Next Issue
Volume 15, October-1
Previous Issue
Volume 15, September-1
 
 

Agriculture, Volume 15, Issue 18 (September-2 2025) – 86 articles

Cover Story (view full-size image): Can simplified implementation of precision feeding enhance productivity and reduce pollutant emissions? This study evaluated a simplified precision feeding strategy on pig fattening farms to assess its effects on economic performance and pollutant emissions: two commercial feeds, a nutrient-rich pre-grower and a nutrient-poor finisher, were blended weekly based on the lysine needs of two groups of pigs, defined by initial body weight. The results show that simplified precision can provide economic benefits without compromising performance, but blend feeding formulation should also address potential NH3 and GHG emissions during slurry storage. The integration of artificial intelligence-driven tools for real-time diet adjustments would be of great interest to enhance sustainability and efficiency. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
15 pages, 2611 KB  
Article
Design and Experiment of Air–Fertilizer Separator for Pneumatic Deep Fertilization in Paddy Fields
by Mingjin Xin, Wenrui Ding, Duo Chen, Man Zhang, Yujue Ao, Bowen Chi, Zhiwen Jiang, Yuqiu Song and Yunlong Guo
Agriculture 2025, 15(18), 1991; https://doi.org/10.3390/agriculture15181991 - 22 Sep 2025
Viewed by 247
Abstract
Supplemental fertilizer application is critical for improving rice yield. Pneumatic deep fertilization effectively improves fertilizer utilization, but high-speed airflow may disturb the soil and affect the location of the fertilizer particles. An air–fertilizer separator was developed in this study to separate the fertilizer [...] Read more.
Supplemental fertilizer application is critical for improving rice yield. Pneumatic deep fertilization effectively improves fertilizer utilization, but high-speed airflow may disturb the soil and affect the location of the fertilizer particles. An air–fertilizer separator was developed in this study to separate the fertilizer from the airflow before the two-phase flow rushes into the soil, and the airflow is directed away from the surface of the paddy soil. The structural and operating parameters of the air–fertilizer separator are determined in this paper. A quadratic orthogonal rotation combination experiment was conducted, taking structural parameters of the device as variables, and fertilizer injection speed, separation loss rate, and outlet airflow speed as performance indicators, to optimize the design parameters of the air–fertilizer separator. The variance analysis and surface response analysis of the experimental data are conducted, and the mathematical models between the indicators and the influencing factors are established. The optimal parameters were determined using multi-objective optimization, and the experimental verification was carried out. The optimal parameters for the air–fertilizer separator were obtained as an arc radius of the AFAST of 380 mm, central angle of arc trough of 45°, and depth of primary separation arc-trough of 12.5 mm. The validation experimental results show that the fertilizer injection speed is 21.45 m/s, the fertilizer separation loss rate is 10.22%, and the outlet airflow speed is 42.54 m/s. The experimental values are close to the predicted values, with errors of 1.2%, 1.7%, and 1.3%. The results of the study may provide a reference for the development of an air–fertilizer separator for pneumatic deep fertilization in paddy fields. Full article
(This article belongs to the Section Agricultural Technology)
Show Figures

Figure 1

17 pages, 2568 KB  
Article
Developing Native Fish to Control Spirogyra in Paddy Fields for Improving the Growth, Nutrient Uptake, and Physiological Characteristics of Oryza sativa L.
by Mei Zhang, Runhai Jiang, Xiaorong Yang, Shaofu Wen, Zexiang Hua, Xiuli Hou and Xuexiu Chang
Agriculture 2025, 15(18), 1990; https://doi.org/10.3390/agriculture15181990 - 22 Sep 2025
Viewed by 209
Abstract
Oryza sativa L. is the largest food crop in the world. The harmful filamentous green algae Spirogyra in paddy fields poses a serious threat to O. sativa yield. Therefore, biological control for Spirogyra is important for sustainable agricultural development. The native fish species [...] Read more.
Oryza sativa L. is the largest food crop in the world. The harmful filamentous green algae Spirogyra in paddy fields poses a serious threat to O. sativa yield. Therefore, biological control for Spirogyra is important for sustainable agricultural development. The native fish species Acrossocheilus yunnanensis can graze on Spirogyra and exhibits strong environmental adaptability, providing a novel approach to the biological control of Spirogyra. Therefore, we designed the O. sativa+Spirogyra+A. yunnanensis co-culture system to study the effects of A. yunnanensis on O. sativa growth and physiological characteristics. The results indicated that Spirogyra stress significantly inhibited O. sativa biomass accumulation, root length and plant height development, reduced photosynthetic efficiency, and increased the contents of oxidative stress markers including malondialdehyde (MDA) and hydrogen peroxide (H2O2). Interestingly, grazing of A. yunnanensis on Spirogyra increased the biomass of Oryza sativa by 58.60%, the root–shoot ratio by 78.01%, and the root length and plant height by 49.83% and 25.85%, respectively. Meanwhile, the soil nitrate nitrogen (NO3-N), ammonium nitrogen (NH4+-N), and available phosphorus (AP) were enhanced, which improved O. sativa nutrient uptake and promoted photosynthetic pigment accumulation. This was manifested by an increase in chlorophyll content, net photosynthetic (Pn), transpiration rate, stomatal conductance (Gs), and intercellular CO2 concentration (Ci). Grazing of A. yunnanensis on Spirogyra alleviated the oxidative damage to O. sativa induced by Spirogyra, as evidenced by decreased malondialdehyde (MDA) and hydrogen peroxide (H2O2) level in both leaves and roots, along with increased protein content. This provides a new strategy for constructing a rice–fish symbiotic system by using indigenous fish species, achieving Spirogyra control and sustainable agricultural development. Full article
(This article belongs to the Section Crop Protection, Diseases, Pests and Weeds)
Show Figures

Graphical abstract

25 pages, 10178 KB  
Article
Super-Resolution Point Cloud Completion for Large-Scale Missing Data in Cotton Leaves
by Hui Geng, Zhiben Yin, Mingdeng Shi, Junzhang Pan and Chunjing Si
Agriculture 2025, 15(18), 1989; https://doi.org/10.3390/agriculture15181989 - 22 Sep 2025
Viewed by 218
Abstract
Point cloud completion for cotton leaves is critical for accurately reconstructing complete shapes from sparse and significantly incomplete data. Traditional methods typically assume small missing ratios (≤25%), which limits their effectiveness for morphologically complex cotton leaves with severe sparsity (50–75%), large geometric distortions, [...] Read more.
Point cloud completion for cotton leaves is critical for accurately reconstructing complete shapes from sparse and significantly incomplete data. Traditional methods typically assume small missing ratios (≤25%), which limits their effectiveness for morphologically complex cotton leaves with severe sparsity (50–75%), large geometric distortions, and extensive point loss. To overcome these challenges, we introduce an end-to-end neural network that combines PF-Net and PointNet++ to effectively reconstruct dense, uniform point clouds from incomplete inputs. The model initially uses a multiresolution encoder to extract multiscale features from locally incomplete point clouds at different resolutions. By capturing both low-level and high-level attributes, these features significantly enhance the network’s ability to represent semantic content and geometric structure. Next, a point pyramid decoder generates missing point clouds hierarchically from layers at different depths, effectively reconstructing the fine details of the original structure. PointNet++ is then used to fuse and reshape the incomplete input point clouds with the generated missing points, yielding a fully reconstructed and uniformly distributed point cloud. To ensure effective task completion at different training stages, a loss function freezing strategy is employed, optimizing the network’s performance throughout the training process. Experimental evaluation on the cotton leaf dataset demonstrated that the proposed model outperformed PF-Net, reducing the Chamfer distance by 80.15% and the Earth Mover distance by 54.35%. These improvements underscore the model’s robustness in reconstructing sparse point clouds for precise agricultural phenotyping. Full article
(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
Show Figures

