Agronomy

21 pages, 7835 KiB

Open AccessArticle

Extraction of Cropland Based on Multi-Source Remote Sensing and an Improved Version of the Deep Learning-Based Segment Anything Model (SAM)

by Kunjian Tao, He Li, Chong Huang, Qingsheng Liu, Junyan Zhang and Ruoqi Du

Agronomy 2025, 15(5), 1139; https://doi.org/10.3390/agronomy15051139 - 6 May 2025

Abstract

Fine extraction of cropland parcels is an essential prerequisite for achieving precision agriculture. Remote sensing technology, due to its large-scale and multi-dimensional characteristics, can effectively enhance the efficiency of collecting information on agricultural land parcels. Currently, semantic segmentation models based on high-resolution remote [...] Read more.

Fine extraction of cropland parcels is an essential prerequisite for achieving precision agriculture. Remote sensing technology, due to its large-scale and multi-dimensional characteristics, can effectively enhance the efficiency of collecting information on agricultural land parcels. Currently, semantic segmentation models based on high-resolution remote sensing imagery utilize limited spectral information and rely heavily on a large amount of fine data annotation, while pixel classification models based on medium-to-low-resolution multi-temporal remote sensing imagery are limited by the mixed pixel problem. To address this, the study utilizes GF-2 high-resolution imagery and Sentinel-2 multi-temporal data, in conjunction with the basic image segmentation model SAM, by additionally introducing a prompt generation module (Box module and Auto module) to achieve automatic fine extraction of cropland parcels. The research results indicate the following: (1) The mIoU of SAM with the Box module is 0.711, and the OA is 0.831, showing better performance, while the mIoU of SAM with the Auto module is 0.679, and the OA is 0.81, yielding higher-quality cropland masks; (2) The combination of various prompts (box, point, and mask), along with the hierarchical extraction strategy, can effectively improve the performance of Box module SAM; (3) Employing a more accurate prompt data source can significantly boost model performance. The mIoU of the superior-performing Box module SAM is increased to 0.920, and the OA is raised to 0.958. Overall, the improved SAM, while reducing the demand for mask annotation and model training, can achieve high-precision extraction results for cropland parcels. Full article

(This article belongs to the Section Precision and Digital Agriculture)

► Show Figures

Figure 1

20 pages, 1525 KiB

Open AccessArticle

Biostimulant Extracts Obtained from the Brown Seaweed Cystoseira barbata Enhance the Growth, Yield, Quality, and Nutraceutical Value of Soil-Grown Tomato

by Yagmur Arikan-Algul, Hande Mutlu-Durak, Umit Baris Kutman and Bahar Yildiz Kutman

Agronomy 2025, 15(5), 1138; https://doi.org/10.3390/agronomy15051138 - 6 May 2025

Abstract

The use of seaweed-derived biostimulants has gained attention as a sustainable strategy to enhance crop production. Brown seaweeds, in particular, are rich in bioactive compounds that can improve plant growth, yield, and quality parameters. This study investigated the biostimulant potential of extracts derived [...] Read more.

The use of seaweed-derived biostimulants has gained attention as a sustainable strategy to enhance crop production. Brown seaweeds, in particular, are rich in bioactive compounds that can improve plant growth, yield, and quality parameters. This study investigated the biostimulant potential of extracts derived from Cystoseira barbata for promoting tomato growth and improving fruit quality. Three different extracts (water, alkali, and acid), applied as soil drenches, were tested on a determinate tomato cultivar under greenhouse conditions. In young plants, alkali and acid extracts increased stem length by 40% and 60%, respectively, while water and acid extracts accelerated early flowering. Alkali and acid extracts also improved fruit yield by approximately 65%. Additionally, all extracts enhanced fruit quality by increasing fruit EC and Brix values, soluble carbohydrate levels, total phenolic content, total antioxidant capacity, lycopene and β-carotene concentrations, and vitamin C content, albeit to varying degrees. Along with increases in fruit K concentration in response to water and alkali extracts, all seaweed extract-treated groups showed elevated fruit S concentrations, accompanied by increases in reduced glutathione levels. These results indicate that C. barbata extracts can enhance plant performance while improving the nutritional and nutraceutical properties of tomato fruits. The observed effects were strongly influenced by the extraction method, which alters the extract composition. Extracts from sustainably sourced C. barbata may contribute to improved productivity and quality in horticulture; however, further research is needed to enable the standardized production of C. barbata, optimize biostimulant formulations, and validate their effectiveness under field conditions. Full article

(This article belongs to the Topic Biostimulants in Agriculture—2nd Edition)

► Show Figures

Graphical abstract

13 pages, 1791 KiB

Open AccessArticle

Increased Light Intensity Mitigates CO₂ and CH₄ Emissions from Paddy Soil by Mediating Iron Redox Cycling Coupled with Organic Carbon Transformation

by Lirong Sun, Mengxiao Jiang, Meng Li, Xugang Wang, Yafeng Han and Xianni Chen

Agronomy 2025, 15(5), 1137; https://doi.org/10.3390/agronomy15051137 - 6 May 2025

Abstract

Iron redox cycling in paddy soils drives the release and mineralisation of dissolved organic carbon (DOC), influencing the emission of CO₂ and CH₄. Light irradiation exerts an inhibitory effect on the mineralisation of soil organic carbon, but the responses to [...] Read more.

