A neurofuzzy logic approach for modeling plant processes: A practical case of in vitro direct rooting and acclimatization of Vitis vinifera L.

Abstract

Understanding of the cause–effect relationships between culture conditions (carbon source: sucrose, plant growth regulators: type and concentration of auxins) and growth parameters (survival, root number and length, plantlet length and height, etc.) is essential for developing quality micropropagated plants. In this study, an artificial intelligence technology – neurofuzzy logic – has been employed as a modeling tool to get inside information on the effect of three variables, type of auxin, auxin concentration and sucrose concentration in the medium, on the success of in vitro direct rooting in soil and subsequent acclimatization protocol for ‘Albariño’ grapevine microshoots. The IF–THEN rule sets generated by neurofuzzy logic were completely in agreement with the findings based on statistical analysis. Additionally, neurofuzzy logic revealed significant terms not pointed out by statistics as type of auxin–sucrose concentration or type of auxin–auxin concentration interactions and advantageously generate understandable and reusable knowledge. Therefore, neurofuzzy logic is easy and rapid to apply and outcomes provided knowledge not revealed via statistical analysis leading an improvement on the understanding of the micropropagation process.