Discrimination of grass pollen of different species by FTIR spectroscopy of individual pollen grains

Sabrina Diehn,Mikael Ohlson,Janina Kneipp,Siri Fjellheim,Boris Zimmermann,Valeria Tafintseva,Murat Bağcıoğlu,Achim Kohler

doi:10.1007/s00216-020-02628-2

Abstract

Fourier-transform infrared (FTIR) spectroscopy enables the chemical characterization and identification of pollen samples, leading to a wide range of applications, such as paleoecology and allergology. This is of particular interest in the identification of grass (Poaceae) species since they have pollen grains of very similar morphology. Unfortunately, the correct identification of FTIR microspectroscopy spectra of single pollen grains is hindered by strong spectral contributions from Mie scattering. Embedding of pollen samples in paraffin helps to retrieve infrared spectra without scattering artifacts. In this study, pollen samples from 10 different populations of five grass species (Anthoxanthum odoratum, Bromus inermis, Hordeum bulbosum, Lolium perenne, and Poa alpina) were embedded in paraffin, and their single grain spectra were obtained by FTIR microspectroscopy. Spectra were subjected to different preprocessing in order to suppress paraffin influence on spectral classification. It is shown that decomposition by non-negative matrix factorization (NMF) and extended multiplicative signal correction (EMSC) that utilizes a paraffin constituent spectrum, respectively, leads to good success rates for the classification of spectra with respect to species by a partial least square discriminant analysis (PLS-DA) model in full cross-validation for several species. PLS-DA, artificial neural network, and random forest classifiers were applied on the EMSC-corrected spectra using an independent validation to assign spectra from unknown populations to the species. Variation within and between species, together with the differences in classification results, is in agreement with the systematics within the Poaceae family. The results illustrate the great potential of FTIR microspectroscopy for automated classification and identification of grass pollen, possibly together with other, complementary methods for single pollen chemical characterization.

Highlights

Many research fields, including paleobiology, climate research, and allergology, rely on a fast and reliable identification of pollen [1,2,3,4]
Comparing the success rates with the results obtained in the leave-one-spectrum-out approach above (Table 4), we find that the success rates are only slightly lower for the species Anthoxanthum odoratum, Hordeum bulbosum, and Poa alpina when spectra come from an unknown population
The results indicate that different spectral preprocessing strategies to minimize the influence of unwanted paraffin spectral contributions in the Fourier-transform infrared (FTIR) microspectra of individual grass pollen grains are feasible

Summary

Introduction

Many research fields, including paleobiology, climate research, and allergology, rely on a fast and reliable identification of pollen [1,2,3,4]. The spectral contribution from Mie scattering, as well as other artifacts, can superimpose the absorbance spectrum, depending on the geometry of the sample, and cause band shifts, distortions, and artificial bands [34]. These scattering problems can be addressed by numerical analytical approaches, such as model-based spectral preprocessing [30] and spectral averaging [32], or by modifying experimental settings, such as measurements of many pollen grains with large microscope apertures [15, 18, 20] or measurement in an embedding matrix [31]

Methods

Results

Conclusion