Search Results (66)

Accurate and timely estimation of soybean emergence at the plot scale using unmanned aerial vehicle (UAV) remote sensing imagery is essential for germplasm evaluation in breeding programs, where breeders prioritize overall plot-scale emergence rates over subimage-based counts. This study proposes PlotCounter, a deep learning regression model based on the TasselNetV2++ architecture, designed for plot-scale soybean seedling counting. It employs a patch-based training strategy combined with full-plot validation to achieve reliable performance with limited breeding plot data. To incorporate additional agronomic information, PlotCounter is extended into a multitask learning framework (MTL-PlotCounter) that integrates sowing metadata such as variety, number of seeds per hole, and sowing density as auxiliary classification tasks. RGB images of 54 breeding plots were captured in 2023 using a DJI Mavic 2 Pro UAV and processed into an orthomosaic for model development and evaluation, showing effective performance. PlotCounter achieves a root mean square error (RMSE) of 6.98 and a relative RMSE (rRMSE) of 6.93%. The variety-integrated MTL-PlotCounter, V-MTL-PlotCounter, performs the best, with relative reductions of 8.74% in RMSE and 3.03% in rRMSE compared to PlotCounter, and outperforms representative YOLO-based models. Additionally, both PlotCounter and V-MTL-PlotCounter are deployed on a web-based platform, enabling users to upload images via an interactive interface, automatically count seedlings, and analyze plot-scale emergence, powered by a multimodal large language model. This study highlights the potential of integrating UAV remote sensing, agronomic metadata, specialized deep learning models, and multimodal large language models for advanced crop monitoring. Full article

Due to the limitations of the sowing machine performance and rice seed germination rates, missing seedlings inevitably occur after rice is sown in large fields. This phenomenon has a direct impact on the rice yield. In the field environment, the existing methods for detecting missing seedlings based on unmanned aerial vehicle (UAV) remote sensing images often have unsatisfactory effects. Therefore, to enable the fast and accurate detection of missing rice seedlings and facilitate subsequent reseeding, this study proposes a UAV remote-sensing-based method for detecting missing rice seedlings in large fields. The proposed method uses an improved PCERT-DETR model to detect rice seedlings and missing seedlings in UAV remote sensing images of large fields. The experimental results show that PCERT-DETR achieves an optimal performance on the self-constructed dataset, with an mean average precision (mAP) of 81.2%, precision (P) of 82.8%, recall (R) of 78.3%, and F₁-score (F₁) of 80.5%. The model’s parameter count is only 21.4 M and its FLOPs reach 66.6 G, meeting real-time detection requirements. Compared to the baseline network models, PCERT-DETR improves the P, R, F₁, and mAP by 15.0, 1.2, 8.5, and 6.8 percentage points, respectively. Furthermore, the performance evaluation experiments were carried out through ablation experiments, comparative detection model experiments and heat map visualization analysis, indicating that the model has a strong detection performance on the test set. The results confirm that the proposed model can accurately detect the number of missing rice seedlings. This study provides accurate information on the number of missing seedlings for subsequent reseeding operations, thus contributing to the improvement of precision farming practices. Full article

This research explores, using discrete element method (DEM) simulations, the behavior of rice seed infiltration into soil when it is deployed via unmanned aerial vehicle (UAV)-mounted systems. Five distinct sowing strategies were analyzed to evaluate their effectiveness in embedding seeds within paddy soil: gravitational drop, centrifugal spreading, airflow propulsion, pneumatic discharge, and pneumatic shooting. A two-step analysis was performed. Initially, the flight dynamics of rice seeds were modeled, and the influence of air and water drag forces were accounted for. Subsequently, soil penetration was simulated with DEM based on the material properties and contact parameters sourced from the existing literature. The results show that the pneumatic methods effectively penetrated the soil, with pneumatic shooting proving to be the most efficient due to its superior impact momentum. Conversely, the methods that failed to penetrate left seeds on the soil surface. These findings demonstrate the necessity to enhance UAV sowing technology to improve penetration depth while maintaining operational efficiency, and they also offer crucial insights for the progress of UAV applications in agriculture. Full article

