Search Results (751)

Alfalfa (Medicago sativa) persists for several years but must be rotated to another crop before replanting. Kura clover (T. ambiguum M. Bieb) is a perennial legume that can persist indefinitely without replanting; however, establishment is slow, which limits economic returns during the process. Two studies, each with four randomized complete blocks, were planted in two consecutive years at New Mexico State University’s Rex E. Kirksey Agricultural Science Center at Tucumcari, NM, USA, as the first known assessment evaluating alfalfa as an economic nurse crop during kura clover establishment using various kura clover–alfalfa drilled and broadcast planting arrangements. Irrigation termination due to drought limited yield measurements to three years after seeding. In that time, kura clover–alfalfa mixtures generally yielded equally to monoculture alfalfa, except for alternate row planting. After 5 years, the alfalfa stand percentage remained >80%, except for the alternate row treatment (69% stand). Kura clover monocultures attained about 40% stand, and the mixtures had a <25% stand. Alfalfa may persist for more than 5 years before relinquishing dominance to kura clover in mixtures, but the alfalfa would continue to provide economic returns as kura clover continues stand development with minimal production, but develops its root system to maximize production when released from the alfalfa nurse crop. Full article

Soybean (Glycine max [L.] Merr.) cultivation is expanding in Central Europe due to the development of early-maturing cultivars and growing demand for plant-based protein produced without the use of genetically modified organisms. However, nitrogen (N) management remains a major challenge in temperate climates, where variable weather conditions can significantly affect nodulation and yield. This study evaluated the effects of three nitrogen fertilisation doses (0, 30, and 60 kg N·ha⁻¹), applied in the form of ammonium nitrate (34% N) and two commercial rhizobial inoculants—HiStick Soy (containing Bradyrhizobium japonicum strain 532C) and Nitragina (including a Polish strain of B. japonicum)—on nodulation, nitrogen uptake, and seed yield. A three-year field experiment (2017–2019) was conducted in southwestern Poland using a two-factor randomized complete block design. Nodulation varied significantly across years, with the highest values recorded under favourable early-season moisture and reduced during drought. In the first year, inoculation with HiStick Soy significantly increased nodule number and seed yield compared to Nitragina and the uninoculated control. Nitrogen fertilisation consistently improved seed yield, although it had no significant effect on nodulation. The highest nitrogen use efficiency was observed with moderate nitrogen input (30 kg N·ha⁻¹) combined with inoculation. These findings highlight the importance of integrating effective rhizobial inoculants with optimized nitrogen fertilisation to improve soybean productivity and nitrogen efficiency under variable temperate climate conditions. Full article

Compiler optimization is a critical component for improving program performance. However, the Rustc optimization process may introduce vulnerabilities due to algorithmic flaws or issues arising from component interactions. Existing testing methods face several challenges, including high randomness in test cases, inadequate targeting of vulnerability-prone regions, and low-quality initial fuzzing seeds. This paper proposes a test case generation method based on large language models (LLMs), which utilizes prompt templates and optimization algorithms to generate a code relevant to specific optimization passes, especially for real-time control logic and safety-critical modules unique to the industrial control field. A vulnerability screening approach based on static analysis and rule matching is designed to locate potential risk points in the optimization regions of both the MIR and LLVM IR layers, as well as in unsafe code sections. Furthermore, the targeted fuzzing strategy is enhanced by designing seed queues and selection algorithms that consider the correlation between optimization areas. The implemented system, RustOptFuzz, has been evaluated on both custom datasets and real-world programs. Compared with state-of-the-art tools, RustOptFuzz improves vulnerability discovery capabilities by 16%–50% and significantly reduces vulnerability reproduction time, thereby enhancing the overall efficiency of detecting optimization-related vulnerabilities in Rustc, providing key technical support for the reliability of industrial control systems. Full article

