Search Results (7,676)

The rice-wheat rotation is the main agricultural cropping system in Jiangsu Province, playing a vital role in ensuring food security and promoting economic development. However, current research on rice-wheat systems mainly focuses on in-situ controlled experiments at the point scale, with limited studies addressing carbon footprint (CF) and energy balance (EB) at the regional scale and long time series. Therefore, we analyzed the evolution patterns of the CF and EB of the rice-wheat system in Jiangsu Province from 1980 to 2022, as well as their influencing factors. The results showed that the sown area and total yield of rice and wheat exhibited an increasing–decreasing–increasing trend during 1980–2022, while the yield per unit area increased continuously. The CF of rice and wheat increased by 4172.27 kg CO₂ eq ha⁻¹ and 2729.18 kg CO₂ eq ha⁻¹, respectively, with the greenhouse gas emissions intensity (GHGI) showing a fluctuating upward trend. Furthermore, CH₄ emission, nitrogen (N) fertilizer, and irrigation were the main factors affecting the CF of rice, with proportions of 36%, 20.26%, and 17.34%, respectively. For wheat, N fertilizer, agricultural diesel, compound fertilizer, and total N₂O emission were the primary contributors, accounting for 42.39%, 22.54%, 13.65%, and 13.14%, respectively. Among energy balances, the net energy (NE) of rice exhibited an increasing and then fluctuating trend, while that of wheat remained relatively stable. The energy utilization efficiency (EUE), energy productivity (EPD), and energy profitability (EPF) of rice showed an increasing and then decreasing trend, while wheat decreased by 46.31%, 46.31%, and 60.62% during 43 years, respectively. Additionally, N fertilizer, agricultural diesel, and compound fertilizer accounted for 43.91–45.37%, 21.63–25.81%, and 12.46–20.37% of energy input for rice and wheat, respectively. Moreover, emission factors and energy coefficients may vary over time, which is an important consideration in the analysis of long-term time series. This study analyzes the ecological and environmental effects of the rice-wheat system in Jiangsu Province, which helps to promote the development of agriculture in a green, low-carbon, and high-efficiency direction. It also offers a theoretical basis for constructing a low-carbon sustainable agricultural production system. Full article

Apomixis-mediated fixation of heterosis could transform hybrid breeding in alfalfa (Medicago sativa), a globally important forage crop. The parthenogenesis-inducing morphogenetic regulator BABY BOOM (BBM) represents a promising candidate for enabling this advancement. Here, we identified BBM homologs from three alfalfa genomes, characterized their promoter regions, and cloned a 2082 bp MsBBM gene encoding a 694-amino acid nuclear-localized protein. Three alfalfa BBM gene promoters primarily contained light- and hormone-responsive elements. Phylogenetic and conserved domain analyses of the MsBBM protein revealed a high sequence similarity with M. truncatula BBM. Expression profiling demonstrated tissue-specific accumulation of MsBBM transcripts, with the highest expression in the roots and developing pods. Hormonal treatments differentially regulated MsBBM. Expression was upregulated by GA₃ (except at 4 h) and SA, downregulated by NAA, MeJA (both except at 8 h), and ABA (except at 4 h), while ETH treatment induced a transient expression peak at 2 h. As an AP2/ERF family transcription factor showing preferential expression in young embryos, MsBBM likely participates in reproductive development and may facilitate apomixis. These findings establish a molecular framework for exploiting MsBBM to enhance alfalfa breeding efficiency through heterosis fixation. Full article

