A variety of biological processes leave marks of their actions on phenotypes in the form of patterns of phenotypic variation. Traditionally, biologists have employed qualitative observation and simple measurements to describe and/or quantify these patterns to test process level hypotheses. However, recent developments in morphometrics, machine learning, and computer modelling have made a new generation of tools of unprecedented flexibility/sensitivity available to biologists for the purpose of finding, characterizing, comparing and interpreting these signals. The Natural History Museum is digitizing 1000s of slide-mounted specimens to facilitate the interpretation of phenotypic information. Data from these digital phenotypes will be analyzed and modelled using artificial intelligence, computer vision and computer modelling algorithms to address a wide range of contemporary biological/palaeobiological questions. An underpinning goal of this research programme is to reinvigorate and explore the role of phenotypic data in the assessment of environmental-phenotypic-taxonomic stationarity and stability.