Search Results (12,444)

Litchi (Litchi chinensis Sonn.) is a pillar of the tropical agricultural economy in southern China, yet its production faces increasing instability due to climate change. Traditional agronomic models often fail to capture the complex, non-linear interactions between meteorological drivers and yield formation in perennial fruit trees. To address this challenge, the study constructed a yield prediction framework using an optimized Random Forest (RF) model integrated with interpretable machine learning (SHAP), based on a comprehensive dataset from 17 major production regions in Hainan Province (2000–2022). The model demonstrated robust predictive capability at the provincial scale (R² = 0.564, RMSE = 2.1 t/ha) and high consistency across regions (R² ranging from 0.51 to 0.94). Feature importance analysis revealed that heat accumulation (specifically growing degree days above 20 °C) is the dominant driver, explaining over 85% of yield variability. Crucially, scenario simulations uncovered asymmetric climate risks across phenological stages: while moderate warming generally enhances yield by promoting vegetative growth and ripening, it acts as a stressor during the Fruit Development stage, where temperatures exceeding 26 °C trigger yield decline. Furthermore, the yield penalty for drought during Flowering (−8.09%) far outweighed the marginal benefits of surplus rainfall, identifying this window as critically sensitive to water deficits. These findings underscore the necessity of phenology-aligned adaptation strategies—specifically, securing irrigation during flowering and deploying cooling interventions during fruit development—providing a data-driven basis for climate-smart management in tropical agriculture. Full article

Targeted coverage of crushed grass segments under the fruit tree canopy synergistically achieves the agronomic goals of soil moisture conservation, weed suppression, and soil fertility improvement. To address issues like incomplete grass cutting and high risk of damaging fruit trees in complex orchard environments with traditional mowing devices, a lateral grass discharge blade for orchard mowers was designed. Based on airflow field theory, the dynamic basis of the airflow field, critical conditions for carrying crushed grass segments, and their movement laws on the blade and in the air were analyzed to identify key factors affecting discharge. CFD simulations were conducted using the Flow Simulation module of SolidWorks 2021 to explore the effects of the blade airfoil’s long side, short side lengths, and horizontal included angle on the outlet velocity and outlet volumetric flow rate of crushed grass segments, determining the reasonable parameter range. With these three as test factors and the two indicators above, orthogonal tests and parameter optimization were performed via Design-Expert 13.0 software, yielding optimal parameters: long side 125 mm, short side 35 mm, horizontal included angle 60°, corresponding to 9.105 m/s outlet velocity and 0.045 m³/s volume flow rate. A prototype mowing device with these parameters was fabricated for orchard field tests. Results show an average stubble stability coefficient of 94.2%, average over-stubble loss rate of 0.39%, and crushed grass segment distribution variation coefficient of 23.8%, meeting orchard mower operation requirements and providing technical support for orchard weed mowing, coverage, and utilization. Full article

Grape pomace is a major byproduct of winemaking and a rich source of bioactive anthocyanins with potential functional value. This study aimed to optimize anthocyanin extraction from Tannat grape pomace and evaluate its antioxidant and anti-aging activities. Ultrasonic-assisted extraction combined with a Box–Behnken design identified optimal conditions of 51.27 °C, 53.46% ethanol, 20.10 min ultrasonication, and a 1:24.05 solid-to-liquid ratio, yielding 186.21 ± 1.03 mg/100 g (R² = 0.9798, p < 0.0001). Tannat Grape Pomace Anthocyanins showed strong antioxidant capacity, with 2,2-Diphenyl-1-picrylhydrazyl scavenging of 89.44% ± 0.87% at 0.2 mg/mL (IC₅₀ = 0.09 mg/mL) and 2,2′-Azino-bis (3-ethylbenzothiazoline-6-sulfonic acid) scavenging of 95.83% ± 0.54% at 0.75 mg/mL (IC₅₀ = 0.26 mg/mL). In Caenorhabditis elegans, TGPA extended lifespan, improved motility, and increased heat and oxidative stress resistance without reducing reproductive capacity. Lifespan is a key indicator of aging. This study holds significant implications for advancing our understanding of the mechanisms underlying lifespan regulation, the connection between aging and disease, as well as the development of anti-aging therapies for humans. In conclusion, these findings indicate that Tannat Grape Pomace Anthocyanins possess promising antioxidant and anti-aging potential and support the sustainable, high-value utilization of grape pomace. This approach directly aligns with the core principles of sustainable agriculture by transforming an agricultural byproduct into a valuable resource. Full article

