Page 1 of 8

Transactions on Engineering and Computing Sciences - Vol. 12, No. 6

Publication Date: December 25, 2024

DOI:10.14738/tecs.126.17881.

Quartey, G. A., Dadzie, P. K., Asante-Okyere, S., & Eshun, J. F. (2024). Estimating Young Modulus of Elasticity of Terminalia catappa:

A Machine Learning Approach. Transactions on Engineering and Computing Sciences, 12(6). 21-28.

Services for Science and Education – United Kingdom

Estimating Young Modulus of Elasticity of Terminalia catappa: A

Machine Learning Approach

Gladys Ama Quartey

ORCID: 0000-0002-7073-6342

Department of Interior Design and Technology

Faculty of Built and Natural Environment,

Takoradi technical University. P. O. Box 256, Takoradi

Peter Kessels Dadzie

Department of Interior Design and Materials Technology

Kumasi technical University P. O. Box 854, Kumasi

Solomon Asante-Okyere

Department of Petroleum and Natural Gas Engineering

University of Mines and Technology. P. O. Box 237 Tarkwa

John Frank Eshun

Department of Interior Design and Technology

Takoradi Technical University. P. O. Box 256 Takoradi

ABSTRACT

The purpose of this research was to evaluate the potential of Magnetic Resonance

Spectroscopy (MRS) in estimating Young’s modulus of elasticity of wood species. To

do so, Terminalia catappa, a wood species of common occurrence was chosen and

its mechanical properties such as bending strength, compression parallel to the

grain, and shear parallel to the grain properties were determined using testing

methods for small and clear specimens of wood with the British (BS 373, 1957) and

American Society of Testing Materials’ specifications (ASTM D143, 1983s. The

results showed that at 18% moisture content the wood has a density of 520 kg/m3

with a mean modulus of rupture of 86.04 Mpa, compressive strength parallel to the

grain of 42.02 Mpa, modulus of elasticity of 10,500 Mpa, and shear strength parallel

to the grain of 16.42 N/mm2. This dataset was used on machine learning approaches

such as decision tree and random forest. The estimated value of Young’s modulus

using the machine learning models varies between 1000 to 13000 MPa. The

obtained results indicated that the use of Magnetic Resonance Spectroscopy (MRS)

is an efficient tool for predicting Wood-Young’s modulus. This research paves the

way for further investigations on the application of MRS and machine learning for

predicting a wider range of wood properties. By employing machine learning

techniques such as decision trees and random forests, researchers can develop

robust models for estimating Young's modulus in other wood species. This

approach allows for leveraging large datasets that encompass various influencing

factors, ultimately leading to more accurate predictions compared to traditional

methods.

Page 2 of 8

22

Transactions on Engineering and Computing Sciences (TECS) Vol 12, Issue 6, December - 2024

Services for Science and Education – United Kingdom

Keywords: Terminalia catappa, Magnetic Resonance Spectroscopy (MRS), Decision Tree,

Random Forest, Young’s modulus, Mean Absolute Percentage Error (MAPE)

INTRODUCTION

Terminalia catappa, a tropical hardwood renowned for its durability and aesthetic appeal, finds

diverse applications in construction, furniture making, and even traditional medicine. However,

a deeper understanding of its mechanical properties, particularly Young's modulus of elasticity,

remains crucial for optimizing its usage. Traditional methods for determining Young's modulus,

using the testing of small clear samples, are time-consuming, destructive, and often limited by

sample availability.

This research proposes a novel approach to estimate Young's modulus of Terminalia catappa

wood using machine learning. By leveraging a dataset of wood characteristics like density,

moisture content, and grain orientation, coupled with existing experimental data, the aim is to

develop an accurate and efficient predictive model. This machine learning model can not only

expedite the estimation process but also offer valuable insights into the factors influencing the

elastic behavior of this valuable hardwood. This research holds significant implications for the

sustainable and optimized utilization of Terminalia catappa wood across various industries.

Terminalia catappa is a tree very easily recognised because of its pagoda-like structure [1].

According to [2] Terminalia catappa is a tall deciduous and erect tree reaching 15-25 m in

height, trunk 1-1.5 m in diameter, and often buttressed at the base. The branches are in whorls

of nearly horizontal, slightly ascending, and are spaced 1-2 m apart in tiers, or stories, up the

trunk. The pagoda-like habit becomes less noticeable as the branches elongate and droop at the

tips [1]. It grows best in moist tropical climates is admirably adapted to sandy and rocky coasts

and flourishes on oolitic limestone. It has many uses including medicinal and construction.

This research explores the potential of Magnetic Resonance Spectroscopy (MRS) in estimating

Young's modulus of elasticity in wood. The study focuses on Terminalia catappa, a commonly

occurring wood species, and investigates the correlation between MRS data and traditional

mechanical properties data. This review will provide context for the research by examining

existing literature on wood mechanical properties and testing methods. Young's modulus is a

fundamental material property that represents the stiffness of a material. It is crucial for

understanding a wood's structural integrity, its response to stress, and its suitability for

different applications. Traditional Testing Methods that is standard methods for determining

wood mechanical properties, like those outlined in [3] and [4], rely on destructive tests on

small, clear specimens. These methods are accurate but time-consuming and require

specialised equipment.

Magnetic Resonance Spectroscopy (MRS) in wood science is used for wood characterization

[5]. MRS is a non-destructive technique used to study the chemical composition and structure

of materials. In wood science, it has been employed to investigate, identify and quantify

different chemical components, such as cellulose, hemicellulose, and lignin. It is also used in

structural analysis to examine the molecular arrangement and changes in the wood cell wall. In

moisture content to determine the amount of water present in the wood. Additionally, MRS has