{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T21:00:53Z","timestamp":1767992453939,"version":"3.49.0"},"reference-count":52,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2020,7,19]],"date-time":"2020-07-19T00:00:00Z","timestamp":1595116800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["ERA-MIN\/0001\/2017"],"award-info":[{"award-number":["ERA-MIN\/0001\/2017"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDB\/04683\/2020"],"award-info":[{"award-number":["UIDB\/04683\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["SFRH\/BD\/136108\/2018"],"award-info":[{"award-number":["SFRH\/BD\/136108\/2018"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014440","name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","award":["RTI2018-094097-B-100"],"award-info":[{"award-number":["RTI2018-094097-B-100"]}],"id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003451","name":"Euskal Herriko Unibertsitatea","doi-asserted-by":"publisher","award":["GIU18\/084"],"award-info":[{"award-number":["GIU18\/084"]}],"id":[{"id":"10.13039\/501100003451","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Machine learning (ML) algorithms have shown great performance in geological remote sensing applications. The study area of this work was the Fregeneda\u2013Almendra region (Spain\u2013Portugal) where the support vector machine (SVM) was employed. Lithium (Li)-pegmatite exploration using satellite data presents some challenges since pegmatites are, by nature, small, narrow bodies. Consequently, the following objectives were defined: (i) train several SVM\u2019s on Sentinel-2 images with different parameters to find the optimal model; (ii) assess the impact of imbalanced data; (iii) develop a successful methodological approach to delineate target areas for Li-exploration. Parameter optimization and model evaluation was accomplished by a two-staged grid-search with cross-validation. Several new methodological advances were proposed, including a region of interest (ROI)-based splitting strategy to create the training and test subsets, a semi-automatization of the classification process, and the application of a more innovative and adequate metric score to choose the best model. The proposed methodology obtained good results, identifying known Li-pegmatite occurrences as well as other target areas for Li-exploration. Also, the results showed that the class imbalance had a negative impact on the SVM performance since known Li-pegmatite occurrences were not identified. The potentials and limitations of the methodology proposed are highlighted and its applicability to other case studies is discussed.<\/jats:p>","DOI":"10.3390\/rs12142319","type":"journal-article","created":{"date-parts":[[2020,7,20]],"date-time":"2020-07-20T10:59:38Z","timestamp":1595242778000},"page":"2319","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":80,"title":["Semi-Automatization of Support Vector Machines to Map Lithium (Li) Bearing Pegmatites"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8265-3897","authenticated-orcid":false,"given":"Joana","family":"Cardoso-Fernandes","sequence":"first","affiliation":[{"name":"Department of Geosciences, Environment and Land Planning, Faculty of Sciences, University of Porto, Rua Campo Alegre, 4169-007 Porto, Portugal"},{"name":"Institute of Earth Sciences (ICT), Pole of University of Porto, 4169-007 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8043-6431","authenticated-orcid":false,"given":"Ana C.","family":"Teodoro","sequence":"additional","affiliation":[{"name":"Department of Geosciences, Environment and Land Planning, Faculty of Sciences, University of Porto, Rua Campo Alegre, 4169-007 Porto, Portugal"},{"name":"Institute of Earth Sciences (ICT), Pole of University of Porto, 4169-007 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6598-5934","authenticated-orcid":false,"given":"Alexandre","family":"Lima","sequence":"additional","affiliation":[{"name":"Department of Geosciences, Environment and Land Planning, Faculty of Sciences, University of Porto, Rua Campo Alegre, 4169-007 Porto, Portugal"},{"name":"Institute of Earth Sciences (ICT), Pole of University of Porto, 