Here, the best ratio of slow-release nitrogen fertilizer to urea was determined to match the nitrogen demand of winter wheat. The fertilizer application structure was also optimized for the efficient use of nitrogen fertilizer and economic benefits. Seven fertilizer treatments were applied into the winter wheat in a two-year field trial: urea only (U), slow-release N fertilizer only (S), slow-release N fertilizer with the urea 1:3 (SU1), 1:1 (SU2), and 3:1 (SU3), no N fertilizer (N0) and no fertilizer (CK). A systematic investigation was made to explore the effects of slow-release N fertilizer application rates on the dry matter accumulation and transport, yield, and N fertilizer use efficiency of winter wheat. The results showed that there was an increase in the rapid growth period and the maximum accumulation rate of dry matter in the winter wheat with the proportion of slow-release N fertilizer. The average dry matter accumulation rate of slow-release nitrogen fertilizer combined with the urea increased by 1.90% to 19.91%, compared with the ordinary urea. The proportion of slow-release nitrogen fertilizer application posed a significant impact on the post post-flowering dry matter production. There was an increase in the pre and post post-flowering dry matter transport. Meanwhile, the post post-flowering dry matter production was contributed 53.18% to 71.83% of the grain yield. The yield increased significantly with the increasing proportion of slow-release N fertilizer, with the two-year yields of 7 243 and 8 021 kg/hm² in the SU3, which were 7.25% and 16.07% higher than the S and U treatments, respectively, and their economic benefits were 15.18% and 25.67%, respectively. The cumulative nitrogen uptake of winter wheat increased by the application of slow-release nitrogen fertilizer with the urea. Specifically, the cumulative nitrogen uptake values were 24.08% to 36.63% higher than those in the SU3, compared with the U treatment. The slow-release N fertilizer with the urea was improved the N fertilizer use efficiency. The agronomic use efficiency, physiological use efficiency, and biased productivity were improved in the SU3, compared with the U treatment. But there was no significant difference between SU2 and SU3 treatments (P>0.05). The slow-release N combined with the urea was significantly improved the N use efficiency, but there was no significant difference between SU2 and SU3 treatments (P>0.05). Therefore, the slow-release N fertilizer mixed with the urea can be expected to improve the winter wheat yield and N use efficiency. The dry matter growth period was significantly extended to promote the maximum accumulation rate for the post-flowering dry matter production and its transport rate to the seed. By comprehensive consideration, under the condition of nitrogen application rate of 180 kg/hm², the combination of slow-release nitrogen fertilizer and urea application ratio of 50% (SU2) can achieve green, high yield, and high efficiency of winter wheat. Among them, the yield is 7 458 kg/hm², the nitrogen fertilizer absorption and utilization rate is 45.97%, and the agronomic utilization rate, physiological utilization rate, and partial productivity are 16.07, 30.49, and 42.09 kg/kg, respectively. The finding can provide the theoretical basis for the rational fertilization of winter wheat. Follow-up studies need to consider the environmental effects and carbon and nitrogen emissions, together with the impact of slow-release nitrogen fertilizer combined with the urea on the soil nitrate nitrate-nitrogen distribution, ammonia volatilization, and greenhouse gas emissions. Further research can be conducted to determine the amount and proportion of slow-release nitrogen fertilizer and urea application for the high yield, high efficiency, and simultaneous emission reduction in winter wheat farmland.