Figure 1

27 pages, 3754 KB  
Article
Performance of Georgian Grapevine Varieties in a Vineyard Infected by Flavescence Dorée Phytoplasma in Piedmont, Northwestern Italy
by Letizia Portaccio, Maria Alessandra Paissoni, Simone Giacosa, Alessandro Passera, Camilla Barbieri, David Maghradze, Luca Rolle, Vincenzo Gerbi, Osvaldo Failla, Piero Attilio Bianco and Fabio Quaglino
Agriculture 2025, 15(18), 1988; https://doi.org/10.3390/agriculture15181988 - 21 Sep 2025
Viewed by 193
Abstract
In Europe, Flavescence dorée (FD), the only epidemic disease within the phytoplasma-associated grapevine yellows complex (GY), reduces productivity and has a negative impact on berry composition and wine quality. Recent studies have shown that Georgian Vitis vinifera L. varieties have low susceptibility to [...] Read more.
In Europe, Flavescence dorée (FD), the only epidemic disease within the phytoplasma-associated grapevine yellows complex (GY), reduces productivity and has a negative impact on berry composition and wine quality. Recent studies have shown that Georgian Vitis vinifera L. varieties have low susceptibility to Bois noir (BN), another GY disease. This study investigated the performance of some Georgian grapevine varieties in a highly FD-affected area in Piedmont (northwestern Italy), exploring their susceptibility to FD and testing their oenological potential through berry and wine quality analyses. Activities, conducted in a case-study vineyard containing central–western European, Georgian, and PIWI (fungus-resistant grape varieties) varieties, included field surveys and molecular analyses. Mortality and infection percentage index were significantly higher in Georgian and central–western European varieties, respectively. All Georgian varieties exhibited none or mild symptoms without a reduction in the number of symptomless berries. Only the FD phytoplasma (FDp) genotype M54 was identified in infected grapevines, suggesting that differences in symptom severity were related to a variety-specific response to infection. Despite infection, Georgian varieties maintained stable berry and wine quality parameters, showing no significant changes in acidity, sugar content, and flavor profile. Thus, Georgian varieties had great oenological potential and responded well to both FDp infection and local agroecosystem conditions. Full article
Show Figures

Figure 1

24 pages, 11251 KB  
Article
Simulation and Experimental Study on Vibration Separation of Residual Film and Soil Based on EDEM
by Xinzhong Wang, Yapeng Li and Jing Bai
Agriculture 2025, 15(18), 1987; https://doi.org/10.3390/agriculture15181987 - 21 Sep 2025
Viewed by 218
Abstract
Due to the complexity of impurity removal from the residual film, there is currently no better impurity removal equipment. To improve the screening performance of the residual film mixture, the vibrating screen was designed. In this paper, the key factors A, B [...] Read more.
Due to the complexity of impurity removal from the residual film, there is currently no better impurity removal equipment. To improve the screening performance of the residual film mixture, the vibrating screen was designed. In this paper, the key factors A, B, C, and D were identified through mechanical analysis of the mixture (where they represented the screen aperture diameter, vibration amplitude, vibration frequency, and screen mesh inclination angle, respectively). The soil screen rate (Y1) and screening loss rate (Y2) were evaluated. And the optimal ranges for these factors were determined by single-factor experiments. Based on the EDEM, the discrete element model was established to simulate the interaction between residual film and soil. And the motion characteristics of the residual film mixture were analyzed within the screen body through a combination of simulation and bench tests. The vibrating screen’s structural parameters were optimized using Box-Behnken experiments. The most suitable combination of settings was as shown below: A = 6.5 mm, B = 25 mm, C = 3.8 Hz, and D = 4°. Following the optimization of these parameters, the screening performance was optimized. Results of bench tests showed that the soil screening rate was 80.33% and the screening loss rate was 19.31%. This study was expected to offer theoretical and simulation-based methods for optimizing the parameters of residual film-soil vibrating screening devices. Full article
(This article belongs to the Section Agricultural Technology)
Show Figures

Figure 1

18 pages, 2911 KB  
Article
Genetic Diversity and Population Structure of Wheat Germplasm for Grain Nutritional Quality Using Haplotypes and KASP Markers
by Qunxiang Yan, Zhankui Zeng, Chunping Wang, Jiachuang Li, Junqiao Song, Qiong Li, Yue Zhao, Chang Liu and Xueyan Jing
Agriculture 2025, 15(18), 1986; https://doi.org/10.3390/agriculture15181986 - 21 Sep 2025
Viewed by 226
Abstract
Wheat germplasm resources are an important material foundation for genetic improvement. In this study, 170 wheat germplasm resources were used from China, the International Maize and Wheat Improvement Center (CIMMYT), Europe (France, Finland, and Sweden), the United States, Canada, and Australia. Seven nutritional [...] Read more.
Wheat germplasm resources are an important material foundation for genetic improvement. In this study, 170 wheat germplasm resources were used from China, the International Maize and Wheat Improvement Center (CIMMYT), Europe (France, Finland, and Sweden), the United States, Canada, and Australia. Seven nutritional quality traits were evaluated for the 2019–2020 and 2020–2021 cropping seasons. The coefficient of variability for seven nutritional quality traits ranged from 6.99% to 30.65%. The average of genetic diversity (Shannon–Wiener diversity index, H′) was 1.87. The results showed that the average frequency of high-throughput competitive allele-specific PCR (KASP) markers was 69.4% on 17 KASP markers related to seven nutritional quality traits, the average of polymorphic information content (PIC) was 0.308, and the genetic effects were from 0.01% to 18.46%. One hundred and seventy wheat germplasm resources were classified into five groups at ΔK = 5 by genetic structure analysis. The first group comprised 62 germplasm resources (36.47%), the second group included 41 germplasm resources (24.11%), the third group contained 20 germplasm resources (11.76%), the fourth group contained 20 germplasm resources (11.76%), and the fifth group had 29 germplasm resources (17.06%). Germplasm resources from CIMMYT and China were found in the first group and the second group, accounting for 56.45% and 65.85%, respectively, while European germplasm resources constituted 50% of those within the fourth group. Five favorable haplotypes were identified, which were located on chromosomes 4A, 6A, 6B, and 7A: G4A1, G4A2, G6A, G6B, and G7A. Their genetic effects were 8.71%, 8.41%, 1.00%, 18.20%, and 1.16%, respectively. In the meantime, we found 12 significant SNPs of seven nutritional quality traits using haplotype analysis. The frequency of favorable haplotypes in the population ranged from 3.53% to 62.35%. Five haplotypes, G4A1, G4A2, G6A, G6B, and G7A, were beneficial, and their genetic effects were positive. Furthermore, the results offered favorable haplotypes and germplasm resources for enhancing nutritional quality. Full article
(This article belongs to the Section Crop Genetics, Genomics and Breeding)
Show Figures

Figure 1

29 pages, 7187 KB  
Article
A Novel Framework for Predicting Daily Reference Evapotranspiration Using Interpretable Machine Learning Techniques
by Elsayed Ahmed Elsadek, Mosaad Ali Hussein Ali, Clinton Williams, Kelly R. Thorp and Diaa Eldin M. Elshikha
Agriculture 2025, 15(18), 1985; https://doi.org/10.3390/agriculture15181985 - 20 Sep 2025
Viewed by 234
Abstract
Accurate estimation of daily reference evapotranspiration (ETo) is crucial for sustainable water resource management and irrigation scheduling, especially in water-scarce regions like Arizona. The standardized Penman–Monteith (PM) method is costly and requires specialized instruments and expertise, making it generally impractical for [...] Read more.
Accurate estimation of daily reference evapotranspiration (ETo) is crucial for sustainable water resource management and irrigation scheduling, especially in water-scarce regions like Arizona. The standardized Penman–Monteith (PM) method is costly and requires specialized instruments and expertise, making it generally impractical for commercial growers. This study developed 35 ETo models to predict daily ETo across Coolidge, Maricopa, and Queen Creek in Pinal County, Arizona. Seven input combinations of daily meteorological variables were used for training and testing five machine learning (ML) models: Artificial Neural Network (ANN), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Support Vector Machine (SVM). Four statistical indicators, coefficient of determination (R2), the normalized root-mean-squared error (RMSEn), mean absolute error (MAE), and simulation error (Se), were used to evaluate the ML models’ performance in comparison with the FAO-56 PM standardized method. The SHapley Additive exPlanations (SHAP) method was used to interpret each meteorological variable’s contribution to the model predictions. Overall, the 35 ETo-developed models showed an excellent to fair performance in predicting daily ETo over the three weather stations. Employing ANN10, RF10, XGBoost10, CatBoost10, and SVM10, incorporating all ten meteorological variables, yielded the highest accuracies during training and testing periods (0.994 ≤ R2 ≤ 1.0, 0.729 ≤ RMSEn ≤ 3.662, 0.030 ≤ MAE ≤ 0.181 mm·day−1, and 0.833 ≤ Se ≤ 2.295). Excluding meteorological variables caused a gradual decline in ET-developed models’ performance across the stations. However, 3-variable models using only maximum, minimum, and average temperatures (Tmax, Tmin, and Tave) predicted ETo well across the three stations during testing (17.655 ≤ RMSEn ≤ 13.469 and Se ≤ 15.45%). Results highlighted that Tmax, solar radiation (Rs), and wind speed at 2 m height (U2) are the most influential factors affecting ETo at the central Arizona sites, followed by extraterrestrial solar radiation (Ra) and Tave. In contrast, humidity-related variables (RHmin, RHmax, and RHave), along with Tmin and precipitation (Pr), had minimal impact on the model’s predictions. The results are informative for assisting growers and policymakers in developing effective water management strategies, especially for arid regions like central Arizona. Full article
(This article belongs to the Section Agricultural Water Management)
Show Figures

