Abstract : The rapid pace and global scope of anthropogenic climate change necessitates that we be able to quickly sample and study organisms in order to understand the impact of environmental perturbation on biological communities. Traditionally, conducting such analyses on marine microfossils requires time-consuming manual labor (picking, measuring, etc.) and specialized taxonomic expertise (species identification), limiting the scale and scope of questions we can ask and answer. Here, I will discuss the application of automation methods such as high-throughput imaging processing and deep learning to the study of both extant and fossil planktonic foraminifera. By using these 'next-generation' techniques, we can automate specimen processing, measuring, and identification, often with superhuman performance. This allows us to rapidly and accurately generate large datasets which can then be applied to understanding large-scale community evolution and responses to environmental change across time and space.