The aim of this study is to develop a rapid method for monitoring leaf nitrogen content (LNC) in winter wheat, which is essential for precise field management and accurate crop growth assessment. This study used a natural winter wheat population at Shanxi Agricultural University’s experimental base as the subject. UAV-mounted multispectral sensors collected images at jointing, heading, pre-grouting, and late grouting stages. Canopy spectral reflectance was extracted using image segmentation, and vegetation indices were calculated. Correlation analysis identified highly relevant indices with LNC. Support Vector Regression (SVR), Random Forest (RF), Ridge Regression (RR), K-Nearest Neighbors (K-NN), and ensemble learning algorithms (Voting and Stacking) were employed to model the relationship between selected vegetation indices and LNC. Model performance was evaluated using the coefficient of determination (R²) and root mean square error (RMSE). Results showed that the Voting-based ensemble learning model outperformed other models. At the pre-grouting stage, this model achieved an R² of 0.85 and an RMSE of 1.57 for the training set, and an R² of 0.82 and an RMSE of 1.64 for the testing set. This study provides a theoretical basis and technical reference for monitoring LNC in winter wheat at key growth stages using low-altitude multispectral sensors, supporting precision agriculture and variety evaluation.

Soil total carbon (TC) and total nitrogen (TN) are key indicators of soil fertility and ecosystem stability, particularly in dryland agroecosystems. However, how rotational tillage combined with straw return affects aggregate formation and aggregate-associated TC and TN stabilization remains insufficiently understood. In this study, we aimed to clarify how rotational tillage affects aggregate structure, stability, and the spatial distribution of TC and TN, thereby revealing internal processes driving nutrient stabilization in dryland farming systems. A long-term field experiment was conducted at the Shenfeng site of Shanxi Agricultural University, China, including three rotational tillage systems with straw return: T1 (two years of no tillage (NT) + one year of deep tillage (DT)), T2 (two years of conventional tillage (CT) + one year of DT), and T3 (two years of DT + one year of CT). Soil aggregates were separated into total mechanical aggregate (TMA), 0.25–2 mm MA, and 2–10 mm MA, and they were further fractionated into water-stable aggregates (WM, Wm, and Wf) for TC and TN analysis. The results showed that aggregate stability, TC, and TN were positively correlated and decreased with soil depth, indicating strong surface enrichment. TC was mainly enriched in 0.25–2 mm MA, whereas TN was concentrated in 2–10 mm MA, and water-stable macroaggregates (WM) acted as the dominant reservoirs for R_C and R_N. Relative to the 2016 baseline (CK), TC in 2022 tended to be higher under rotational tillage with straw return, while NT-containing systems better maintained TN across the 0–60 cm profile. Among the treatments, T1 provided the most balanced performance, with a higher MWD and GMD, lower D, and improved aggregate-associated TC and TN retention. These findings suggest that rotational tillage with straw return, particularly the NT–NT–DT sequence, can support aggregate stability and is associated with improved aggregate-mediated TC and TN retention in the Loess Plateau dryland winter wheat system.