Nitrification inhibitor (NI) and urease inhibitor (UI) with fertilizer have the potential to reduce nitrogen (N) loss as well as improve grain yields. Urea–ammonium nitrate (UAN) solution as liquid fertilizer is superior to conventional solid nitrogen (N) fertilizer in terms of fertilizer efficiency, energy savings, environmental pollution reduction and economic benefits. However, comprehensive assessments of UAN with inhibitors from an environmental and agronomy perspective, including insights into the mechanisms of UAN with inhibitors, are lacking. In a field trial, three single-inhibitor and two double-inhibitor (DI) treatments were set to quantify the grain yield, the N losses and the N recovery efficiency of maize treated with urea supplemented with dicyandiamide (DCD), 3,4-dimethylpyrazole phosphate (DMPP) and N-(n-buty_l) thiophosphoric triamide (NBPT). Compared with the UAN treatment, the supply of urease inhibitors reduced NH₃ emission by 13.0% but increased N₂O emission by 13.0%. The supply of nitrification inhibitors delayed the conversion of ammonium N to nitrate N and improved NH₃ emission by 23.5–28.7%, but reduced N₂O emission by 31.4% and significantly increased the maize yield by 21.3%. The combined use of NBPT and DCD were not compatible in UAN and cannot achieve the maximum potential for optimizing yields and reducing nitrogen losses. Considering the grain yield, the N use efficiency and the N losses, the combined use of NBPT and DMPP in maize production system significantly improved the grain yield and N use efficiency, as well as reduced N losses.

In response to the demand for real-time monitoring of the nitrogen nutritional status of peanut populations, this paper proposes a real-time monitoring system for the nitrogen nutritional status of peanut populations based on the YOLOv11 framework and spectral attention module. Traditional nitrogen detection methods have problems such as low efficiency and difficulty in achieving population-scale monitoring, while crop phenotyping technology based on computer vision faces challenges such as small leaf targets, severe occlusion, easy confusion of nitrogen deficiency symptoms, and difficulty in deploying deep learning models on mobile terminals. This study improves the YOLOv11 model, introduces the ASF (Attentional Scale Fusion) module and the DySample dynamic upsampling mechanism, enhances the model’s perception and feature expression capabilities for multi-scale targets, and effectively improves the monitoring accuracy and robustness of the nitrogen nutritional status of peanut populations. Experimental results show that the ADS-YOLO model performs well in evaluation indicators such as accuracy, recall, and mean average precision (mAP), providing technical support for precision fertilization of peanuts.