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 demonstrates that salinity stress induces a photomorphogenic‑like response in dark‑grown Arabidopsis thaliana seedlings, resulting in reduced apical hook curvature and impaired soil emergence. This phenotype is linked to disrupted asymmetric epidermal cell elongation, decreased auxin signaling and PIN3 abundance on the hook’s concave side, repression of BBX28 expression, and loss of a spatial COP1 gradient, highlighting spatial regulation as a key factor in stress‑affected seedling development.

The study examined how soil phosphorus and nitrogen availability influence wheat root-associated arbuscular mycorrhizal fungal (AMF) communities and the expression of mycorrhizal nutrient transporters. Field sampling across two years combined with controlled pot experiments showed that P and N jointly affect AMF colonisation, community composition (with Funneliformis dominance under high P), and regulation of phosphate, ammonium, and nitrate transporters. Integrating metabarcoding and RT‑qPCR provides a framework to assess AMF contributions to crop nutrition.