To address low productivity and water constraints in lucerne fields of China’s Gansu Yellow River Irrigation Region, this study optimized lucerne (Medicago sativa L.) cultivation through synergistic planting nitrogen regimes. A two-year field trial (2021–2022) evaluated three systems: ridge-furrow with ordinary mulch (PM), ridge-furrow with biodegradable mulch (BM), and conventional flat planting (FP), under four controlled-release N rates (0, 80, 160, 240 kg ha⁻¹). Multidimensional assessments included growth dynamics, dry matter yield, forage quality (crude protein [CP], acid/neutral detergent fiber [ADF/NDF], relative feed value [RFV]), and resource efficiency metrics (water use efficiency [WUE], irrigation WUE [IWUE], partial factor productivity of N [PFPN], agronomic N use efficiency [ANUE]). The results showed the following: (1) Compared with conventional flat planting, ridge planting with film mulching significantly promoted lucerne growth, with ordinary plastic film providing a stronger effect than biodegradable film. Plant height and stem diameter exhibited a quadratic response to elevated nitrogen (N) application rates under identical planting patterns, peaking at intermediate N levels before declining with further increases. (2) Ridge planting with both ordinary plastic film and biodegradable film combined with an appropriate N rate improved lucerne yield and quality. In particular, the PMN2 treatment reached the highest value of yield (14,600 kg ha⁻¹), CP (19.19%) and RFV (124.18), and the lowest value of ADF (29.63%) and NDF (48.86%), and all of them were significantly better than the other treatments (p < 0.05). (3) WUE, IWUE, PFPN, and ANUE followed the pattern PM > BM > FP. With increasing N application rates, WUE, IWUE, and ANUE initially rose and then declined, peaking under N2, whereas PFPN showed a decreasing trend and reached its maximum under N1. Principal component analysis revealed that ridge planting with ordinary plastic film combined with 160 kg·ha⁻¹ N (PMN2) optimized lucerne performance, achieving balanced improvements in yield, forage quality, and water–nitrogen use efficiency. This regimen is recommended as the optimal strategy for lucerne cultivation in the Gansu Yellow River Irrigation Region and analogous ecoregions.

Soil moisture plays a critical role in the global water cycle, the exchange of matter and energy within ecosystems, and the movement of water in plants. Accurate monitoring of soil moisture is essential for drought early warning systems, irrigation decision-making, and crop growth assessment. The use of drone-based multispectral remote sensing technology for estimating the soil moisture content offers advantages such as wide coverage, high accuracy, and efficiency. However, the soil background can often interfere with the accuracy of these estimations. In specific environments, such as areas with strong winds, removing soil background noise may not necessarily enhance the precision of estimates. This study utilizes unmanned aerial vehicle (UAV) multispectral imagery and employs a vegetation index threshold method to remove soil background noise. It systematically analyzes the response relationship between spectral reflectance, spectral indices, and the soil moisture content in the top 0–10 cm layer of alfalfa; constructs K-Nearest Neighbors (KNN), Random Forest Regression (RFR), ridge regression (RR), and XG-Boost inversion models; and comprehensively evaluates model performance. The results indicate the following: (1) The XG-Boost model validation set had the highest R² value (0.812) when spectral reflectance was used as the input variable, which was significantly better than the other models (R² = 0.465 to 0.770), and the RFR model validation set had the highest R² value when the spectral index was used as the input variable (0.632), which was significantly better than the other models (R² = 0.366 to 0.535). (2) After removing soil background noise, the accuracy of the soil moisture estimates for each model did not show significant changes; specifically, the R² value for the XG-Boost model decreased to 0.803 when using spectral reflectance as the input, and the R² value for the RFR model dropped to 0.628 when using spectral indices. (3) Before and after removing the soil background noise, the spectral reflectance can provide more accurate data support for the inversion of the soil moisture content than the spectral index, and the XG-Boost model is the most effective in the inversion of the soil moisture content when using the spectral reflectance as the input variable. The research findings provide both theoretical and technical support for the retrieval of the surface soil moisture content in alfalfa using drone-based multispectral remote sensing. Additionally, they offer evidence that validates large-scale soil moisture remote sensing monitoring.

Rational nitrogen applications can not only improve nutrient use efficiency, but also reduce environmental pollution caused by nitrogen leaching. To explore reasonable nitrogen application strategies for synergistically enhancing alfalfa production and ecological benefits, this study calibrated and validated the APSIM–Lucerne model based on field experiments conducted from 2021 to 2023. The effects of nitrogen application levels of 0, 80, 120, 140, 160, 180, 200, and 240 kg/ha on alfalfa yield, soil NO₃⁻–N and NH₄⁺–N residues, and nitrogen use efficiency under dry, normal, and wet years were simulated. The results indicate: (1) The calibrated APSIM–Lucerne model effectively simulates alfalfa yield and soil nitrogen residuals (R² ranging from 0.67 to 0.91, NRMSE between 6.55% and 24.03%). (2) Increased nitrogen application significantly elevates soil nitrogen residue, yet alfalfa yield follows a pattern of initial increase followed by decline, with nitrogen fertilizer use efficiency continuously decreasing. Under identical nitrogen application rates, the wet year type proves more advantageous for achieving high yields, low nitrogen residue, and high nitrogen fertilizer use efficiency. (3) The nitrogen application thresholds for achieving increased alfalfa yields and high efficiency during dry years, normal years, and wet years are 107–140 kg/ha, 135–160 kg/ha, and 150–183 kg/ha, respectively.

