SciX 2024: October 21-25, 2024

Using an AI-powered spectrum prediction engine derived from its high-quality, comprehensive databases of measured spectra is a current strategy to expand chemical compound coverage by generating computed spectral data. Augmenting coverage of empirical databases within the bounds of a model (the chemical space of the underlying training set) is a strategy to help improve overall available compound coverage for unknown identification, especially for rarer compounds and materials.

Our validation studies on each of the SmartSpectra computed datasets demonstrate that these computed libraries, constructed from extensive and high-quality empirical reference datasets, demonstrate performance levels closely approaching that of empirical datasets.

View Case Study