Figure 1

18 pages, 5642 KB  
Article
Harvest Date Monitoring in Cereal Fields at Large Scale Using Dense Stacks of Sentinel-2 Imagery Validated by Real Time Kinematic Positioning Data
by Fernando Sedano, Daniele Borio, Martin Claverie, Guido Lemoine, Philippe Loudjani, David Alfonso Nafría, Vanessa Paredes-Gómez, Francisco Javier Rojo-Revilla, Ferdinando Urbano and Marijn Van der Velde
Agriculture 2025, 15(18), 1984; https://doi.org/10.3390/agriculture15181984 - 20 Sep 2025
Viewed by 210
Abstract
This study presents an operational and robust method for detecting and dating cereal harvest events using temporal stacks of Copernicus Sentinel-2 imagery and crop and fields border information from ancillary records. The proposed approach is exempt from training data, thereby enabling its application [...] Read more.
This study presents an operational and robust method for detecting and dating cereal harvest events using temporal stacks of Copernicus Sentinel-2 imagery and crop and fields border information from ancillary records. The proposed approach is exempt from training data, thereby enabling its application across diverse geographical contexts. The method was used to generate 10 m resolution maps of harvest dates for all wheat and barley fields in 2021, 2022, and 2023 in Castilla y León, a major cereal-producing region of Spain. This work also investigates the use of a reference dataset derived from real time kinematic records (RTK) in agricultural machinery as an alternative source of large-scale in situ data reference as for Earth observation-based agricultural products. The initial comparison of annual harvest date maps with the RTK-based reference datasets revealed that the temporal lag in the detection of harvest events between Earth observation-derived maps and reference harvest dates was less than 10 days for 65.7% of fields, while the temporal lag was between 10 and 30 days for 26.1% of the fields. The 3-year average root mean square error of the lag between harvest dates in the reference dataset and maps was 16.1 days. An in-depth visual analysis of the Sentinel-2 temporal series was carried out to understand and evaluate the potential and limitations of the RTK-based reference dataset. The visual inspection of a representative sample of 668 fields with large temporal lags revealed that the date of harvest of 41.11% of these fields had been correctly identified in the Sentinel-2 based maps and 16.43% of them had been incorrectly identified. The visual inspection could not find evidence of harvest in 10.52% of the analyzed fields. Monte Carlo simulations were parameterized using the findings of the visual inspection to build a series of synthetic reference datasets. Accuracy metrics calculated from synthetic datasets revealed that the quality of the harvest maps was higher than what the initial comparison against the RTK-based reference dataset suggested. The date of harvest was registered within 10 days in both the maps and the synthetic reference datasets for 90.5% of the fields, the root mean squared error of the comparison was 9.5 days, and harvest dates were registered in the Sentinel-2 based maps 2 days (median) after the dates registered in the reference dataset. These results highlight the feasibility of mapping harvest dates in cereal fields with time series of high-resolution satellite imagery and expose the potential use of alternative sources of calibration and validation datasets for Earth observation products. More generally, these results contribute to defining plausible targets for monitoring of agricultural practices with Earth observation data. Full article
(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
Show Figures

Figure 1

16 pages, 2079 KB  
Article
Climatic and Topographic Controls on Soil Organic Matter Heterogeneity in Northeast China’s Black Soil Region: Implications for Sustainable Management
by Depiao Kong, Nanchen Chu and Chong Luo
Agriculture 2025, 15(18), 1983; https://doi.org/10.3390/agriculture15181983 - 20 Sep 2025
Viewed by 222
Abstract
Soil organic matter (SOM) plays a critical role in maintaining soil fertility, sustaining ecosystem stability, and mitigating climate change impacts, making its conservation essential for agricultural sustainability. However, systematic county-level assessments of SOM spatial heterogeneity and its drivers across Northeast China remain limited, [...] Read more.
Soil organic matter (SOM) plays a critical role in maintaining soil fertility, sustaining ecosystem stability, and mitigating climate change impacts, making its conservation essential for agricultural sustainability. However, systematic county-level assessments of SOM spatial heterogeneity and its drivers across Northeast China remain limited, constraining region-specific soil management strategies. Understanding the spatial distribution and drivers of SOM is therefore vital for effective black soil protection in Northeast China. This study investigated the spatial heterogeneity and driving mechanisms of SOM in Northeast China, covering 289 counties across Heilongjiang, Jilin, and Liaoning Provinces. High-resolution (10 m) SOM data combined with 15 natural, climatic, soil, vegetation, and socioeconomic variables were analyzed using spatial autocorrelation (global and local Moran’s I) and the Geodetector model. Results showed that SOM exhibited a clear spatial pattern of “higher in the north and east, lower in the south and west,” with significant spatial clustering (Moran’s I = 0.730, p < 0.001). At the regional scale, climate factors were the dominant drivers, with potential evapotranspiration (q = 0.810) and mean annual temperature (q = 0.794) exerting the strongest explanatory power. At the provincial scale, dominant factors varied: topographic controls in Liaoning, climate–topography interactions in Jilin, and climate dominance in Heilongjiang. Anthropogenic footprint had limited overall influence but showed amplifying effects in certain local areas. These findings highlight the multi-scale, multi-factor nature of SOM heterogeneity and underscore the need for region-specific management strategies. Full article
(This article belongs to the Section Agricultural Soils)
Show Figures

Figure 1

23 pages, 7497 KB  
Article
RFA-YOLOv8: A Robust Tea Bud Detection Model with Adaptive Illumination Enhancement for Complex Orchard Environments
by Qiuyue Yang, Jinan Gu, Tao Xiong, Qihang Wang, Juan Huang, Yidan Xi and Zhongkai Shen
Agriculture 2025, 15(18), 1982; https://doi.org/10.3390/agriculture15181982 - 19 Sep 2025
Viewed by 271
Abstract
Accurate detection of tea shoots in natural environments is crucial for facilitating intelligent tea picking, field management, and automated harvesting. However, the detection performance of existing methods in complex scenes remains limited due to factors such as the small size, high density, severe [...] Read more.
Accurate detection of tea shoots in natural environments is crucial for facilitating intelligent tea picking, field management, and automated harvesting. However, the detection performance of existing methods in complex scenes remains limited due to factors such as the small size, high density, severe overlap, and the similarity in color between tea shoots and the background. Consequently, this paper proposes an improved target detection algorithm, RFA-YOLOv8, based on YOLOv8, which aims to enhance the detection accuracy and robustness of tea shoots in natural environments. First, a self-constructed dataset containing images of tea shoots under various lighting conditions is created for model training and evaluation. Second, the multi-scale feature extraction capability of the model is enhanced by introducing RFCAConv along with the optimized SPPFCSPC module, while the spatial perception ability is improved by integrating the RFAConv module. Finally, the EIoU loss function is employed instead of CIoU to optimize the accuracy of the bounding box positioning. The experimental results demonstrate that the improved model achieves 84.1% and 58.7% in mAP@0.5 and mAP@0.5:0.95, respectively, which represent increases of 3.6% and 5.5% over the original YOLOv8. Robustness is evaluated under strong, moderate, and dim lighting conditions, yielding improvements of 6.3% and 7.1%. In dim lighting, mAP@0.5 and mAP@0.5:0.95 improve by 6.3% and 7.1%, respectively. The findings of this research provide an effective solution for the high-precision detection of tea shoots in complex lighting environments and offer theoretical and technical support for the development of smart tea gardens and automated picking. Full article
(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
Show Figures

