Predicting Optimal in Vitro Culture Medium for Pistacia Vera Micropropagation Using Neural Networks Models

In this study, artificial intelligence techniques—specifically artificial neural networks (ANNs) in combination with fuzzy logic (neurofuzzy logic) or with genetic algorithms (ANNs–GA)—have been employed, as modeling tools, to get insight, to predict and to optimize the effect of several independent factors on four growth parameters during Pistacia vera micropropagation. Twenty-six media ingredients, including mineral ions (or salts), glycine, vitamins and plant growth regulators (PGRs) at different concentrations, were used as inputs and four growth parameters: proliferation rate, shoot length, total and healthy fresh weight as outputs on the models. The IF-THEN rules from neurofuzzy logic models have allowed discovering the positive (BAP, nicotinic-acid and pyridoxine-HCl) and negative (NO3 −, Mg2+, Ag+ and gluconate−) effects on the growth parameters and the fundamental role of BAP over all of them. Also, ANNs–GA technology has permitted to estimate the best combination of media ingredients to simultaneously maximize the four parameters of growth: 4.4 new shoots per explant; 28.7 mm length; 1.1 and 0.53 g total and healthy fresh weight, respectively, minimizing physiological disorders. In our opinion, the information obtained in this study is extremely useful to improve the massive multiplication of pistachio plant, in particular, but also demonstrate the ability of artificial intelligence technology to design plant tissue culture media with predictable and tailorable characteristics.