Functional flours, high in bioactive compounds, have garnered increasing attention, driven by consumer demand for alternative ingredients and the nutritional limitations of wheat flour. This study explores the thermal stability of phenolic compounds in various functional flours using visible, near and shortwave-infrared (Vis–NIR–SWIR) spectroscopy (350–2500 nm), integrated with machine learning (ML) algorithms. Random Forest models were employed to classify samples based on flour type, baking temperature, and phenolic concentration. The full spectral range yielded high classification accuracy (0.98, 0.98, and 0.99, respectively), and an explainability framework revealed the wavelengths most relevant for each class. To address concerns regarding color as a confounding factor, a targeted spectral refinement was implemented by sequentially excluding the visible region. Models trained on the 1000–2500 nm and 1400–2500 nm ranges showed minor reductions in accuracy, suggesting that classification is not solely driven by visible characteristics. Results indicated that legume and wheat flours retain higher total phenolic content (TPC) under mild thermal conditions, whereas grape seed flour (GSF) and olive stone flour (OSF) exhibited notable thermal stability of TPC even at elevated temperatures. These first findings suggest that the proposed non-destructive spectroscopic approach enables rapid classification and quality assessment of functional flours, supporting future applications in precision food formulation and quality control. Full article

Fall detection is a critical task in healthcare monitoring systems, especially for elderly populations, for whom timely intervention can significantly reduce morbidity and mortality. This study proposes a privacy-preserving and scalable fall-detection framework that integrates federated learning (FL) with transfer learning (TL) to train deep learning models across decentralized data sources without compromising user privacy. The pipeline begins with data acquisition, in which annotated video-based fall-detection datasets formatted in YOLO are used to extract image crops of human subjects. These images are then preprocessed, resized, normalized, and relabeled into binary classes (fall vs. non-fall). A stratified 80/10/10 split ensures balanced training, validation, and testing. To simulate real-world federated environments, the training data is partitioned across multiple clients, each performing local training using pretrained CNN models including MobileNetV2, VGG16, EfficientNetB0, and ResNet50. Two FL topologies are implemented: a centralized server-coordinated scheme and a ring-based decentralized topology. During each round, only model weights are shared, and federated averaging (FedAvg) is applied for global aggregation. The models were trained using three random seeds to ensure result robustness and stability across varying data partitions. Among all configurations, decentralized MobileNetV2 achieved the best results, with a mean test accuracy of 0.9927, F1-score of 0.9917, and average training time of 111.17 s per round. These findings highlight the model’s strong generalization, low computational burden, and suitability for edge deployment. Future work will extend evaluation to external datasets and address issues such as client drift and adversarial robustness in federated environments. Full article

Nested named entity recognition (NER) is a task that identifies hierarchically structured entities, where one entity can contain other entities within its span. This study introduces a nested NER model for few-shot learning environments, addressing the difficulty of building extensive datasets for general named entities. We enhance the Biaffine nested NER model by modifying its output layer to incorporate label semantic information through a novel label description embedding (LDE) approach, improving performance with limited training data. Our method replaces the traditional biaffine classifier with a label attention mechanism that leverages comprehensive natural language descriptions of entity types, encoded using BERT to capture rich semantic relationships between labels and input spans. We conducted comprehensive experiments on four benchmark datasets: GENIA (nested NER), ACE 2004 (nested NER), ACE 2005 (nested NER), and CoNLL 2003 English (flat NER). Performance was evaluated across multiple few-shot scenarios (1-shot, 5-shot, 10-shot, and 20-shot) using F1-measure as the primary metric, with five different random seeds to ensure robust evaluation. We compared our approach against strong baselines including BERT-LSTM-CRF with nested tags, the original Biaffine model, and recent few-shot NER methods (FewNER, FIT, LPNER, SpanNER). Results demonstrate significant improvements across all few-shot scenarios. On GENIA, our LDE model achieves 45.07% F1 in five-shot learning compared to 30.74% for the baseline Biaffine model (46.4% relative improvement). On ACE 2005, we obtain 44.24% vs. 32.38% F1 in five-shot scenarios (36.6% relative improvement). The model shows consistent gains in 10-shot (57.19% vs. 49.50% on ACE 2005) and 20-shot settings (64.50% vs. 58.21% on ACE 2005). Ablation studies confirm that semantic information from label descriptions is the key factor enabling robust few-shot performance. Transfer learning experiments demonstrate the model’s ability to leverage knowledge from related domains. Our findings suggest that incorporating label semantic information can substantially enhance NER models in low-resource settings, opening new possibilities for applying NER in specialized domains or languages with limited annotated data. Full article

In this study the objective was to morphologically characterize fruits, seeds and seedlings of Cereus fernambucensis Lem., as well as evaluate the seed germination and phenological dynamics of these columnar cacti, native to Brazil, which occur in restinga ecosystems. Biometric and morphological determinations were performed using 100 fruits, describing seed morphology in external and internal aspects and considering five stages of development for the characterization of seedlings. In the study of seed germination, two light conditions (12 h photoperiod and complete darkness) were tested under 25 °C, in a completely randomized design with four replicates of 50 seeds each. In the estimation of reproductive phenology, information was collected from herbarium specimens on the SpeciesLink online platform, and the exsiccatae were analyzed for the notes on their labels to evaluate reproductive aspects. Fruits showed an average mass of 21.11 g, length of 44.76 mm, diameter of 28.77 mm and about 336 seeds per fruit. Seeds behave as positive photoblastic, with a high percentage of germination under controlled conditions (94%). Germination is epigeal and phanerocotylar, with slow growth and, at 30 days after sowing, the seedling measures approximately 2 cm, which makes it possible to visualize the appearance of the epicotyl and the first spines. The species blooms and bears fruit throughout the year, with peaks of flowering and fruiting in January and March, respectively. The various characteristics make C. fernambucensis a key species for maintaining the biodiversity of restingas. Full article

Opuntia ficus-indica L. (Mill) belongs to the Cactaceae family. The plant produces edible and juicy fruits called cactus pear, recognized for their pleasant flavor and functional properties. However, the fruits have a short shelf life, hard seeds, and the presence of glochidia in the pericarpel. Recently, by inducing parthenocarpy, seedless fruits of cactus pear have been obtained. They have attractive colors, soft and small seminal residues, with a similar flavor to their original seeded counterparts. Nevertheless, their postharvest physiological behavior has not yet been documented. The aim of this study was to compare the biochemical, anatomical, and physiological characteristics of pollinated fruits, CP30 red and CP40 yellow varieties, with their parthenocarpic counterparts (CP30-P and CP40-P), obtained by the application of growth regulators in preanthesis. Fruits of each type were harvested at horticultural maturity, and analyses were carried out on both pulp and pericarpel (peel), using a completely randomized design. Results showed that red fruits CP30 and CP30-P showed higher concentrations of betacyanins in pulp (13.4 and 18.4 mg 100 g⁻¹ FW) and in pericarpel (25.9 and 24.1 mg 100 g⁻¹ FW), respectively; flavonoid content was significantly higher in partenocarpic fruits compared with the pollinated ones. Parthenocarpy mainly affected the shelf life, in pollinated fruits, CP30 was 14 days but 32 days in CP30-P; for CP40, it was 16 days, and 30 days in CP40-P. Also, the partenocarpic fruits were smaller but with a thicker pericarpel, and lower stomatal frequency. Overall, parthenocarpic fruits represent a viable alternative for commercial production due to their extended shelf life, lower weight loss, and soft but edible pericarpel. Full article

Organic amendments provide a sustainable strategy to enhance soil quality in degraded environments while also helping to reduce greenhouse gas emissions, for example, by improving soil structure, minimizing the use of synthetic fertilizers, and promoting a green economy. This study assessed the comparative effects of two organic amendments—vermicompost leachate and biochar—on the performance of popcorn maize (Zea mays L. var. everta) cultivated in saline soil conditions. Four treatments were evaluated: T0 (Control), T1 (Vermicompost leachate), T2 (Biochar), and T3 (Vermicompost leachate + Biochar), each with 10 replicates arranged in a Completely Randomized Design (CRD). Although various soil physicochemical, microbiological, and agronomic parameters displayed no significant differences compared to the control, the application of biochar resulted in considerable improvements in soil total organic carbon, the microbial community (mesophilic aerobic bacteria, molds, and yeasts), and increased seed length and diameter. In contrast, vermicompost leachate alone negatively impacted plant growth, leading to decreases in leaf area, stem thickness, and grain yield. Specifically, grain yield declined by 46% with leachate alone and by 31% when combined with biochar, compared to the control. These findings emphasize the superior effectiveness of biochar over vermicompost leachate as a soil amendment under saline conditions and highlight the potential risks of widely applying compost teas in stressed soils. It is recommended to conduct site-specific assessments and screenings for phytotoxins and phytopathogens prior to use. Additionally, the combined application of leachate and biochar may not be advisable given the tested soil characteristics. Full article