Figure 1

19 pages, 1118 KB  
Article
Grapevine Phenology, Vegetative and Reproductive Characteristics of Vitis vinifera L. cv Chardonnay in the Cape South Coast Region in South Africa
by Erna Hailey Blancquaert, Emile Tomas Majewski, Sam Crauwels, Zhanwu Dai and Daniel Schorn-García
Agriculture 2025, 15(18), 1981; https://doi.org/10.3390/agriculture15181981 - 19 Sep 2025
Viewed by 187
Abstract
Climate change necessitates the exploration of new, cooler viticultural regions globally. Chardonnay is an early ripening variety which is subjected to temperature extremes. This study aimed to investigate the response of Chardonnay in cool climatic regions in the Cape South Coast region of [...] Read more.
Climate change necessitates the exploration of new, cooler viticultural regions globally. Chardonnay is an early ripening variety which is subjected to temperature extremes. This study aimed to investigate the response of Chardonnay in cool climatic regions in the Cape South Coast region of South Africa over two growing seasons in 2021–2022 and 2022–2023 in three commercial vineyards. An evaluation of the climatic, vegetative and reproductive characteristics was performed. Seasonal variation was the biggest driver of the Growing Degree Days (GDD) at the sites. Overall, the 2021–2022 season was warmer than the 2022–2023 season, but the microclimatic conditions were impacted by the cultivation practices which were applied. The canopy density and total leaf surface varied between the different sites (p < 0.01) and by season × site (p < 0.05). Site and the site × season interaction were the main drivers of the environmental conditions and cultivation practices. Canopy characteristics impacted the sugar accumulation rate over the two seasons. Grape berry transpiration was impacted by the environmental conditions at the sites. Chemical composition varied with soil depth. From the results of our study, although Chardonnay is suitable for cultivation in the Cape South region, site-specific conditions impact fruit development and the quality at harvest. Full article
(This article belongs to the Special Issue Climate Change and Plant Phenology: Challenges for Fruit Production)
Show Figures

Figure 1

84 pages, 64140 KB  
Article
Assessing the Influence of Temperature and Precipitation on the Yield and Losses of Key Highland Crops in Ecuador
by Luis Fernando Guerrero-Vásquez, María del Cisne Ortega-Cabrera, Nathalia Alexandra Chacón-Reino, Graciela del Rocío Sanmartín-Mesías, Paul Andrés Chasi-Pesántez and Jorge Osmani Ordoñez-Ordoñez
Agriculture 2025, 15(18), 1980; https://doi.org/10.3390/agriculture15181980 - 19 Sep 2025
Viewed by 177
Abstract
Food production systems in Ecuador’s high Andean region are pivotal for food security, rural livelihoods, and agrobiodiversity, yet they are increasingly exposed to climate stress. We assessed four representative crops (tree tomato, quinoa, potato, and maize) across three Andean zones (North, Center, South) [...] Read more.
Food production systems in Ecuador’s high Andean region are pivotal for food security, rural livelihoods, and agrobiodiversity, yet they are increasingly exposed to climate stress. We assessed four representative crops (tree tomato, quinoa, potato, and maize) across three Andean zones (North, Center, South) in 2015–2022 using monthly NASA POWER (MERRA-2) climate fields. After confirming non-normality, Spearman correlations and multiple linear regressions with leave-one-year-out validation were applied to quantify the influence of maximum/minimum temperature and precipitation on cultivated and harvested area, production, sales, and loss categories. To place monthly signals in a process context, daily extreme-event diagnostics (ETCCDI-style) were also computed: heat days (TX90), ≥5-day dry spells, and the annual maximum consecutive dry days (CDDmax). Models explained a wide range of variability across crops and zones (approx. R20.55–0.99), with quinoa showing the most consistent fits (several outcomes R2>0.90). Extremes provide an eye-catching, actionable picture: the Southern zone concentrated dryness hazards, with 1–5 dry spells 5 days per year and CDDmax up to ∼8 days, while heat-day frequency showed non-significant declines across zones in 2015–2022. Reanalysis frost days were virtually zero—consistent with under-detection of local valley frosts at coarse resolution—so frost risk was interpreted via monthly signals and reported losses. Overall, the results show precipitation-driven vulnerabilities in the South and support quinoa’s role as a resilient option under increasing climate stress, offering concrete guidance for water management and climate-smart planning in mountain agroecosystems. Full article
Show Figures

Figure 1

21 pages, 3795 KB  
Article
Grading and Detecting of Organic Matter in Phaeozem Based on LSVM-Stacking Model Using Hyperspectral Reflectance Data
by Zifang Zhang, Zhihua Liu, Qinghe Zhao, Kezhu Tan and Junlong Fang
Agriculture 2025, 15(18), 1979; https://doi.org/10.3390/agriculture15181979 - 19 Sep 2025
Viewed by 166
Abstract
Phaeozem, which is recognized as one of the world’s most fertile soils, derives much of its productivity from soil organic matter (SOM). Because SOM strongly influences fertility, soil structure, and ecological functions, it is the SOM content that must be rapidly and accurately [...] Read more.
Phaeozem, which is recognized as one of the world’s most fertile soils, derives much of its productivity from soil organic matter (SOM). Because SOM strongly influences fertility, soil structure, and ecological functions, it is the SOM content that must be rapidly and accurately determined to ensure sustainable soil management. Traditional chemical methods are reliable but time-consuming and labor-intensive, which makes them inadequate for large-scale applications. Hyperspectral reflectance, which is highly sensitive to SOM variations, provides a non-destructive alternative for rapid SOM grading. This study proposes an ensemble learning strategy model based on phaeozem hyperspectral reference data for the rapid grading and detection of SOM content. First, the SOM content of the collected phaeozem samples was determined using the potassium dichromate volumetric method. Next, hyperspectral reflectance data of the phaeozem were collected using a hyperspectral imaging sensor, with a wavelength range of 400–1000 nm. Furthermore, stacking models were constructed by modifying the internal structure, with five classifiers (MLP, SVC, DTree, XGBoost, kNN) as the L1 layer. Then, global optimization was performed using the simulated annealing algorithm. Through comparative analysis, the LSVM-stacking model demonstrated the highest accuracy and generalization capabilities. The results demonstrated that the LSVM-stacking model not only achieved the highest overall accuracy (0.9488 on the independent test set) but also improved the classification accuracy of “Category 1” samples to 1.0. Compared with other models, this framework significantly improved generalization ability and robustness. It is therefore evident that combining hyperspectral reflectance with improved stacking strategies provides a novel and effective approach for the rapid grading and detection of SOM in phaeozem. Full article
(This article belongs to the Topic Digital Agriculture, Smart Farming and Crop Monitoring)
Show Figures

