Machine Learning-Assisted In Vitro Rooting Optimization in Passiflora caerulea

In vitro rooting as one of the most critical steps micropropagation is affected by various extrinsic (e.g., medium composition, auxins) and intrinsic factors species, explant). Passiflora in adventitious a difficult, complex, non-linear process. Since multivariable complex biological process, efficient reliable computational approaches such machine learning (ML) are required to model, predict, optimize this Therefore, current study, hybrid generalized regression neural network (GRNN) genetic algorithm (GA) was employed predict responses (rooting percentage, number roots, root length) caerulea based on optimization level auxins (indole-3-acetic acid (IAA), indolebutyric (IBA), 1-naphthaleneacetic (NAA)) type explant (microshoots derived from leaf, node, internode). Based results, GRNN model accurate predicting all P. (R2 > 0.92) either training or testing sets. The result validation experiment also showed that there negligible difference between predicted-optimized values validated results demonstrating reliability developed GRNN-GA model. Generally, study caerulea.