Uniform spatial distribution of plants is crucial in arable crops. Seeding quality is affected by numerous parameters, including the working speed and vibrations of the seeder. Therefore, investigating effective and rapid methods to evaluate seeding quality and the parameters affecting the seeders’ performance is of high importance. With the latest advancements in unmanned aerial vehicle (UAV) technology, the potential for acquiring accurate agricultural data has significantly increased, making UAVs an ideal tool for scouting applications in agricultural systems. This study investigates the effectiveness of utilizing different plant recognition algorithms applied to UAV-derived images for evaluating seeder performance based on detected plant spacings. Additionally, it examines the impact of seeding unit vibrations on seeding quality by analyzing accelerometer data installed on the seeder. For the image analysis, three plant recognition approaches were tested: an unsupervised segmentation method based on the Visible Atmospherically Resistant Index (VARI), template matching (TM), and a deep learning model called Mask R-CNN. The Mask R-CNN model demonstrated the highest recognition reliability at 96.7%, excelling in detecting seeding errors such as misses and doubles, as well as in evaluating the quality of feed index and precision when compared to ground-truth data. Although the VARI-based unsupervised method and TM outperformed Mask R-CNN in recognizing double spacings, overall, the Mask R-CNN was the most promising. Vibration analysis indicated that the seeder’s working speed significantly affected seeding quality. These findings suggest areas for potential improvements in machine technology to improve sowing operations. Full article

Tarwi (Lupinus mutabilis Sweet) is a key crop for Andean indigenous communities, offering proteins and fats. Both the pods and seeds of tarwi are consumed, either in their tender (immature) state or as dried, fully ripe seeds. Tarwi, like other Lupinus species, contains high alkaloid levels in its fruits and seeds that must be removed before consumption. This study evaluated the fat, protein, fibre, and alkaloid contents of four cultivars at five maturity stages ranging from 180 to 212 days after sowing. Samples of the pods and the seeds were analysed to determine their colour and protein, crude fibre, fat, and alkaloid contents. The results showed that while the protein concentration in the pods decreased as the fruits matured, the protein content in the seeds increased, reaching approximately 41%. Moreover, the pods exhibited a significant decrease in alcohol content, with the values dropping below 1% at the senescent (dry) stage for all the cultivars. In contrast, the alkaloid levels in the seeds remained stable from 196 days after sowing in the Guaranguito, Andean, and Ecuadorian cultivars, with concentrations around 4%. The present study showed that as the pods matured, their overall protein content decreased, while their seed protein content increased to around 41%. The alkaloid levels in the pods dropped below 1% in the dry stage, while the seed alkaloid levels remained stable at around 4% in the Guaranguito, Andean, and Ecuadorian cultivars after 196 days. However, in the Peruvian cultivar, the alkaloid content remained constant starting from 188 days after sowing, with concentrations just over 3%. This result suggests that as the pods mature, their alkaloid content decreases, while the alkaloid levels in the seeds stabilise from around 188 to 196 days after seeding. Consequently, the alkaloid contents found in the seeds likely originate from other aerial parts of the plant and are not significantly increased by the pods. Full article

The Hunshandake Sandy Land is one of the largest sandy areas in China and the closest source of sand dust to the Beijing and Tianjing areas. Sand fixation by vegetation is considered the most efficient strategy for sand control and sustainable development, so clarifying the vegetation coverage and plant adaptation characteristics in the Hunshandake Sandy Land is helpful in guiding restoration and improving local sustainability. Here, we investigated the vegetation growth on the mobile sand dunes in the Hunshandake Sandy Land and specified the photosynthesis and stomatal characteristics of the pioneer plants for sand fixation. The vegetation survey showed that the windward slopes of the mobile sand dunes had far lower plant coverage (6.3%) and plant biodiversity (two species m⁻²) than the leeward ones (41.0% and eight species m⁻², respectively). Elymus sibiricus L. and Agriophyllum squarrosum (L.) Moq. were the only two sand-fixing pioneer plants that grew on both the windward and leeward slopes of the mobile sand dunes and had higher plant heights, greater abundance, and more biomass than other plants. Physiological measurements revealed that Elymus sibiricus L. and Agriophyllum squarrosum (L.) Moq. also had higher photosynthetic rates, transpiration rates, and water use efficiency. In addition, the stomata density (151–197 number mm⁻²), length (18–29 μm), and area index (13–19%) of these two pioneer species were smaller than those of the common grassland species in Inner Mongolia, suggesting that they were better adapted to the dry habitat of the mobile sand dunes. These findings not only help in understanding the adaptive strategies of pioneer plants on mobile sand dunes, but also provide practical guidance for sand dune restoration and the sustainable development of local areas. Pioneer sand-fixing plant species that are well adapted to sand dunes can be used for sowing or aerial seeding in sand fixation during ecosystem restoration. Full article

