Optimizing Micropropagation and Rooting Protocols for Diverse Lavender Genotypes: A Synergistic Approach Integrating Machine Learning Techniques
-
Published:2024-01-04
Issue:1
Volume:10
Page:52
-
ISSN:2311-7524
-
Container-title:Horticulturae
-
language:en
-
Short-container-title:Horticulturae
Author:
Şimşek Özhan1ORCID, Dalda Şekerci Akife1, Isak Musab A.2ORCID, Bulut Fatma1, İzgü Tolga3ORCID, Tütüncü Mehmet4ORCID, Dönmez Dicle5
Affiliation:
1. Horticulture Department, Agriculture Faculty, Erciyes University, 38030 Kayseri, Türkiye 2. Agricultural Sciences and Technology Department, Graduate School of Natural and Applied Sciences, Erciyes University, 38030 Kayseri, Türkiye 3. Institute of BioEconomy, National Research Council of Italy (CNR), 50019 Florence, Italy 4. Department of Horticulture, University of Ondokuz Mayıs, 55200 Samsun, Türkiye 5. Biotechnology Research and Application Center, Çukurova University, 01330 Adana, Türkiye
Abstract
This study comprehensively explored the micropropagation and rooting capabilities of four distinct lavender genotypes, utilizing culture media with and without 2 g/L of activated charcoal. A systematic examination of varying concentrations of BAP for micropropagation and IBA for rooting identified an optimal concentration of 1 mg/L for both BAP and IBA, resulting in excellent outcomes. Following robust root development, the acclimatization of plants to external conditions achieved a 100% survival rate across all genotypes. In addition to the conventional techniques employed, integrating machine learning (ML) methodologies holds promise for further enhancing the efficiency of lavender propagation protocols. Using cutting-edge computational tools, including MLP, RBF, XGBoost, and GP algorithms, our findings were rigorously examined and forecast using three performance measures (RMSE, R2, and MAE). Notably, the comparative evaluation of different machine learning models revealed distinct R2 rates for plant characteristics, with MLP, RBF, XGBoost, and GP demonstrating varying degrees of effectiveness. Future studies may leverage ML models, such as XGBoost, MLP, RBF, and GP, to fine-tune specific variables, including culture media composition and growth regulator treatments. The adaptability and ability of ML techniques to analyze complex biological processes can provide valuable insights into optimizing lavender micropropagation on a broader scale. This collaborative approach, combining traditional in vitro techniques with machine learning, validates the success of current micropropagation and rooting protocols and paves the way for continuous improvement. By embracing ML in lavender propagation studies, researchers can contribute to advancing sustainable and efficient plant propagation techniques, thereby fostering the preservation and exploitation of genetic resources for conservation and agriculture.
Subject
Horticulture,Plant Science
Reference40 articles.
1. The French lavender and lavandin industry;Guenther;Econ. Bot.,1954 2. Upson, T., and Andrews, S. (2004). The Genus Lavandula, Royal Botanic Gardens, Kew Nature. 3. Effects of drying methods, storage conditions and periods on the essential oil content and composition of lavender (Lavandula spp.);Kara;Yuz. Yil Univ. J. Agr. Sci.,2014 4. Urwin, N. (2009). Improvement of Lavender Varieties by Manipulation of Chromosome Number, Charles Sturt University. RIRDC (Rural Industries Research and Development Corporation, Australia). 5. Scent composition of essential oil, concrete, absolute and hydrosol from lavandin (Lavandula x intermedia Emeric ex Loisel.);Baydar;J. Essent. Oil-Bear.,2009
|
|