Iron redox cycling in paddy soils drives the release and mineralisation of dissolved organic carbon (DOC), influencing the emission of CO₂ and CH₄. Light irradiation exerts an inhibitory effect on the mineralisation of soil organic carbon, but the responses to light intensity of iron redox processes coupled with organic carbon transformation and greenhouse gas emissions remain underexplored. Here, we conducted a slurry incubation experiment with paddy soil at varying light intensities. The dynamics of soil ferrous iron [Fe(II)], DOC, dissolved inorganic carbon (DIC), and chlorophyll a, as well as headspace CO₂ and CH₄, were monitored over a 40-day period. The results demonstrated that light irradiation inhibited iron reduction, leading to a 58.1–74.7% decrease in soil Fe(II) concentration compared to dark incubation. The oxidation of Fe(II) generated from iron reduction was enhanced under light incubation (3.12–3.53 mg g⁻¹), and the oxidation rate constant trended higher with increasing light intensity. Light irradiation reduced CO₂ and CH₄ emissions to 8.8–76.9% and 2.3–6.7% of those under dark incubation, respectively. With the extension of incubation time, soil DIC concentration showed an increase followed by a decrease under light incubation, and the earlier DIC decrease occurred at higher light intensities. The DOC decrease rate constant was greater under light incubation (0.024–0.042 d⁻¹) than under dark incubation (0.012 d⁻¹). Light irradiation activated phototrophic microorganisms producing chlorophyll a (4.71–6.46 mg g⁻¹), whereas this pigment was undetectable under dark incubation. Organic carbon mineralisation was positively correlated with Fe(II) concentration, and Fe(II) oxidation was positively correlated with chlorophyll a concentration and DOC decrease (p < 0.05). Agricultural practices optimizing light exposure, such as shallow flooding or reducing plant density, are promising approaches to bolster DOC sequestration and mitigate CO₂ and CH₄ emissions in paddy fields. Full article

(This article belongs to the Topic Greenhouse Gas Emission Reductions and Carbon Sequestration in Agriculture)

► Show Figures

Figure 1

19 pages, 8805 KiB

Open AccessArticle

Field Inoculation of Pleurotus tuoliensis in Natural Habitat Promotes Microbial Communities That Enhance Its Growth

by Ying Luo, Hanbing Liu, Wenjie Jia, Nuerziya Yalimaimaiti, Qi Zhu, Peisong Jia, Yilin Huang, Wenting Shi, Chunhua Sun and Jianhua Guan

Agronomy 2025, 15(5), 1136; https://doi.org/10.3390/agronomy15051136 - 6 May 2025

Abstract

Pleurotus tuoliensis is a valuable edible mushroom native to Xinjiang in northwest China. It colonizes the roots and stems of Ferula plants. Field inoculation in its natural habitat has been shown to significantly enhance the colonization rate of P. tuoliensis hyphae in Ferula [...] Read more.

Pleurotus tuoliensis is a valuable edible mushroom native to Xinjiang in northwest China. It colonizes the roots and stems of Ferula plants. Field inoculation in its natural habitat has been shown to significantly enhance the colonization rate of P. tuoliensis hyphae in Ferula plants. However, the effects of field inoculation on P. tuoliensis hyphal colonization, soil properties, and microbial communities remain underexplored. In this study, we examined the characteristics of rhizosphere soil and microbial communities under four conditions: natural environments with and without hyphal colonization, and field inoculation with and without colonization. High-throughput sequencing results revealed that field inoculation markedly increased the relative abundance of Pleurotus species (57.98%) compared to natural colonization (14.11%). However, field inoculation also resulted in a reduction in microbial community diversity compared to hyphal colonization. Concurrently, the relative abundance of Pseudomonadota, Bacteroidota, and Bacillota significantly increased following field inoculation. LEfSe analysis suggested that the identified potential biomarkers were most likely associated with the Bacillus genus within Bacillota. Furthermore, mushroom growth-promoting bacteria were successfully isolated and identified as members of the Bacillus cereus group (L5) and Bacillus safensis (S16). This finding suggests that field inoculation with P. tuoliensis in its natural habitat promotes microbial communities that enhance its growth. This study offers new insights into conserving wild edible fungi and their interactions with soil microbiota. Full article

(This article belongs to the Section Horticultural and Floricultural Crops)

► Show Figures

Figure 1

20 pages, 6453 KiB

Open AccessArticle

A Robust Tomato Counting Framework for Greenhouse Inspection Robots Using YOLOv8 and Inter-Frame Prediction

by Wanli Zheng, Guanglin Dai, Miao Hu and Pengbo Wang

Agronomy 2025, 15(5), 1135; https://doi.org/10.3390/agronomy15051135 - 6 May 2025

Abstract

Accurate tomato yield estimation and ripeness monitoring are critical for optimizing greenhouse management. While manual counting remains labor-intensive and error-prone, this study introduces a novel vision-based framework for automated tomato counting in standardized greenhouse environments. The proposed method integrates YOLOv8-based detection, depth filtering, [...] Read more.