In agricultural practice, in addition to determining the nitrogen (N_f) dose, it is necessary to effectively control its effect on currently grown crops. Meeting these conditions requires not only the use of phosphorus (P) and potassium (K), but also nutrients such as magnesium (Mg) and sulfur (S). This hypothesis was verified in a single-factor field experiment with winter wheat (WW) carried out in the 2015/2016, 2016/2017, and 2017/2018 growing seasons. The experiment consisted of seven variants: absolute control (AC), NP, NPK-MOP (K as Muriate of Potash), NPK-MOP+Ki (Kieserite), NPK-KK (K as Korn–Kali), NPK-KK+Ki, and NPK-KK+Ki+ES (Epsom Salt). The use of K as MOP increased grain yield (GY) by 6.3% compared to NP. In the NPK-KK variant, GY was 13% (+0.84 t ha⁻¹) higher compared to NP. Moreover, GYs in this fertilization variant (FV) were stable over the years (coefficient of variation, CV = 9.4%). In NPK-KK+Ki+ES, the yield increase was the highest and mounted to 17.2% compared to NP, but the variability over the years was also the highest (CV ≈ 20%). The amount of N in grain N (GN) increased progressively from 4% for NPK-MOP to 15% for NPK-KK and 25% for NPK-KK+Ki+ES in comparison to NP. The nitrogen harvest index was highly stable, achieving 72.6 ± 3.1%. All analyzed NUE indices showed a significant response to FVs. The PFP-N_f (partial factor productivity of N_f) indices increased on NPK-MOP by 5.8%, NPK-KK by 12.9%, and NPK-KK+Ki+ES by 17.9% compared to NP. The corresponding N_f recovery of N_f in wheat grain was 47.2%, 55.9%, and 64.4%, but its total recovery by wheat (grain + straw) was 67%, 74.5%, and 87.2%, respectively. In terms of the theoretical and practical value of the tested indexes, two indices, namely, NUP (nitrogen unit productivity) and NUA (nitrogen unit accumulation), proved to be the most useful. From the farmer’s production strategy, FV with K applied in the form of Korn–Kali proved to be the most stable option due to high and stable yield, regardless of weather conditions. The increase in the number of nutritional factors optimizing the action of nitrogen in winter wheat caused the phenomenon known as the “scissors effect”. This phenomenon manifested itself in a progressive increase in nitrogen unit productivity (NUP) combined with a regressive trend in unit nitrogen accumulation (NUA) in the grain versus the balance of soil available Mg (Mg_b). The studies clearly showed that obtaining grain that met the milling requirements was recorded only for NUA above 22 kg N t⁻¹ grain. This was possible only with the most intensive Mg treatment (NPK-KK+Ki and NPK-KK+Ki+ES). The study clearly showed that three of the six FVs fully met the three basic conditions for sustainable crop production: (i) stabilization and even an increase in grain yield; (ii) a decrease in the mass of inorganic N in the soil at harvest, potentially susceptible to leaching; and (iii) stabilization of the soil fertility of P, K, and Mg. Full article

This research aims to analyze the evolution of productivity and efficiency in tractors featuring varying propulsion system designs through the development of a parametric modeling approach. Recognizing that large row-crop tractors represent a significant capital investment—ranging from USD 0.4 to over 0.8 million for current-generation models—and that machinery costs constitute a substantial share of farm production expenses, this study addresses the urgent need for data-driven decision-making in agricultural enterprises. Utilizing consolidated OECD Code 2 tractor test data for all large row-crop John Deere tractors from the MFWD era to the latest generation, the study evaluates tractor performance across multiple productivity and efficiency indicators. The analysis culminates in the creation of a robust, user-friendly parametric model (R² = 0.9337, RMSE = 1.0265), designed to assist stakeholders in making informed decisions regarding tractor replacement or upgrading. By enabling the optimization of productivity and efficiency while accounting for agronomic and timeliness constraints, this model supports sustainable and profitable management practices in modern agriculture. Full article

