The recognition and localization of strawberries are crucial for automated harvesting and yield prediction. This article proposes a novel RTF-YOLO (RepVgg-Triplet-FocalLoss-YOLO) network model for real-time strawberry detection. First, an efficient convolution module based on structural reparameterization is proposed. This module was integrated into the backbone and neck networks to improve the detection speed. Then, the triplet attention mechanism was embedded into the last two detection heads to enhance the network’s feature extraction for strawberries and improve the detection accuracy. Lastly, the focal loss function was utilized to enhance the model’s recognition capability for challenging strawberry targets, which thereby improves the model’s recall rate. The experimental results demonstrated that the RTF-YOLO model achieved a detection speed of 145 FPS (frames per second), a precision of 91.92%, a recall rate of 81.43%, and an $mAP$ (mean average precision) of 90.24% on the test dataset. Relative to the baseline of YOLOv5s, it showed improvements of 19%, 2.3%, 4.2%, and 3.6%, respectively. The RTF-YOLO model performed better than other mainstream models and addressed the problems of false positives and false negatives in strawberry detection caused by variations in illumination and occlusion. Furthermore, it significantly enhanced the speed of detection. The proposed model can offer technical assistance for strawberry yield estimation and automated harvesting.

The application of slow-release fertilizers is essential for improving fertilizer utilization efficiency and promoting sustainable agricultural development. Unlike traditional single organic polymer-coated or inorganic-coated fertilizers, this study utilized biodegradable modified polyvinyl alcohol (PVA) as a binder and cheap, readily available phosphogypsum–bentonite as an inorganic coating material to develop a novel slow-release potassium magnesium sulfate fertilizer (SRPMSF). This study initially examined the influence of SA dosage on PVA properties. XRD, FTIR, TGA, and water resistance analyses revealed that sodium alginate exhibits good compatibility with polyvinyl alcohol, enhancing its heat and water resistance. Ultimately, PVA–SA-2 (1.2% sodium alginate) was chosen as the optimal binder for SRPMSF production. Furthermore, this study investigated the impact of bentonite on the physical and slow-release properties of the SRPMSF by varying the phosphogypsum-to-bentonite ratio. This experiment included five treatment methods: the treatments consist of SRPMSF-1 (0 g bentonite), SRPMSF-2 (phosphogypsum/bentonite ratio of 4:1), SRPMSF-3 (3:2), SRPMSF-4 (2:3), and SRPMSF-5 (1:4). A control group (PMSF) was also included. The results indicated that, as the bentonite content increased, both the particle size and compressive strength of the coated slow-release fertilizer increased, with the SRPMSF particle sizes ranging from 3.00 to 4.50 mm. The compressive strength of the SRPMSF ranged from 20.85 to 43.78 N, meeting the requirements for industrial production. The soil column leaching method was employed to assess the nutrient release rate of the fertilizers. The experimental results indicated that, compared to the PMSF, the SRPMSF effectively regulated nutrient release. Pot experiments demonstrated that the SRPMSF significantly enhanced garlic seedling growth compared to the PMSF. In conclusion, a new type of slow-release fertilizer with good slow-release performance is prepared in this paper, which can improve the utilization rate of fertilizer and reduce the economic loss and is conducive to the sustainable development of agriculture.

The humanoid torso is crucial for the overall performance of a humanoid robot. Developing an effective humanoid spine is essential for enhancing this mechanism. This paper introduces a one-vertebral-disc unit inspired by human spine anatomy. A prototype was created using 3D-printed parts and commercially available components. Two general human-like motions are achieved using two servo motors and two pulleys, reducing the number of servo motors needed. The results indicate that a one-vertebral-disc unit can bend up to 15 degrees. The proposed mechanism functions effectively and successfully mimics human movements. It holds potential for integration into humanoid torsos, enabling efficient performance in human-like tasks in the future.

To address the issue of excessive chemical fertilizer use in agricultural production, this study conducted a pot experiment with four treatments: CK (no fertilization), T1 (the application of potassium magnesium sulfate fertilizer), T2 (the application of slow-release fertilizer equal to T1), and T3 (the application of slow-release fertilizer with the same fertility as T1). The effects of these treatments on garlic seedling yield, growth quality, chlorophyll content, photosynthetic characteristics, and the soil environment were investigated to evaluate the feasibility of replacing conventional fertilizers with slow-release formulations. The results showed that compared with CK, all three fertilized treatments (T1, T2, and T3) significantly increased the plant heights and stem diameters of the garlic sprouts (p < 0.05). Plant height increased by 14.85%, 17.81%, and 27.75%, while stem diameter increased by 9.36%, 8.83%, and 13.96%, respectively. Additionally, the chlorophyll content increased by 4.34%, 7.22%, and 8.05% across T1, T2, and T3, respectively. Among the treatments, T3 exhibited the best overall growth performance. Compared with those in the CK group, the contents of soluble sugars, soluble proteins, free amino acids, vitamin C, and allicin increased by 64.74%, 112.17%, 126.82%, 36.15%, and 45.43%, respectively. Furthermore, soil organic matter, available potassium, magnesium, and phosphorus increased by 109.02%, 886.25%, 91.65%, and 103.14%, respectively. The principal component analysis indicated that soil pH and exchangeable magnesium were representative indicators reflecting the differences in the soil’s chemical properties under different fertilization treatments. Compared with the CK group, the metal contents in the T1 group slightly increased, while those in T2 and T3 generally decreased, suggesting that the application of slow-release fertilizer exerts a certain remediation effect on soils contaminated with heavy metals. This may be attributed to the chemical precipitation and ion exchange capacities of phosphogypsum, as well as the high adsorption and cation exchange capacity of bentonite, which help reduce the leaching of soil metal ions. In summary, slow-release fertilizers not only promote garlic sprout growth but also enhance soil quality by regulating its chemical properties.

While organic amendments are promoted for enhancing soil quality, their impacts on the net global warming potential (GWP) and the underlying microbial mechanisms in the maize system remain elusive. By using a long-term field experiment established in 2007 under a winter wheat-summer maize rotation system, a field study was conducted to investigate the effects of different organic-amended treatments (manure application and straw return coupled with conventional or no tillage) on greenhouse gas (i.e., nitrous oxide [N ₂ O] and carbon dioxide [CO ₂ ]) emissions, soil organic carbon (SOC) stocks and functional genes governing soil C and N cycling during the 2021 and 2022 maize growing seasons. Compared to conventional N fertilization (CN), long-term organic amendments, particularly manure application, significantly enhanced SOC stocks by 16.7–46.2% while reducing cumulative N ₂ O emissions by 22.9–30.2%, respectively. Although a 22.6–44.5% increase in CO ₂ emissions were observed under organic amendments relative to CN, the concurrent SOC gains and N ₂ O mitigation shifted the field-scale net GWP from positive to negative. Multivariate analyses implied that enhanced SOC sequestration under organic amendments was mainly associated with greater exogenous organic matter inputs and enriched C fixation genes, and lower N ₂ O emissions were accompanied by lower bacterial amoA and higher nosZ gene abundances, suggesting that reduced nitrification and enhanced N ₂ O reduction potential may have contributed to N ₂ O mitigation. Therefore, long-term manure application is a viable strategy to achieve climate-smart maize production by enhancing SOC sequestration, mitigating N ₂ O emissions and maintaining yield without additional chemical N input.