BDFlower: Growth stage flower image dataset for precision agriculture and floriculture.

Fixed spray delivery system (FSDS), an alternative to conventional pesticide technologies, is gaining interest in grapevine. Indeed, especially in steep-sloped vineyards, optimal configured FSDS layout can enhance operator safety and potentially provide adequate spray performance. This study compared the spray performance of two modern 2-tier hydraulic-based FSDS layouts (L1 and L2), tailored to a vertical shoot positioning-trained vineyard. The investigation was conducted across three vine growth stages, with two canopy densities evaluated at each stage. Spray performance was assessed in terms of canopy deposits, in-field ground losses, and the impact of the plant protection product (PPP) wash-off effect caused by water used as propellant. Results were compared with field data obtained under comparable conditions using a conventional airblast sprayer. With respect to L1 layout, L2 layout achieved across the growth stages 1.75 and 1.55 times more canopy deposit and ground losses, respectively. Moreover, the L2 layout resulted in a more uniform canop y deposit within the sampled area resulting in a more promising HSD-FSDS configuration for grapevine spray applications. The PPP wash-off effect evaluation further supported this outcome but also identified areas for refinement to enhance spray performance. Based also on the comparison with the conventional airblast sprayer, recommendations for future protection plans are proposed, providing a step-forward toward large-scale adoption and implementation of HSD-FSDS technology. • Hydraulic-based fixed spray delivery system (HSD-FSDS) was evaluated in a vertical shoot positioning trained vineyard. • Two HSD-FSDS layouts were tested across three growth stages and two canopy densities. • Spray deposit in the canopy, in-field ground losses, and wash-off effects were assessed. • Layout configuration influenced spray uniformity and spray performance. • Design modifications and tailored agricultural practices may help optimize HSD-FSDS.

Prior research has demonstrated that the natural regeneration of Korean pine ( Pinus koraiensis ) in old-growth forests is quantitatively constrained by the composition of parent trees. To further explore the spatial relationships between regenerated and maternal Korean pine, we examined the spatial patterns of its regeneration across four ontogenetic stages (younger seedlings, older seedlings, smaller saplings, and taller saplings) in five old-growth mixed forest stands representing a gradient of Korean pine basal area proportion (33%-77%). Using spatial point pattern analysis with crown-projected coordinates, we quantified intra- and interspecific spatial associations. Results revealed that Korean pine natural regeneration is forest-type-specific, with the ribbed birch ( Betula costata )-Korean pine forest being the most conducive to regeneration. Distribution patterns indicated a density-dependent ontogenetic shift: regenerated individuals exhibited strong aggregation at the early stage, which shifted to a random-dominated distribution in later stages, a trend amplified in stands with higher proportions of Korean pine. Associations between younger seedlings and parent trees transitioned from fine-scale facilitation to broad-scale repulsion ( p < 0.05), but only where the Korean pine proportion was approximately 50%. Notably, most heterospecific associations were neutral, with facilitation being highly species- and context-specific. We conclude that high conspecific occupancy intensifies intraspecific competition, whereas neutral associations with broadleaved species suggest that niche partitioning governs coexistence. Conservation strategies should therefore focus on regulating parent tree density and maintaining stand diversity to ensure sustainable regeneration. Methodologically, we recommend that future point pattern analyses of large canopy trees, particularly those with severe crown asymmetry, using crown coordinates.

HIF-2α could be a key regulator of Fe homeostasis in the gut of yellow-feathered broilers.

Accurate aboveground biomass estimation with quantified uncertainty is essential for precision agriculture, enabling risk-aware decision-making and strategic model improvement. Existing approaches predominantly provide point estimates without uncertainty quantification, limiting their operational utility for trustworthy Artificial Intelligence (AI) deployment. This study presents a Multi-modal Attention-based Uncertainty Quantification Network (MA-UQNet), which achieves superior prediction accuracy (R 2 = 0.856) with well-calibrated uncertainty (97.18% coverage) for wheat aboveground biomass estimation through integrated multi-modal attention, growth stage-specific processing, and epistemic–aleatoric uncertainty decomposition. The framework integrates hyperspectral remote sensing with environmental variables via joint attention mechanisms that adapt to phenological variations. Model development employed a decade-spanning dataset (2012–2022, 1272 samples) collected under factorial combinations of nitrogen rates (0–270 kg/ha), irrigation levels (0–384 mm), and wheat cultivars across four growth stages. Temporal extrapolation validation using chronological partitioning (2012–2019 for training and 2020–2021 for testing) demonstrated robust generalization, substantially outperforming Random Forest (R 2 = 0.751, coverage = 76.61%) and nine representative baselines, including Bayesian Neural Networks (R 2 = 0.805, coverage = 38.31%). Uncertainty decomposition revealed epistemic uncertainty to be moderately dominant (53%) relative to aleatoric uncertainty (47%), indicating that strategic data collection offers greater potential for uncertainty reduction than improving measurement precision alone. These findings provide validated tools for uncertainty-aware biomass estimation in precision agriculture. • A multi-modal uncertainty quantification network is proposed for wheat biomass estimation. • Integrating hyperspectral and environmental data outperforms single-source approaches. • Epistemic uncertainty moderately dominates aleatoric uncertainty. • Well-calibrated uncertainty estimates enable reliable decision-making in precision agriculture.