Figure 1

16 pages, 5620 KB  
Article
Development and Properties of Starches in Vitreous and Floury Endosperm of Maize
by Yuzhi Han, Shuchang Wei, Ahui Xu and Cunxu Wei
Agriculture 2025, 15(18), 1978; https://doi.org/10.3390/agriculture15181978 - 19 Sep 2025
Viewed by 157
Abstract
Starches from vitreous and floury endosperm in mature maize kernels exhibit significantly different properties, yet the developmental basis for the differences remains unclear. In this research, inner endosperm (IE) and outer endosperm (OE) regions, which develop into floury and vitreous endosperm, respectively, were [...] Read more.
Starches from vitreous and floury endosperm in mature maize kernels exhibit significantly different properties, yet the developmental basis for the differences remains unclear. In this research, inner endosperm (IE) and outer endosperm (OE) regions, which develop into floury and vitreous endosperm, respectively, were separated from developing maize kernels. Their starch development and properties were investigated using morphological observation, physicochemical characterization, transcriptome analysis, and biochemical assays. The IE contained small, spherical starch granules with loose arrangement, ultimately forming floury endosperm, whereas the OE displayed large, polygonal starch granules packed tightly, contributing to vitreous endosperm formation. The OE exhibited a higher starch filling degree compared to the IE. Throughout endosperm development, amylose content progressively increased in both regions, but was consistently higher in OE starch than in IE starch. The relative crystallinity and lamellar peak intensity of starch decreased gradually during endosperm development; however, at later stages, both parameters were higher in IE starch than in OE starch. Transcriptome analysis revealed that processes such as anaerobic respiration, glycolysis, and response to hypoxia were more enriched in IE compared to OE. Nearly all genes associated with glycolysis and ethanol fermentation pathways were upregulated in IE. Although no significant difference was observed in the activity of granule-bound starch synthase I between IE and OE, the activity of pyruvate orthophosphate dikinase was higher in OE than in IE. These findings suggest that the insufficient nutrient supply and pronounced hypoxic conditions in the IE reduced the availability of carbon substrates for starch synthesis, thereby impairing starch development and accumulation. In contrast, the larger granule size of OE starch facilitates higher amylose accumulation, leading to distinct physicochemical properties between IE and OE starches. Full article
Show Figures

Figure 1

4 pages, 149 KB  
Editorial
Productivity and Efficiency of Agricultural and Livestock Systems
by Alexandros Theodoridis and Katerina Melfou
Agriculture 2025, 15(18), 1977; https://doi.org/10.3390/agriculture15181977 - 19 Sep 2025
Viewed by 219
Abstract
Agricultural and livestock production systems are continuously confronted with new structural, operational, market, and environmental challenges, which pose threats to their future sustainability [...] Full article
(This article belongs to the Special Issue Productivity and Efficiency of Agricultural and Livestock Systems)
32 pages, 4637 KB  
Article
Long-Term Global Trends in Vineyard Coverage and Fresh Grape Production
by Noa Ohana-Levi and Yishai Netzer
Agriculture 2025, 15(18), 1976; https://doi.org/10.3390/agriculture15181976 - 19 Sep 2025
Viewed by 188
Abstract
Monitoring and tracking the long-term dynamics of vineyard coverage and fresh grape production can support sustainable agricultural planning under evolving climate, market, and land-use pressures. This study presents a comprehensive, data-driven analysis of global viticulture trends from 1961 to 2023, integrating the official [...] Read more.
Monitoring and tracking the long-term dynamics of vineyard coverage and fresh grape production can support sustainable agricultural planning under evolving climate, market, and land-use pressures. This study presents a comprehensive, data-driven analysis of global viticulture trends from 1961 to 2023, integrating the official statistical database of the Food and Agriculture Organization of the United Nations (FAOSTAT) for grape-producing countries. We applied statistical trend analysis (Mann–Kendall test), Random Forest regression modeling, cross-correlation functions, and dissimilarity analysis to examine patterns and drivers of change in vineyard area, production volume, yield efficiency, and land-use intensity. Our results reveal a significant global decoupling of production from vineyard areas, driven by increasing yields and technological intensification, particularly in rapidly expanding table grape markets in Asia. While traditional European wine regions are reducing vineyard coverage, emerging producers such as China and India are achieving high production with improved land efficiency. Production volume emerged as the dominant predictor of vineyard-harvested areas, while climatic factors, urbanization, and socio-economic dynamics also exerted significant influence. Our findings point to growing polarization in production amounts, alongside convergence in yield and management efficiency across countries. These findings contribute to the understanding of global viticulture transformation and provide insights into optimizing land-use strategies for sustainable grape production under climate change and market evolution. Full article
Show Figures

Figure 1

27 pages, 1236 KB  
Article
Does Institutional Quality Shape Agricultural Credit Orientation? Evidence from D-8 Nations
by Ömer Keskin, Batuhan Medetoğlu, Yusuf Bahadır Kavas and Musa Gün
Agriculture 2025, 15(18), 1975; https://doi.org/10.3390/agriculture15181975 - 19 Sep 2025
Viewed by 366
Abstract
The agricultural sector, which has long been overshadowed by industrialization, has reemerged with renewed strategic significance in the face of global crises, including pandemics and armed conflicts. This study examines the causal relationship between institutional quality and agricultural credit orientation in the Developing-Eight [...] Read more.
The agricultural sector, which has long been overshadowed by industrialization, has reemerged with renewed strategic significance in the face of global crises, including pandemics and armed conflicts. This study examines the causal relationship between institutional quality and agricultural credit orientation in the Developing-Eight countries from 2002 to 2023. Using the agriculture orientation index for credit as a key indicator, this study investigates how disaggregated institutional dimensions—control of corruption, government effectiveness, political stability and absence of violence, rule of law, regulatory quality, and voice and accountability—affect the allocation of commercial bank credit to agriculture. Both the standard Kónya panel causality test and its time-varying extension are employed to capture static and dynamic causal patterns. The findings demonstrate that institutional quality exerts a substantial effect on credit orientation, although the magnitude and characteristics of this influence differ across countries. Türkiye, Indonesia, Nigeria, and Egypt exhibit consistent causal relationships, whereas other countries reveal episodic or latent effects linked to specific political or legal shifts. By combining dynamic methodology with a policy-relevant indicator, this study offers novel insights into how governance shapes agricultural finance. The results underscore the need for country-specific and institution-sensitive credit strategies to increase resilience and equity in financial systems. Full article
(This article belongs to the Section Agricultural Economics, Policies and Rural Management)
Show Figures

Figure 1

21 pages, 3101 KB  
Article
GIS-Based Land Suitability Analysis for Sustainable Almond Cultivation in Lebanon
by Pascale Elbared, Nadine Nassif, Georges Hassoun and Maurizio Mulas
Agriculture 2025, 15(18), 1974; https://doi.org/10.3390/agriculture15181974 - 19 Sep 2025
Viewed by 263
Abstract
Almonds are one of the major products that are economically competent and compatible with the Mediterranean climate, a key characteristic that distinguishes Lebanon. The present study aims to examine the suitability of land use and land cover on the Lebanese territory for sustainable [...] Read more.
Almonds are one of the major products that are economically competent and compatible with the Mediterranean climate, a key characteristic that distinguishes Lebanon. The present study aims to examine the suitability of land use and land cover on the Lebanese territory for sustainable almond cultivation, based on the FAO land suitability criteria. The research explored the existing areas of almond cultivation and the land possessing the potential for almond cultivation in Lebanon using an analysis model developed on GIS. The evaluation of Land Suitability (LS) based on GIS and Multi-Criteria Evaluation methods (MCE) with Weighted Overlay (WO) was applied, and the almond suitability map was rendered using the seven following parameters: temperature, rainfall, slope, elevation, soil pH, soil texture, and soil depth. These variables were integrated through GIS and were allocated to different weights to each thematic layer, as per its relevance. Ultimately, the almond suitability map was established, comprising four categories: highly suitable, moderately suitable, marginally suitable, and not suitable. The obtained results indicated that almond cultivation areas were around 5500 ha in 2010, while more than 60% of the study area can be planted with almonds in accordance with the almond suitability map. In closing, the targeted decision-makers will potentially deem this study as a valid source of knowledge for planning land use, and a tool to mitigate land degradation. Full article
(This article belongs to the Section Ecosystem, Environment and Climate Change in Agriculture)
Show Figures