An AquaCrop model has been used to simulate the crop growth of the mulched farmland in the arid regions of Northwest China. This study aims to optimize the film-mulched maize growth dynamics for high adaptability and accuracy. Four-year field experiments (2018, 2019, 2023, and 2024) were conducted with three treatments: flat planting without film mulching (NM), flat planting with full film mulching (PM), and full film double ridge furrow sowing (BM). The temperature compensation was proposed to adjust the external meteorological inputs. A compensation coefficient was derived from the relationship between soil and air temperature under mulched conditions. The individual coefficients in the different growth stages were determined to compare with those in the entire growth period; Alternatively, temperature source replacement was implemented to replace daily extreme air temperatures with daily extreme soil temperatures, in order to directly deduce the model. The performance of the improved model was finally evaluated on the simulated and observed canopy cover, biomass, and yield using root mean square error (RMSE) and normalized root mean square error (NRMSE). The results showed that there was a significant correlation between the 20 cm soil and air temperature (P < 0.05) for the NM, PM, and BM treatments, with the determination coefficients (R²) ranging from 0.56 to 0.92. The mean slopes of the linear regression equations for the NM, PM, and BM were 0.77, 0.86, and 0.80, respectively. Compared with the NM, the warming performance was more pronounced under PM, followed by BM. Moreover, the PM and BM treatments significantly increased to accumulate the surface soil temperature, particularly from the seedling stage to pre-tasseling. There was a significantly different soil-air temperature in this period. The substantial compensation was then obtained to calculate the growing degree days. The heat accumulation was accelerated to shorten the duration from seedling emergence to tasseling. In both PM and BM treatments, the temperature compensation coefficient from sowing to seedling emergence (1.23-1.76) was greater than that from seedling emergence to tasseling (0.50-0.67). Moreover, the overall temperature compensation increment from sowing to tasseling (0.70-1.54 °C) was intermediate between that from sowing to seedling emergence (1.12-5.12 °C) and from seedling emergence to tasseling (0.57-1.13 °C). According to the temperature compensation, the NRMSE of canopy cover, biomass, and yield for the PM and BM treatments over four growing seasons was reduced from 3.1%-15.7%, 11.0%-20.6%, and 10.9-20.9% in the original model to 1.7%-10.2%, 10.3%-18.1%, and 3.7%-20.1%, respectively, with the maximum NRMSE improvement of 16.5%, in order to effectively enhance the simulation accuracy of mulched maize growth. With the temperature source replacement, the simulated biomass and yield NRMSE for the PM and BM treatments were improved from 11.0%-20.6% and 10.9%-23.0% in the original model to 10.3%-18.1% and 1.4%-17.4%, respectively. Compared with the temperature compensation approach, the temperature source replacement further reduced the biomass RMSE and NRMSE by 0-0.6 t/hm² and 0-4.1%, while the yield RMSE and NRMSE by 0-0.8 t/hm² and 0-7.9%, respectively. The accuracy of the AquaCrop model was enhanced to simulate the growth and development of the mulched maize, indicating more precise predictions of the growth dynamics. Both approaches were significantly improved to simulate the dynamic variations in the biomass and yield. The better performance was confirmed to incorporate the mulching-induced warming. The applicability of the model was extended to mulched agriculture in arid regions. The finding can also provide a reliable quantitative tool to evaluate the different mulching patterns and practices.