Mechanisms of coexistence between Scomber australasicus and Scomber japonicus from the perspective of feeding ecology.

Polylactic acid microplastics regulate organophosphorus pesticide impacts on phosphorus bioavailability in soil-plant systems.

Demethylation and depolymerization of pectin polysaccharides during ripening of Goji berry:Pectin methylesterase and Pectin methylesterase inhibitors as the main regulators of fruit texture characteristics.

Pollination optimization in apple orchards faces increasing challenges from climate variability and declining pollinator populations, necessitating precision timing strategies. This study introduces a novel Pollination Importance Index (PII) integrated with a hybrid multi-task deep learning framework (PII-CNN-LSTM) to identify critical pollination windows. The PII dynamically quantifies pollination potential by incorporating flower receptivity, resource availability, biotic stress, and pollinator activity across five apple flower growth stages. The PII-CNN-LSTM architecture simultaneously performs growth stage classification and importance prediction through CNN spatial feature extraction and LSTM temporal modeling, enhanced by attention mechanisms and residual connections. Comparative evaluation against PII-CNN-BiLSTM, PII-CNN-GRU, and PII-CNN-TCN architectures demonstrated superior performance with 97% classification accuracy and minimal prediction error (validation loss: 0.0065, MAE: 0.0505). The model achieved exceptional full-bloom stage identification (99% F1-score), corresponding to its dominant 61.5% contribution to overall pollination importance. Cross-validation using 2024–2025 ground truth data and real-time drone deployment confirmed robust generalizability with temporal correlations exceeding 0.94. The framework successfully identified the critical pollination window from 3rd to 9th days, with optimal intervention timing at 5th to 7th days when importance scores exceeded 0.40. This biologically-grounded temporal precision enables targeted deployment of pollination resources during peak receptivity periods, reducing the need for continuous monitoring and intervention throughout the entire flowering season. The biologically-grounded approach provides scalable, data-driven decision support for precision agriculture, representing a significant advancement in agricultural automation and orchard productivity optimization. • Developed Pollination Importance Index (PII) integrating key pollination factors. • Identified optimal pollination window at days 5–7 with >0.94 temporal correlations. • PII-CNN-LSTM achieved 97% accuracy, outperforming BiLSTM, GRU, and TCN models. • Real-time drone deployment achieved 90% accuracy with YOLOv8s-PII-CNN-LSTM pipeline. • Six-channel fusion combining RGB imagery, PII score, image labels, and temporal sequences.

Amphiphilic xanthotoxin derivatives with phosphatidylglycerol-targeting membrane disruption for potent anti-methicillin-resistant Staphylococcus aureus (MRSA) activity.

Nutritional alternatives to commercial lipid sources: Impact of the dietary inclusion of black soldier fly (Hermetia illucens) larvae oil on broiler chicken productivity, breast meat quality traits and caeca microbiome.

Cross-domain microbial interactions mediate soil multifunctionality during crop growth stages

Precise reconstruction of plant phenotypes is crucial for smart agriculture. Conventional methods struggle with low efficiency and strong dependency on high-quality data, especially for low-texture and structurally complex crops like wheat. We propose a novel 3D reconstruction framework—Plant3R—that fuses deep feature learning with 3D Gaussian Splatting (3DGS). It innovatively uses the Matching and Stereo 3D Reconstruction (MASt3R) model for sparse point cloud reconstruction and camera pose estimation via its 3D feature matching capabilities, which substantially improve image matching rates and the quality of sparse point clouds. Subsequently, 3DGS is employed for rendering and optimization, enabling end-to-end, high-fidelity, and high-robust 3D reconstruction of wheat plants. Validated on potted wheat at multiple growth stages using handheld images, our experimental results demonstrate that Plant3R performs well in feature extraction and matching, and the reconstructed point cloud provides a good geometric prior for the subsequent rendering stage. In most scenes, its key rendering metrics—Peak Signal-to-Noise Ratio (PSNR) > 34, Structural Similarity Index Measure (SSIM) of 0.94, and Learned Perceptual Image Patch Similarity (LPIPS) < 0.26—surpassed Neural Radiance Fields (NeRF) and the original 3DGS. Moreover, extracted phenotypic traits such as plant height, leaf length, and width showed high correlation with manual measurements (R 2 > 0.94), confirming its utility for accurate and quantitative phenotype analysis. Overall, Plant3R not only improves the rendering quality and geometric precision of 3D modeling, but also provides a reliable tool for accurate phenotypic parameter extraction and high-throughput crop phenotyping in precision agriculture.