Accurate tomato yield estimation and ripeness monitoring are critical for optimizing greenhouse management. While manual counting remains labor-intensive and error-prone, this study introduces a novel vision-based framework for automated tomato counting in standardized greenhouse environments. The proposed method integrates YOLOv8-based detection, depth filtering, and an inter-frame prediction algorithm to address key challenges such as background interference, occlusion, and double-counting. Our approach achieves 97.09% accuracy in tomato cluster detection, with mature and immature single fruit recognition accuracies of 92.03% and 91.79%, respectively. The multi-target tracking algorithm demonstrates a MOTA (Multiple Object Tracking Accuracy) of 0.954, outperforming conventional methods like YOLOv8 + DeepSORT. By fusing odometry data from an inspection robot, this lightweight solution enables real-time yield estimation and maturity classification, offering practical value for precision agriculture. Full article

(This article belongs to the Special Issue Robotics and Automation in Farming)

► Show Figures

Figure 1

25 pages, 5725 KiB

Open AccessArticle

Dynamic Modeling and Parameter Optimization of Potato Harvester Under Multi-Source Excitation

by Jianguo Meng, Zhipeng Li, Zheng Li, Yanzhou Li and Wenxia Xie

Agronomy 2025, 15(5), 1134; https://doi.org/10.3390/agronomy15051134 - 5 May 2025

Abstract

During field operations, the potato harvester is subjected to multiple sources of excitation, including internal vibratory mechanisms and field surface excitation, resulting in significant vibrations in the frame. Based on the physical parameters of the harvester’s internal structure and the connection parameters between [...] Read more.

During field operations, the potato harvester is subjected to multiple sources of excitation, including internal vibratory mechanisms and field surface excitation, resulting in significant vibrations in the frame. Based on the physical parameters of the harvester’s internal structure and the connection parameters between components, a 12-degree-of-freedom (12-DOF) dynamic model of the entire machine was constructed. The corresponding simulation model was created in a MATLAB/Simulink environment to analyze the vibration characteristics of each component during harvesting operations. The comparison between actual and simulated signals shows that the RMS error of acceleration is only 2.42%, indicating that introducing two degrees of freedom in pitch and roll directions to the potato harvester can accurately describe its vibration characteristics. On this basis, the Bayesian optimization algorithm was used to obtain optimal connection parameters. The optimization results demonstrate a 0.85 m/s² and 0.45 m/s² increase in RMS values for the soil-cutting disc and lifting chain, respectively, effectively enhancing the harvester’s work efficiency, while the frame exhibited a 0.31 m/s² reduction in RMS value, significantly improving structural stability. This study provides a theoretical foundation for the parameter optimization of large-scale agricultural machinery. Full article

(This article belongs to the Section Agricultural Biosystem and Biological Engineering)

► Show Figures

Figure 1

19 pages, 7499 KiB

Open AccessArticle

Strawberry Growth Medium Made with Biogas Residues: Feasibility and Economic Benefit Potential

by Jing Zhou, Xiaochen Zhang, Baoping Wang, Jitao Zhang, Xiuhong Wang and Xiangyuan Shi

Agronomy 2025, 15(5), 1133; https://doi.org/10.3390/agronomy15051133 - 5 May 2025

Abstract

In this study, we examined the impact of various physical and chemical properties of growth media on strawberry growth, yield, quality, and economic returns. Six treatments were established: T1 (biogas residue/peat/perlite/vinegar residue = 1:5:1:4), T2 (biogas residue/peat/perlite/vinegar residue = 2:3:1:5), T3 (biogas residue/peat/perlite/vinegar [...] Read more.

In this study, we examined the impact of various physical and chemical properties of growth media on strawberry growth, yield, quality, and economic returns. Six treatments were established: T1 (biogas residue/peat/perlite/vinegar residue = 1:5:1:4), T2 (biogas residue/peat/perlite/vinegar residue = 2:3:1:5), T3 (biogas residue/peat/perlite/vinegar residue = 2:3:1:4), T4 (biogas residue/peat/perlite/vinegar residue = 2:4:1:3), T5 (biogas residue/peat/perlite/vinegar residue = 3:4:1:5), and CK (peat/perlite = 4:1). The results showed that compared with CK treatment, the total nitrogen level increased by 3.26- to 3.95-fold and the organic matter content increased by 14.13–25.70%. In particular, T3 (biogas residue/peat/perlite/vinegar residue = 2:3:1:4) exhibited significant growth advantages, with stem diameter, root volume, and fresh weight increasing by 18.89%, 36.41%, and 35.26%, respectively, compared to CK. The yield per plant saw a 14.54% increase, soluble solids rose by 29.34%, and the solid acid ratio was 1.68 times higher than that of CK. Furthermore, the net income was 2.37 times greater than that of CK. A comprehensive assessment revealed that the T3 treatment demonstrated superior performance in both growth parameters and economic returns, suggesting its suitability as an optimal formulation for further experimentation. Full article

(This article belongs to the Section Agricultural Biosystem and Biological Engineering)

► Show Figures

Figure 1

16 pages, 1934 KiB

Open AccessArticle

The Effects of Long-Term Land Use Changes on Bacterial Community Structure and Soil Physicochemical Properties in the Northeast Mollisol Region of China

by Xu Wang, Qiang Chen, Zhao Li, Weiping Yin and Dalong Ma

Agronomy 2025, 15(5), 1132; https://doi.org/10.3390/agronomy15051132 - 5 May 2025

Abstract

Soil microorganisms are essential for maintaining the function and health of agricultural ecosystems. However, the responses of microbial communities to long-term changes in land use have been insufficiently explored. Hence, based on a 15 years of field experiments in the northeast Mollisol region [...] Read more.

