A comparison of linear regression, regularization, and machine learning algorithms to develop Europe-wide spatial models of fine particles and nitrogen dioxide

著者: Jie Chen, Kees de Hoogh, John Gulliver, Barbara Hoffmann, Ole Hertel, Matthias Ketzel, Mariska Bauwelinck, Aaron van Donkelaar, Ulla Arthur Hvidtfeldt, Klea Katsouyanni, Nicole Janssen, Randall V. Martin, Evangelia Samoli, Per E. Schwartz, Massimo Stafoggia, Tom Bellander, Maciek Strak, Kathrin Wolf, Danielle Vienneau, Roel Vermeulen, Bert Brunekreef, Gerard Hoek - Environment International 2019 被引用: 338

models in all algorithms that allow assessment of the importance of variables. Different statistical algorithms performed similarly when modelling spatial variation in annual average air pollution concentrations using a large number of training sites.