Clarification of Water Stress in Apple Seedlings Using HSI Texture with Machine Learning Technique

Aug 3, 2026

Apples are valued for nutrition and economic importance, making early identification of water status in apple seedlings essential for precision irrigation. This study proposes a rapid, non-destructive leaf-level method using hyperspectral imaging (400–1000 nm) to estimate water content in individual rootstock-related seedlings. Spatial texture information is extracted via gray-level co-occurrence matrix features (GLCM) from wavelength images, then classified with machine learning. Spectral responses are analyzed to separate dry, normal, and overwater treatments, supported by chlorophyll measurements to link optical features with physiological changes. Results indicate texture–hyperspectral fusion with machine learning is promising for detecting leaf water stress.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages35

Reading Time1 h 28 min

AccessFree to download

Introduction

Importance of water management for apple orchards

Existing methods for detecting water stress

Role of chlorophyll and plant physiology in stress detection

Clarification of Water Stress in Apple Seedlings Using HSI Texture with Machine Learning Technique Yanying An School of Information Technology, Murdoch University, Australia School of Horticulture, Qingdao Agricultural University, China Ran Wang School of Horticulture, Qingdao Agricultural University, China Doi: 10.19044/esipreprint.1.2024.p518 | Approved: 20 January 2024
Posted: 23 January 2024 | Copyright 2024 Author(s)
Under Creative Commons CC-BY 4.0 OPEN ACCESS | | --- | --- | | Cite As:
An Y. & Wang R. (2024) . Clarification of Water Stress in Apple Seedlings Using HSI Texture with Machine Learning Technique. ESI Preprints.
[https://doi.org/10.19044/esipreprint.1.2024.p518](https://doi.org/10.19044/esipreprint.1.2024.p518) | | | Abstract
Apples are known for their nutrition and economic value. Accurate and rapid diagnosis of water status in apple seedlings on an individual rootstock basis is a prerequisite for precision water management. This study presents a rapid and non-destructive approach for estimating water content in apple seedlings at leaf levels. A PIKA L system collects hyperspectral images(400-1000nm) of apple leaves. To the author's knowledge, no prior work was conducted using the spectral-texture approach in plant water stress. Our research extracts spatial information, gray-level co-occurrence matrix (GLCM), from feature wavelength images of hypercubes. Machine learning methods are applied to these spatial feature matrixs to identify apple leaves under different water stresses. In addition, differences in spectral responses were analysed using machine learning techniques for sorting apple seedlings with varying water treatments (dry, normal, and overwatering) . Also, we measure chlorophyll to determine the relationship between hyperspectral characteristics and physiological changes. The achievements of the research indicate that the fusion of texture and hyperspectral imaging coupled with machine learning techniques is promising and presents a powerful potential to determine the water stress in the leaves of apple seedlings. | | Keywords: Hyperspectral imaging; machine learning; plant water stress; plant leaf; plant physiology 1. Introduction Apple (Malus domestica Borkh) is one of the world's most widely planted and nutritionally significant fruit crops (Duan et al.,2017) . Apples are rich in nutrients vital for good health and disease prevention, making them a valuable choice each day for enhancing the quality of our diet. With increased income and public awareness of balanced nutrition, Global apple consumption is increasing annually (Li et al.,2013) . Apple seedlings are tiny and propagated tree stems grafted onto a hardy rootstock (Loucks, 2021) . They are hugely profitable. In 2021, according to Willis Orchard Co. (2021), ten seedling trees at the height of 1-2 feet made a profit of $34.95, whereas ten seedling trees at the height of 2-3 feet earned $59.95. Water management is vital for apple orchards (Apple & Pear Australia Limited,2023) . As a result of drought and increasing competition for water, orchardists need to adopt efficient water management strategies (PIRSA,2006) . Newly planted apple trees require weekly watering. Ideal apple tree irrigation involves deep root soaking (Ellis,2021) . The key is to let the water flow into the soil slowly to allow for deep watering until it is established (The Home Depot,2021) . A plant induces leaf senescence prematurely if water shortage exceeds a critical level (Lim and Nam,2007) . This process is characterised by loss of chlorophyll and leaf yellowing (Yamaguchi et al.,2010) . If wilting leaves are observable, irreversible damage to plants and yield occurs (Behmann et al.,2014) . On the other hand, creating standing water and soggy roots can be as damaging as drought conditions for the apple seedlings. Too much water depletes oxygen from the soil, prevents the roots from absorbing necessary minerals, and makes a t

FAQs

Why is early detection of water stress important for apple seedlings?

Water stress can disrupt photosynthesis and cause premature leaf senescence, chlorophyll loss, yellowing, and potentially irreversible damage to plants and yield. Detecting stress early enables timely irrigation decisions.

How does the proposed method estimate water content in apple seedlings?

The approach collects hyperspectral images of apple leaves, extracts spatial texture features using gray-level co-occurrence matrix (GLCM) from feature wavelength images, and applies machine learning to classify different water stress conditions.

What treatments were used to evaluate machine learning-based sorting?

The study sorts apple seedlings subjected to dry, normal, and overwatering conditions, using differences in spectral responses captured by hyperspectral texture features.

Aug 3, 2026

Upload by Emma Wilson