Soil microorganisms are essential for maintaining the function and health of agricultural ecosystems. However, the responses of microbial communities to long-term changes in land use have been insufficiently explored. Hence, based on a 15 years of field experiments in the northeast Mollisol region of China, we applied the Illumina high-throughput sequencing technology to study the effects of different land use types, including conventional tillage (CT), bare land (BL), no tillage (NT), natural vegetation restoration (NVR), and afforestation (AF), on bacterial communities along the soil profile (0–5 cm, 5–10 cm, 10–20 cm, and 20–30 cm) and co-occurrence networks and identified their relationships with soil physicochemical properties. The findings indicated that the land use type as well as soil depth affected the diversity and structure of bacterial communities significantly. There was no marked difference in the diversity of bacterial communities between CT and NT at different soil depths, except for a depth of 20–30 cm. In NT, NVR, and AF, the relative abundance of Actinomycetota and Firmicutes was higher than that in CT. Conversely, CT showed a remarkably higher abundance of Proteobacteria and Acidobacteriota than BL, NT, NVR, and AF. Compared with CT and BL, increased stability and complexity of the community co-occurrence networks was identified for NT, NVR, and AF. Additionally, the diversity and composition of bacterial communities were correlated with the soil’s total nitrogen (TN), pH as well as total organic carbon (TOC). Our study revealed the potential mechanism by which long-term land use changes affected the distribution of soil bacterial communities, which was of high importance for sustainable development of agriculture and optimal management of land resources. Full article

(This article belongs to the Section Farming Sustainability)

► Show Figures

Figure 1

30 pages, 3961 KiB

Open AccessReview

Nanoparticles for Sustainable Agriculture: Assessment of Benefits and Risks

by Mohammed Bouhadi, Qaiser Javed, Monika Jakubus, M’hammed Elkouali, Hassan Fougrach, Ayesha Ansar, Smiljana Goreta Ban, Dean Ban, David Heath and Marko Černe

Agronomy 2025, 15(5), 1131; https://doi.org/10.3390/agronomy15051131 - 4 May 2025

Abstract

Nanotechnology is rapidly emerging as a transformative force in agriculture, offering innovative solutions to support sustainable crop production. This review examines the interactions between nanoparticles (NPs) and plants, elucidating the underlying mechanisms that govern NP uptake, translocation, and interactions at the cellular level. [...] Read more.

Nanotechnology is rapidly emerging as a transformative force in agriculture, offering innovative solutions to support sustainable crop production. This review examines the interactions between nanoparticles (NPs) and plants, elucidating the underlying mechanisms that govern NP uptake, translocation, and interactions at the cellular level. We explore how NPs influence key physiological processes and modulate plant defense responses to both biotic and abiotic stresses, highlighting their potential for enhancing stress resistance. The diverse applications of NPs in agriculture are also comprehensively surveyed, encompassing targeted delivery of nutrients, enhanced biocontrol of phytopathogens, and engineering improved tolerance to environmental extremes. We also address the broader environmental and socioeconomic implications of the widespread use of NPs in agriculture, critically evaluating their ecotoxicity, impacts on biodiversity, and the associated economic costs and benefits. Finally, we offer a perspective on future directions for research, including emerging trends in NPs synthesis and characterization, challenges to sustainable implementation, and the prospects for large-scale deployment of nanotechnology-enabled agricultural solutions. This review provides a rigorous and balanced assessment of the potential of nanotechnology to revolutionize agricultural practices while acknowledging the need for responsible innovation and risk mitigation. Full article

(This article belongs to the Special Issue Nano-Farming: Crucial Solutions for the Future)

► Show Figures

Figure 1

19 pages, 4271 KiB

Open AccessArticle

A Low-Energy Lighting Strategy for High-Yield Strawberry Cultivation Under Controlled Environments

by Jun Zou, Zihan Wang, Haitong Huang, Xiaohua Huang and Mingming Shi

Agronomy 2025, 15(5), 1130; https://doi.org/10.3390/agronomy15051130 - 4 May 2025

Abstract

Optimizing light conditions in controlled-environment agriculture is critical for enhancing crop yield and energy efficiency, particularly in high-value crops like strawberries, where precise spectral tuning can significantly influence both vegetative growth and fruit production. In this study, a windmill-style vertical farming system was [...] Read more.

