Sets of weather variables for estimation of LWD were evaluated using CART(Classification AndRegression Tree) models. Input variables were sets of hourly observations of air temperature at 0.3-m and1.5-m height, relative humidity(RH), and wind speed th...
Sets of weather variables for estimation of LWD were evaluated using CART(Classification AndRegression Tree) models. Input variables were sets of hourly observations of air temperature at 0.3-m and1.5-m height, relative humidity(RH), and wind speed that were obtained from May to September in 1997,1998, and 1999 at 15 weather stations in Iowa, Illinois, and Nebraska, USA. A model that included airtemperature at 0.3-m height, RH, and wind speed showed the lowest misidentification rate for wetness.The model estimated presence or absence of wetness more accurately (85.5%) than the CART/SLD model(84.7%) proposed by Gleason et al. (1994). This slight improvement, however, was insufficient to justify theuse of our model, which requires additional measurements, in preference to the CART/SLD model. Thisstudy demonstrated that the use of measurements of temperature, humidity, and wind from automatedstations was sufficient to make LWD estimations of reasonable accuracy when the CART/SLD model wasused. Therefore, implementation of crop disease-warning systems may be facilitated by application of theCART/SLD model that inputs readily obtainable weather observations.