Plant nitrogen content (PNC) is a core physiological parameter characterizing crop nitrogen nutrition status. Its precise and dynamic monitoring is crucial for crop growth diagnosis, optimizing nitrogen fertilizer management, enhancing fertilizer use efficiency, and reducing agricultural nonpoint source pollution. This study utilized multispectral imagery from unmanned aerial vehicles (UAVs) to extract vegetation indices (VIs) and texture feature values (TFVs) during critical growth stages of alfalfa. By combining TFVs to construct texture indices (TIs), variables exhibiting extremely significant correlations with alfalfa PNC (p < 0.001) were identified. We used VIs, TIs, and their combined features as model inputs. The performance of four machine learning models—random forest regression (RFR), Support Vector Regression (SVR), Backpropagation Neural Network (BPNN), and gradient boosting (XG-Boost)—was comprehensively assessed for estimating alfalfa PNC. Our results indicate the following: (1) The correlation coefficients |r| between VIs and alfalfa PNC ranged from 0.56 to 0.68; TIs constructed from TFVs significantly enhanced PNC correlation compared to raw texture values, with |r| exceeding 0.6. (2) Integrating VIs and TIs substantially improved the accuracy of PNC estimation models across growth stages. Compared to using VIs or TIs alone, the validation set R² increased by 5.4–19.7%, 1.7–16.4%, and 5.2–17.2% for the branching, budding, and initial flowering stages, respectively. (3) The XG-Boost model demonstrated optimal performance across all growth stages and input variables. Particularly during the budding stage, the VIs + TIs model achieved the highest fitting accuracy: training set R² = 0.81, RMSE = 0.15%; validation set R² = 0.80, RMSE = 0.12%. In summary, integrating multispectral vegetation indices and texture indices effectively enhances the accuracy of PNC estimation in alfalfa, providing scientific support for precision field management and fertilization decisions in alfalfa cultivation.

Timely access to soil moisture conditions in farmland crops is the foundation and key to achieving precise irrigation. Due to their high spatiotemporal resolution, unmanned aerial vehicle (UAV) remote sensing has become an important method for monitoring soil moisture. This study addresses soil moisture retrieval in alfalfa fields across different growth stages. Based on UAV multispectral images, a multi-source feature set was constructed by integrating spectral and texture features. The performance of three machine learning models—random forest regression (RFR), K-nearest neighbors regression (KNN), and XG-Boost—as well as two ensemble learning models, Voting and Stacking, was systematically compared. The results indicate the following: (1) The integrated learning models generally outperform individual machine learning models, with the Voting model performing best across all growth stages, achieving a maximum R² of 0.874 and an RMSE of 0.005; among the machine learning models, the optimal model varies with growth stage, with XG-Boost being the best during the branching and early flowering stages (maximum R² of 0.836), while RFR performs better during the budding stage (R² of 0.790). (2) The fusion of multi-source features significantly improved inversion accuracy. Taking the Voting model as an example, the accuracy of the fused features (R² = 0.874) increased by 0.065 compared to using single-texture features (R² = 0.809), and the RMSE decreased from 0.012 to 0.005. (3) In terms of inversion depth, the optimal inversion depth for the branching stage and budding stage is 40–60 cm, while the optimal depth for the early flowering stage is 20–40 cm. In summary, the method that integrates multi-source feature fusion and ensemble learning significantly improves the accuracy and stability of alfalfa soil moisture inversion, providing an effective technical approach for precise water management of artificial grasslands in arid regions.

Scientific nitrogen management is essential for maximizing crop growth potential while minimizing resource waste and environmental impacts. Alfalfa (Medicago sativa L.) is the most widely cultivated high-quality leguminous forage crop globally, and is capable of providing nitrogen through nitrogen fixation. However, there remains some disagreement regarding its nitrogen management strategies. This study conducted a three-year field experiment and calibrated the APSIM-Lucerne model. Based on the calibrated model, three typical precipitation year types (dry, normal, and wet years) were selected. Combining field experiments, eight nitrogen application scenarios (0, 80, 120, 140, 160, 180, 200, and 240 kg·ha⁻¹) were set up. With the objectives of increasing alfalfa yield, nitrogen partial productivity, and nitrogen agronomic efficiency, this study investigates the appropriate nitrogen application thresholds for alfalfa under different precipitation year types. The results showed the following: (1) Alfalfa yield increased first and then decreased with the increase in nitrogen application level. The annual yield of the N160 treatment was the highest (13.39 t·ha⁻¹), which was 5.15% to 32.39% higher than that of the other treatments. (2) The APSIM-Lucerne model could well reflect the growth process and yield of alfalfa under different precipitation year types. The R² and NRMSE between the simulated and observed values of the former were 0.85–0.91 and 5.33–7.44%, respectively. The R² and NRMSE between the simulated and measured values of the latter were 0.74–0.96 and 2.73–5.25%, respectively. (3) Under typical dry, normal, and wet years, the optimal nitrogen application rates for alfalfa yield increases were 120 kg·ha⁻¹, 140 kg·ha⁻¹, and 160 kg·ha⁻¹, respectively. This study can provide a basis for precise nitrogen management of alfalfa under different precipitation year types.