Crop disease identification is a pivotal research area in smart agriculture, forming the foundation for disease mapping and targeted prevention strategies. Among the most prevalent global wheat diseases, powdery mildew—caused by fungal infection—poses a significant threat to crop yield and quality, making early and accurate detection crucial for effective management. In this study, we present QY-SE-MResNet34, a deep learning-based classification model that builds upon ResNet34 to perform multi-class classification of wheat leaf images and assess powdery mildew severity at the single-leaf level. The proposed methodology begins with dataset construction following the GBT 17980.22-2000 national standard for powdery mildew severity grading, resulting in a curated collection of 4248 wheat leaf images at the grain-filling stage across six severity levels. To enhance model performance, we integrated transfer learning with ResNet34, leveraging pretrained weights to improve feature extraction and accelerate convergence. Further refinements included embedding a Squeeze-and-Excitation (SE) block to strengthen feature representation while maintaining computational efficiency. The model architecture was also optimized by modifying the first convolutional layer (conv1)—replacing the original 7 × 7 kernel with a 3 × 3 kernel, adjusting the stride to 1, and setting padding to 1—to better capture fine-grained leaf textures and edge features. Subsequently, the optimal training strategy was determined through hyperparameter tuning experiments, and GrabCut-based background processing along with data augmentation were introduced to enhance model robustness. In addition, interpretability techniques such as channel masking and Grad-CAM were employed to visualize the model’s decision-making process. Experimental validation demonstrated that QY-SE-MResNet34 achieved an 89% classification accuracy, outperforming established models such as ResNet50, VGG16, and MobileNetV2 and surpassing the original ResNet34 by 11%. This study delivers a high-performance solution for single-leaf wheat powdery mildew severity assessment, offering practical value for intelligent disease monitoring and early warning systems in precision agriculture. Full article

Barcodes are ubiquitous in manufacturing and logistics, but defects can reduce decoding efficiency and disrupt the supply chain. Existing studies primarily focus on a single barcode type or rely on small-scale datasets, limiting generalizability. We propose Y8-LiBAR Net, a lightweight two-stage framework for multi-type barcode defect detection. In stage 1, a YOLOv8n backbone localizes 1D and 2D barcodes in real time. In stage 2, a dual-branch network integrating ResNet50 and ViT-B/16 via hierarchical attention performs three-class classification on cropped regions of interest (ROIs): intact, defective, and non-barcode. Experiments conducted on the public BarBeR dataset, covering planar/non-planar surfaces, varying illumination, and sensor noise, show that Y8-LiBARNet achieves a detection-stage mAP@0.5 = 0.984 (1D: 0.992; 2D: 0.977) with a peak F1 score of 0.970. Subsequent defect classification attains 0.925 accuracy, 0.925 recall, and a 0.919 F1 score. Compared with single-branch baselines, our framework improves overall accuracy by 1.8–3.4% and enhances defective barcode recall by 8.9%. A Cohen’s kappa of 0.920 indicates strong label consistency and model robustness. These results demonstrate that Y8-LiBARNet delivers high-precision real-time performance, providing a practical solution for industrial barcode quality inspection. Full article

Accurate phenological information on sugarcane is crucial for guiding precise cultivation management and enhancing sugar production. Remote sensing offers an efficient approach for large-scale phenology retrieval, but most studies have primarily focused on staple crops. The methods for retrieving the sugarcane phenology—the germination, tillering, elongation, and maturity stages—remain underexplored. This study addresses the challenge of accurately monitoring the sugarcane phenology in complex terrains by proposing an optimized strategy integrating spatiotemporal fusion data. Ground-based validation showed that the change detection method based on the Double-Logistic curve significantly outperformed the threshold-based approach, with the highest accuracy for the elongation and maturity stages achieved at the maximum slope points of the ascending and descending phases, respectively. For the germination and tillering stages with low canopy cover, a novel time-windowed change detection method was introduced, using the first local maximum of the third derivative curve (denoted as Point A) to establish a temporal buffer. The optimal retrieval models were identified as 25 days before and 20 days after Point A for germination and tillering, respectively. Among the six commonly used vegetation indices, the NDVI (normalized difference vegetation index) performed the best across all the phenological stages. Spatiotemporal fusion using the ESTARFM (Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model) significantly improved the monitoring accuracy in heterogeneous agricultural landscapes, reducing the RMSE (root-mean-squared error) by 21–46%, with retrieval errors decreasing from 18.25 to 12.97 days for germination, from 8.19 to 4.41 days for tillering, from 19.17 to 10.78 days for elongation, and from 19.02 to 15.04 days for maturity, highlighting its superior accuracy. The findings provide a reliable technical solution for precision sugarcane management in heterogeneous landscapes. Full article

