Comparison of several background compensation methods useful for evaluation of energy-dispersive X-ray fluorescence spectra

Abstract A number of background estimation and modelling strategies suitable for evaluating energy-dispersive X-ray spectra by means of non-linear least squares fitting are evaluated and intercompared. As background modelling functions, exponential and linear combinations of mutually orthogonal polynomials are considered. These functions allow the shape of the background to be determined together with the photopeak intensities. As background estimation algorithms, an iterative stripping algorithm and a background channel selection procedure which is also based on the use of orthogonal polynomials are studied. The last two methods calculate the spectral background prior to the actual fitting process. For the intercomparison, the various methods were incorporated in the software package AXIL (Analysis of X-ray spectra by means of Iterative Least Squares). By using simulated spectra in which the intensity of all lines is a priori known, the accuracy and noise-sensitivity of the different background compensation strategies are evaluated. The method in which the background is modelled as a linear combination of orthogonal polynomials is identified as being the most robust and yielding the most accurate results.