The study introduces a hybrid modeling framework that integrates a logistic ordinary differential equation with a Long Short-Term Memory neural network to form a Physics-Informed Neural Network (PINN) for predicting wheat plant height. Using only time and temperature as inputs, the PINN outperformed other longitudinal growth models, achieving the lowest average RMSE and reduced variability across multiple random initializations. The results suggest that embedding biological growth constraints within data‑driven models can substantially improve prediction accuracy for plant traits.

The study investigated whether wheat homoeologous genes actively compensate for each other when one copy acquires a premature termination codon (PTC) mutation. By analyzing mutagenised wheat lines, the authors found that only about 3% of cases exhibited upregulation of the unaffected homoeolog, indicating that widespread active transcriptional compensation is absent in wheat.