Integrating phenotypic traits, multivariate statistics, and machine-learning models to predict yield in Himalayan...

Understanding the morphological and physiological determinants of kiwifruit (Actinidia deliciosa A. Chev.) yield is essential to improve orchard productivity in Himalayan hill agro-ecosystems. However, most previous studies have focused on individual agronomic factors and have rarely integrated multivariate phenotypic traits with advanced predictive modeling approaches. The aim of this study was to evaluate whether combining multivariate statistical techniques with machine-learning algorithms could improve identification of key traits influencing yield variability in Himalayan kiwifruit orchards.

Thirty vegetative, floral, phenological, and fruit biometric traits were recorded from 210 vines of Actinidia deliciosa 'Allison' across three major kiwifruit-growing districts of Himachal Pradesh, India. Descriptive analysis revealed substantial phenotypic variability in canopy vigor, flowering intensity, and fruit morphology. Correlation analysis showed that fruit number per shoot, fruit width, and flowering duration were associated positively with total fruit yield, whereas leaf-to-fruit ratio showed a negative association. Principal component analysis identified five components explaining 79.1% of total phenotypic variance, representing canopy vigor, floral load, fruit morphology, and source-sink balance. Among machine-learning models, random forest achieved the highest predictive accuracy (R² = 0.84; RMSE = 6.20 kg), outperforming gradient boosting and support vector regression. Feature importance analysis consistently identified fruits per shoot, fruit width, vine girth, flowering duration, and leaf-to-fruit ratio as the most influential predictors.

The integration of multivariate statistical analysis with machine learning provides a robust framework for identifying key trait-based indicators of yield variability. These findings can support clonal selection, optimized pruning strategies, and site-specific orchard management to increase productivity in Himalayan kiwifruit systems. © 2026 Society of Chemical Industry.