{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T02:54:59Z","timestamp":1768272899025,"version":"3.49.0"},"reference-count":32,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2019,6,19]],"date-time":"2019-06-19T00:00:00Z","timestamp":1560902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>A Support Vector Machine (SVM) for regression is a popular machine learning model that aims to solve nonlinear function approximation problems wherein explicit model equations are difficult to formulate. The performance of an SVM depends largely on the selection of its parameters. Choosing between an SVM that solves an optimization problem with inequality constrains and one that solves the least square of errors (LS-SVM) adds to the complexity. Various methods have been proposed for tuning parameters, but no article puts the SVM and LS-SVM side by side to discuss the issue using a large dataset from the real world, which could be problematic for existing parameter tuning methods. We investigated both the SVM and LS-SVM with an artificial dataset and a dataset of more than 200,000 points used for the reconstruction of the global surface ocean CO2 concentration. The results reveal that: (1) the two models are most sensitive to the parameter of the kernel function, which lies in a narrow range for scaled input data; (2) the optimal values of other parameters do not change much for different datasets; and (3) the LS-SVM performs better than the SVM in general. The LS-SVM is recommended, as it has less parameters to be tuned and yields a smaller bias. Nevertheless, the SVM has advantages of consuming less computer resources and taking less time to train. The results suggest initial parameter guesses for using the models.<\/jats:p>","DOI":"10.3390\/make1020043","type":"journal-article","created":{"date-parts":[[2019,6,20]],"date-time":"2019-06-20T10:49:59Z","timestamp":1561027799000},"page":"745-755","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Generalization of Parameter Selection of SVM and LS-SVM for Regression"],"prefix":"10.3390","volume":"1","author":[{"given":"Jiye","family":"Zeng","sequence":"first","affiliation":[{"name":"National Institute for Environmental Studies, Tsukuba, Ibaraki 305-0053, Japan"}]},{"given":"Zheng-Hong","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Environmental Science, Hainan University, Haikou 570228, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3380-5230","authenticated-orcid":false,"given":"Tsuneo","family":"Matsunaga","sequence":"additional","affiliation":[{"name":"National Institute for Environmental Studies, Tsukuba, Ibaraki 305-0053, Japan"}]},{"given":"Tomoko","family":"Shirai","sequence":"additional","affiliation":[{"name":"National Institute for Environmental Studies, Tsukuba, Ibaraki 305-0053, Japan"}]}],"member":"1968","published-online":{"date-parts":[[2019,6,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.rse.2018.09.019","article-title":"Modeling alpine grassland cover based on MODIS data and support vector machine regression in the headwater region of the Huanghe River, China","volume":"218","author":"Ge","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1007\/s00704-017-2227-1","article-title":"Comprehensive modeling of monthly mean soil temperature using multivariate adaptive regression splines and support vector machine","volume":"133","author":"Mehdizadeh","year":"2018","journal-title":"Theor. Appl. Climatol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Jang, E., Im, J., Park, G.H., and Park, Y.G. (2017). Estimation of fugacity of carbon dioxide in the east sea using in situ measurements and geostationary ocean color imager satellite data. Remote Sens., 9.","DOI":"10.3390\/rs9080821"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5551","DOI":"10.5194\/bg-14-5551-2017","article-title":"Empirical methods for the estimation of Southern Ocean CO2: Support vector and random forest regression","volume":"14","author":"Gregor","year":"2017","journal-title":"Biogeosciences"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3452","DOI":"10.1109\/TGRS.2006.876297","article-title":"Prediction of Continental-Scale Evapotranspiration by Combining MODIS and AmeriFlux Data Through Support Vector Machine","volume":"44","author":"Yang","year":"2006","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1002\/joc.3493","article-title":"Least square support vector and multi-linear regression for statistically downscaling general circulation model outputs to catchment streamflows","volume":"33","author":"Sachindra","year":"2013","journal-title":"Int. J. Climatol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"303","DOI":"10.5194\/os-13-303-2017","article-title":"Technical note: Evaluation of three machine learning models for surface ocean CO2 mapping","volume":"13","author":"Zeng","year":"2017","journal-title":"Ocean Sci."},{"key":"ref_9","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_10","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1023\/B:STCO.0000035301.49549.88","article-title":"A tutorial on support vector regression","volume":"14","author":"Smola","year":"2004","journal-title":"Stat. Comput."