1"},"reference-count":54,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T00:00:00Z","timestamp":1675641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005416","name":"Research Council of Norway and several partners","doi-asserted-by":"publisher","award":["237859"],"award-info":[{"award-number":["237859"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005416","name":"Research Council of Norway and several partners","doi-asserted-by":"publisher","award":["GBV 2020 & 2021"],"award-info":[{"award-number":["GBV 2020 & 2021"]}],"id":[{"id":"10.13039\/501100005416","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Norwegian Geotechnical Institute","award":["237859"],"award-info":[{"award-number":["237859"]}]},{"name":"Norwegian Geotechnical Institute","award":["GBV 2020 & 2021"],"award-info":[{"award-number":["GBV 2020 & 2021"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Landslide risk mitigation is limited by data scarcity; however, this could be improved using continuous landslide detection systems. To investigate which image types and machine learning models are most useful for landslide detection in a Norwegian setting, we compared the performance of five different machine learning models, for the J\u00f8lster case study (30 July 2019), in Western Norway. These included three globally pre-trained models; (i) the continuous change detection and classification (CCDC) algorithm, (ii) a combined k-means clustering and random forest classification model, and (iii) a convolutional neural network (CNN), and two locally trained models, including; (iv) classification and regression Trees and (v) a U-net CNN model. Images used included Sentinel-1, Sentinel-2, as well as digital elevation model (DEM) and slope. The globally trained models performed poorly in shadowed areas and were all outperformed by the locally trained models. A maximum Matthew\u2019s correlation coefficient (MCC) score of 89% was achieved with a CNN U-net deep learning model, using combined Sentinel-1 and -2 images as input. This is one of the first attempts to apply deep learning to detect landslides with both Sentinel-1 and -2 images. Using Sentinel-1 images only, the locally-trained deep-learning model significantly outperformed the conventional machine learning model. These findings contribute to developing a national continuous monitoring system for landslides.<\/jats:p>","DOI":"10.3390\/rs15040895","type":"journal-article","created":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T02:56:08Z","timestamp":1675738568000},"page":"895","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Globally vs. Locally Trained Machine Learning Models for Landslide Detection: A Case Study of a Glacial Landscape"],"prefix":"10.3390","volume":"15","author":[{"given":"Alexandra Jarna","family":"Ganer\u00f8d","sequence":"first","affiliation":[{"name":"Department of Geography, Norwegian University of Science and Technology, 7049 Trondheim, Norway"},{"name":"Geological Survey of Norway (NGU), 7040 Trondheim, Norway"}]},{"given":"Erin","family":"Lindsay","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Norwegian University of Science and Technology, 7034 Trondheim, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0803-3312","authenticated-orcid":false,"given":"Ola","family":"Fredin","sequence":"additional","affiliation":[{"name":"Department of Geoscience and Petroleum, Norwegian University of Science and Technology, 7034 Trondheim, Norway"}]},{"given":"Tor-Andre","family":"Myrvoll","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Norwegian University of Science and Technology, 7034 Trondheim, Norway"}]},{"given":"Steinar","family":"Nordal","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Norwegian University of Science and Technology, 7034 Trondheim, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2935-6206","authenticated-orcid":false,"given":"Jan Ketil","family":"R\u00f8d","sequence":"additional","affiliation":[{"name":"Department of Geography, Norwegian University of Science and Technology, 7049 Trondheim, Norway"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,6]]},"reference":[{"key":"ref_1","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_2","doi-asserted-by":"crossref","first-page":"1197","DOI":"10.1007\/s11069-022-05423-7","article-title":"Machine learning and landslide studies: Recent advances and applications","volume":"114","author":"Tehrani","year":"2022","journal-title":"Nat. Hazards"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"24005","DOI":"10.1088\/1748-9326\/abd0a8","article-title":"Forest disturbance alerts for the Congo Basin using Sentinel-1","volume":"16","author":"Reiche","year":"2021","journal-title":"Environ. Res. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"34008","DOI":"10.1088\/1748-9326\/11\/3\/034008","article-title":"Humid tropical forest disturbance alerts using Landsat data","volume":"11","author":"Hansen","year":"2016","journal-title":"Environ. Res. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"121002","DOI":"10.1088\/2515-7620\/ab4ec3","article-title":"Early warning tropical forest loss alerts in Peru using Landsat","volume":"1","author":"Vargas","year":"2019","journal-title":"Environ. Res. Commun."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Katiyar, V., Tamkuan, N., and Nagai, M. (2021). Near-real-time flood mapping using off-the-shelf models with SAR imagery and deep learning. Remote Sens., 13.","DOI":"10.3390\/rs13122334"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1038\/s41598-019-56967-x","article-title":"Near real-time wildfire progression monitoring with Sentinel-1 SAR time series and deep learning","volume":"10","author":"Ban","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"112467","DOI":"10.1016\/j.rse.2021.112467","article-title":"Learning U-Net without forgetting for near real-time wildfire monitoring by the fusion of SAR and optical time series","volume":"261","author":"Zhang","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_9","unstructured":"Devoli, G., Bell, R., and Cepeda, J. (2019). Susceptibility Map at Catchment Level, to Be Used in Landslide Forecasting, Norwegian Water Resources and Energy Directorate."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.rse.2014.01.011","article-title":"Continuous change detection and classification of land cover using all available Landsat data","volume":"144","author":"Zhu","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"576740","DOI":"10.3389\/fclim.2020.576740","article-title":"A Suite of Tools for Continuous Land Change Monitoring in Google Earth Engine","volume":"2","author":"Bullock","year":"2020","journal-title":"Front. Clim."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"9722","DOI":"10.1038\/s41598-021-89015-8","article-title":"A new strategy to map landslides with a generalized convolutional neural network","volume":"11","author":"Prakash","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ghorbanzadeh, O., Gholamnia, K., and Ghamisi, P. (2022). The application of ResU-net and OBIA for landslide detection from multi-temporal sentinel-2 images. Big Earth Data, 1\u201326.","DOI":"10.1080\/20964471.2022.2031544"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Nava, L., Bhuyan, K., Meena, S.R., Monserrat, O., and Catani, F. (2022, January 23\u201327). Assessment of deep learning based landslide detection and mapping performances with backscatter SAR data. Proceedings of the EGU General Assembly 2022, Vienna, Austria.","DOI":"10.5194\/egusphere-egu22-10072"},{"key":"ref_15","unstructured":"Bai, L., Li, W., Xu, Q., Peng, W., Chen, K., Duan, Z., and Lu, H. (2022, January 25). Multispectral U-Net: A Semantic Segmentation Model Using Multispectral Bands Fusion Mechanism for Landslide Detection. Proceedings of the 2nd Workshop on Complex Data Challenges in Earth Observation, Vienna, Austria."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Dong, Z., An, S., Zhang, J., Yu, J., Li, J., and Xu, D. (2022). L-Unet: A Landslide Extraction Model Using Multi-Scale Feature Fusion and Attention Mechanism. Remote Sens., 14.","DOI":"10.3390\/rs14112552"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Fang, C., Fan, X., Zhong, H., Lombardo, L., Tanyas, H., and Wang, X. (2022). A Novel historical landslide detection approach based on LiDAR and lightweight attention U-Net. Remote Sens., 14.","DOI":"10.3390\/rs14174357"},{"key":"ref_18","first-page":"1","article-title":"Improving Landslide Detection on SAR Data through Deep Learning","volume":"19","author":"Nava","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_19","first-page":"94","article-title":"Detection of Landslide Candidate Interference Fringes in DInSAR Imagery Using Deep Learning","volume":"90","author":"Kamiyama","year":"2018","journal-title":"Recall"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103574","DOI":"10.1016\/j.earscirev.2021.103574","article-title":"Landslide failures detection and mapping using Synthetic Aperture Radar: Past, present and future","volume":"216","author":"Mondini","year":"2021","journal-title":"Earth Sci. Rev."