• Lima beans ( Phaseolus lunatus ) reduced tailings cyanide from ∼33 to 13.4 mg/kg. • Cyanide accumulated mainly in roots, suggesting root-zone attenuation. • First-order kinetics predicted remediation (R 2 = 0.921). • Safe cyanide levels achievable in ∼130 days at 10 plants/m 2 . Cyanide contamination from gold mine tailings poses significant ecological and human health risks, particularly in artisanal and small-scale mining regions of Uganda. This study evaluated the phytoremediation potential of lima beans ( Phaseolus lunatus) for cyanide-laden tailings obtained from Greenstone Mining Limited under field conditions. Experimental plots were established at planting densities of 0, 5, 10, and 15 plants/m 2 and monitored over an 84-day growth period. Soil and plant tissue cyanide concentrations were quantified using a titrimetric method. Cyanide attenuation increased with planting density, reaching 42.6 ± 1.8%, 54.7 ± 1.4%, and 59.1 ± 0.8% at 5, 10, and 15 plants/m 2 , respectively, compared to 3.4 ± 1.2% in the unplanted control. Cyanide removal was most pronounced during the vegetative growth stage, coinciding with increased root biomass development. Tissue analysis showed cyanide distribution in the order of roots > stems > leaves > seeds, suggesting that attenuation occurred predominantly within the root zone through combined plant uptake, in situ phytodegradation, and rhizosphere-mediated processes, with limited translocation to edible tissues. First-order kinetic modeling provided the best fit to the 10 plants/m 2 treatment (R 2 = 0.921). Based on this model, the estimated indicative remediation time to reach the Canadian soil quality guideline limit for cyanide of 8 mg/kg is approximately 130 days. These findings demonstrate that P. lunatus significantly enhances cyanide attenuation beyond natural background processes and highlight its potential as a low-cost, field-applicable phytoremediation strategy for cyanide-contaminated mine tailings in tropical environments.

Comparative RNA-seq profiling of hepatic transcriptomes in Kadaknath and commercial broiler chickens at distinct growth stages

Optimizing water and fertilizer management is crucial for improving cotton yield and quality. However, reliable and generalizable models for quickly and accurately estimating cotton canopy leaves water and nutritional status at a low cost throughout the entire growth stage are scarce. Therefore, this study aims to construct the generalization and adaptation retrieval model of cotton canopy leaf nitrogen content (LNC) and equivalent water thickness (EWT) based on PROSAIL, hyperspectral reconstruction with UAV multispectral imagery and module transfer learning. In the hyperspectral reconstruction module, the new hyperspectral reconstruction model (swinT-HSCNN) based on multispectral showing superior performance in reducing pixel-scale systematic errors and effectively captured spectral variations than HSCNN+ and MST++ model. In the PROSAIL module, the proposed Original-E2DCOS method demonstrated greater sensitivity to spectral response characteristics, especially for parameters and bands with low correlation values, and three bands (702 nm, 762 nm, and 938 nm) were selected as the sensitive bands corresponding to chlorophyll content (Cab) and equivalent water thickness (Cw) of cotton. The improved PROSAIL with hyperparameter optimization based on full spectrum and multispectral band shown better fitting performance than the model based on sensitive bands, and achieved high accuracy on simulated data, with R 2 values exceeding 0.98 for both Cab and Cw. Moreover, the new developed modular transfer learning retrieval model of cotton canopy water and nitrogen content through PROSAIL model and hyperspectral reconstruction with UAV multispectral imagery achieved good inversion accuracy with R 2 of 0.83, 0.85, RMSE of 0.0048, 0.0052, for LNC and EWT, respectively after verifying with actual experiment data. In summary, the proposed modular transfer learning retrieval model of cotton canopy water and nitrogen content integrates physical constraints into retrieval models, which enhancing their accuracy and generalization capability, and providing valuable technical support for precision agriculture in cotton production across different regions. • A modular transfer learning model integrates PROSAIL and hyperspectral reconstruction. • Achieves high accuracy for LNC and EWT estimation across diverse environments. • Combines UAV multispectral data with physical constraints for crop monitoring. • Reduces reliance on expensive hyperspectral sensors, ensuring cost-effectiveness. • Validated on multi-regional datasets, demonstrating scalability and generalizability.