Accurate monitoring of canopy equivalent water thickness (EWT) in winter wheat can greatly contribute to precision water management and irrigation strategies in sustainable agriculture. However, traditional machine learning is limited to the complex and non-linear relationships between feature interactions. This study aimed to enhance the estimation of the wheat canopy EWT by multi-modal unmanned aerial vehicle (UAV) remote sensing features and advanced deep learning techniques. High accuracy was also obtained to monitor the canopy EWT of winter wheat. An optimal estimation model was then established to facilitate the high-precision and field-scale monitoring of the crop water status throughout the growth stages. Firstly, the field experiments under different water and nitrogen treatments were conducted during the turning green, jointing, and heading stages of winter wheat in 2022−2023. The experimental treatments included three irrigation levels (rainfed, 30 mm in overwintering and 30 mm in the jointing stage, and 60 mm at overwintering and 60 mm at the jointing stage), four amounts of nitrogen fertilization (0, 100, 200, and 300 kg/hm²). The high-resolution images of the wheat canopies were collected at turning green, jointing, and heading stages using visible (red, green, and blue), and multispectral (red-edge and near-infrared) sensors carried by the UAV platform. The canopy EWTs were simultaneously made for the destructive sampling by manual in-field experiments. Secondly, the spectral features (visible and multispectral indices), textural features (normalized difference texture index, ratio texture index, and difference texture index), and structural features (plant height and canopy cover) were extracted by band calculation, gray-level co-occurrence matrix, and three-dimensional point cloud data processing, respectively. The feature importance scores were analyzed by recursive elimination feature (REF), BORUTA, and least absolute shrinkage and selection operator (LASSO) algorithms, respectively. Finally, a composite neural network (MDFNN) was constructed to extract the multi-modal deep features by combining a convolutional neural network (CNN) and a long short-term memory network (LSTM). The CNN module contained three independent convolutional architectures for depth feature extraction at three growth stages. The deep features of each growth stage were concatenated by a fully connected layer as the input of the LSTM. The final output was set as the EWT. The four algorithms of machine learning were adopted to compare the model accuracy, including k-nearest neighbors, partial least squares, random forest, and support vector machine. The results showed that the multi-modal feature fusion improved the estimation accuracy of the EWT, compared with any single modal feature, with the determination coefficients (R²) of 0.709−0.810, root mean square errors (RMSE) of 0.054−0.063 mm, and mean absolute percentage errors (MAPE) of 9.00%−21.5%. The most retained features by all three-feature selections were the texture features, followed by spectral and structural features. The REF shared the best optimization (8 spectral features, 10 texture features, and 2 structural features.), while the BORUTA and LASSO failed to optimize the model performance and even reduced model accuracy. Compared with the accuracy of machine learning models with the single modal features, the texture features showed excellent performance, with R² of 0.629−0.706, RMSE of 0.063−0.078 mm, and MAPE of 20.20%−29.10%. Compared with four machine learning models, the MDFNN significantly improved the estimation accuracy of the wheat canopy EWT and reduced the prediction error using all feature selection datasets. The estimation accuracy of MDFNN with the REF features was achieved with the highest estimation accuracy, with the R² of 0.88, RMSE of 0.050 mm, and MAPE of 6.60%. The inverse maps were obtained from the optimal MDFNN model and accurately reflected the changes of canopy EWT with the temporal and spatial variations. The UAV-based monitoring framework was combined with the multi-modal data and deep learning for the high-resolution EWT estimation of the wheat canopy. The MDFNN model outperformed the conventional machine learning. The complex feature interactions were effectively obtained across spatial and temporal dimensions. The finding can provide the theoretical references for the UAV remote sensing to monitor the winter wheat canopy EWT, particularly with the potential applications in irrigation scheduling and stress monitoring.

