Related Experiment Video
Updated: Aug 6, 2026
09:16
Optimization of Processing Technology for Tiebangchui with Zanba Based on CRITIC Combined with Box-Behnken Response Surface Method
Published on: May 12, 2023
Predicting and Optimizing Zerumbone Content in Zingiber zerumbet Using Artificial Neural Network (ANN) Model: A
Biswabhusan Dash1, Asit Ray1, Swagat Mohanty1
1Centre for Biotechnology, Siksha O Anusandhan (Deemed to be University), Bhubaneswar, Odisha, India.
Chemistry & Biodiversity
|July 16, 2026
Summary
This study used artificial neural networks (ANNs) to identify optimal cultivation sites for Zingiber zerumbet, maximizing zerumbone yield. Key soil nutrients like manganese, zinc, and iron significantly influence zerumbone content.
Area of Science:
- Pharmacognosy
- Computational Biology
- Agricultural Science
Background:
- Zingiber zerumbet possesses significant pharmacological potential, primarily due to its bioactive compound, zerumbone.
- Zerumbone exhibits antioxidant, antiproliferative, anti-inflammatory, antimicrobial, and anticancer properties.
- Zerumbone content in Z. zerumbet varies considerably based on habitat and environmental factors.
Purpose of the Study:
- To employ an artificial neural network (ANN) to analyze the impact of abiotic factors on zerumbone content in Z. zerumbet.
- To predict optimal cultivation sites for Z. zerumbet to maximize zerumbone yield.
- To identify key soil nutrients and environmental parameters influencing zerumbone production.
Main Methods:
- Analysis of 60 Z. zerumbet rhizome accessions from Eastern India using 18 input variables (soil nutrients, climatic parameters).
- High-Performance Thin-Layer Chromatography (HPTLC) for quantifying zerumbone content.
- Development and validation of a multilayer perceptron artificial neural network model (18-11-1 architecture).
Main Results:
- Zerumbone content ranged from 0.91% to 21.46% (dry weight).
- The ANN model achieved high predictive accuracy (R² = 0.978) and 96% efficiency.
- Sensitivity analysis identified manganese (Mn), zinc (Zn), and iron (Fe) as critical factors influencing zerumbone content.
Conclusions:
- The ANN model provides a robust tool for developing site-specific cultivation strategies for Z. zerumbet.
- Optimizing soil nutrients like Mn, Zn, and Fe can significantly enhance predicted zerumbone yield.
- This approach facilitates maximizing zerumbone production for pharmacological applications.