Figure 1

21 pages, 4780 KB  
Article
Influence of Soil Physical and Hydraulic Properties on Cacao Productivity Under Agroforestry Systems in the Amazonian Piedmont
by Fabio Buriticá, José Iván Vanegas and Juan Carlos Suárez
Agriculture 2025, 15(18), 1973; https://doi.org/10.3390/agriculture15181973 - 19 Sep 2025
Viewed by 231
Abstract
In the Amazonian piedmont, cacao-based agroforestry systems (cAFSs) were significantly influenced by the soil’s physical, hydraulic, and structural characteristics, which largely determined agricultural productivity. A total of 122 plots with cocoa-based agroforestry systems measuring 1000 m2 were randomly selected from different farms [...] Read more.
In the Amazonian piedmont, cacao-based agroforestry systems (cAFSs) were significantly influenced by the soil’s physical, hydraulic, and structural characteristics, which largely determined agricultural productivity. A total of 122 plots with cocoa-based agroforestry systems measuring 1000 m2 were randomly selected from different farms located in the Amazonian foothills in the department of Caquetá. Different variables related to soil physics and hydrology, as well as production, were determined for each plot. Soil characteristics explain 33% of the total variance in cocoa yield. Sand content (71.2%) correlated positively with yield, while clay (22.62%) and silt (23.99%) correlated negatively. Three soil types were identified: sandy loam (high productivity, yield 1129.07 g) and two variants of sandy clay loam (lower yield, 323.97 g). Hydraulic properties were important, with total porosity of 56.04% and hydraulic conductivity of 20.45 mm h−1. The CCN-51 and ICS-60 clones performed better in sandy loam soils, while ICS-95 and TSH-565 adapted better to sandy clay loam soils with medium stability. The physical and hydric soil properties are crucial factors that directly influence cocoa productivity in agroforestry systems of the Amazon piedmont, where the appropriate selection of clones according to soil characteristics is fundamental to optimize crop productivity and sustainability. Full article
(This article belongs to the Section Agricultural Soils)
Show Figures

Figure 1

25 pages, 15287 KB  
Article
Research on a UAV-Based Litchi Flower Cluster Detection Method Using an Improved YOLO11n
by Baoxia Sun, Yanggang Ou, Jiatong Tang, Shuqin Cai, Yutao Chen, Wenyi Bao, Juntao Xiong and Yanan Li
Agriculture 2025, 15(18), 1972; https://doi.org/10.3390/agriculture15181972 - 18 Sep 2025
Viewed by 283
Abstract
The number of litchi flower clusters is an important indicator for predicting the fruit set rate and yield of litchi trees. However, their dense distribution, scale variation, and occlusion make it very challenging to achieve high-precision intelligent detection of litchi flower clusters in [...] Read more.
The number of litchi flower clusters is an important indicator for predicting the fruit set rate and yield of litchi trees. However, their dense distribution, scale variation, and occlusion make it very challenging to achieve high-precision intelligent detection of litchi flower clusters in natural scenes. This study proposes a UAV-based litchi flower cluster detection method using an improved YOLO11n. First, the backbone introduces a WTConv-improved C3k2 module (C3k2_WTConv) to enhance feature extraction capability; then, the neck adopts a SlimNeck structure for efficient multi-scale fusion and parameter reduction; and finally, the DySample module replaces the original up-sampling to mitigate accuracy loss caused by scale variation. Experimental results on UAV-based litchi flower cluster detection show that the model achieves an mAP@0.5 of 87.28%, with recall, precision, F1-score, and mAP@0.5 improved by 6.26%, 4.03%, 5.14%, and 5.16% over YOLO11n. Computational cost and parameters decrease by 7.69% and 2.37%, respectively. In counting tasks, MAE, RMSE, MAPE, and R2 reach 5.23, 6.89, 9.72%, and 0.9205, indicating excellent performance. The proposed method offers efficient and accurate technical support for intelligent litchi blossom management and yield estimation, and provides optimization strategies applicable to dense multi-scale object detection tasks. Full article
(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
Show Figures

Figure 1

26 pages, 5592 KB  
Article
AGRI-YOLO: A Lightweight Model for Corn Weed Detection with Enhanced YOLO v11n
by Gaohui Peng, Kenan Wang, Jianqin Ma, Bifeng Cui and Dawei Wang
Agriculture 2025, 15(18), 1971; https://doi.org/10.3390/agriculture15181971 - 18 Sep 2025
Viewed by 328
Abstract
Corn, as a globally significant food crop, faces significant yield reductions due to competitive growth from weeds. Precise detection and efficient control of weeds are critical technical components for ensuring high and stable corn yields. Traditional deep learning object detection models generally suffer [...] Read more.
Corn, as a globally significant food crop, faces significant yield reductions due to competitive growth from weeds. Precise detection and efficient control of weeds are critical technical components for ensuring high and stable corn yields. Traditional deep learning object detection models generally suffer from issues such as large parameter counts and high computational complexity, making them unsuitable for deployment on resource-constrained devices such as agricultural drones and portable detection devices. Based on this, this paper proposes a lightweight corn weed detection model, AGRI-YOLO, based on the YOLO v11n architecture. First, the DWConv (Depthwise Separable Convolution) module from InceptionNeXt is introduced to reconstruct the C3k2 feature extraction module, enhancing the feature extraction capabilities for corn seedlings and weeds. Second, the ADown (Adaptive Downsampling) downsampling module replaces the Conv layer to address the issue of redundant model parameters; The LADH (Lightweight Asymmetric Detection) detection head is adopted to achieve dynamic weight adjustment while ensuring multi-branch output optimization for target localization and classification precision. Experimental results show that the AGRI-YOLO model achieves a precision rate of 84.7%, a recall rate of 73.0%, and a mAP50 value of 82.8%. Compared to the baseline architecture YOLO v11n, the results are largely consistent, while the number of parameters, G FLOPs, and model size are reduced by 46.6%, 49.2%, and 42.31%, respectively. The AGRI-YOLO model significantly reduces model complexity while maintaining high recognition precision, providing technical support for deployment on resource-constrained edge devices, thereby promoting agricultural intelligence, maintaining ecological balance, and ensuring food security. Full article
(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
Show Figures

Figure 1

22 pages, 30314 KB  
Article
Knowledge-Enhanced Deep Learning for Identity-Preserved Multi-Camera Cattle Tracking
by Shujie Han, Alvaro Fuentes, Jiaqi Liu, Zihan Du, Jongbin Park, Jucheng Yang, Yongchae Jeong, Sook Yoon and Dong Sun Park
Agriculture 2025, 15(18), 1970; https://doi.org/10.3390/agriculture15181970 - 18 Sep 2025
Viewed by 238
Abstract
Accurate long-term tracking of individual cattle is essential for precision livestock farming but remains challenging due to occlusions, posture variability, and identity drift in free-range environments. We propose a multi-camera tracking framework that combines bird’s-eye-view (BEV) trajectory matching with cattle face recognition to [...] Read more.
Accurate long-term tracking of individual cattle is essential for precision livestock farming but remains challenging due to occlusions, posture variability, and identity drift in free-range environments. We propose a multi-camera tracking framework that combines bird’s-eye-view (BEV) trajectory matching with cattle face recognition to ensure identity preservation across long video sequences. A large-scale dataset was collected from five synchronized 4K cameras in a commercial barn, capturing both full-body movements and frontal facial views. The system employs center point detection and BEV projection for cross-view trajectory association, while periodic face recognition during feeding refreshes identity assignments and corrects errors. Evaluations on a two-day dataset of more than 600,000 images demonstrate robust performance, with an AssPr of 84.481% and a LocA score of 78.836%. The framework outperforms baseline trajectory matching methods, maintaining identity consistency under dense crowding and noisy labels. These results demonstrate a practical and scalable solution for automated cattle monitoring, advancing data-driven livestock management and welfare. Full article
(This article belongs to the Special Issue Computer Vision Analysis Applied to Farm Animals)
Show Figures

