Preprint
Machine Learning

Effect of Different Indole Butyric Acid (IBA) Concentrations in Various Rooting Media on the Rooting Success of Loropetalum chinense var. rubrum Yieh Cuttings and Its Modeling with Artificial Neural Networks

Türker Oğuztürk(Department of Landscape Architecture, Recep Tayyip Erdoğan University, Rize 53020, Türkiye), Cem Alparslan(Department of Mechanical Engineering, Recep Tayyip Erdoğan University, Rize 53020, Türkiye), Yusuf Aydın(Department of Landscape Architecture, Recep Tayyip Erdoğan University, Rize 53020, Türkiye), Umut Öztatar(Department of Landscape Architecture, Recep Tayyip Erdoğan University, Rize 53020, Türkiye), Gülcay Ercan Oğuztürk(Department of Landscape Architecture, Recep Tayyip Erdoğan University, Rize 53020, Türkiye)
May 22, 2025Horticulturae7 citations
DOI

7

Citations

0

Influential Citations

Horticulturae

Venue

2025

Year

Abstract

This study aimed to evaluate the rooting success of Loropetalum chinense var. rubrum Yieh cuttings in three different rooting media: 100% peat, 100% perlite, and a 50% peat–50% perlite mixture. Additionally, three concentrations of Indole Butyric Acid (IBA)—1000 ppm, 3000 ppm, and 6000 ppm—were tested, along with a control group consisting of non-hormone-treated cuttings. The chlorophyll content of the leaves was measured in µmol/m2, and its relationship with rooting success was examined. Measurements were conducted every 15 days over a 120-day period. The collected data were analyzed using both an artificial neural network (ANN) and SPSS 29.0.2 statistical software. Results indicated that perlite medium yielded the highest rooting rate and chlorophyll concentration, whereas the peat medium performed the poorest. While 1000 ppm IBA led to the greatest improvement in rooting rate, 6000 ppm resulted in the highest chlorophyll concentration. The highest chlorophyll levels were observed during measurement periods M7, M8, and M9. Analyses of peat moisture and pH indicated that the physicochemical properties of the rooting media significantly influenced cutting development. This study aims to support the identification of optimal propagation methods for this species and to contribute to the literature by developing an ANN model based on the measured parameters.

Analysis

Why This Paper Matters

This paper addresses a practical horticultural challenge—optimizing vegetative propagation of an ornamental shrub—using both traditional statistical methods and modern machine learning. For AI practitioners, it exemplifies how neural networks can be applied to biological systems where nonlinear relationships between multiple factors (hormone concentration, media type, time) affect outcomes. The integration of ANN modeling with experimental data offers a template for similar optimization problems in agriculture and forestry.

Technical Contributions

  • Experimental Design: Systematic testing of three rooting media (peat, perlite, peat-perlite mix) crossed with three IBA concentrations plus control, with repeated chlorophyll measurements over 120 days.
  • ANN Modeling: Development of a predictive model using measured parameters (IBA concentration, media type, time, chlorophyll content) to estimate rooting success. The ANN captures complex interactions that linear models might miss.
  • Physicochemical Analysis: Measurement of peat moisture and pH to explain media effects on cutting development, linking physical properties to biological outcomes.

Results

  • Perlite medium achieved the highest rooting rate and chlorophyll concentration; peat medium performed worst.
  • 1000 ppm IBA gave the greatest improvement in rooting rate, while 6000 ppm IBA produced the highest chlorophyll concentration.
  • Chlorophyll peaked during measurement periods M7, M8, and M9 (days 105–120).
  • The ANN model successfully learned the relationship between inputs and rooting success, though specific accuracy metrics are not provided in the abstract.

Significance

This work demonstrates a practical application of machine learning in horticulture, showing how ANNs can model biological processes with multiple interacting variables. For the AI community, it highlights the value of domain-specific datasets and the potential for neural networks to replace or augment traditional statistical analyses in experimental sciences. The approach could be extended to other plant species and propagation challenges, reducing the need for extensive empirical trials.

artificial-neural-networkrooting-mediaindole-butyric-acidloropetalum-chinenseplant-propagationmachine-learninghorticulture
Neural Networks

Related Papers