Visible Image-Based Machine Learning for Identifying Abiotic Stress in Sugar Beet Crops

Abstract

Results: proved that synchronized use of inexpensive RGB images, image processing, and machine learning (ML) can accurately identify crop stress. Four Machine Learning Image Modules (MLIMs) were developed to enable rapid and cost-effective identification of sugar beet stresses caused by water and/or nitrogen deficiencies. RGB images representing stressed and non-stressed crops were used in the analysis. Each MLIM was trained and tested using 54 combinations derived from nine canopy and RGB-based input features and six ML algorithms. The most accurate MLIM used RGB bands as input to a Multi-Layer Perceptron, achieving 100% accuracy for overall stress detection, and 95.6% and 86.7% for water and nitrogen stress identification, respectively. A Stochastic Gradient Descent model, using only the green band, achieved 97.78% accuracy for stress detection while requiring only one-fourth the computation time. For specific stresses, a Random Forest (RF) model using RGB bands and canopy cover achieved 86.7% for water stress, while RF with the excess green index reached 75.6% for nitrogen stress. To address the trade-off between accuracy and computational cost, a bargaining theory-based framework was applied. This approach identified optimal MLIMs that balance performance and execution efficiency.

Plant phenotyping relevance

RGB画像・画像処理・機械学習を用いてテンサイの水・窒素ストレスを識別する画像ベースの表現型推定手法を開発・比較しており、ストレス状態の取得・抽出が研究の中心です。

Code and data availability

The paper's Data Availability Statement explicitly states the supporting data (the sugar beet RGB image dataset and derived inputs used for stress-detection ML) are openly available in a HydroShare repository, matching an allowed URL. No code or model deposit is stated.