In order to accurately obtain the seedling emergence rate of breeding sunflower and to assess the quality of sowing as well as the merit of sunflower varieties, a method of extracting the sunflower seedling emergence rate using multi-source remote sensing information from unmanned aerial vehicles is proposed. Visible and multispectral images of sunflower seedlings were acquired using a UAV. The thresholding method was used to segment the excess green image of the visible image into vegetation and non-vegetation, to obtain the center point of the vegetation to generate a buffer, and to mask the visible image to achieve weed removal. The components of color models such as the hue–saturation value (HSV), green-relative color space (YCbCr), cyan-magenta-yellow-black (CMYK), and CIELAB color space (L*A*B) models were compared and analyzed. The A component of the L*A*B model was preferred for the optimization of K-means clustering to segment sunflower seedlings and mulch using the genetic algorithm, and the segmentation accuracy was improved by 4.6% compared with the K-means clustering algorithm. All told, 10 geometric features of sunflower seedlings were extracted using segmented images, and 10 vegetation indices and 48 texture features of sunflower seedlings were calculated based on multispectral images. The Pearson’s correlation coefficient method was used to filter the three types of features, and the geometric feature set, the vegetation index set, the texture feature set, and the preferred feature set were constructed. The construction of a sunflower plant number estimation model using the crested porcupine optimizer–support vector machine is proposed and compared with the sunflower plant number estimation models constructed based on decision tree regression, BP neural network, and support vector machine regression. The results show that the accuracy of the model based on the preferred feature set is higher than that of the other three feature sets, indicating that feature screening can improve the accuracy and stability of models; assessed using the CPO-SVR model, the accuracy of the preferred feature set was the highest, with an R² of 0.94, an RMSE of 5.16, and an MAE of 3.03. Compared to the SVR model, the value of the R² is improved by 3.3%, the RMSE decreased by 18.3%, and the MAE decreased by 18.1%. The results of the study can be cost-effective, accurate, and reliable in terms of obtaining the seedling emergence rate of sunflower field breeding. Full article

Rice is cataloged as one of the most widely cultivated crops globally, providing food for a large proportion of the global population. Integrating Geographic Information Systems (GISs), such as unmanned aerial vehicles (UAVs), into agricultural practices offers numerous benefits. UAVs, equipped with imaging sensors and geolocation technology, enable precise crop monitoring and management, enhancing yield and efficiency. However, Peru lacks sufficient experience with the application of these technologies, making them somewhat unfamiliar in the context of modern agriculture. In this study, we conducted experiments involving four distinct rice varieties (n = 24) at various stages of growth to predict yield using vegetation indices (VIs). A total of nine VIs (NDVI, GNDVI, ReCL, CIgreen, MCARI, SAVI, CVI, LCI, and EVI) were assessed across four dates: 88, 103, 116, and 130 days after sowing (DAS). Pearson correlation analysis, principal component analysis (PCA), and multiple linear regression were used to build prediction models. The results showed a general prediction model (including all the varieties) with the best performance at 130 days after sowing (DAS) using NDVI, EVI, and SAVI, with a coefficient of determination (adjusted-R² = 0.43). The prediction models by variety showed the best performance for Esperanza at 88 DAS (adjusted-R² = 0.94) using EVI as the vegetation index. The other varieties showed their best performance using different indices at different times: Capirona (LCI and CIgreen, 130 DAS, adjusted-R² = 0.62); Conquista Certificada (MCARI, 116 DAS, R² = 0.52); and Conquista Registrada (CVI and LCI, 116 DAS, adjusted-R² = 0.79). These results provide critical information for optimizing rice crop management and support the use of unmanned aerial vehicles (UAVs) to inform timely decision making and mitigate yield losses in Peruvian agriculture. Full article

Net photosynthetic rate (Pn) is a common indicator used to measure the efficiency of photosynthesis and growth conditions of plants. In this study, soybeans under different moisture gradients were selected as the research objects. Fourteen vegetation indices (VIS) and five canopy structure characteristics (CSC) (plant height (PH), volume (V), canopy cover (CC), canopy length (L), and canopy width (W)) were obtained using an unmanned aerial vehicle (UAV) equipped with three different sensors (visible, multispectral, and LiDAR) at five growth stages of soybeans. Soybean Pn was simultaneously measured manually in the field. The variability of soybean Pn under different conditions and the trend change of CSC under different moisture gradients were analysed. VIS, CSC, and their combinations were used as input features, and four machine learning algorithms (multiple linear regression, random forest, Extreme gradient-boosting tree regression, and ridge regression) were used to perform soybean Pn inversion. The results showed that, compared with the inversion model using VIS or CSC as features alone, the inversion model using the combination of VIS and CSC features showed a significant improvement in the inversion accuracy at all five stages. The highest accuracy (R² = 0.86, RMSE = 1.73 µmol m⁻² s⁻¹, RPD = 2.63) was achieved 63 days after sowing (DAS63). Full article

