Quantifying Visual Differences in Drought-Stressed Maize through Reflectance and Data-Driven Analysis

Abstract

Environmental factors, such as drought stress, significantly impact maize growth and productivity worldwide. To improve yield and quality, effective strategies for early detection and mitigation of drought stress in maize are essential. This paper presents a detailed analysis of three imaging trials conducted to detect drought stress in maize plants using an existing, custom-developed, low-cost, high-throughput phenotyping platform. A pipeline is proposed for early detection of water stress in maize plants using a Vision Transformer classifier and analysis of distributions of near-infrared (NIR) reflectance from the plants. A classification accuracy of 85% was achieved in one of our trials, using hold-out trials for testing. Suitable regions on the plant that are more sensitive to drought stress were explored, and it was shown that the region surrounding the youngest expanding leaf (YEL) and the stem can be used as a more consistent alternative to analysis involving just the YEL. Experiments in search of an ideal window size showed that small bounding boxes surrounding the YEL and the stem area of the plant perform better in separating drought-stressed and well-watered plants than larger window sizes enclosing most of the plant. The results presented in this work show good separation between well-watered and drought-stressed categories for two out of the three imaging trials, both in terms of classification accuracy from data-driven features as well as through analysis of histograms of NIR reflectance.

Plant phenotyping relevance

マルチスペクトル画像とVision Transformerを用いて、トウモロコシ個体の干ばつストレス状態を推定する解析パイプラインを開発・評価しており、表現型取得・抽出手法が研究の中心である。

Code and data availability

The paper's raw maize drought-stress imaging dataset (three trials, downsampled NGB/NIR images) is openly deposited on Zenodo with DOI 10.5281/zenodo.10991581. No author analysis code, trained models, or annotations are stated as publicly available.