Optimizing light conditions in controlled-environment agriculture is critical for enhancing crop yield and energy efficiency, particularly in high-value crops like strawberries, where precise spectral tuning can significantly influence both vegetative growth and fruit production. In this study, a windmill-style vertical farming system was developed to facilitate efficient strawberry cultivation under low-light conditions. A custom LED lighting fixture, measuring 3 m in length, was suspended 30 cm above the canopy to uniformly illuminate a planting zone of 3.0 m × 0.3 m. The lighting system, which combines red (655–665 nm) and full-spectrum white LEDs, was optimized using a particle swarm optimization (PSO) algorithm to enhance spatial light distribution. The uniformity of photosynthetic photon flux density (PPFD) improved from 71% to 85%, and the standard deviation decreased from 75 to 15. Under a 16 h optimized lighting regime, strawberry plants exhibited a 55% increase in height compared to the non-supplemented control group (Group D), a 40% increase in leaf width, and a 36% increase in fruit weight (69.76 g per plant) relative to the 12 h supplemental lighting group (Group A). The system operates at a fixture-level power consumption of just 160 W, with its spectral output aligned with the absorption characteristics of strawberry foliage and fruit. These results demonstrate that an algorithm-driven lighting layout can significantly enhance both vegetative and reproductive performance in vertical strawberry farming while maintaining high energy efficiency. Full article

(This article belongs to the Topic Advances in Smart Agriculture with Remote Sensing as the Core and Its Applications in Crops Field)

► Show Figures

Figure 1

24 pages, 15025 KiB

Open AccessArticle

Drift Suppression by Adjusting Flight Parameters for Manned Helicopters in Forested Regions

by Shuping Fang, Liping Chen, Yu Ru, Ningning Wang, Xiaojun Jin, Yangyang Liu and Lingyuan Sun

Agronomy 2025, 15(5), 1129; https://doi.org/10.3390/agronomy15051129 - 4 May 2025

Abstract

Under complex climatic conditions, variable application parameters and a two-dimensional application route, it is difficult to ensure the accurate deposition of pesticide droplets during helicopter aerial applications. This is especially true when the deposition area is forested. The Agricultural Dispersal (AGDISP) model was [...] Read more.

Under complex climatic conditions, variable application parameters and a two-dimensional application route, it is difficult to ensure the accurate deposition of pesticide droplets during helicopter aerial applications. This is especially true when the deposition area is forested. The Agricultural Dispersal (AGDISP) model was used with an optimization procedure to study the influence of flight height, flight speed, and ambient wind speed. Optimization techniques were used to obtain the best fit between the simulation results. Three objectives were used to propose a new application strategy, namely (i) the average deposition in the forest area; (ii) the uniformity of droplet deposition; and (iii) the deposition at a distance of 50 m downwind outside the forest area. A new application strategy was proposed, where the forest area was divided into two subareas, namely the safe area (the area away from forest boundaries) and the edge area (the area close to forest boundaries). Flight height and speed were adjusted to ensure the desired average deposition and uniformity in the safety area and the desired deposition at 50 m downwind in the edge area. Six helicopter spraying experiments at different wind speeds were conducted at Longtan, Nanjing, China. The deposition effects of the new strategy were compared with those of the common manual empirical method (operating at the same height and speed over the whole forest). It was found that at wind speeds of 2 m/s, 1 m/s, and 2.5 m/s, the average deposition in the safe area was improved by 4.82%, 0.91%, and 8.24%, respectively, and that in the edge area, it was improved by 7.04%, 0.90%, and 0.77%, respectively. Conversely, the deposition at 50 m downwind was reduced by 25.00%, 16.58% and 22.90%, respectively. These experimental results demonstrated that the new strategy can effectively reduce the droplet drift. We achieved the synergistic optimization goal of moderate (and uniform) deposition in the forest area with low deposition outside the forest area. This study can provide important technical references for precision forestry. Full article

(This article belongs to the Special Issue Advances in Precision Pesticide Spraying Technology and Equipment)

► Show Figures

Figure 1

28 pages, 4125 KiB

Open AccessArticle

YOLO_SSP: An Auto-Algorithm to Detect Mature Soybean Stem Nodes Based on Keypoint Detection

by Qiong Wu, Hang Liu, Hongfei Zhu, Cong Wang, Haoyu Wang, Zhongzhi Han, Longgang Zhao and Fei Liu

Agronomy 2025, 15(5), 1128; https://doi.org/10.3390/agronomy15051128 - 2 May 2025

Abstract

The soybean stem node is a key part of soybean growth and development, and its numbers play a crucial role in soybean yield formation. Traditional manual methods are labor-intensive and error-prone. The keypoint detection method is an ideal choice for stem node detection [...] Read more.

The soybean stem node is a key part of soybean growth and development, and its numbers play a crucial role in soybean yield formation. Traditional manual methods are labor-intensive and error-prone. The keypoint detection method is an ideal choice for stem node detection due to its high accuracy and wide applicability. In this study, a new deep learning method, You Only Look Once _Soybean Stalk Pose (YOLO_SSP) was proposed, which innovatively applied the Small_Effective Low-Level Aggregation Network (S_ELAN) module and fused it with a smaller detection head for detecting stem nodes in mature soybeans. After optimization and iteration, the model achieved 88.1% accuracy on the dataset. Subsequently, by ablating the model, it was found that different improvements were effective in increasing the accuracy of the model. In addition, when comparing the classic YOLO series of keypoint detection models, the results show that YOLO_SSP achieved up to 87.7% of APs, which was higher than YOLOv7-w6-pose, YOLOv7-tiny-pose, YOLOv3s-pose, YOLOv5n-pose, YOLOv5s-pose, YOLOv5m- pose, YOLOv6n-pose, YOLOv8n-pose, and YOLOv10b-pose, which were 2.5%, 12.8%, 5.3%, 3.8%, 3.5%, 3.5%, 5.1%, 5.1%, 5.0%, and 4.5% higher, respectively. Finally, the proposed model was applied to the unique dataset with 85.3% precision and 82.6% accuracy, and the visualization of the model’s detection results proved its applicability and universality. This study provides an effective strategy for soybean stem node detection and significantly improves the accuracy of detection. Full article