Drought stress is a significant factor affecting soybean growth and yield. A lack of suitable high-throughput phenotyping techniques hinders the drought tolerance evaluation of multi-genotype samples. A method for evaluating drought tolerance in soybeans is proposed based on multimodal remote sensing data from an unmanned aerial vehicle (UAV) and machine learning. Hundreds of soybean genotypes were repeatedly planted under well water (WW) and drought stress (DS) in different years and locations (Jiyang and Yazhou, Sanya, China), and UAV multimodal data were obtained in multiple fertility stages. Notably, data from Yazhou were repeatedly obtained during five significant fertility stages, which were selected based on days after sowing. The geometric mean productivity (GMP) index was selected to evaluate the drought tolerance of soybeans. Compared with the results of manual measurement after harvesting, support vector regression (SVR) provided better results (N = 356, R² = 0.75, RMSE = 29.84 g/m²). The model was also migrated to the Jiyang dataset (N = 427, R² = 0.68, RMSE = 15.36 g/m²). Soybean varieties were categorized into five Drought Injury Scores (DISs) based on the manually measured GMP. Compared with the results of the manual DIS, the accuracy of the predicted DIS gradually increased with the soybean growth period, reaching a maximum of 77.12% at maturity. This study proposes a UAV-based method for the rapid high-throughput evaluation of drought tolerance in multi-genotype soybean at multiple fertility stages, which provides a new method for the early judgment of drought tolerance in individual varieties, improving the efficiency of soybean breeding, and has the potential to be extended to other crops. Full article

Charcoal rot disease (CRD), caused by the phytopathogenic fungus Macrophomina phaseolina, is a significant threat to cotton production in Israel and worldwide. The pathogen secretes toxins and degrading enzymes that disrupt the water and nutrient uptake, leading to death at the late stages of growth. While many control strategies were tested over the years to reduce CRD impact, reaching that goal remains a significant challenge. The current study aimed to establish, improve, and deepen our understanding of a new approach combining biological agents and chemical pesticides. Such intervention relies on reducing fungicides while providing stability and a head start to eco-friendly bio-protective Trichoderma species. The research design included sprouts in a growth room and commercial field plants receiving the same treatments. Under a controlled environment, comparing the bio-based coating treatments with their corresponding chemical coating partners resulted in similar outcomes in most measures. At 52 days, these practices gained up to 38% and 45% higher root and shoot weight and up to 78% decreased pathogen root infection (tracked by Real-Time PCR), compared to non-infected control plants. Yet, in the shoot weight assessment (day 29 post-sowing), the treatment with only biological seed coating outperformed (p < 0.05) all other biological-based treatments and all Azoxystrobin-based irrigation treatments. In contrast, adverse effects are observed in the chemical seed coating group, particularly in above ground plant parts, which are attributable to the addition of Azoxystrobin irrigation. In the field, the biological treatments had the same impact as the chemical intervention, increasing the cotton plants’ yield (up to 17%), improving the health (up to 27%) and reducing M. phaseolina DNA in the roots (up to 37%). When considering all treatments within each approach, a significant benefit to plant health was observed with the bio-chemo integrated management compared to using only chemical interventions. Specific integrated treatments have shown potential in reducing CRD symptoms, such as applying bio-coating and sprinkling Azoxystrobin during sowing. Aerial remote sensing based on high-resolution visible-channel (RGB), green–red vegetation index (GRVI), and thermal imaging supported the above findings and proved its value for studying CRD control management. This research validates the combined biological and chemical intervention potential to shield cotton crops from CRD. Full article

Soil moisture content is one of the most important soil indices for agriculture production. With the increasing food requirement and limited irrigation water sources, it is of great significance to accurately and quickly measure the soil moisture content for precision irrigation, especially in deficient agricultural areas, such as North China Plain. To achieve this goal, more attention was paid to the application of unmanned aerial vehicle multispectral reflectance technology. However, it was urgent to enhance the regression models between spectral data and soil realistic moisture content, and there were limited studies about the regression research on deep soil layers. Thus, the farmland of winter wheat–summer maize double cropping at Yongnian District, Hebei, North China, was selected as the study area. A six-band multispectral camera mounted on a low-altitude unmanned aerial vehicle (UAV) was used to obtain the field spectral reflectance with bands from 470~810 nm, and meanwhile, soil moisture content at different depths (10, 20, 30, 40, 50, and 60 cm) was measured after maize sowing. Unary linear regression (ULR), multivariate linear regression (MLR), ridge regression (RR), and an artificial neural network (ANN) were employed to establish regression models. The results demonstrated that the sensitive bands of spectral reflectance were 690 nm, 470 nm, and 810 nm. Those models all established significant regression at the depths of 0–20 cm and 40–60 cm, particularly at 10, 50, and 60 cm soil layers. However, for a depth of 20–40 cm, the prediction accuracy was generally lower. Among MLR, RR, and BP models, the MLR exhibited the highest identification accuracy, which was most recommended for the application. The findings of this study provide technical guidance and effective regression for the multispectral reflectance on the farmland of North China Plain, especially for deep soil layer moisture prediction. Full article

