Optimizing plant traits to increase yield quality and quantity in tobacco using artificial neural network

Abstract

<span>There are complex inter- and intra-relations between regressors (independent variables) and<br /><span>yield quantity (W) and quality (Q) in tobacco. For instance, nitrogen (N) increases W but<br /><span>decreases Q; starch harms Q but soluble sugars promote it. The balance between (optimization<br /><span>of) regressors is needed for simultaneous increase in W and Q components [higher potassium<br /><span>(K), medium nicotine and lower chloride (Cl) contents in cured leaf]. This study was aimed to<br /><span>optimize 10 regressors (content of N and soluble sugars in root, stem and leaf, leaf nicotine<br /><span>content at flowering and nitrate reductase activity (NRA) at 3 phenological stages) for increased<br /><span>W and Q components, using an artificial neural network (ANN). Two field experiments were<br /><span>conducted to get diversified regressors, Q and W, using 2 N sources and 4 application patterns<br /><span>in Tirtash and Oromieh. Treatments and 2 locations produced a wide range of variation in<br /><span>regressors, W and Q components which is prerequisite of ANN. The results indicated that<br /><span>configuration of 12 neurons in one hidden layer was the best for prediction. The obtained<br /><span>optimum values of regressors (1.64%, 2.12% and 1.04% N content, 4.32%, 13.04% and 9.54%<br /><span>soluble sugar content for leaf, stem and root, respectively; 2.31% nicotine content and NRA of<br /><span>13.11, 4.74 and 4.70 µmol.NO<span>2<span>.g<span>-1<span>.h<span>-1 <span>for pre-flowering, flowering and post-flowering stages,<br /><span>respectively) increased W by 3% accompanied by 4.75% K, 1.87% nicotine and 1.5% Cl<br /><span>in cured leaf.</span></span></span></span></span></span></span></span></span></span></span></span></span></span></span></span><br /><br class="Apple-interchange-newline" /></span></span></span></span></span></span></span>