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Suykens, J.A.K., Van Gestel, T., De Brabanter, J., De Moor, B., and Vandewalle, J. (2002). Least Squares Support Vector Machines, World Scientific.","DOI":"10.1142\/5089"},{"key":"ref_12","first-page":"23","article-title":"Parameter selection in least squares-support vector machines regression oriented, using generalized cross-validation","volume":"171","author":"Meza","year":"2011","journal-title":"Rev. DYNA"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Dorronsoro, J.R. (2002, January 28\u201330). Selection of Meta-Parameters for Support Vector Regression. Proceedings of the International Conference on Artificial Neural Networks 2002, Madrid, Spain. LNCS.","DOI":"10.1007\/3-540-46084-5"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1023\/A:1012450327387","article-title":"Choosing multiple parameters for support vector machines","volume":"46","author":"Chapelle","year":"2002","journal-title":"Mach. Learn."},{"key":"ref_15","unstructured":"Frauke, F., and Christian, I. (2004, January 27\u201329). Evolutionary Tuning of Multiple SVM Parameters. Proceedings of the ESANN\u20192004 Proceedings\u2014European Symposium on Artificial Neural Networks, Bruges, Belgium."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2099","DOI":"10.1162\/0899766054615635","article-title":"Gradient-based adaptation of general gaussian kernels","volume":"17","author":"Glasmachers","year":"2005","journal-title":"Neural Comput."},{"key":"ref_17","first-page":"625","article-title":"LS-SVM hyperparameter selection with a nonparametric noise estimator","volume":"3697","author":"Lendasse","year":"2005","journal-title":"Robotics"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"158056","DOI":"10.1155\/2013\/158056","article-title":"Study on Parameter Optimization for Support Vector Regression in Solving the Inverse ECG Problem","volume":"2013","author":"Jiang","year":"2013","journal-title":"Comput. Math. Methods Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.chemolab.2018.11.011","article-title":"On the optimization of the support vector machine regression hyperparameters setting for gas sensors array applications","volume":"184","author":"Laref","year":"2019","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_20","first-page":"21","article-title":"Using Genetic Algorithm to Optimize Parameters of Support Vector Machine and Its Application in Material Fatigue Life Prediction","volume":"8","author":"Zhang","year":"2015","journal-title":"Adv. Nat. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"De Brabanter, K., Suykens, J.A.K., and De Moor, B. (2015). Nonparametric Regression via StatLSSVM. J. Stat. Softw., 55.","DOI":"10.18637\/jss.v055.i02"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","article-title":"Libsvm","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_23","unstructured":"Sch\u00f6lkopf, B., Burges, J.C.C., and Smola, A.J. (1998). Making Large-Scale SVM Learning Practical. Advances in Kernel Methods\u2014Support Vector Learning, MIT Press."},{"key":"ref_24","first-page":"143","article-title":"SVMTorch: Support Vector Machines for Large-Scale Regression Problems","volume":"1","author":"Collobert","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1838","DOI":"10.1175\/JTECH-D-13-00137.1","article-title":"A global surface ocean fCO2 climatology based on a feed-forward neural network","volume":"31","author":"Zeng","year":"2014","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"383","DOI":"10.5194\/essd-8-383-2016","article-title":"A multi-decade record of high-quality fCO2 data in version 3 of the Surface Ocean CO2 Atlas (SOCAT)","volume":"8","author":"Bakker","year":"2016","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1609","DOI":"10.1175\/1520-0442(2002)015<1609:AIISAS>2.0.CO;2","article-title":"An Improved In Situ and Satellite SST Analysis for Climate","volume":"15","author":"Reynolds","year":"2002","journal-title":"J. Clim."},{"key":"ref_28","unstructured":"Levitus, S., and Mishonoc, A. (2013). World Ocean Database 2013, NOAA Atlas NESDIS 72."},{"key":"ref_29","first-page":"9","article-title":"Ocean color chlorophyll a algorithms for SeaWiFS, OC2, and OC4: Version 4","volume":"Volume 11","author":"Maritorena","year":"2000","journal-title":"SeaWiFS Postlaunch Technical Report Series; SeaWiFS Postlaunch Calibration and Validation Analyses, Part 3"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1658","DOI":"10.1002\/jgrc.20122","article-title":"MIMOC: A global monthly isopycnal upper-ocean climatology with mixed layers","volume":"118","author":"Schmidtko","year":"2013","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0169-7439(00)00122-2","article-title":"Monte Carlo cross validation","volume":"56","author":"Xu","year":"2001","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1002\/gdj3.26","article-title":"Surface ocean CO2 in 1990\u20132011 modelled using a feed-forward neural network","volume":"2","author":"Zeng","year":"2015","journal-title":"Geosci. Data J."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/1\/2\/43\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:59:48Z","timestamp":1760187588000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/1\/2\/43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,19]]},"references-count":32,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2019,6]]}},"alternative-id":["make1020043"],"URL":"https:\/\/doi.org\/10.3390\/make1020043","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,19]]}}}