Tillage practices influence winter wheat grain yield prediction using seasonal precipitation

Making the best use of limited precipitation in semi-arid dryland cropping systems is important for crop production. Tillage practices may influence how this precipitation is utilized to predict winter wheat grain yield (Triticum aestivum L.). This study examined how tillage practices influence winter wheat grain yield prediction accuracy using precipitation received at three different periods of the season. Data were obtained from the period of 1972 to 2010 from a long-term tillage experiment. The study was designed as a winter wheat-fallow experiment. Each phase of the winter wheat-fallow rotation was present each year. The trial was set up as a randomized complete block design with three replications. Tillage treatments included no-till (NT), stubble mulch (SM), and moldboard plow (MP). Feed-forward neural network and multiple linear regression (ordinary least squares) were used to fit models under each tillage practice. No-till had the highest yield prediction accuracy with a root mean square error (RMSE) of 0.53 Mg ha(-1) and accounted for 81% of the variability in grain yield. Stubble mulch had an RMSE of 0.55 Mg ha(-1) and explained 73% of the variability in yield. Stubble mulch and NT were more accurate in yield prediction than MP which had an RMSE of 0.77 Mg ha(-1) and accounted for 53% of the variability in yield. The multiple linear regression model was less accurate than the feed-forward neural network model since it had at least 0.30 Mg ha(-1) more RMSE and accounted for only 5-8% of the variability in yield. Relative RMSE classified all neural network models as fair (21.6-27.3%) while linear regression models for the different tillage practices was classified as poor (33.3-43.6%), an illustration that the neural network models improve yield prediction accuracy. This study demonstrated that a large proportion of the variability in grain yield may be accounted for under NT and SM systems when using precipitation as predictors with neural networks.