What is to be gained by ensemble models in analysis of spectroscopic data?

Vibrational spectroscopic techniques, including near-infrared (NIR), mid-infrared (MIR), and Raman, use the effect of light to provide information about the constituents of a sample. These low cost, rapid and noninvasive techniques are widely and routinely used in many application domains. Prediction in spectroscopic data is a topic of major interest in chemometric literature, see for example Frizzarin et al. (2021c,b); Singh and Domijan (2019). Numerous advances in statistical machine learning model methodology in the past few decades offer the potential to improve prediction performance over the well-established partial least squares (PLS) approach. Comparative analyses of algorithm prediction ability for spectroscopic data have shown that PLS variants perform strongly Frizzarin et al. (2021b); Singh and Domijan (2019), but that there isn't a single model that will outperform others in all settings.