Hyperspectral imaging has recently emerged in the geosciences as a technology that provides rapid, accurate, and high-resolution information from lake sediment cores. Here we introduce a new methodology to infer particle size distribution, an insightful proxy that tracks past changes in aquatic ecosystems and their catchments, from laboratory hyperspectral images of lake sediment cores. The proposed methodology includes data preparation, spectral preprocessing and transformation, variable selection, and model fitting. We evaluated random forest regression and other commonly used statistical methods to find the best model for particle size determination. We tested the performance of combinations of spectral transformation techniques, including absorbance, continuum removal, and first and second derivatives of the reflectance and absorbance, along with different regression models including partial least squares, multiple linear regression, principal component regression, and support vector regression, and evaluated the resulting root mean square error (RMSE), R-squared, and mean relative error (MRE). Our results show that a random forest regression model built on spectra absorbance significantly outperforms all other models. The new workflow demonstrated herein represents a much-improved method for generating inferences from hyperspectral imagery, which opens many new opportunities for advancing the study of sediment archives.

An analysis of sediment records from two lakes located along the southeastern shore of the Fury and Hecla Strait (Nunavut, Canada) allowed us to reconstruct the regional environmental history since deglaciation. Multiproxy profiles, namely particle‐size distribution, elemental geochemistry (based on X‐ray fluorescence) and diatom assemblages, revealed a regional deglaciation and marine inundation around 8200 cal a bp. This suggests that glacial retreat in this region likely occurred several hundred years earlier than previously extrapolated. At that time, the connection between the Atlantic and Pacific Ocean currents must have been established and glacial isostatic adjustment gradually isolated the lacustrine basins from marine influence. Diatom assemblages revealed an abrupt marine–brackish–freshwater transition (ca. 6670–6130 cal a bp) through a shift in dominance from initial polyhalobian (e.g. Tabularia fasciculata, Navicula directa), intermediate mesohalobian (e.g. Cyclostephanos dubius, Thalassiosira baltica) to oligohalobian (fragilarioid Staurosirella pinnata, Staurosira venter, Pseudostaurosira pseudoconstruens, P. brevistriata) taxa. Multivariate analyses (redundancy analysis and multivariate regression tree) conducted on the biological and lithogeochemical data also suggest that climatic conditions may have remained relatively warm throughout the interval ~6000–3900 cal a bp, before significantly cooling over the past few millennia, as inferred from a decrease in organic matter accumulation and shifts in diatom communities.