Despite its abundance in the fossil record, grass pollen is largely overlooked as a source of ecological and evolutionary data because most Poaceae species cannot be differentiated using traditional optical microscopy. However, deep learning techniques can quantify the small variations in grass pollen morphology visible under superresolution microscopy. We use the abstracted morphological features output by deep learning to estimate the taxonomic diversity and physiology of fossil grass pollen assemblages. Using a semi-supervised learning strategy, we trained convolutional neural networks (CNNs) on pollen images of 60 widely distributed grass species and unlabeled fossil Poaceae. Semi-supervised learning improved the CNN models' capability to generalize feature recognition in fossil pollen specimens. Our models successfully captured both the taxonomic diversity of an assemblage and morphological differences between C3and C4species. We applied our trained models to fossil grass pollen assemblages from a 25,000-year lake-sediment record from eastern equatorial Africa and correlated past shifts in grass diversity with atmospheric CO2concentration and proxy records of local temperature, precipitation, and fire occurrence. We quantified grass diversity for each time window using morphological variability, calculating both Shannon entropy and morphotype counts from the specimens' CNN features. Reconstructed C3:C4ratios suggest a gradual increase in C4grasses with rising temperature and fire activity across the late-glacial to Holocene transition. Our results demonstrate that quantitative machine-learned features of pollen morphology can significantly advance palynological analysis, enabling robust estimation of grass diversity and C3:C4ratio in ancient grassland ecosystems.