Predicting Mean Daily River Water Temperature to Identify Brook Trout Habitat

Temperature is a fundamental property of river habitat, but measurements to characterize thermal regimes are not available for most streams and rivers. We developed an artificial neural network (ANN) ensemble model to predict mean daily water temperature in individual stream reaches during the warm season throughout the native range of Brook Trout Salvelinus fontinalis in the eastern U.S. The final model predicted mean daily water temperatures with moderate accuracy as determined by root mean squared error (RMSE) at 886 training sites with data from 1980 – 2009 (RMSE = 1.91°C). Based on validation at 96 sites (RMSE = 1.82) and separately for data from 2010 (RMSE = 1.93), a year with relatively warmer conditions, the model was able to generalize to new stream reaches and warmer years. Air temperature and network catchment area both had strong positive effects, whereas forest land cover at both riparian and catchment extents had relatively weak but clear negative effects. Predictions matched expected spatial trends with cooler temperatures in headwaters and at higher elevations and latitudes. We discuss how the model can be used to identify cold water habitat for Brook Trout under current conditions and potential changes under future projections of climate change.