4169-007 Porto, Portugal"}]},{"given":"Encarnaci\u00f3n","family":"Roda-Robles","sequence":"additional","affiliation":[{"name":"Departamento de Mineralog\u00eda y Petrolog\u00eda, University of Pa\u00eds Vasco (UPV\/EHU), Barrio Sarriena, Leioa, 48940 Bilbao, Spain"}]}],"member":"1968","published-online":{"date-parts":[[2020,7,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Cardoso-Fernandes, J., Teodoro, A.C., and Lima, A. (2018, January 10\u201313). Potential of Sentinel-2 data in the detection of lithium (Li)-bearing pegmatites: A study case. Proceedings of the SPIE Remote Sensing, Berlin, Germany.","DOI":"10.1117\/12.2326285"},{"key":"ref_2","first-page":"10","article-title":"Remote sensing data in lithium (Li) exploration: A new approach for the detection of Li-bearing pegmatites","volume":"76","author":"Teodoro","year":"2019","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_3","unstructured":"Perrotta, M.M., Souza Filho, C.R., and Leite, C.A.S. (2005, January 16\u201321). Mapeamento espectral de intrus\u00f5es pegmat\u00edticas relacionadas a mineraliza\u00e7\u00f5es de l\u00edtio, gemas e minerais industriais na regi\u00e3o do vale do Jequitinhonha (MG) a partir de imagens ASTER. Proceedings of the Anais do XII Simp\u00f3sio Brasileiro de Sensoriamento Remoto, Goi\u00e2nia, Brazil."},{"key":"ref_4","unstructured":"Mendes, D., Perrotta, M.M., Costa, M.A.C., and Paes, V.J.C. (2017, January 28\u201329). Mapeamento espectral para identifica\u00e7\u00e3o de assinaturas espectrais de minerais de l\u00edtio em imagens ASTER (NE\/MG). Proceedings of the Anais do XVIII Simp\u00f3sio Brasileiro de Sensoriamento Remoto, Santos-SP, Brazil."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Cardoso-Fernandes, J., Teodoro, A.C., Lima, A., and Roda-Robles, E. (2019, January 9\u201312). Evaluating the performance of support vector machines (SVMs) and random forest (RF) in Li-pegmatite mapping: Preliminary results. Proceedings of the SPIE Remote Sensing, Strasbourg, France.","DOI":"10.1117\/12.2532577"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Santos, D., Teodoro, A., Lima, A., and Cardoso-Fernandes, J. (2019, January 9\u201312). Remote sensing techniques to detect areas with potential for lithium exploration in Minas Gerais, Brazil. Proceedings of the SPIE Remote Sensing, Strasbourg, France.","DOI":"10.1117\/12.2532744"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cardoso-Fernandes, J., Teodoro, A.C., Lima, A., Perrotta, M., and Roda-Robles, E. (2020). Detecting Lithium (Li) Mineralizations from Space: Current Research and Future Perspectives. Appl. Sci., 10.","DOI":"10.3390\/app10051785"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/j.cageo.2011.11.019","article-title":"Towards automatic lithological classification from remote sensing data using support vector machines","volume":"45","author":"Yu","year":"2012","journal-title":"Comput. Geosci."},{"key":"ref_9","first-page":"377","article-title":"Regolith-geology mapping with support vector machine: A case study over weathered Ni-bearing peridotites, New Caledonia","volume":"64","author":"Sevin","year":"2018","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6867","DOI":"10.3390\/rs6086867","article-title":"Improving Lithological Mapping by SVM Classification of Spectral and Morphological Features: The Discovery of a New Chromite Body in the Mawat Ophiolite Complex (Kurdistan, NE Iraq)","volume":"6","author":"Othman","year":"2014","journal-title":"Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Latifovic, R., Pouliot, D., and Campbell, J. (2018). Assessment of Convolution Neural Networks for Surficial Geology Mapping in the South Rae Geological Region, Northwest Territories, Canada. Remote Sens., 10.","DOI":"10.3390\/rs10020307"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1007\/s12517-016-2791-1","article-title":"PCA and SVM as geo-computational methods for geological mapping in the southern of Tunisia, using ASTER remote sensing data set","volume":"9","author":"Gasmi","year":"2016","journal-title":"Arab. J. Geosci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1967","DOI":"10.1016\/j.cageo.2010.09.014","article-title":"Support vector machine: A tool for mapping mineral prospectivity","volume":"37","author":"Zuo","year":"2011","journal-title":"Comput. Geosci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.cageo.2011.12.014","article-title":"Support vector machine for multi-classification of mineral prospectivity areas","volume":"46","author":"Abedi","year":"2012","journal-title":"Comput. Geosci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1016\/j.oregeorev.2015.01.001","article-title":"Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines","volume":"71","year":"2015","journal-title":"Ore Geol. Rev."