Machine Learning Analysis of Maize Seedling Traits Under Drought Stress.

Abstract

The increasing concentration of greenhouse gases is amplifying the global risk of drought on crop productivity. This study sought to investigate the effects of drought on the growth of maize (Zea mays L.) seedlings. A total of 78 maize hybrids were employed in this study to replicate drought conditions through the potting method. The maize seedlings were subjected to a 10-day period of water breakage following a standard watering cycle until they reached the third leaf collar (V3) stage. Parameters including plant height, stem diameter, chlorophyll content, and root number were assessed. The eight phenotypic traits include the fresh and dry weights of both the aboveground and underground parts. Three machine learning methods-random forest (RF), K-nearest neighbor (KNN), and extreme gradient boosting (XGBoost)-were employed to systematically analyze the relevant traits of maize seedlings' drought tolerance and to assess their predictive performance in this regard. The findings indicated that plant height, aboveground weight, and chlorophyll content constituted the primary indices for phenotyping maize seedlings under drought conditions. The XGBoost model demonstrated optimal performance in the classification (AUC = 0.993) and regression (R² = 0.863) tasks, establishing itself as the most effective prediction model. This study provides a foundation for the feasibility and reliability of screening drought-tolerant maize varieties and refining precision breeding strategies.