In the field of precision agriculture, accurately detecting rice panicles is crucial for monitoring rice growth and managing rice production. To address the challenges posed by complex field backgrounds, including variety differences, variations across growth stages, background interference, and occlusion due to dense distribution, this study develops an improved YOLO11-based rice panicle detection model, termed DRPU-YOLO11. The model incorporates a task-oriented CSP-PGMA module in the backbone to enhance multi-scale feature extraction and provide richer representations for downstream detection. In the neck network, DySample and CGDown are adopted to strengthen global contextual feature aggregation and suppress background interference for small targets. Furthermore, fine-grained P2 level information is integrated with higher-level features through a cross-scale fusion module (CSP-ONMK) to improve detection robustness in dense and occluded scenes. In addition, the PowerTAL strategy adapts quality-aware label assignment to emphasize high-quality predictions during training. The experimental results based on a self-constructed dataset demonstrate that DRPU-YOLO11 significantly outperforms baseline models in rice panicle detection under complex field environments, achieving an accuracy of 82.5%. Compared with the baseline model YOLO11 and RT-DETR, the mAP₅₀ increases by 2.4% and 5.0%, respectively. These results indicate that the proposed task-driven design provides a practical and high-precision solution for rice panicle detection, with potential applications in rice growth monitoring and yield estimation. Full article

Scutellaria baicalensis is an important medicinal plant, and the diversity of its rhizosphere microbiota may influence its growth, development, and yield. Numerous studies have reported that warming associated with global climate change significantly altered plant-associated soil microbial diversity. To reveal the effects of night-time warming on the rhizosphere microbial community of S. baicalensis, soil microbial diversity in the rhizosphere (RS) and bulk soil (BS) of S. baicalensis were analyzed by employing bacterial 16S rRNA and fungal ITS sequencing technology. Warming significantly altered both bacterial and fungal communities in the rhizosphere and bulk soils of S. baicalensis, with pronounced changes in OTU composition, relative abundances at both phylum and species levels. The analysis of alpha and beta diversity showed that warming significantly altered the fungal community structure in the rhizosphere soil (R² = 0.423, p < 0.05) and significantly reduced the species richness in the bulk soil of S. baicalensis (Shannon and Simpson index, p < 0.05). LEfSe and functional prediction analyses revealed that warming altered the taxonomic composition of both bacterial (35 taxa, LDA > 3) and fungal (24 taxa, LDA > 4) communities in rhizosphere and bulk soils of S. baicalensis, with multiple bacterial and fungal taxa serving as treatment-specific biomarkers. Functional predictions indicated that fungal functional groups, including saprotrophic and mycorrhizal guilds, were more strongly affected by warming than bacteria. Overall, warming has a significantly stronger impact on fungal communities in the rhizosphere and bulk soils of S. baicalensis than on bacteria, and has a significantly greater effect on the diversity of microbial communities in bulk soils than that in rhizosphere soils. This study provides important data for understanding the impact of global climate change on the rhizosphere microbial communities of cultivated plants. Full article