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"113043","DOI":"10.1016\/j.rse.2022.113043","article-title":"Timeliness in forest change monitoring: A new assessment framework demonstrated using Sentinel-1 and a continuous change detection algorithm","volume":"276","author":"Bullock","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Doblas, J., Reis, M.S., Belluzzo, A.P., Quadros, C.B., Moraes, D.R.V., Almeida, C.A., Maurano, L.E.P., Carvalho, A.F.A., Sant\u2019Anna, S.J.S., and Shimabukuro, Y.E. (2022). DETER-R: An operational near-real time tropical forest disturbance warning system based on Sentinel-1 time series analysis. Remote Sens., 14.","DOI":"10.3390\/rs14153658"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shumilo, L., Kussul, N., and Lavreniuk, M. (2021, January 11\u201316). U-Net Model for Logging Detection Based on the Sentinel-1 and Sentinel-2 Data. Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium.","DOI":"10.1109\/IGARSS47720.2021.9554885"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1007\/s11069-009-9401-4","article-title":"A global landslide catalog for hazard applications: Method, results, and limitations","volume":"52","author":"Kirschbaum","year":"2010","journal-title":"Nat. Hazards"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J. (2017). Classification and Regression Trees, Routledge.","DOI":"10.1201\/9781315139470"},{"key":"ref_26","unstructured":"(2022, December 21). NGU Landslides. Available online: https:\/\/www.ngu.no\/en\/topic\/landslides."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/j.earscirev.2016.08.011","article-title":"Earth-Science Reviews Landslides in a changing climate","volume":"162","author":"Luigi","year":"2016","journal-title":"Earth Sci. Rev."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1007\/s10346-017-0902-z","article-title":"Landslide databases in the Geological Surveys of Europe","volume":"15","author":"Herrera","year":"2018","journal-title":"Landslides"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"469","DOI":"10.5194\/nhess-9-469-2009","article-title":"Integrated database for rapid mass movements in Norway","volume":"9","author":"Jaedicke","year":"2009","journal-title":"Nat. Hazards Earth Syst. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Malamud, B.D., Heijenk, R.A., Taylor, F.E., and Wood, J.L. (2022, January 23\u201327). Road Influences on Landslide Inventories. Proceedings of the EGU General Assembly 2022, Vienna, Austria.","DOI":"10.5194\/egusphere-egu22-7616"},{"key":"ref_31","first-page":"202212","article-title":"Extreme precipitation-induced landslide event on 30th 3 July 2019 in J\u00f8lster, western Norway","volume":"102","author":"Ruther","year":"2022","journal-title":"Nor. J. Geol."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Lindsay, E., Frauenfelder, R., R\u00fcther, D., Nava, L., Rubensdotter, L., Strout, J., and Nordal, S. (2022). Multi-Temporal Satellite Image Composites in Google Earth Engine for Improved Landslide Visibility: A Case Study of a Glacial Landscape. Remote Sens., 14.","DOI":"10.3390\/rs14102301"},{"key":"ref_33","unstructured":"Meteorologisk Institutt (2019). Rapport om Intense Byger med store Konsekvenser i Sogn og Fjordane 30. juli, Meteorologic Institute. Available online: https:\/\/www.met.no\/nyhetsarkiv\/rapport-om-intense-byger-med-store-konsekvenser-i-sogn-og-fjordane-30.juli."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Casagli, N., Tofani, V., Sassa, K., Bobrowsky, P.T., and Takara, K. (2021). Understanding and Reducing Landslide Disaster Risk: Volume 3 Monitoring and Early Warning, Springer International Publishing.","DOI":"10.1007\/978-3-030-60311-3"},{"key":"ref_35","unstructured":"Hanssen-Bauer, I., Drange, H., F\u00f8rland, E.J., Roald, L.A., B\u00f8rsheim, K.Y., Hisdal, H., Lawrence, D., Nesje, A., Sandven, S., and Sorteberg, A. (2022, December 22). Climate in Norway 2100. Available online: https:\/\/www.researchgate.net\/profile\/Ingjerd-Haddeland\/publication\/316922280_Climate_in_Norway_2100\/links\/59194fab4585152e19a24c98\/Climate-in-Norway-2100.pdf."