The availability of “fixed” nitrogen limits the growth of marine phytoplankton in large part of the ocean. It has been suggested that considerable changes in nitrogen inventory could occur in the recent past or in the future, which may change the fertilization of the ocean and drive significant changes in atmospheric carbon dioxide. In this talk, I will discuss two cases for changes in marine nitrogen cycle across two different time scales. In the first case, I will present an 860,000-yr sedimentary record of nitrogen isotope preserved within planktonic foraminifera shells in the South China Sea. The record demonstrates significant changes in N 2 fixation rate (the main input of bioavailable N in the ocean) which covaried with the rise and fall of sea level over the past 8 glacial cycles. The N 2 fixation changes are best explained as a response to changes in regional excess phosphorus supply due to sea level-driven variations in shallow sediment denitrification associated with the cyclic drowning and emergence of the continental shelves. This hypothesis is consistent with a glacial ocean that hosted globally lower rates of fixed N input and loss and a longer residence time for oceanic fixed N—a “sluggish” ocean N budget during ice ages. In the second case, I will discuss a coral record of nitrogen isotopes of skeleton-bound organic matter from Dongsha Atoll in the South China Sea, which provide a test of the hypothesis that anthropogenic atmospheric nitrogen has significantly augmented the nitrogen supply to the open surface ocean. In this record, we observe a decline in the 15 N/ 14 N of coral skeleton-bound organic matter, signaling increased deposition of anthropogenic atmospheric N on the open ocean and its incorporation into plankton and in turn the corals living on the atoll. The decrease began just several years before 2000 CE, decades later than predicted by other work, and the amplitude of decline suggests that anthropogenic atmospheric N input is now 20±5% of the annual N input to the surface ocean in this region, less than two-thirds of that estimated by models and analyses of nutrient ratio changes.