Prediction of sunflower grain oil concentration as a function ofvariety, crop management and environment using statistical models
Résumé
Sunflower (Helianthus annuus L.) raises as a competitive oilseed crop in the current environmentallyfriendly context. To help targeting adequate management strategies, we explored statistical models astools to understand and predict sunflower oil concentration. A trials database was built upon experi-ments carried out on a total of 61 varieties over the 2000–2011 period, grown in different locations inFrance under contrasting management conditions (nitrogen fertilization, water regime, plant density).25 literature-based predictors of seed oil concentration were used to build 3 statistical models (multiplelinear regression, generalized additive model (GAM), regression tree (RT)) and compared to the refer-ence simple one of Pereyra-Irujo and Aguirrezábal (2007) based on 3 variables. Performance of modelswas assessed by means of statistical indicators, including root mean squared error of prediction (RMSEP)and model efficiency (EF). GAM-based model performed best (RMSEP = 1.95%; EF = 0.71) while the simplemodel led to poor results in our database (RMSEP = 3.33%; EF = 0.09). We computed hierarchical contribu-tion of predictors in each model by means of R2and concluded to the leading determination of potentialoil concentration (OC), followed by post-flowering canopy functioning indicators (LAD2 and MRUE2),plant nitrogen and water status and high temperatures effect. Diagnosis of error in the 4 statistical mod-els and their domains of applicability are discussed. An improved statistical model (GAM-based) wasproposed for sunflower oil prediction on a large panel of genotypes grown in contrasting environments.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...