(This article belongs to the Section Precision and Digital Agriculture)

► Show Figures

Figure 1

15 pages, 2407 KiB

Open AccessArticle

Dominant Role of Irrigation Regime over Biochar in Controlling GHG Emissions from Paddy Fields

by Yanbing Chi, Yan Wang, Yalong Li, Cheng Yan, Miaomiao Shi, Linlin Fan and Chenchen Wei

Agronomy 2025, 15(5), 1127; https://doi.org/10.3390/agronomy15051127 - 2 May 2025

Abstract

Biochar is widely used in agriculture to enhance crop yield, improve soil fertility, and regulate greenhouse gas (GHG) emissions. Its effectiveness, however, depends not only on its properties but also on soil moisture conditions, making integrated water management essential for maximizing its benefits. [...] Read more.

Biochar is widely used in agriculture to enhance crop yield, improve soil fertility, and regulate greenhouse gas (GHG) emissions. Its effectiveness, however, depends not only on its properties but also on soil moisture conditions, making integrated water management essential for maximizing its benefits. The study reports the results of a laboratory incubation experiment using three biochar application rates (0, 20, and 40 t ha⁻¹) and two irrigation regimes—flooded irrigation and alternate wetting and drying (AWD)—to investigate the effects of biochar amendment and water management on soil greenhouse gas (GHG) emissions. The results indicated that there was no significant interaction between biochar and water regulation on GHG emissions, and changes in soil moisture and biochar application levels had no significant impact on carbon dioxide (CO₂) emissions. Compared to flooded irrigation, AWD effectively enhanced soil microbial activity, increasing nitrous oxide (N₂O) emissions by 62.50% to 88.35%, but significantly reducing methane (CH₄) emissions by 44.30% to 68.55%, thereby lowering the soil’s global warming potential (GWP). Additionally, biochar amendment significantly increased soil SOC and TN contents, enhanced soil enzyme activities, and significantly improved microbial carbon use efficiency (CUE), the C/N ratio, and the net nitrification rate (NNR). However, it had no significant effect on soil N₂O and CO₂ emissions, while significantly suppressed CH₄ emissions. Throughout the entire growth period, biochar application increased soil GWP overall. However, during the first water cycle, GWP increased with higher biochar application rates, whereas in the second water cycle, biochar application exhibited a suppressive effect on GWP. In conclusion, integrating biochar application with AWD irrigation can optimize soil CUE, enhance soil nutrient supply, and mitigate, to some extent, the potential increase in GHG emissions induced by biochar. This provides valuable insights for carbon management and sustainable agricultural development. Full article

(This article belongs to the Section Water Use and Irrigation)

► Show Figures

Figure 1

15 pages, 2156 KiB

Open AccessArticle

Effect of Essential Oil Components on the Growth Inhibition of Fusarium solani var. coeruleum During Potato Storage

by Martin Kmoch, Věra Loubová, Renata Švecová and Barbora Jílková

Agronomy 2025, 15(5), 1126; https://doi.org/10.3390/agronomy15051126 - 2 May 2025

Abstract

Fusarium dry rot of potato may be caused by several species of the genus Fusarium. This study aimed to evaluate the effect of essential oil (EO) components (α-pinene, carvacrol, cinnamaldehyde, D-carvone, eucalyptol, L-linalool, L-menthol, L-menthone, (R)-(+)-limonene and thymol) on the growth [...] Read more.

Fusarium dry rot of potato may be caused by several species of the genus Fusarium. This study aimed to evaluate the effect of essential oil (EO) components (α-pinene, carvacrol, cinnamaldehyde, D-carvone, eucalyptol, L-linalool, L-menthol, L-menthone, (R)-(+)-limonene and thymol) on the growth of Fusarium solani var. coeruleum using in vitro and in vivo experiments. All the evaluated EO components had a significant effect on the pathogen growth inhibition. Under in vitro conditions, the strongest inhibitory effect on mycelial growth was recorded for carvacrol, thymol, L-menthol and cinnamaldehyde. In vivo experiments confirmed the efficacy of selected EO components. The application of EO components was done by tuber dressing and fumigation. After treating tubers with EO components by dressing and fumigation, a statistically highly significant reduction in tuber infection with the pathogen was observed. Dressing usually had a stronger effect on the reduction in pathogen tuber infection (56.07–81.44%) compared to fumigation (40.03–69.63%). EO components did not have any significant effect on the organoleptic characteristics of cooked tubers; however, during tasting, a deteriorated quality of EO component-dressed tubers was found due to the off-odor and taste of the applied EO components. EO components have a high potential for ecological tuber protection against F. solani var. coeruleum during storage. Full article

(This article belongs to the Section Pest and Disease Management)

► Show Figures

Figure 1

20 pages, 10100 KiB

Open AccessArticle

A Method for Identifying Picking Points in Safflower Point Clouds Based on an Improved PointNet++ Network

by Baojian Ma, Hao Xia, Yun Ge, He Zhang, Zhenghao Wu, Min Li and Dongyun Wang

Agronomy 2025, 15(5), 1125; https://doi.org/10.3390/agronomy15051125 - 2 May 2025

Abstract

To address the challenge of precise picking point localization in morphologically diverse safflower plants, this study proposes PointSafNet—a novel three-stage 3D point cloud analysis framework with distinct architectural and methodological innovations. In Stage I, we introduce a multi-view reconstruction pipeline integrating Structure from [...] Read more.

