Three sequential hurricanes, Dennis, Floyd, and Irene, affected coastal North Carolina in September and October 1999. These hurricanes inundated the region with up to 1 m of rainfall, causing 50-to 500-year flooding in the watershed of the Pamlico Sound, the largest lagoonal estuary in the United States and a key West Atlantic fisheries nursery. We investigated the ecosystem-level impacts on and responses of the Sound to the floodwater discharge. Floodwaters displaced three-fourths of the volume of the Sound, depressed salinity by a similar amount, and delivered at least half of the typical annual nitrogen load to this nitrogen-sensitive ecosystem. Organic carbon concentrations in floodwaters entering Pamlico Sound via a major tributary (the Neuse River Estuary) were at least 2-fold higher than concentrations under prefloodwater conditions. A cascading set of physical, chemical, and ecological impacts followed, including strong vertical stratification, bottom water hypoxia, a sustained increase in algal biomass, displacement of many marine organisms, and a rise in fish disease. Because of the Sound's long residence time (Ϸ1 year), we hypothesize that the effects of the short-term nutrient enrichment could prove to be multiannual. A predicted increase in the frequency of hurricane activity over the next few decades may cause longer-term biogeochemical and trophic changes in this and other estuarine and coastal habitats.
Abstract. Recently, deep learning (DL) has emerged as a revolutionary and
versatile tool transforming industry applications and generating new and
improved capabilities for scientific discovery and model building. The
adoption of DL in hydrology has so far been gradual, but the field is now
ripe for breakthroughs. This paper suggests that DL-based methods can open up a
complementary avenue toward knowledge discovery in hydrologic sciences. In
the new avenue, machine-learning algorithms present competing hypotheses that
are consistent with data. Interrogative methods are then invoked to interpret
DL models for scientists to further evaluate. However, hydrology presents
many challenges for DL methods, such as data limitations, heterogeneity
and co-evolution, and the general inexperience of the hydrologic field with
DL. The roadmap toward DL-powered scientific advances will require the
coordinated effort from a large community involving scientists and citizens.
Integrating process-based models with DL models will help alleviate data
limitations. The sharing of data and baseline models will improve the
efficiency of the community as a whole. Open competitions could serve as the
organizing events to greatly propel growth and nurture data science education
in hydrology, which demands a grassroots collaboration. The area of
hydrologic DL presents numerous research opportunities that could, in turn,
stimulate advances in machine learning as well.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.