USING NEURAL NETWORKS TO ASSESS THE INFLUENCE OF CHANGING SEASONAL CLIMATES IN MODIFYING DISCHARGE, DISSOLVED ORGANIC-CARBON, AND NITROGEN EXPORT IN EASTERN CANADIAN RIVERS

Changes in both air temperature and precipitation are expected as atmo spheric CO2 increases because of anthropogenic activities. These chang es will not be evenly distributed across seasons because of the comple xity of climate patterns. Using climate, hydrology, and water chemistr y data, we investigated how changes in the seasonal climates of the At lantic Provinces of Canada would change both hydrology and geochemical cycling of 14 river basins influenced by wetlands. We calculated mont hly discharge (Q) and dissolved organic carbon (DOG) and dissolved org anic nitrogen (DON) exports from 1983 to 1992 and developed three neur al network models relating climate variability to hydrologic and geoch emical fluxes from the basins. We then identified a series of potentia l temperature/precipitation scenarios which we applied to the models. We then studied how changes in climate regimes would affect water disc harge and aquatic dissolved carbon and nitrogen released from these ba sins. Our results predict a complex series of possible outcomes for wa ter and elemental fluxes. Warming or cooling in each season combined w ith potential changes in precipitation will cause completely different outcomes as snowpack melting dominates winter and early spring condit ions and evapotranspiration controls summer and fall. A warming winter would cause less snow storage and more runoff, with little evapotrans piration. Warmer summers, on the other hand, will be influenced by eva potranspiration, and water flows will be lower. Carbon and nitrogen ex ports from basins generally mirror those of Q. Our results suggest tha t major hydrological changes in basins may lead to significant ecologi cal and water resource impacts, especially in the spring and early sum mer.