The high-Andean grass Jarava ichu (Poaceae) plays a vital role in water regulation and aquifer recharge. However, its limited use is often linked to forest fires, highlighting the need for sustainable alternatives. Therefore, this study aims to explore the valorization of ichu as a substrate for the cultivation of Pleurotus spp. (P. citrinopileatus, P. djamor, and P. ostreatus) and to evaluate the potential of the residual substrate as a biofertilizer, offering an ecological alternative to grassland burning in the Peruvian Andes. Samples of ichu from the district of Tomás (Lima, Peru) were used as culture substrate, analyzing productivity indicators such as crop cycle (CC), biological efficiency (BE), and production rate (PR), together with the nutritional profile of the fungi and the chemical properties of the residual substrate. The results showed an average biological efficiency of 19.8%, with no significant differences (p > 0.05) in CC, BE, or PR among the species, confirming the viability of ichu as a substrate. The fungi presented a high protein content (24.1–30.41% on a dry basis), highlighting its nutritional value. In addition, the residual substrate exhibited elevated levels of phosphorus (795.9–1296.9 ppm) and potassium (253.1–291.3 ppm) compared to raw ichu (0.11–7.77 ppm for both nutrients). Germination tests on radish seeds showed rates between 80% and 100%, without inhibition, supporting its potential as a biofertilizer. This study demonstrates the double potential of ichu as a substrate for the sustainable production of edible mushrooms of high nutritional value and as a source of biofertilizers. Full article

Minor cereals are an important part of the Chinese grain industry, accounting for about 8 percent of the country’s total grain-growing area. Minor cereals include millet, buckwheat, Panicum miliaceum, and other similar grains. Influenced by topographical and climatic factors, the distribution of minor cereals in China is mainly concentrated in the plateau and hilly areas north of the Yangtze River. In addition, there are large concentrations of minor cereals in Inner Mongolia, Heilongjiang, and other areas with flatter terrain. However, the level of mechanized harvesting in these areas is still low, and there is little research on the whole process of mechanized harvesting of minor cereals. This paper aims to discuss the current status of the minor cereal industry and its mechanization level, with particular attention to the challenges encountered in research related to the mechanized harvesting of minor cereals, including limited availability of suitable machinery, high losses, and low efficiency. The article provides a comprehensive overview of the key technologies that must be advanced to achieve mechanized harvesting throughout the process, such as header design, threshing, cleaning, and intelligent modular systems. It also summarizes current research progress on advanced equipment for mechanized harvesting of minor cereals. In addition, the article puts forward suggestions to promote the development of mechanized harvesting of minor cereals, focusing on aspects such as crop variety optimization, equipment modularization, and intelligentization technology, aiming to provide a reference for the further development and research of mechanized harvesting technology for minor cereals in China. Full article

The acquisition of plant phenotypic traits is essential for selecting superior varieties, improving crop yield, and supporting precision agriculture and agricultural decision-making. Therefore, it plays a significant role in modern agriculture and plant science research. Traditional manual measurements of phenotypic traits are labor-intensive and inefficient. In contrast, combining 3D reconstruction technologies with autonomous vehicles enables more intuitive and efficient trait acquisition. This study proposes a 3D semantic reconstruction system based on an improved ORB-SLAM3 framework, which is mounted on an unmanned vehicle to acquire phenotypic traits in tomato cultivation scenarios. The vehicle is also equipped with the A * algorithm for autonomous navigation. To enhance the semantic representation of the point cloud map, we integrate the BiSeNetV2 network into the ORB-SLAM3 system as a semantic segmentation module. Furthermore, a two-stage filtering strategy is employed to remove outliers and improve the map accuracy, and OctoMap is adopted to store the point cloud data, significantly reducing the memory consumption. A spherical fitting method is applied to estimate the number of tomato fruits. The experimental results demonstrate that BiSeNetV2 achieves a mean intersection over union (mIoU) of 95.37% and a frame rate of 61.98 FPS on the tomato dataset, enabling real-time segmentation. The use of OctoMap reduces the memory consumption by an average of 96.70%. The relative errors when predicting the plant height, canopy width, and volume are 3.86%, 14.34%, and 27.14%, respectively, while the errors concerning the fruit count and fruit volume are 14.36% and 14.25%. Localization experiments on a field dataset show that the proposed system achieves a mean absolute trajectory error (mATE) of 0.16 m and a root mean square error (RMSE) of 0.21 m, indicating high localization accuracy. Therefore, the proposed system can accurately acquire the phenotypic traits of tomato plants, providing data support for precision agriculture and agricultural decision-making. Full article