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1080\/19475705.2021.1912196","article-title":"Multi-Regional landslide detection using combined unsupervised and supervised machine learning","volume":"12","author":"Tehrani","year":"2021","journal-title":"Geomat. Nat. Hazards Risk"},{"key":"ref_37","unstructured":"Herrera Herrera, M. (2019). Landslide Detection Using Random Forest Classifier, Delft University of Technology."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.cageo.2013.03.025","article-title":"The KEA image file format","volume":"57","author":"Bunting","year":"2013","journal-title":"Comput. Geosci."},{"key":"ref_39","unstructured":"Braaten, J. (2022, December 22). Sentinel-2 Cloud Masking with s2cloudless. Available online: https:\/\/developers.google.com\/earth-engine\/tutorials\/community\/sentinel-2-s2cloudless."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Vollrath, A., Mullissa, A., and Reiche, J. (2020). Angular-Based Radiometric Slope Correction for Sentinel-1 on Google Earth Engine. Remote Sens., 12.","DOI":"10.3390\/rs12111867"},{"key":"ref_41","first-page":"329","article-title":"Lab 4-Image Classification-part 1","volume":"9","author":"Levick","year":"2017","journal-title":"Remote Sens."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","article-title":"Fully Convolutional Networks for Semantic Segmentation","volume":"39","author":"Shelhamer","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2545","DOI":"10.1109\/TIFS.2017.2710946","article-title":"Deep Learning Hierarchical Representations for Image Steganalysis","volume":"12","author":"Ye","year":"2017","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_45","unstructured":"Huang, S.-C., and Le, T.-H. (2021). Principles and Labs for Deep Learning, Elsevier."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"062032","DOI":"10.1088\/1742-6596\/1087\/6\/062032","article-title":"Feature Extraction and Image Recognition with Convolutional Neural Networks","volume":"1087","author":"Liu","year":"2018","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_47","unstructured":"(2022, December 22). ArcGIS Pro Export Training Data For Deep Learning (Image Analyst). Available online: https:\/\/pro.arcgis.com\/en\/pro-app\/latest\/tool-reference\/image-analyst\/export-training-data-for-deep-learning.htm."},{"key":"ref_48","unstructured":"Lindsay, E., Devoli, G., Reiches, J., and Nordal, S. (2023). In Progress: Spatial and Temporal Signatures of Landslides in C-Band SAR Data."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Chicco, D., and Jurman, G. (2020). The Advantages of the Matthews Correlation Coefficient (MCC) over F1 Score and Accuracy in Binary Classification Evaluation, Springer.","DOI":"10.1186\/s12864-019-6413-7"},{"key":"ref_50","first-page":"28","article-title":"MPC-Team Terrain over-correction on shaded areas","volume":"Volume 45","author":"Clerc","year":"2022","journal-title":"S2 MPC Level 2A Data Quality Report"},{"key":"ref_51","unstructured":"Jackson, J. (2022, December 22). Clarification on Difference between L1C and L2A Data. Available online: https:\/\/forum.step.esa.int\/t\/clarification-on-difference-between-l1c-and-l2a-data\/24940\/12."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Ghorbanzadeh, O., Blaschke, T., Gholamnia, K., Meena, S.R., 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_53","doi-asserted-by":"crossref","unstructured":"Prakash, N., 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_54","unstructured":"(2022, December 22). NASA Quick Facts, Available online: https:\/\/nisar.jpl.nasa.gov\/mission\/quick-facts\/."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/4\/895\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:25:42Z","timestamp":1760120742000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/4\/895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,6]]},"references-count":54,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["rs15040895"],"URL":"https:\/\/doi.org\/10.3390\/rs15040895","relation":{"has-preprint":[{"id-type":"doi","id":"10.20944\/preprints202301.0231.v1","asserted-by":"object"}]},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,6]]}}}