Peas possess significant nutritional properties due to their high protein levels, carbohydrates, fiber, and vitamins. Increased climate variability can lead to water stress in crops like peas. Therefore, priming plants through seed priming is a technique that has proven effective as a pre-conditioning method for plants to cope with more severe future stresses. Different doses and soaking times of ‘Santa Isabel’ pea seeds in NaCl and H₂O₂ were evaluated to enhance and promote germination. Two experiments were conducted under controlled conditions (average temperature 15.8 °C) through a completely randomized design with a 4 × 3 factorial arrangement, comprising 12 treatments in each trial. In the first trial, NaCl doses (0, 50, 100, or 150 mM) and the soaking time of the seeds in NaCl (12, 24, or 36 h) were examined. In the second trial, H₂O₂ doses (0, 20, 40, or 60 mM) were tested with the same imbibition times. The 50 mM NaCl dose at 24 h demonstrated the best values for germination rate index, mean germination time, germination rate (GR), and germination potential (GP). Seed imbibition for 24 h in NaCl, as well as in H₂O₂, is the ideal time to achieve the best GR and GP. The dry mass of leaf and stipule recorded the highest values with a 60 mM dose of H₂O₂ and 24 h of imbibition. An application of 150 mM NaCl resulted in the highest values of germinated seed dry mass, while causing lower dry mass in roots, stems, leaves, and stipules; however, it maintained similar total dry mass values. Full article

We propose a data-efficient framework for automating sowing operations by agricultural robots in densely mixed polyculture environments. This study addresses the challenge of enabling robots to identify suitable sowing positions with minimal labeled data by integrating image-based field sensing with expert agricultural knowledge. We collected 84 RGB-depth images from seven field sites, labeled by synecological farming practitioners of varying proficiency levels, and trained a regression model to estimate optimal sowing positions and seeding quantities. The model’s predictions were comparable to those of intermediate-to-advanced practitioners across diverse field conditions. To implement this estimation in practice, we mounted a Kinect v2 sensor on a robot arm and integrated its 3D spatial data with axis-specific movement control. We then applied a trajectory optimization algorithm based on the traveling salesman problem to generate efficient sowing paths. Simulated trials incorporating both computation and robotic control times showed that our method reduced sowing operation time by 51% compared to random planning. These findings highlight the potential of interpretable, low-data machine learning models for rapid adaptation to complex agroecological systems and demonstrate a practical approach to combining structured human expertise with sensor-based automation in biodiverse farming environments. Full article

With the increasing application of hyperspectral technology, rapid and accurate monitoring of cotton leaf nitrogen concentrations (LNCs) has become an effective tool for large-scale areas. This study used Tahe No. 2 cotton seeds with four nitrogen levels (0, 200, 350, 500 kg ha⁻¹) and four phosphorus levels (0, 100, 200, 300 kg ha⁻¹). Spectral data were acquired using an ASD FieldSpec HandHeld2 portable spectrometer, which measures spectral reflectance covering a band of 325–1075 nm with a spectral resolution of 1 nm. LNCs determination and spectral estimation were conducted at six growth stages: squaring, initial bloom, peak bloom, initial boll, peak boll, and boll opening. Thirty-seven spectral indices (SIs) were selected. First derivative (FD), standard normal variate (SNV), multiplicative scatter correction (MSC), and Savitzky–Golay (SG) were applied to preprocess the spectra. Feature bands were screened using partial least squares discriminant analysis (PLS–DA), and support vector machine (SVM) and random forest (RF) models were used for accuracy validation. The results revealed that (1) LNCs initially increased and then decreased with growth, peaking at the full-flowering stage before gradually declining. (2) The best LNC recognition models were SVM–MSC in the squaring stage, SVM–FD in the initial bloom stage, SVM–FD in the peak bloom stage, SVM–FD in the initial boll stage, RF–SNV in the peak boll Mstage, and SVM–FD in the boll opening stage. FD showed the best performance compared with the other three treatments, with SVM outperforming RF in terms of higher R² and lower RMSE values. The SVM–FD model effectively improved the accuracy and robustness of LNCs prediction using hyperspectral leaf spectra, providing valuable guidance for large-scale information production in high-standard cotton fields. Full article