Meloidogyne enterolobii, a highly virulent and broad-host-range plant-parasitic nematode, poses an increasing threat to global agricultural production. By inducing the formation of nutrient-rich giant cells in host roots and deploying a diverse array of effector proteins to modulate plant immune responses, this nematode achieves efficient colonization and invasion, resulting in impaired crop growth and significant economic losses. In recent years, global climate warming combined with the rapid development of protected agriculture has broken the traditional geographical limits of tropical and subtropical regions, thereby increasing the risk of M. enterolobii occurrence in temperate and high-latitude areas. Concurrently, conventional chemical control methods are increasingly limited by environmental pollution and the development of resistance, steering research toward green control strategies. This review systematically summarizes the latest research progress of M. enterolobii in terms of ecological diffusion trends, pathogenic mechanisms, and green control, and explored the feasibility of integrating multidisciplinary technologies to construct an efficient and precise control system. The ultimate aim is to provide theoretical support and technical supports for green and sustainable development of global agriculture. Full article

Rice lodging severely affects crop growth, yield, and mechanized harvesting efficiency. The accurate detection and quantification of lodging areas are crucial for precision agriculture and timely field management. However, Unmanned Aerial Vehicle (UAV)-based lodging detection faces challenges such as complex backgrounds, variable lighting, and irregular lodging patterns. To address these issues, this study proposes SWRD–YOLO, a lightweight instance segmentation model that enhances feature extraction and fusion using advanced convolution and attention mechanisms. The model employs an optimized loss function to improve localization accuracy, achieving precise lodging area segmentation. Additionally, a grid-based lodging ratio estimation method is introduced, dividing images into fixed-size grids to calculate local lodging proportions and aggregate them for robust overall severity assessment. Evaluated on a self-built rice lodging dataset, the model achieves 94.8% precision, 88.2% recall, 93.3% mAP@0.5, and 91.4% F1 score, with real-time inference at 16.15 FPS on an embedded NVIDIA Jetson Orin NX device. Compared to the baseline YOLOv8n-seg, precision, recall, mAP@0.5, and F1 score improved by 8.2%, 16.5%, 12.8%, and 12.8%, respectively. These results confirm the model’s effectiveness and potential for deployment in intelligent crop monitoring and sustainable agriculture. Full article

Efficient object detection is crucial to real-time monitoring applications such as autonomous driving or security systems. Modern RGB cameras can produce high-resolution images for accurate object detection. However, increased resolution results in increased network latency and power consumption. To minimise this latency, Convolutional Neural Networks (CNNs) often have a resolution limitation, requiring images to be down-sampled before inference, causing significant information loss. Event-based cameras are neuromorphic vision sensors with high temporal resolution, low power consumption, and high dynamic range, making them preferable to regular RGB cameras in many situations. This project proposes the fusion of an event-based camera with an RGB camera to mitigate the trade-off between temporal resolution and accuracy, while minimising power consumption. The cameras are calibrated to create a multi-modal stereo vision system where pixel coordinates can be projected between the event and RGB camera image planes. This calibration is used to project bounding boxes detected by clustering of events into the RGB image plane, thereby cropping each RGB frame instead of down-sampling to meet the requirements of the CNN. Using the Common Objects in Context (COCO) dataset evaluator, the average precision (AP) for the bicycle class in RGB scenes improved from 21.08 to 57.38. Additionally, AP increased across all classes from 37.93 to 46.89. To reduce system latency, a novel object detection approach is proposed where the event camera acts as a region proposal network, and a classification algorithm is run on the proposed regions. This achieved a 78% improvement over baseline. Full article