To address the challenge of precise picking point localization in morphologically diverse safflower plants, this study proposes PointSafNet—a novel three-stage 3D point cloud analysis framework with distinct architectural and methodological innovations. In Stage I, we introduce a multi-view reconstruction pipeline integrating Structure from Motion (SfM) and Multi-View Stereo (MVS) to generate high-fidelity 3D plant point clouds. Stage II develops a dual-branch architecture employing Star modules for multi-scale hierarchical geometric feature extraction at the organ level (filaments and frui balls), complemented by a Context-Anchored Attention (CAA) mechanism to capture long-range contextual information. This synergistic feature learning approach addresses morphological variations, achieving 86.83% segmentation accuracy (surpassing PointNet++ by 7.37%) and outperforming conventional point cloud models. Stage III proposes an optimized geometric analysis pipeline combining dual-centroid spatial vectorization with Oriented Bounding Box (OBB)-based proximity analysis, resolving picking coordinate localization across diverse plants with 90% positioning accuracy and 68.82% mean IoU (13.71% improvement). The experiments demonstrate that PointSafNet systematically integrates 3D reconstruction, hierarchical feature learning, and geometric reasoning to provide visual guidance for robotic harvesting systems in complex plant canopies. The framework’s dual emphasis on architectural innovation and geometric modeling offers a generalizable solution for precision agriculture tasks involving morphologically diverse safflowers. Full article

(This article belongs to the Section Precision and Digital Agriculture)

► Show Figures

Figure 1

14 pages, 265 KiB

Open AccessReview

Optimising the Vase Life of Cut Hydrangeas: A Review of the Impact of Various Treatments

by Sutrisno, Ewa Skutnik and Julita Rabiza-Świder

Agronomy 2025, 15(5), 1124; https://doi.org/10.3390/agronomy15051124 - 2 May 2025

Abstract

The vase life of cut hydrangea (Hydrangea macrophylla) flowers is a critical quality parameter, influencing their marketability and consumer satisfaction. This review examines the influence of various treatments on prolonging the postharvest lifespan of cut hydrangea blooms. It discusses hydrangea in [...] Read more.

The vase life of cut hydrangea (Hydrangea macrophylla) flowers is a critical quality parameter, influencing their marketability and consumer satisfaction. This review examines the influence of various treatments on prolonging the postharvest lifespan of cut hydrangea blooms. It discusses hydrangea in general and its after-harvest mechanism, the vase life of cut hydrangea inflorescence in two phases, and conditions such as different storage temperatures and storage terms and length. It also highlights postharvest factors affecting cut flowers longevity like interventions targeting water balance, carbohydrate degradation, and sensitiveness to ethylene. Specific treatments that positively extend the life span of cut hydrangeas, such as sucrose, biocides, essential oil compounds, and commercial preservative solutions, are also evaluated. These treatments successfully increased the vase life of cut flowers from 3.6 to 12.3 days. The most effective solution for significantly extending the vase life of cut hydrangea flowers (‘Magical Jewel’) by 12.3 days was the combination of 1% sucrose and 8-HQS (8-hydroxyquinoline sulphate). The focus is on hydrangeas’ physiological and biochemical responses to these treatments, particularly their effects on water absorption, microbial activity, and the senescence process. By synthesising recent advancements and identifying research gaps, this review aims to provide actionable steps for growers, florists, and researchers to optimise the vase life of cut hydrangeas and improve the sustainability of their postharvest handling. Full article

(This article belongs to the Special Issue Applications of Pre- and Post-harvest Techniques in Horticultural Products)

34 pages, 16178 KiB

Open AccessArticle

YOLO11-PGM: High-Precision Lightweight Pomegranate Growth Monitoring Model for Smart Agriculture

by Rijun Wang, Yesheng Chen, Guanghao Zhang, Chunhui Yang, Xianglong Teng and Changjun Zhao

Agronomy 2025, 15(5), 1123; https://doi.org/10.3390/agronomy15051123 - 1 May 2025

Abstract

As a vital cash crop, intelligent monitoring of pomegranate growth stages plays a crucial role in improving orchard management efficiency and yield. Current research on pomegranates primarily focuses on the detection and quality classification of diseases and pests. Furthermore, the difficulty in deploying [...] Read more.