Reliable aerodynamic performance estimation is essential for both preliminary design and optimization in various aeronautical applications. In this study, a hybrid deep learning model is proposed, combining convolutional neural networks (CNNs) and operating directly on raw airfoil geometry, with parallel branches of fully connected deep neural networks (DNNs) that process operational parameters and engineered features. The model is trained on an extensive database of NACA four-digit airfoils, covering angles of attack ranging from −5° to 14° and ten Reynolds numbers increasing in steps of 500,000 from 500,000 up to 5,000,000. As a novel contribution, this work investigates the impact of random seed initialization on model accuracy and reproducibility and introduces a seed-based ensemble strategy to enhance generalization. The best-performing single-seed model tested (seed 0) achieves a mean absolute percentage error (MAPE) of 1.1% with an ${\mathrm{R}}^2$ of 0.9998 for the lift coefficient prediction and 0.57% with an ${\mathrm{R}}^2$ of 0.9954 for the drag coefficient prediction. In comparison, the best ensemble model tested (seeds 610, 987, and 75025) achieves a lift coefficient MAPE of 1.43%, corresponding to ${\mathrm{R}}^2$ 0.9999, and a drag coefficient MAPE of 1.19%, corresponding to ${\mathrm{R}}^2$ = 0.9968. All the tested seed dependencies in this paper (ten single seeds and five ensembles) demonstrate an overall ${\mathrm{R}}^2$ greater than 0.97, which reflects the model architecture’s strong foundation. The novelty of this study lies in the demonstration that the same machine learning model, trained on identical data and architecture, can exhibit up to 250% variation in prediction error solely due to differences in random seed selection. This finding highlights the often-overlooked impact of seed initialization on model performance and highlights the necessity of treating seed choice as an active design parameter in ML aerodynamic predictions. Full article

Intercropping is an eco-friendly agricultural practice that can lead to increased productivity and improved resource efficiency. This two-year field study (2022–2023 and 2023–2024) aimed to evaluate the yield and quality (protein content) of lentil when intercropping with bread wheat (Yekora) and oat (Kassandra) under two spatial arrangements (1:1 alternate rows and mixed rows at a 50:50 seeding ratio) in northwestern Greece. A completely randomized design was applied with three replications. Differences were found between treatments regarding yield as well as protein content. Results showed that the highest total grain yield (2478.6 kg/ha) and land equivalent ratio (LER = 2.50) were recorded in the Yekora + Thessalia combination (alternate rows). Legume protein content remained consistently high (27–31%), while cereal protein content varied with genotype. Intercropping in alternate rows generally outperformed mixed sowing, indicating the importance of spatial arrangement in optimizing resource use. These findings suggest that properly designed cereal–lentil intercropping systems can enhance yield and quality while supporting sustainable agricultural practices. Intercropping of Yekora with lentil was superior compared to lentil and bread wheat monocultures and can be recommended as an alternative method for the production of human and animal food. Full article

Understanding the influence of environmental factors on cotton performance is crucial for enhancing yield and fiber quality in the context of climate change. This study investigates genotype-by-environment (G×E) interactions in cotton, using data from 250 recombinant inbred lines (CCRI70 RILs) cultivated across 14 diverse environments in China’s major cotton cultivation areas. Our findings reveal that environmental effects predominantly influenced yield-related traits (boll weight, lint percentage, and the seed index), contributing to 34.7% to 55.7% of their variance. In contrast fiber quality traits showed lower environmental sensitivity (12.3–27.0%), with notable phenotypic plasticity observed in the boll weight, lint percentage, and fiber micronaire. Employing six machine learning models, Random Forest demonstrated superior predictive ability (R² = 0.40–0.72; predictive Pearson correlation = 0.63–0.86). Through SHAP-based interpretation and sliding-window regression, we identified key environmental drivers primarily active during mid-to-late growth stages. This approach effectively reduced the number of influential input variables to just 0.1–2.4% of the original dataset, spanning 2–9 critical time windows per trait. Incorporating these identified drivers significantly improved cross-environment predictions, enhancing Random Forest accuracy by 0.02–0.15. These results underscore the strong potential of machine learning to uncover critical temporal environmental factors underlying G×E interactions and to substantially improve predictive modeling in cotton breeding programs, ultimately contributing to more resilient and productive cotton cultivation. Full article