TY - JOUR
T1 - A regional neural network ensemble for predicting mean daily river water temperature
AU - DeWeber, Jefferson Tyrell
AU - Wagner, Tyler
N1 - Funding Information:
We thank the following individuals and agencies for generous contributions of water temperature data: Andy Dollof, Anthony Raburn of the Georgia DNR, Joan Trial of the Maine DMR, John Sweka of the USFWS Northeast Fishery Center, Mark Hudy, the Maryland DNR Monitoring and Non-tidal Assessment Division, Neal Hagstrom of the Connecticut DEEP, the New Hamphsire FGC, Rich Kern of the Vermont FWD, Roy Martin, Steve Means of the Pennsylvania DEP, the Susquehana River Basin Commission, Tamara Smith, and the Wood-Pawcatuck Watershed Association. We would also like to thank J. Olden and three anonymous reviewers for constructive comments on a previous version of this manuscript, as well as all members of the Fish Habitat, Climate, and Land Use Change group for support and ideas leading to this manuscript. Data included in this document were provided by the Maryland Department of Natural Resources Monitoring and Non-tidal Assessment Division. Funding for this research was provided by the U.S. Geological Survey, National Climate Change and Wildlife Science Center. Any use of trade, firm, or product names if for descriptive purposes only and does not imply endorsement by the U.S. Government.
Publisher Copyright:
© 2014 Elsevier B.V.
PY - 2014/9/9
Y1 - 2014/9/9
N2 - Water temperature is a fundamental property of river habitat and often a key aspect of river resource management, but measurements to characterize thermal regimes are not available for most streams and rivers. As such, we developed an artificial neural network (ANN) ensemble model to predict mean daily water temperature in 197,402 individual stream reaches during the warm season (May-October) throughout the native range of brook trout Salvelinus fontinalis in the eastern U.S. We compared four models with different groups of predictors to determine how well water temperature could be predicted by climatic, landform, and land cover attributes, and used the median prediction from an ensemble of 100 ANNs as our final prediction for each model. The final model included air temperature, landform attributes and forested land cover and predicted mean daily water temperatures with moderate accuracy as determined by root mean squared error (RMSE) at 886 training sites with data from 1980 to 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 years. The most important predictors were mean daily air temperature, prior 7 day mean air temperature, and network catchment area according to sensitivity analyses. Forest land cover at both riparian and catchment extents had relatively weak but clear negative effects. Predicted daily water temperature averaged for the month of July matched expected spatial trends with cooler temperatures in headwaters and at higher elevations and latitudes. Our ANN ensemble is unique in predicting daily temperatures throughout a large region, while other regional efforts have predicted at relatively coarse time steps. The model may prove a useful tool for predicting water temperatures in sampled and unsampled rivers under current conditions and future projections of climate and land use changes, thereby providing information that is valuable to management of river ecosystems and biota such as brook trout.
AB - Water temperature is a fundamental property of river habitat and often a key aspect of river resource management, but measurements to characterize thermal regimes are not available for most streams and rivers. As such, we developed an artificial neural network (ANN) ensemble model to predict mean daily water temperature in 197,402 individual stream reaches during the warm season (May-October) throughout the native range of brook trout Salvelinus fontinalis in the eastern U.S. We compared four models with different groups of predictors to determine how well water temperature could be predicted by climatic, landform, and land cover attributes, and used the median prediction from an ensemble of 100 ANNs as our final prediction for each model. The final model included air temperature, landform attributes and forested land cover and predicted mean daily water temperatures with moderate accuracy as determined by root mean squared error (RMSE) at 886 training sites with data from 1980 to 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 years. The most important predictors were mean daily air temperature, prior 7 day mean air temperature, and network catchment area according to sensitivity analyses. Forest land cover at both riparian and catchment extents had relatively weak but clear negative effects. Predicted daily water temperature averaged for the month of July matched expected spatial trends with cooler temperatures in headwaters and at higher elevations and latitudes. Our ANN ensemble is unique in predicting daily temperatures throughout a large region, while other regional efforts have predicted at relatively coarse time steps. The model may prove a useful tool for predicting water temperatures in sampled and unsampled rivers under current conditions and future projections of climate and land use changes, thereby providing information that is valuable to management of river ecosystems and biota such as brook trout.
UR - http://www.scopus.com/inward/record.url?scp=84904879046&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84904879046&partnerID=8YFLogxK
U2 - 10.1016/j.jhydrol.2014.05.035
DO - 10.1016/j.jhydrol.2014.05.035
M3 - Article
AN - SCOPUS:84904879046
SN - 0022-1694
VL - 517
SP - 187
EP - 200
JO - Journal of Hydrology
JF - Journal of Hydrology
ER -