White lupine (Lupinus albus L.) is a well-known green manure crop in Hungary, but the production of seeds can be badly impacted by weeds. The sweet white lupine ‘Nelly’ was grown on acidic sandy soil, and experimental plots were treated with different herbicides. Flumioxazin (0.06 kg ha⁻¹), pendimethalin (5 L ha⁻¹), dimethenamid-P (1.4 L ha⁻¹), pethoxamid (2 L ha⁻¹), clomazone (0.2 L ha⁻¹), metobromuron (3 L ha⁻¹), and metribuzin (0.55 L ha⁻¹) were applied pre-emergence (1–2 days after sowing). Imazamox was also tested and applied post-emergence (1 L ha⁻¹) when some basal leaves were clearly distinct (BBCH 2.3). In this paper, the weed control efficiency and the phytotoxicity of herbicides applied to lupine are examined. Vegetation index datasets were collected 12 times using a manual device and 2 times using an unmanned aerial vehicle (UAV). The phytotoxicity caused by herbicides was visually assessed on several occasions throughout the breeding season. The frequency of weed occurrence per treatment was assessed. The harvested seed yields, in kg ha⁻¹, were analyzed after the seeds were cleaned. The herbicides metribuzin and imazamox caused extensive damage to white lupine. While pendimethalin, dimethenamid-P, pethoxamid, and clomazone were outstanding in several measured indicators, the final ranking which summarizes all the variables showed that only the pethoxamid and clomazone treatments performed better than the control. Metribuzin and imazamox were highly phytotoxic to white lupine. In the future, it would be appropriate to integrate more post-emergence active substances into trials, and the pre-emergence herbicides involved in this study should be further tested. Full article

The adoption of artificial intelligence tools can improve production efficiency in the agroindustry. Our objective was to perform the predictive modeling of carrot yield and quality. The crop was grown in two commercial areas during the summer season in Brazil. The root samples were taken at 200 points with a 30 × 30 m sampling grid at 82 and 116 days after sowing in both areas. The total fresh biomass, aerial part, and root biometry were quantified for previous crop harvesting to measure yield. The quality of the roots was assessed by sub-sampling three carrots by the concentration of total soluble solids (°Brix) and firmness in the laboratory. Vegetation indices were extracted from satellite imagery. The most important variables for the predictive models were selected by principal component analysis and submitted to the Artificial Neural Network (ANN), Random Forest (RF), and Multiple Linear Regression (MLR) algorithms. SAVI and NDVI indices stood out as predictors of crop yield, and the results from the ANN (R² = 0.68) were superior to the RF (R² = 0.67) and MLR (R² = 0.61) models. Carrot quality cannot be modeled by the predictive models in this study; however, it should be explored in future research, including other crop variables. Full article

The production of seedlings is one of the main activities for implementing agricultural crops. Many factors are involved in producing quality seedlings, including nutrition, health, genetics, and climatic factors such as temperature, humidity, and light. To evaluate the effect of light supplementation, a study was conducted using supplementary artificial light to produce lettuce and cauliflower seedlings. Sowing was carried out in styrofoam trays under a floating irrigation system. Part of the experiment containing the two species, received treatment with LED light for an additional 4 h per day, in addition to solar radiation (10 h∙day⁻¹). The remaining seedlings received only solar radiation (without supplementation). After 37 days, the seedlings’ biometric (leaf area, root length, aerial dry mass, and root dry mass) and biochemical parameters (phenolic compounds, flavonoids, chlorophyll a/b, and total chlorophyll) were analyzed. The data showed that the complementary light enhanced the performance in all the biometric parameters evaluated in the experiment for lettuce and cauliflower. The biochemical parameters in lettuce were also higher in seedlings with light supplementation. For cauliflower, supplementary light did not differ from the natural photoperiod for biochemical parameters except for a reduction in the levels of total phenolic compounds. Considering the enhanced biometric and biochemical parameters and greater dry weight and leaf area of the seedlings grown with supplemental light, using such a tool can optimize seedling development, possibly reducing production time in the nursery and providing greater productivity. Full article