Weeds are a major problem in wheat crop causing low productivity. Nowadays, maximum doses of herbicides are used in wheat crop production, but after some time their negative effects are visible on crop and soil. The presence of 'sorgoleone' allelochemical in sorghum extract reduces weed density in early growth stage and increases the quality as well as soil microbial activity. Sequential application of sorghum extract (1:3) + ready-mix of clodinafop + metsulfuron 64g/ha as post emergence, significantly increased the microbial population in soil, and enhanced quality and production of wheat. Same treatment produced significantly higher grain yield of 4543kg/ha and magnitude of increments were 34.87% over weedy check and it was found statistically similar with sorghum extract (1:2) + ready-mix of clodinafop + metsulfuron 64g/ha. However, both the treatments showed significant superiority over all other treatments. Maximum soil bacterial and fungal populations were obtained under lower concentration of sorghum extract (1:3) at 60 DAS and at harvest stages of crop, respectively, which measured in terms of magnitude improvements as compared to the population recorded before spraying.

Desmostylus is an extinct genus of large, quadrupedal, herbivorous marine mammals from the Oligocene to Miocene strata of the North Pacific. Despite abundant fossil discoveries, the taxonomic, ontogenetic, and ecological aspects of this genus remain insufficiently understood. In this study, we reexamined a previously misidentified specimen (NMNS-PV 44111) from the Miocene Chikubetsu Formation in Hokkaido, Japan. Archival records rediscovered in 2024 enabled precise documentation of the locality and its stratigraphic context. Comparative anatomical analysis of the humerus revealed that the specimen represented a juvenile Desmostylus, with a body size larger than that of early desmostylians but smaller than that of fully mature Desmostylus individuals. The growth stage suggests a rapid increase in body size during the early ontogenetic phases. Stratigraphic and paleontological evidence places the specimen within the Middle Miocene Climatic Optimum (MMCO), a period linked to marine transgression and warm conditions that may have facilitated a northward range expansion of this genus. Our findings underscore the importance of reassessing legacy specimens using updated stratigraphic and comparative frameworks to better understand the evolutionary history of marine mammals in the North Pacific.

ABSTRACT Sauropod dinosaurs are one of the most common components of the Cretaceous continental fauna of South America. However, juvenile specimens are poorly documented to date. Here, we describe an incomplete juvenile titanosaur from the Upper Cretaceous of Argentina. The preserved material belongs to a single individual and is sufficiently diagnostic to classify it as a juvenile Neuquensaurus australis. The specimen represents an individual approximately 44–63% of adult individual size. Anatomical comparison with adult specimens reveals that fusion between different structures (neural arches and their centra, scapula and coracoid, and sacral centra) started late during the ontogeny (at least in ontogenetic stages more advanced than inferred for the juvenile individual here studied). Invasion of pneumatic diverticula within the bones also appears to be developed in a more advanced ontogenetic stage. Overlapping elements between the juvenile and adult skeletons indicate allometric changes for Neuquensaurus australis throughout ontogeny, which contrast with previous hypotheses about isometric growth in titanosaurs. Histological data reveals a rapid growth rate in the juvenile individual. However, the presence of at least one cyclical growth mark in the cortex challenges previous hypotheses regarding growth dynamics in sauropod dinosaurs, which postulate that interrupted growth only occurred at advanced ontogenetic stages.

Accurate rapeseed yield and biomass estimation at the meter scale prior to harvest is crucial for precision harvesting. However, there is a scarcity of structured research on the estimation of rapeseed biomass yield. This study aims to address this gap by focusing on rapeseed in Jiangsu Province. Multispectral and RGB images captured by unmanned aerial vehicles (UAVs) were taken during key growth stages (budding, flowering, and podding stages). Using the extracted multidimensional features, we developed biomass-yield estimation models using four machine learning techniques. Subsequently, we employed ensemble learning with multidimensional, multi-stage data and used Shapley additive explanation (SHAP) for feature contribution analysis, thereby constructing a framework for predicting rapeseed harvest characteristics with high estimation accuracy and interpretability. Our analysis indicates that spectral‒texture is the most effective feature combination for biomass estimation, whereas the optimal combination for yield estimation includes three-dimensional (3D) spectral‒textural‒structural features. The synergy of these features, coupled with an ensemble learning model, significantly enhanced the accuracy of rapeseed biomass-yield estimation (biomass: coefficient of determination (R2)=0.72, relative root mean square error (rRMSE)=14.35%; yield: R2=0.68, rRMSE=13.67%). The proposed model also achieved stable prediction results across the variety‒density interaction. Overall, this study presents an accurate and generalizable approach for estimating rapeseed biomass yield across various planting patterns, offering new insights for precision harvesting.