The aim of this study was to accurately meet the demand of real-time detection of seedling shortage in large-scale seedling production and solve the problems of low precision of traditional models and insufficient adaptability of mainstream lightweight models. This study proposed a Light-YOLO-Pepper seedling shortage detection model based on the improvement of YOLOv8n. This model was based on YOLOv8n. The SE (Squeeze-and-Excitation) attention module was introduced to dynamically suppress the interference of the nutrient soil background and enhance the features of the seedling shortage area. Depth-separable convolution (DSConv) was used to replace the traditional convolution, which can reduce computational redundancy while retaining core features. Based on K- means clustering, customized anchor boxes were generated to adapt to the hole sizes of 72-unit (large size) and 128-unit (small size and high-density) seedling trays. The results show that the overall mAP@0.5, accuracy and recall rate of Light-YOLO-Pepper model were 93.6 ± 0.5%, 94.6 ± 0.4% and 93.2 ± 0.6%, which were 3.3%, 3.1%, and 3.4% higher than YOLOv8n model, respectively. The parameter size of the Light-YOLO-Pepper model was only 1.82 M, the calculation cost was 3.2 G FLOPs, and the reasoning speeds with regard to the GPU and CPU were 168.4 FPS and 28.9 FPS, respectively. The Light-YOLO-Pepper model was superior to the mainstream model in terms of its lightweight and real-time performance. The precision difference between the two seedlings was only 1.2%, and the precision retention rate in high-density scenes was 98.73%. This model achieves the best balance of detection accuracy, lightweight performance, and scene adaptability, and can efficiently meet the needs of embedded equipment and real-time detection in large-scale seedling production, providing technical support for replanting automation. Full article

Based on panel data from China’s 31 provinces and municipalities covering 2011–2023, this study constructs a multidimensional evaluation system for digital economic development and agricultural industrial chain resilience within the Technology-Organization-Environment (TOE) framework. It systematically examines the impact of the digital economy on agricultural industrial chain resilience and its sub-dimensions, while introducing green finance as a moderating variable. The findings reveal: First, the development of the digital economy significantly enhances the resilience of the agricultural industrial chain. This conclusion withstands multiple robustness tests, and the impact of the digital economy on the three dimensions of agricultural industrial chain resilience (resistance, recovery, and reconstruction) varies, particularly exhibiting a negative effect on reconstruction. Second, the enabling effect of the digital economy on agricultural industrial chain resilience shows a significant spatial gradient. Regionally, resilience is ranked as “Production-Sales Balance Zones > Main Sales Zones > Main Production Zones” within grain functional zones, and “Northeast > West > East > Central” across China’s four major economic regions. Third, green finance development exerts a negative moderating effect on the pathway through which the digital economy enhances agricultural supply chain resilience, higher green finance levels weaken the marginal improvement effect of the digital economy. This study fills research gaps regarding the multidimensional impact of digital economic development on agricultural industrial chain resilience and empirically supplements the lack of evidence on the negative moderating mechanism of green finance and its sub-dimensions, providing policy tools for agricultural modernization and resilience governance. Full article

Dairy cow body temperature is a key physiological indicator that reflects metabolic level, immune status, and environmental stress responses, and it has been widely used for early disease recognition. Infrared thermography (IRT), as a non-contact imaging technique capable of remotely acquiring the surface radiation temperature distribution of animals, is regarded as a powerful alternative to traditional temperature measurement methods. Under practical cowshed conditions, IRT images of dairy cows are easily affected by complex background interference and generally suffer from low resolution, poor contrast, indistinct boundaries, weak structural perception, and insufficient texture information, which lead to significant degradation in target detection and temperature extraction performance. To address these issues, a lightweight detection model named YOLOv11n-CGSD is proposed for dairy cow IRT images, aiming to improve the accuracy and robustness of region of interest (ROI) detection and body temperature extraction under complex background conditions. At the architectural level, a C3Ghost lightweight module based on the Ghost concept is first constructed to reduce redundant feature extraction while lowering computational cost and enhancing the network capability for preserving fine-grained features during feature propagation. Subsequently, a space-to-depth convolution module is introduced to perform spatial rearrangement of feature maps and achieve channel compression via non-strided convolution, thereby improving the sensitivity of the model to local temperature variations and structural details. Finally, a dynamic sampling mechanism is embedded in the neck of the network, where the upsampling and scale alignment processes are adaptively driven by feature content, enhancing the model response to boundary temperature changes and weak-texture regions. Experimental results indicate that the YOLOv11n-CGSD model can effectively shift attention from irrelevant background regions to ROI contour boundaries and increase attention coverage within the ROI. Under complex IRT conditions, the model achieves P, R, and mAP50 values of 89.11%, 86.80%, and 91.94%, which represent improvements of 3.11%, 5.14%, and 4.08%, respectively, compared with the baseline model. Using T_max as the temperature extraction parameter, the maximum error (Max. Error) and mean error (MAE. Error) in the lower udder region are reduced by 33.3% and 25.7%, respectively, while in the around the anus region, the Max. Error and MAE. Error are reduced by 87.5% and 95.0%, respectively. These findings demonstrate that, under complex backgrounds and low-quality IRT imaging conditions, the proposed model achieves lightweight and high-performance detection for both lower udder (LU) and around the anus (AA) regions and provides a methodological reference and technical support for non-contact body temperature measurement of dairy cows in practical cowshed production environments. Full article