Figure 1

23 pages, 7750 KB  
Article
Simulation and Experiment on Parameters of an Airflow-Guiding Device for a Centrifugal Air-Assisted Sprayer
by Sibo Tian, Hao Guo, Jianping Li, Yang Li, Zhu Zhang and Peng Wang
Agriculture 2025, 15(18), 1969; https://doi.org/10.3390/agriculture15181969 - 18 Sep 2025
Viewed by 210
Abstract
Orchard air-assisted sprayers have become key equipment for the prevention and control of fruit tree diseases and pests. However, centrifugal fans are rarely used in orchard air-assisted sprayers. To address the issue that the airflow generated by single-duct centrifugal air-assisted sprayers is insufficient [...] Read more.
Orchard air-assisted sprayers have become key equipment for the prevention and control of fruit tree diseases and pests. However, centrifugal fans are rarely used in orchard air-assisted sprayers. To address the issue that the airflow generated by single-duct centrifugal air-assisted sprayers is insufficient to cover the lower canopy, a flow-guiding device for the lower canopy of fruit trees was designed. The Flow Simulation software of SOLIDWORKS 2021 was used to simulate the airflow field, and various structural parameters of the air outlet were analyzed to determine the optimal configuration of the upper edge inclination angle, the position of the upper air outlet, and the length of the upper air outlet. The results showed that the position of the upper air outlet had the most significant impact on the uniformity of the external flow field, followed by the upper edge inclination angle and the length of the upper air outlet. The optimal parameter settings for the air supply guiding device were determined as follows: upper edge inclination angle of 79°, upper air outlet position of 307 mm, and upper air outlet length of 190 mm. The verification test showed that the relative error between the simulated and actual airflow velocity measurements did not exceed 10%, confirming the accuracy of the simulation. The orchard field test showed that the average deposition density in the inner canopy of fruit trees was 78 particles/cm2, indicating strong penetration ability; the distribution of spray droplets in the vertical direction of the canopy was uniform, meeting the requirements of fruit tree pesticide application operations. This technology provides a new approach for the application of centrifugal fans in fruit tree pesticide spraying. Full article
(This article belongs to the Section Agricultural Technology)
Show Figures

Figure 1

25 pages, 13160 KB  
Article
LWCD-YOLO: A Lightweight Corn Seed Kernel Fast Detection Algorithm Based on YOLOv11n
by Wenbin Sun, Kang Xu, Dongquan Chen, Danyang Lv, Ranbing Yang, Songmei Yang, Rong Wang, Ling Wang and Lu Chen
Agriculture 2025, 15(18), 1968; https://doi.org/10.3390/agriculture15181968 - 18 Sep 2025
Viewed by 290
Abstract
As one of the world’s most important staple crops providing food, feed, and industrial raw materials, corn requires precise kernel detection for seed phenotype analysis and seed quality examination. In order to achieve precise and rapid detection of corn seeds, this study proposes [...] Read more.
As one of the world’s most important staple crops providing food, feed, and industrial raw materials, corn requires precise kernel detection for seed phenotype analysis and seed quality examination. In order to achieve precise and rapid detection of corn seeds, this study proposes a lightweight corn seed kernel rapid detection model based on YOLOv11n (LWCD-YOLO). Firstly, a lightweight backbone feature extraction module is designed based on Partial Convolution (PConv) and an efficient multi-scale attention module (EMA), which reduces model complexity while maintaining model detection performance. Secondly, a cross layer multi-scale feature fusion module (MSFFM) is proposed to facilitate deep feature fusion of low-, medium-, and high-level features. Finally, we optimized the model using the WIOU bounding box loss function. Experiments were conducted on the collected Corn seed kernel detection dataset, and LWCD-YOLO only required 1.27 million (M) parameters and 3.5 G of FLOPs. Its precision (P), mean Average Precision at 0.50 (mAP0.50), and mean Average Precision at 0.50:0.95 (mAP0.50:0.95) reached 99.978%, 99.491%, and 99.262%, respectively. Compared to the original YOLOv11n, the model size, parameter count, and computational complexity were reduced by 50%, 51%, and 44%, respectively, and the FPS was improved by 94%. The detection performance, model complexity, and detection efficiency of LWCD-YOLO are superior to current mainstream object detection models, making it suitable for fast and precise detection of corn seeds. It can provide guarantees for achieving seed phenotype analysis and seed quality examination. Full article
(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
Show Figures

Figure 1

23 pages, 63827 KB  
Article
A Two-Stage Weed Detection and Localization Method for Lily Fields Targeting Laser Weeding
by Yanlei Xu, Chao Liu, Jiahao Liang, Xiaomin Ji and Jian Li
Agriculture 2025, 15(18), 1967; https://doi.org/10.3390/agriculture15181967 - 18 Sep 2025
Viewed by 275
Abstract
The cultivation of edible lilies is highly susceptible to weed infestation during its growth period, and the application of herbicides is often impractical, leading to the rampant growth of diverse weed species. Laser weeding, recognized as an efficient and precise method for field [...] Read more.
The cultivation of edible lilies is highly susceptible to weed infestation during its growth period, and the application of herbicides is often impractical, leading to the rampant growth of diverse weed species. Laser weeding, recognized as an efficient and precise method for field weed management, presents a novel solution to the weed challenges in lily fields. The accurate localization of weed regions and the optimal selection of laser targeting points are crucial technologies for successful laser weeding implementation. In this study, we propose a two-stage weed detection and localization method specifically designed for lily fields. In the first stage, we introduce an enhanced detection model named YOLO-Morse, aimed at identifying and removing lily plants. YOLO-Morse is built upon the YOLOv8 architecture and integrates the RCS-MAS backbone, the SPD-Conv spatial enhancement module, and an adaptive focal loss function (ATFL) to enhance detection accuracy in conditions characterized by sample imbalance and complex backgrounds. Experimental results indicate that YOLO-morse achieves a mean Average Precision (mAP) of 86%, reflecting a 3.2% improvement over the original YOLOv8, and facilitates stable identification of lily regions. Subsequently, a ResNet-based segmentation network is employed to conduct semantic segmentation on the detected lily targets. The segmented results are utilized to mask the original lily areas in the image, thereby generating weed-only images for the subsequent stage. In the second stage, the original RGB field images are first converted into weed-only images by removing lily regions; these weed-only images are then analyzed in the HSV color space combined with morphological processing to precisely extract green weed regions. The centroid of the weed coordinate set is automatically determined as the laser targeting point.The proposed system exhibits superior performance in weed detection, achieving a Precision, Recall, and F1-score of 94.97%, 90.00%, and 92.42%, respectively. The proposed two-stage approach significantly enhances multi-weed detection performance in complex environments, improving detection accuracy while maintaining operational efficiency and cost-effectiveness. This method proposes a precise, efficient, and intelligent laser weeding solution for weed management in lily fields. Although certain limitations remain, such as environmental lighting variation, leaf occlusion, and computational resource constraints, the method still exhibits significant potential for broader application in other high-value crops. Full article
(This article belongs to the Special Issue Plant Diagnosis and Monitoring for Agricultural Production)
Show Figures

Figure 1

21 pages, 664 KB  
Article
The Role of Food Safety in Sustainable Gastronomic Tourism: Insights from Farm-Stay Tourist Experiences
by Dragan Vukolić, Mladen Radišić, Maja Radišić, Dušan Pevac, Srđan Milošević and Tamara Gajić
Agriculture 2025, 15(18), 1966; https://doi.org/10.3390/agriculture15181966 - 18 Sep 2025
Viewed by 309
Abstract
In contemporary tourism, gastronomic offerings increasingly go beyond the boundaries of mere taste enjoyment, becoming an important element of the sustainable development of destinations. At the same time, food safety is gaining importance as a key aspect of the tourist experience and trust [...] Read more.
In contemporary tourism, gastronomic offerings increasingly go beyond the boundaries of mere taste enjoyment, becoming an important element of the sustainable development of destinations. At the same time, food safety is gaining importance as a key aspect of the tourist experience and trust in a destination. The research was conducted in Serbia, focusing specifically on agritourism farm stays known for their local food production and sustainable hospitality practices. This study highlights the crucial link between local agricultural practices and tourists’ perceptions of food safety, positioning food safety as a key dimension of both sustainable gastronomy and rural development. The research was conducted on a sample of 650 tourists in farm stays, using a structured survey questionnaire, with data analysed through descriptive statistics, factor analysis, Pearson correlation, ANOVA, and multiple regression analysis. The results indicate that tourists highly value food safety, particularly in the context of local and traditional gastronomy, and that there is a significant correlation between the perception of food safety and the intention to revisit or recommend a destination. This study suggests that the integration of food safety standards into sustainable gastronomic practices is essential for enhancing competitiveness and building long-term trust among individuals of various sociodemographic profiles. Full article
Show Figures