The ridge film and furrow sowing model has been widely used in the arid region of northwest China, in order to solve the problems of low yield , water and nitrogen use efficiency of winter wheat caused by drought, and unreasonable nitrogen application rate and planting density in northwest China, we explored the optimal nitrogen fertilizer and density management for high yield and efficient use of water and nitrogen of winter wheat in the ridge mulching and furrow sowing mode. Three density gradients of 150 kg/hm² (D1), 187.5 kg/hm² (D2) and 225 kg/hm² (D3) and three nitrogen application rate of 180 kg N/hm² (N1), 270 kg N/hm² (N2) and 360 kg N/hm² (N3) were set in the experiment. In a two-year field experiment (2021-2022 and 2022-2023), taking “Xiaoyan 22” as the test variety, to study the effects of different nitrogen and density treatments on the physiological growth, aboveground dry matter, yield, water and nitrogen use efficiency of winter wheat. Study the following conclusions are obtained: leaf area index (LAI) and aboveground dry matter accumulation showed a parabolic trend with the increase of nitrogen application rate or planting density, compared with local conventional nitrogen and density treatment (D1N3), reasonably increasing planting density and decreasing nitrogen application could increase LAI at the tasseling stage, and the maximum dry matter accumulation and accumulation rate by 147.25% and 65.29%. With the increase of soil depth, the soil moisture content increased at jointing stage, but decreased then increased at heading stage and filling stage. The average soil water content of 100 cm soil layer in 2 years was the highest in D3N3 and D1N3, respectively. Chlorophyll content reaches the maximum at heading stage, the suitable nitrogen and density management increased the chlorophyll content by 0.53%-31.25%. The interaction between nitrogen fertilizer and density had significant (P＜0.001) effects on yield, water and nitrogen use efficiency. Reasonable density and nitrogen management measures are conducive to the increase of yield and water and nitrogen use efficiency. Excessive nitrogen application rate or excessive planting density had certain inhibitory effects on crop growth. With the increasing of planting density or nitrogen application, the yield and water use efficiency (WUE) showed a tendency of increasing and then decreasing, and the yield reached the maximum in the D2N2 treatment, with a two-year average of 11911.93 kg/hm². Based on the regression model, comprehensive evaluation of yield, WUE and NPFP, the optimization conditions were 95% of the maximum value of yield and WUE, 85% of the maximum value of NPFP, the combination pattern of planting density of 180.45-190.04 kg/hm² and nitrogen application rate of 201.66-256.67 kg/hm² was finally determined as the nitrogen and density management measures for high yield and nitrogen efficient utilization of ridge mulching and furrow sowing winter wheat, it realized the synergistic improvement of yield and resource utilization efficiency to the maximum extent. The results of the study can provide practical guidance and theoretical basis for the high yield and efficiency cultivation of winter wheat in Northwest of China.

Ridge-furrow film mulching has been widely used as a water-saving and yield-increasing planting pattern in arid and semiarid regions. Planting density is also a vitally important factor influencing crop yield, and the optimal planting density will vary in different environments (such as ridge-furrow film mulching). How the combination of film mulching and planting density will affect the growth, physiology, yield, and water and radiation use efficiencies of winter oilseed rape is not clear yet. Therefore, a three-year field experiment was conducted from 2017 to 2020 to explore the responses of leaf chlorophyll (Chl) content, net photosynthetic rate (P_n), leaf area index (LAI), aboveground dry matter (ADM), root growth and distribution, yield, evapotranspiration (ET), water use efficiency (WUE), and radiation use efficiency (RUE) of winter oilseed rape to different film mulching patterns (F, ridge-furrow planting with plastic film mulching over the ridges; N, flat planting without mulching) and planting densities (LD, 100,000 plants ha^–1; MD, 150,000 plants ha^–1; HD, 200,000 plants ha^–1). The results showed that the F treatments led to significantly greater leaf Chl contents, P_n, LAI, and ADM, and a stronger root system than treatments without film mulching throughout the whole winter rapeseed growing seasons. Winter oilseed rape in the MD treatments had better physiological (leaf Chl contents and P_n) and growth (LAI, ADM, taproot, and lateral root) conditions than in LD and HD at the late growth period after stem-elongation. Grain yield in FMD was the greatest, and it was significantly greater by 34.8–46.0%, 6.7–9.6%, 87.8–108.3%, 38.7–50.3%, and 50.2–61.8% compared to those of FLD, FHD, NLD, NMD, and NHD, respectively. Furthermore, the ET in FMD was equivalent to FLD and FHD, but was markedly lower by 12.2–18.4%, 14.5–20.3%, and 14.6–20.4% than in NLD, NMD, and NHD. Finally, the WUE and RUE in FMD were significantly improved by 88.5–94.0% and 29.0–41.8% compared to NHD (the local conventional planting pattern and planting density for winter rapeseed). In summary, FMD is a favorable cultivation management strategy to save water, increase yield and improve resource utilization efficiencies in winter oilseed rape in Northwest China.