Crop production in the desert Southwest of the United States, as well as in other arid and semi-arid regions, requires tools that provide accurate crop evapotranspiration (ET) estimates to support efficient irrigation management. Such tools include the web-based OpenET platform, which provides real-time ET data generated from six satellite-based models, their Ensemble, and a field-based system (LI-710, LI-COR Inc., Lincoln, NE, USA). This study evaluated simulated ET (ET_SIM) of cotton (Gossypium hirsutum L.) derived from OpenET models (ALEXI/DisALEXI, eeMETRIC, geeSEBAL, PT-JPL, SIMS, and SSEBop), their Ensemble approach, and LI-710. Field data were utilized to estimate cotton ET using the soil water balance (SWB) method (ET_SWB) from June to October 2025 in Gila Bend, AZ, USA. Four evaluation metrics, the normalized root-mean-squared error (NRMSE), mean bias error (MBE), simulation error (S_e), and coefficient of determination (R²), were employed to evaluate the performance of OpenET models, their Ensemble, and the LI-710 in estimating cotton ET. Statistical analysis indicated that the ALEXI/DisALEXI, geeSEBAL, and PT-JPL models substantially underestimated ET_SWB, with simulation errors ranging from −26.92% to −20.57%. The eeMETRIC, SIMS, SSEBop, and Ensemble provided acceptable ET estimates (22.57% ≤ NRMSE ≤ 29.85%, −0.36 mm. day⁻¹ ≤ MBE ≤ 0.16 mm. day⁻¹, −7.58% ≤ S_e ≤ 3.42%, 0.57 ≤ R² ≤ 0.74). Meanwhile, LI-710 simulated cotton ET acceptably with a slight tendency to overestimate daily ET by 0.21 mm. A strong positive correlation was observed between daily ET_SIM from LI-710 and ET_SWB, with S_e and NRMSE of 4.40% and 23.68%, respectively. Based on our findings, using a singular OpenET model, such as eeMETRIC, SIMS, or SSEBop, the OpenET Ensemble, and the LI-710 can offer growers and decision-makers reliable guidance for efficient irrigation management of late-planted cotton in arid and semi-arid climates. Full article

