Application of laser-induced breakdown spectroscopy with a generalized regression neural network and LASSO-type methods for estimation of arsenic and chromium in soil

Abstract

Hybrid models based on a generalized regression neural network (GRNN), adaptive least absolute shrinkage and selection operator (AdaLASSO), and sparse group LASSO (SGL) were used for quantitative analysis of arsenic (As) and chromium (Cr) in soil.