Journal of Environmental Biology

Growth estimation during hardening phase of tissue cultured banana plantlets using bootstrapped artificial neural network

Paper received: 19.06.2018??????????????????? Revised received: 13.11.2018????????????????? Re-revised received: 24.12.2018???????????? Accepted: 16.03.2019

Authors Info

S. Revathi¹, N. Sivakumaran¹,

D. Ramajayam²*,

M.S. Saraswathi², S. Backiyarani² and S. Uma²

¹Department of Instrumentation and Control Engineering, National Institute of Technology, Tiruchirappalli-620 015, India

²ICAR - National Research Centre for Banana, Tiruchirappalli-620 102, India

*Corresponding Author Email :

ramajayamd@gmail.com

Abstract

Aim: The study aims to develop an advanced non-destructive method to estimate the plant growth rate of tissue culture propagated banana plantlets during primary hardening phase inside the greenhouse using Bootstrapped Artificial Neural Network (BANN). ??  

Methodology: Both non-destructive growth parameters like plant height, girth, number of leaves, leaf length and leaf breadth, and destructive growth parameters like number of roots, longest root length, fresh and dry weight were measured periodically on selected plants of one week to nine week old which were kept in greenhouse at ICAR-National Research Centre for banana. In addition to plant growth parameters, greenhouse temperature, radiation and carbon dioxide concentration were also recorded daily. The experimental data obtained using destructive measurements were recorded on a small sample of size n, and hence re-sampling for bootstrap involves n repeated trials of simple random sampling with replacement. These sets of bootstrap samples were finally used as input to develop neural model using a novel methodology of bootstrap re-sampling based artificial neural network (ANN) for studying the progress of plant ontogeny. 

Results: The growth estimation analysis of plants in terms of its leaf area and biomass production was performed without physically handling the test plants using bootstrap ANN. The notion of prediction performance is validated through statistical indices namely Nash and Sutcliffe efficiency coefficient, root means square error and mean absolute error. The approximate estimates of mean relative growth and net assimilation rate of plants were 0.036 and 0.027, and the corresponding variance were 1.5 x 10^-6 and 2.12 x 10^-6, respectively.

Interpretation: Based on the non-destructive plant growth observations, the measures to increase the overall plant growth can be significantly predicted well in advance. This projected plant growth statistics at an early stage of hardening serves as an essential component in planning and evaluation of investments on protected structure to improve the productivity and profitability of banana tissue culture industry.

Key words: Artificial neural network, Bootstrapped sample, Greenhouse technology, Tissue culture banana

Copyright ? 2019 Triveni Enterprises. All rights reserved. No part of the Journal can be reproduced in any form without prior permission. Responsibility regarding the authenticity of the data, and the acceptability of the conclusions enforced or derived, rest completely with the author(s).