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/s11053-015-9271-2","article-title":"Application of Discriminant Analysis and Support Vector Machine in Mapping Gold Potential Areas for Further Drilling in the Sari-Gunay Gold Deposit, NW Iran","volume":"25","author":"Geranian","year":"2016","journal-title":"Nat. Resour. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.isprsjprs.2010.11.001","article-title":"Support vector machines in remote sensing: A review","volume":"66","author":"Mountrakis","year":"2011","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2784","DOI":"10.1080\/01431161.2018.1433343","article-title":"Implementation of machine-learning classification in remote sensing: An applied review","volume":"39","author":"Maxwell","year":"2018","journal-title":"Int. J. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Noi, P.T., and Kappas, M. (2017). Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery. Sensors, 18.","DOI":"10.3390\/s18010018"},{"key":"ref_20","unstructured":"Roda, E. (1993). Distribuci\u00f3n, Caracteristicas y Petrogenesis de las Pegmatitas de La Fregeneda (Salamanca). [Ph.D. Thesis, UPV\/EHU]."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1180\/002646199548709","article-title":"The granitic pegmatites of the Fregeneda area (Salamanca, Spain): Characteristics and petrogenesis","volume":"63","author":"Pesquera","year":"1999","journal-title":"Miner. Mag."},{"key":"ref_22","unstructured":"Vieira, R. (2010). Aplitopegmatitos com elementos raros da regi\u00e3o entre Almendra (V.N. de Foz C\u00f4a) e Barca d\u2019Alva (Figueira de Castelo Rodrigo). Campo aplitopegmat\u00edtico da Fregeneda- Almendra. [Ph.D. Thesis, Faculdade de Ci\u00eancias da Universidade do Porto]."},{"key":"ref_23","unstructured":"Costa, J.C.S.D. (1950). Not\u00edcia sobre uma carta geol\u00f3gica do Bu\u00e7aco, de Nery Delgado, Servi\u00e7os Geol\u00f3gicos de Portugal."},{"key":"ref_24","unstructured":"Teixeira, C. (1955). Notas sobre geologia de Portugal o complexo xisto-grauv\u00e1quico ante-ordoviciano, Empresa Literaria Fluminense Lda."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s00710-010-0117-7","article-title":"Chemical variations and significance of phosphates from the Fregeneda-Almendra pegmatite field, Central Iberian Zone (Spain and Portugal)","volume":"100","author":"Vieira","year":"2010","journal-title":"Miner. Pet."},{"key":"ref_26","unstructured":"Silva, A.F.d., Rebelo, J.A., and Ribeiro, M.L. (1989). Not\u00edcia Explicativa da folha 11-C Torre de Moncorvo, Servi\u00e7os Geol\u00f3gicos de Portugal."},{"key":"ref_27","unstructured":"Silva, A.F.d., and Ribeiro, M.L. (1991). Not\u00edcia Explicativa da folha 15-A Vila Nova de Foz C\u00f4a, Servi\u00e7os Geol\u00f3gicos de Portugal."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Vapnik, V.N. (1995). The Nature of Statistical Learning Theory, Springer.","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Souli\u00e9, F.F., and H\u00e9rault, J. (1990). Single-layer learning revisited: A stepwise procedure for building and training a neural network. Neurocomputing, Springer.","DOI":"10.1007\/978-3-642-76153-9"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_31","unstructured":"G\u00e9ron, A. (2017). Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O\u2019Reilly Media, Inc."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"723","DOI":"10.3749\/canmin.AB00004","article-title":"Constraints and potentials of remote sensing data\/techniques applied to lithium (Li)-pegmatites","volume":"57","author":"Lima","year":"2019","journal-title":"Can. Miner."