Figure 1

16 pages, 1995 KB  
Article
Powdery Mildew Resistance Gene (Pm) Stability and Blumeria graminis f. sp. avenae Virulence Trends in Poland (2021–2023): Challenges to Durable Resistance in Oat
by Weronika Grzelak, Aleksandra Nucia and Sylwia Okoń
Agriculture 2025, 15(18), 1965; https://doi.org/10.3390/agriculture15181965 - 18 Sep 2025
Viewed by 268
Abstract
Oat (Avena sativa L.) is a widely cultivated cereal crop valued for both its nutritional benefits and agricultural versatility. However, oat production is increasingly challenged by powdery mildew, which is caused by Blumeria graminis f. sp. avenae (Bga) and can [...] Read more.
Oat (Avena sativa L.) is a widely cultivated cereal crop valued for both its nutritional benefits and agricultural versatility. However, oat production is increasingly challenged by powdery mildew, which is caused by Blumeria graminis f. sp. avenae (Bga) and can lead to considerable yield losses. Genetic resistance remains the most sustainable and environmentally friendly method of disease control. This study aimed to evaluate the effectiveness of 14 oat genotypes carrying known resistance genes (Pm1Pm12) and Avena strigosa accessions against Bga populations collected across four regions of Poland between 2021 and 2023. Host–pathogen assays were used to assess resistance levels, virulence frequency, and pathotype diversity. Resistance genes were categorized into three groups based on performance: highly effective (Pm2, Pm4, Pm5, Pm7 in APR122 and A. strigosa), variably effective (Pm7 in ‘Canyon’ and Pm9Pm12), and moderately effective (Pm1, Pm3, Pm6 and Pm3+8). Pathogen populations exhibited decreasing virulence complexity and diversity over time, with substantial regional variation. There were few dominant pathotypes, but most were rare and transient. This study confirms the long-term effectiveness of several resistance genes and the necessity of continuous resistance monitoring. It supports the use of gene pyramiding to ensure durable, regionally adapted protection. These results highlight the importance of combining resistance breeding with integrated disease management to ensure sustainable oat production under changing environmental conditions. Full article
Show Figures

Figure 1

24 pages, 4730 KB  
Article
Fertility-Based Nitrogen Management Strategies Combined with Straw Return Enhance Rice Yield and Soil Quality in Albic Soils
by Qiuju Wang, Xuanxuan Gao, Baoguang Wu, Jingyang Li, Xin Liu, Jiahe Zou and Qingying Meng
Agriculture 2025, 15(18), 1964; https://doi.org/10.3390/agriculture15181964 - 17 Sep 2025
Viewed by 284
Abstract
Low productivity in albic soils often results in excessive nitrogen input, while straw return further increases nitrogen accumulation through decomposition. To address this issue, a three-year field experiment was conducted in albic soils of high, medium, and low fertility. Two nitrogen management strategies [...] Read more.
Low productivity in albic soils often results in excessive nitrogen input, while straw return further increases nitrogen accumulation through decomposition. To address this issue, a three-year field experiment was conducted in albic soils of high, medium, and low fertility. Two nitrogen management strategies were assessed: nitrogen addition and reduction. Addition treatments included conventional nitrogen application rate alone (N), straw return (8250 kg ha−1) with conventional nitrogen application rate (SN), and straw return with increased nitrogen (SN+). Reduction treatments comprised SN and straw return with 10%, 20%, and 30% reduced nitrogen (SN0.9, SN0.8, and SN0.7). Soil physical properties, nutrient content, and rice yield were evaluated. Results showed that SN0.9 exhibited advantages in high-fertility albic soils, as it increased rice yield and improved some soil quality while reducing the nitrogen input by 10%. However, yield under SN0.9 declined progressively over the three years, indicating limitations of long-term application. SN performed better than both N and SN+ in medium- and low-fertility albic soils, offering better yield and soil quality improvements. However, nitrogen overaccumulation risk under continuous application should not be overlooked. These findings highlight that fertility-based nitrogen adjustment combined with straw return can simultaneously improve rice productivity and soil quality while reducing nitrogen input in albic soils. Full article
(This article belongs to the Section Agricultural Soils)
Show Figures

Graphical abstract

20 pages, 13462 KB  
Article
An AI-Based System for Monitoring Laying Hen Behavior Using Computer Vision for Small-Scale Poultry Farms
by Jill Italiya, Ahmed Abdelmoamen Ahmed, Ahmed A. A. Abdel-Wareth and Jayant Lohakare
Agriculture 2025, 15(18), 1963; https://doi.org/10.3390/agriculture15181963 - 17 Sep 2025
Viewed by 298
Abstract
Small-scale poultry farms often lack access to advanced monitoring tools and rely heavily on manual observation, which is time-consuming, inconsistent, and insufficient for precise flock management. Feeding and drinking behaviors are critical, as they serve as early indicators of health and environmental issues. [...] Read more.
Small-scale poultry farms often lack access to advanced monitoring tools and rely heavily on manual observation, which is time-consuming, inconsistent, and insufficient for precise flock management. Feeding and drinking behaviors are critical, as they serve as early indicators of health and environmental issues. With global poultry production expanding, raising over 70 billion hens annually, there is an urgent need for intelligent, low-cost systems that can continuously and accurately monitor bird behavior in resource-limited farm settings. This paper presents the development of a computer vision-based chicken behavior monitoring system, specifically designed for small barn environments where at most 10–15 chickens are housed at any time. The developed system consists of an object detection model, created on top of the YOLOv8 model, trained with an imagery dataset of laying hen, feeder, and waterer objects. Although chickens are visually indistinguishable, the system processes each detection per frame using bounding boxes and movement-based approximation identification rather than continuous identity tracking. The approach simplifies the tracking process without losing valuable behavior insights. Over 700 frames were annotated manually for high-quality labeled data, with different lighting, hen positions, and interaction angles with dispensers. The images were annotated in YOLO format and used for training the detection model for 100 epochs, resulting in a model having an average mean average precision (mAP@0.5) metric value of 91.5% and a detection accuracy of over 92%. The proposed system offers an efficient, low-cost solution for monitoring chicken feeding and drinking behaviors in small-scale farms, supporting improved management and early health detection. Full article
Show Figures

Figure 1

16 pages, 1646 KB  
Article
Suitability of Slovakian Landscapes for Vegetable Growing
by Jozef Vilček, Štefan Koco, Adam Kupec, Stanislav Torma and Matúš Maxin
Agriculture 2025, 15(18), 1962; https://doi.org/10.3390/agriculture15181962 - 17 Sep 2025
Viewed by 227
Abstract
The cultivation of vegetables in Slovakia has traditionally occurred in the vicinity of human settlements, predominantly in allotments. Large-scale vegetable production requires not only intensification measures but also a strategic selection of regions with optimal soil and climatic conditions. In Slovakia, this selection [...] Read more.
The cultivation of vegetables in Slovakia has traditionally occurred in the vicinity of human settlements, predominantly in allotments. Large-scale vegetable production requires not only intensification measures but also a strategic selection of regions with optimal soil and climatic conditions. In Slovakia, this selection is limited by the availability of arable land suitable for vegetable cultivation. This study quantifies and delineates areas that are very suitable, suitable, poorly suitable, and unsuitable for the major vegetable species grown in the region. The findings indicate that the largest proportion of very suitable arable land is best suited for the cultivation of cauliflower (35%), celery (33%), beans (31%), and beetroot (28%). Conversely, the analysis reveals that a significant proportion of arable soils possess potentially unsuitable conditions for specific crops, with asparagus (94%), peppers (80%), and cucumbers (71%) exhibiting the highest percentages. In addition, an analysis of actual vegetable cultivation between the years 2020 and 2024 indicates that a substantial portion of certain crops, specifically 75% of celery, 59% of tomatoes, 56% of cauliflower, and 54% of carrots are cultivated in areas that are very suitable for their growth. In contrast, 81% of pumpkin, 79% of beetroot, and 47% of beans are produced under unsuitable conditions. By optimizing the selection of suitable areas and soils, the potential of the Slovak landscape can be utilized more efficiently for domestic vegetable production. Full article
Show Figures

Figure 1

Previous Issue
Back to TopTop