Background: Conventional practices for the cultivation of “Cipollotto Nocerino” spring onion are mainly based on growers’ experience, and up to 250 kg/ha for N is commonly furnished among growing cycles. Facing the issue of reduced availability of natural resources for crop production (for example mineral resources), we investigated the optimization of the productivity. Methods: In our research, we tested the use of depletion nutrient supply strategy (CAL-FERT^®) to enhance fertilization in accordance with the principle of sustainable agriculture included in the Farm to Fork strategy. In our study, besides the common initial fertilization, three different strategies for cover fertilizations have been elaborated with the support of CAL-FERT^® software. The treatments were as follows: (i) commercial standard fertilization as control (named CF); (ii) fertilization equivalent to 50% of the N applied in the control (named F-50); (iii) fertilization corresponding to 25% of the N applied in the control (named F-25); and (iv) strongly reduced fertilization compared to the control (named F-0). The parameters investigated included the following: plant height, yield, SPAD index, nitrogen use efficiency, dry matter, soluble solid content, and pyruvate contents in bulbs and leaves. Nitrogen content was also analyzed for both hypogeous and epigeous apparatuses. Results: Among the most interesting vegetative results, plant height and SPAD readings were reduced only by the extreme treatment F-0 compared with the other treatments at 104 days after planting. Regarding qualitative and productive parameters, the treatments F-50 and F-25 showed the highest yield without prejudging Soluble Solid Content and reducing pungency. Conclusion: In nutritional experiments, onion could be considered as a crop model to investigate quality in vegetables due to its consumption as fresh product and for its particular response, in terms of yield and quality, to fertilization. The use of simulation software can support the identification of strategies to reduce the nutrient supply without any detrimental effect on yield and other vegetative and qualitative parameters in onion crops. Full article

To address the challenges of low recognition accuracy and substantial model complexity in crop disease identification models operating in complex field environments, this study proposed a novel hybrid model named ConvTransNet-S, which integrates Convolutional Neural Networks (CNNs) and transformers for crop disease identification tasks. Unlike existing hybrid approaches, ConvTransNet-S uniquely introduces three key innovations: First, a Local Perception Unit (LPU) and Lightweight Multi-Head Self-Attention (LMHSA) modules were introduced to synergistically enhance the extraction of fine-grained plant disease details and model global dependency relationships, respectively. Second, an Inverted Residual Feed-Forward Network (IRFFN) was employed to optimize the feature propagation path, thereby enhancing the model’s robustness against interferences such as lighting variations and leaf occlusions. This novel combination of a LPU, LMHSA, and an IRFFN achieves a dynamic equilibrium between local texture perception and global context modeling—effectively resolving the trade-offs inherent in standalone CNNs or transformers. Finally, through a phased architecture design, efficient fusion of multi-scale disease features is achieved, which enhances feature discriminability while reducing model complexity. The experimental results indicated that ConvTransNet-S achieved a recognition accuracy of 98.85% on the PlantVillage public dataset. This model operates with only 25.14 million parameters, a computational load of 3.762 GFLOPs, and an inference time of 7.56 ms. Testing on a self-built in-field complex scene dataset comprising 10,441 images revealed that ConvTransNet-S achieved an accuracy of 88.53%, which represents improvements of 14.22%, 2.75%, and 0.34% over EfficientNetV2, Vision Transformer, and Swin Transformer, respectively. Furthermore, the ConvTransNet-S model achieved up to 14.22% higher disease recognition accuracy under complex background conditions while reducing the parameter count by 46.8%. This confirms that its unique multi-scale feature mechanism can effectively distinguish disease from background features, providing a novel technical approach for disease diagnosis in complex agricultural scenarios and demonstrating significant application value for intelligent agricultural management. Full article