Comparison of parametric and non-parametric estimations of the annual date of positive water temperature onset

SummaryThe onset date of positive water temperature in the annual thermal cycle of North-American streams is modeled using parametric (regression) and non-parametric (artificial neural networks) approaches. Physiographic, land cover and weather-related variables are used to predict the date of positive temperature onset for 191 station-years at 48 locations in Canada and in Northern US. Preliminary correlation analysis is performed in order to test the relationships between the physiographic/land cover/weather variables and the date of positive temperature onset. Moreover, several different subsets of variables are tested as inputs to each model type. Artificial neural networks can predict the date of positive temperature onset for a given station-year, given its longitude, lake coverage of its drainage basin, and two January–February daily temperature indices, with a split-sample validation root mean square error (RMSE) ∼8.8 days. Ordinary least square (OLS) regression models allow to predict the onset date with RMSE ∼9.5 days, given the station’s latitude, longitude, lake coverage and one January–February daily temperature index. OLS regression models adjusted on canonical variates combining 13 physiographic/land cover and weather variables achieve prediction performance ∼9.1 days. The precipitation does not impact much on the onset date prediction for all tested models.