As a vital cash crop, intelligent monitoring of pomegranate growth stages plays a crucial role in improving orchard management efficiency and yield. Current research on pomegranates primarily focuses on the detection and quality classification of diseases and pests. Furthermore, the difficulty in deploying complex models in practical scenarios hinders the widespread adoption of pomegranate monitoring technology. To address these challenges, this paper proposes a lightweight pomegranate growth stage detection model, YOLO11-PGM, based on YOLO11n. The model integrates several innovative designs, including a Multi-Scale Edge Enhancement (MSEE) module to mitigate the effects of leaf and fruit occlusion, a Slim Shared Convolutional Head (SSCH) to resolve feature inconsistency across different scales in the feature pyramid, and a High-level Screening Feature Pyramid Network (HSFPN) to replace the standard neck network and achieve a balance between accuracy and complexity. Experimental results demonstrate that YOLO11-PGM achieves an accuracy of 92.3%, a recall of 86.3%, and an mAP50 of 94.0% with only 1.63 M parameters, 4.8 G FLOPs, and a model size of 3.7 MB. It outperforms YOLOv5s, YOLOv7, YOLOv8s, YOLOv9s, and YOLOv10s. Compared with the baseline YOLO11n, YOLO11-PGM improves the mAP50 by 2.6%, reduces the number of parameters by 36.9%, decreases computational complexity by 23.8%, and shrinks the model size by 32.7%. This model offers an effective solution for intelligent monitoring of pomegranate growth stages and provides valuable theoretical and technical references for orchard yield prediction, growth monitoring, planting management optimization, and the development of automated harvesting systems. Full article

(This article belongs to the Section Precision and Digital Agriculture)

► Show Figures

Figure 1

26 pages, 3742 KiB

Open AccessArticle

A Lightweight and High-Performance YOLOv5-Based Model for Tea Shoot Detection in Field Conditions

by Zhi Zhang, Yongzong Lu, Yun Peng, Mengying Yang and Yongguang Hu

Agronomy 2025, 15(5), 1122; https://doi.org/10.3390/agronomy15051122 - 30 Apr 2025

Abstract

Accurate detection of tea shoots in field conditions is a challenging task for production management and harvesting in tea plantations. Deep learning is well-suited for performing complex tasks due to its robust feature extraction capabilities. However, low-complexity models often suffer from poor detection [...] Read more.

Accurate detection of tea shoots in field conditions is a challenging task for production management and harvesting in tea plantations. Deep learning is well-suited for performing complex tasks due to its robust feature extraction capabilities. However, low-complexity models often suffer from poor detection performance, while high-complexity models are hindered by large size and high computational cost, making them unsuitable for deployment on resource-limited mobile devices. To address this issue, a lightweight and high-performance model was developed based on YOLOv5 for detecting tea shoots in field conditions. Initially, a dataset was constructed based on 1862 images of the tea canopy shoots acquired in field conditions, and the “one bud and one leaf” region in the images was labeled. Then, YOLOv5 was modified with a parallel-branch fusion downsampling block and a lightweight feature extraction block. The modified model was then further compressed using model pruning and knowledge distillation, which led to additional improvements in detection performance. Ultimately, the proposed lightweight and high-performance model for tea shoot detection achieved precision, recall, and average precision of 81.5%, 81.3%, and 87.8%, respectively, which were 0.4%, 0.6%, and 2.0% higher than the original YOLOv5. Additionally, the model size, number of parameters, and FLOPs were reduced to 8.9 MB, 4.2 M, and 15.8 G, representing decreases of 90.6%, 90.9%, and 85.3% compared to YOLOv5. Compared to other state-of-the-art detection models, the proposed model outperforms YOLOv3-SPP, YOLOv7, YOLOv8-X, and YOLOv9-E in detection performance while maintaining minimal dependency on computational and storage resources. The proposed model demonstrates the best performance in detecting tea shoots under field conditions, offering a key technology for intelligent tea production management. Full article

(This article belongs to the Collection Advances of Agricultural Robotics in Sustainable Agriculture 4.0)

12 pages, 2848 KiB

Open AccessArticle

Optimizing Hemp (Cannabis sativa L.) Residue Management: Influence on Soil Chemical Properties Across Different Application Technologies

by Urte Mecione, Modupe Olufemi Doyeni and Vita Tilvikiene

Agronomy 2025, 15(5), 1121; https://doi.org/10.3390/agronomy15051121 - 30 Apr 2025

Abstract

The use of crop residues is increasing across farming systems as part of climate change mitigation efforts and agricultural management practices to improve soil health. Hemp residues offer valuable potential in these efforts due to their rich nutrient composition. However, the complex chemical [...] Read more.

The use of crop residues is increasing across farming systems as part of climate change mitigation efforts and agricultural management practices to improve soil health. Hemp residues offer valuable potential in these efforts due to their rich nutrient composition. However, the complex chemical composition of hemp residue could pose a significant challenge by slowing the decomposition rate if not adequately managed. The aim of this study is to evaluate the influence of different timings of hemp residue incorporation, soil tillage practices, and mode of application on the rate of mineralization and soil chemical parameters. A complete randomized design field trial was conducted on hemp (Cannabis sativa L.) residue incorporation across different seasonal periods and modes of application. The results showed that the fastest mineralization occurred when hemp residue was incorporated in autumn, while the slowest mineralization was observed when the residue was left on the surface of the soil as mulch. The application of hemp residues over three years led to a slight increase in soil pH from an initial value of 4.9; however, this change was not statistically significant. Similarly, nitrogen content did not change significantly between the different periods after applying hemp residues. In contrast, hemp residues contributed to an increase in soil carbon content. Overall, this study emphasizes the need to optimize hemp residue management to maximize its benefits for enhancing soil chemical properties and promoting sustainable agriculture. Full article

(This article belongs to the Special Issue Soil Health and Properties in a Changing Environment)

► Show Figures

Figure 1

Journal Description

Agronomy

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI