Abstract
Crop simulation models are often used for estimating crop growth, development, and yield for locations with missingor incomplete observed weather data. An accurate estimation of these weather variables is thus important. The goal of this studywas to use weather data from neighboring weather stations to develop artificial neural network (ANN) models for estimatingand interpolating daily maximum air temperature, minimum air temperature, and total solar radiation for Tifton (south Georgia)and Griffin (north Georgia). Historical daily weather data from 1996 to 1998 were used for model development, and datafrom 1999 to 2000 were used for the evaluation of the ANN.<br><br>The preferred input variables for the ANNs for each weather variable included the straight line distance (.s) and theelevation difference (.z) between the target location and input weather stations as well as the values of the variable beingestimated at the input stations. For estimating solar radiation, maximum temperature from the input weather stations was alsodetermined to be important. The optimum number of input weather stations for estimating each weather variable was alsodetermined. Based on the evaluation data set, the Tifton models had a mean absolute error (MAE) of 0.61C for maximumtemperature, 0.74C for minimum temperature, and 1.24 MJ/m2 for solar radiation. The Griffin models had an MAE value of0.36C for maximum temperature, 0.82C for minimum temperature, and 1.51 MJ/m2 for solar radiation. The best ANN modelswere also compared with other spatial interpolation techniques, including inverse distance, average, and multi-linearregression methods. The results showed that ANN and regression models provided greater accuracy than the inverse distanceand average methods. ANN models and regression models were comparable in estimating maximum temperature. The ANNmodel was more accurate than the regression model for estimating minimum temperature for Griffin and comparable for Tifton.The ANN models were more accurate in estimating solar radiation for both locations. ANN models thus provided an accurateapproach for estimating daily weather variables for a particular location based on daily data from neighboring weatherstations.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.