Empirical-statistical reconstruction of surface marine winds along the western coast of Canada

Abstract

CANFIS, an empirical-statistical technique, is used to reconstruct continuous daily surface marine winds at 6-hourly intervals at 13 Canadian buoy sites along the western coast of Canada for the 40 yr period 1958-1997. CANFIS combines Classification and Regression Trees (CART) and the NeuroFuzzy Inference System (NFIS) in a 2-step procedure. CART is a tree-based algorithm used to optimize the process of selecting relevant predictors from a large pool of potential predictors. Using the selected predictors, NFIS builds a model for continuous output of the predictand. In this project we used CAN-FIS to link large-scale atmospheric predictors with regional wind observations during a learning phase from 1990 to 1995 in order to generate empirical-statistical relationships between the predictors and buoy winds. The large-scale predictors are derived from the NCAR/NCEP 40 yr reanalysis project while the buoy winds come from the Canadian Atmospheric Environment Service buoy network. Validation results with independent buoy wind data show a good performance of CANFIS. The CANFIS winds reproduce the independent buoy winds with greater accuracy than winds reconstructed with a stepwise multivariate linear regression technique. In addition, they are better than the NCEP reanalyzed winds interpolated to the buoy locations. The reconstructed statistical winds recover more than 60% of the observed wind variance during an independent verification period. In particular, correlation coefficients between independent buoy wind time series and CANFIS wind time series vary between 0.61 and 0.98. Our results suggest that CANFIS is a successful downscaling method. It is able to recover a substantial fraction of the variation of surface marine winds, especially along coastal regions where ageostrophic effects are relatively important.

Surface Wind Speed Prediction in the Canadian Arctic using Non-Linear Machine Learning Methods

“…Because Schemes 1 and 3 have many predictors, we used stepwise linear regression (Draper and Smith, 1981) to select relevant predictors for all three schemes in this paper to avoid using an excessive number of predictors. The alternative of using the non-liner classification and regression tree (CART) method to select relevant predictors (Faucher et al, 1999) was also tried but did not lead to improved results.…”

Downscaling of precipitation for climate change scenarios: A support vector machine approach

“…More recently, downscaling has found wide application in hydroclimatology for scenario construction and simulation/ prediction of (i) regional precipitation (Kim et al, 2004); (ii) low-frequency rainfall events (Wilby, 1998) (iii) mean, minimum and maximum air temperature (Kettle and Thompson, 2004); (iv) soil moisture (Georgakakos and Smith, 2001;Jasper et al, 2004); (v) runoff (Arnell et al, 2003) and streamflows (Cannon and Whitfield, 2002); (vi) ground water levels (Bouraoui et al, 1999); (vii) transpiration (Misson et al, 2002), wind speed (Faucher et al, 1999) and potential evaporation rates (Weisse and Oestreicher, 2001); (viii) soil erosion and crop yield (Zhang et al, 2004); (ix) landslide occurrence (Buma and Dehn, 2000;Schmidt and Glade, 2003) and (x) water quality (Hassan et al, 1998).…”

A two‐dimensional nitrogen and carbon flux model in a coastal upwelling region

“…The Pacific Northwest experiences thick cloud cover during a large part of the year, so light availability is often low. Wind data [Faucher et al, 1999] were averaged over the seasons to calculate the piston velocity. A typical seasonal cycle in temperature was prescribed (http://www.ios.bc.ca/ios/osap/data/ lighthouse/bcsop.htm; R. Brown, unpublished data, 1998).…”