SEARCH

SEARCH BY CITATION

Please note: Wiley-Blackwell are not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing material) should be directed to the New Phytologist Central Office.

FilenameFormatSizeDescription
nph4291-sup-0001-TableS1-S8.pdfapplication/PDF251K

Table S1 Metadata for the modern reference pollen dataset, taken from collections at the University of Illinois and the Illinois State Museum.

Table S2 Metadata for the Nelson Lake fossil samples, collected from Kane County, Illinois.

Table S3 Morphological characters of Picea glauca and Picea mariana assessed in three influential studies.

Table S4 Machine-learning outputs for the modern three-class problem, the discrimination of Picea, Abies, and Pinus.

Table S5 Machine-learning outputs for the modern five-class problem, the discrimination of Picea mariana, P. glauca, P. rubens, Abies, and Pinus.

Table S6 Machine-learning outputs for grain-to-grain analysis of the fossil two-class problem, the discrimination of Nelson Lake Picea mariana and P. glauca, using grains identified with high expert confidence (≥ 95%).

Table S7 Machine-learning outputs for slide-level analysis of the fossil two-class problem, the discrimination of Nelson Lake Picea mariana and P. glauca, using grains identified with high expert confidence (≥ 95%).

Table S8 Machine-learning outputs for slide ratio analysis of the fossil two-class problem, the discrimination of Nelson Lake Picea mariana and P. glauca.