},{"key":"ref_33","unstructured":"(2020, April 20). Missions: Sentinel-2. Available online: https:\/\/sentinel.esa.int\/web\/sentinel\/missions\/sentinel-2."},{"key":"ref_34","unstructured":"(2020, April 20). MultiSpectral Instrument (MSI) Overview. Available online: https:\/\/sentinel.esa.int\/web\/sentinel\/technical-guides\/sentinel-2-msi\/msi-instrument."},{"key":"ref_35","unstructured":"(2020, April 20). Sentinel-2 MSI: Products and Algorithms. Available online: https:\/\/sentinel.esa.int\/web\/sentinel\/technical-guides\/sentinel-2-msi\/products-algorithms."},{"key":"ref_36","unstructured":"(2020, April 20). SNAP. Available online: https:\/\/step.esa.int\/main\/toolboxes\/snap\/."},{"key":"ref_37","unstructured":"(2018, August 03). Google Earth Pro. Available online: https:\/\/www.google.com\/intl\/en_uk\/earth\/desktop\/."},{"key":"ref_38","unstructured":"(2019, May 09). Esri World Imagery. Available online: https:\/\/www.arcgis.com\/home\/item.html?id=10df2279f9684e4a9f6a7f08febac2a9."},{"key":"ref_39","unstructured":"(2019, July 12). Geomatica 2018. Available online: https:\/\/www.pcigeomatics.com\/."},{"key":"ref_40","unstructured":"(2019, April 23). Geomatica Help. Available online: http:\/\/www.pcigeomatics.com\/geomatica-help\/."},{"key":"ref_41","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_42","unstructured":"(2020, April 24). 1.4. Support Vector Machines\u2014Scikit-Learn 0.20.4 Documentation. Available online: https:\/\/scikit-learn.org\/0.20\/modules\/svm.html#svm-classification."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1007\/s11004-008-9156-6","article-title":"An Objective Analysis of Support Vector Machine Based Classification for Remote Sensing","volume":"40","author":"Oommen","year":"2008","journal-title":"Math. Geosci."},{"key":"ref_44","unstructured":"Schanafelt, D. (2016). Chapter 5. Model Evaluation and Improvement. Introduction to Machine Learning with Python: A Guide for Data Scientists, O\u2019Reilly Media, Inc."},{"key":"ref_45","first-page":"397","article-title":"Accuracy assessment: A user\u2019s perspective","volume":"52","author":"Story","year":"1986","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/0034-4257(91)90048-B","article-title":"A review of assessing the accuracy of classifications of remotely sensed data","volume":"37","author":"Congalton","year":"1991","journal-title":"Remote Sens. Environ."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A Coefficient of Agreement for Nominal Scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educ. Psychol. Meas."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1080\/08120099.2014.858081","article-title":"Mapping geology and volcanic-hosted massive sulfide alteration in the Hellyer\u2013Mt Charter region, Tasmania, using Random Forests\u2122 and Self-Organising Maps","volume":"61","author":"Cracknell","year":"2014","journal-title":"Aust. J. Earth Sci."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1080\/01431160512331314083","article-title":"Support vector machines for classification in remote sensing","volume":"26","author":"Pal","year":"2005","journal-title":"Int. J. Remote Sens."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from Imbalanced Data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1778","DOI":"10.1109\/TGRS.2004.831865","article-title":"Classification of hyperspectral remote sensing images with support vector machines","volume":"42","author":"Melgani","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"e1264","DOI":"10.1002\/widm.1264","article-title":"Deep learning for remote sensing image classification: A survey","volume":"8","author":"Li","year":"2018","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/14\/2319\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:49:48Z","timestamp":1760176188000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/14\/2319"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,19]]},"references-count":52,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2020,7]]}},"alternative-id":["rs12142319"],"URL":"https:\/\/doi.org\/10.3390\/rs12142319","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,19]]}}}