The causes of agricultural drought are complex, and its actual occurrence process is often characterized by rapid onset in terms of time and small scale in terms of space. Monitoring agricultural drought using satellite remote sensing with low spatial resolution makes it difficult to accurately capture the details of small-scale drought events. High-resolution satellite remote sensing has relatively long revisit cycles, making it difficult to capture the rapid evolution of drought conditions. Furthermore, the occurrence of agricultural drought is linked to multiple factors including precipitation, evapotranspiration, soil properties, and crop physiological characteristics. Consequently, relying on a single variable or indicator is insufficient for multidimensional monitoring of agricultural drought. This study takes Hebi City, Henan Province as the research area. It uses Sentinel-1 satellite data (HV, VV), Sentinel-2 data (NDVI, B2, B11), elevation, slope, aspect, and GPM precipitation data from 2019 to 2024 as independent variables. Three machine learning algorithms—Random Forest (RF), Random Forest-Recursive Feature Elimination (RF-RFE), and eXtreme Gradient Boosting (XGBoost)—were employed to construct a multi-dimensional agricultural drought monitoring model at the field scale. Additionally, the study verified the sensitivity of different environmental variables to agricultural drought monitoring and analyzed the accuracy performance of different machine learning algorithms in agricultural drought monitoring. The research results indicate that under the condition of full-factor input, all three models exhibit the optimal predictive performance. Among them, the XGBoost model performs the best, with the smallest Relative Root Mean Square Error (RRMSE) of 0.45 and the highest Correlation Coefficient (R) of 0.79. The absence of Digital Elevation Model (DEM) data impairs the models’ ability to capture the patterns of key features, which in turn leads to a reduction in predictive accuracy. Meanwhile, there is a significant correlation between model performance and sample size. Ultimately, the constructed XGBoost model takes the lead with an accuracy of 89%, while the accuracies of Random Forest (RF) and Random Forest-Recursive Feature Elimination (RF-RFE) are 88% and 86%, respectively. Based on these three drought monitoring models, this study further monitored a drought event that occurred in Hebi City in 2023, presented the spatiotemporal distribution of agricultural drought in Hebi City, and applied the Mann–Kendall test for time series analysis, aiming to identify the abrupt change process of agricultural drought. Meanwhile, on the basis of the research results, the feasibility of verifying drought occurrence using irrigation signals was discussed, and the potential reasons for the significantly lower drought occurrence probability in the western mountainous areas of the study region were analyzed. Full article

The effects of pelleting a total mixed ration (TMR) for dairy sheep were investigated in an experiment involving 24 lactating Assaf ewes, which were assigned to two groups and fed the same TMR ad libitum, offered either in pelleted (PTMR group, n = 12) or in unpelleted form (CTMR group, n = 12). The experiment lasted 28 days, during which feed intake, eating behavior (including meal frequency and size, meal duration, eating rate, between-meal interval), and milk yield were recorded daily. Body weight (BW) was recorded on days 1 and 28 and milk samples were collected on days 1, 8, 15, 22 and 28 for milk composition analysis. Blood acid-base status was determined at the beginning and at the end of the trial. Ewes fed the CTMR diet exhibited (p < 0.05) a higher meal frequency and longer meal duration, along with a smaller meal size and slower eating rate. However, feed intake in this group was less than that in ewes fed PTMR only during the final two weeks of the experimental period. Total eating time was also longer (p < 0.001) in the CTMR group, whereas the average time between meals was shorter (p < 0.002). No differences (p > 0.05) were observed between dietary treatments in blood acid-base status, milk yield or milk composition. However, a diet x day interaction (p < 0.05) was detected for milk yield, as during the last 2 weeks of the experimental period the ewes fed the PTMR yielded more milk than those fed the CTMR. Feed conversion ratio did not differ between groups (p > 0.05), but body weight loss was greater in ewes fed the CTMR diet (−3.00 vs. −0.58 kg; p < 0.05). A trend toward improved feed efficiency was observed in the PTMR group when calculated based on milk yield corrected for that theoretically derived from the mobilization of body reserves (1.98 vs. 1.41 g DMI/kg milk; p = 0.077), with estimated contributions from body reserves of 485 g/day in the CTMR group and 70 g/day in the PTMR group. In conclusion, the use of pelleted total mixed rations in high-yielding dairy ewes enhances feed intake, feed efficiency, milk yield, and energy balance without adversely affecting milk composition or animal health in the short term. Full article

Meteorological data from automatic weather stations (AWS) in tea plantations is critical for agricultural management, but is often compromised by sensor errors and physical implausibilities that traditional quality control (QC) methods fail to detect. This study proposes a novel, meteorologically informed QC framework that mines association rules from long-term ERA5 reanalysis data (2012–2023) using the Apriori algorithm to establish a knowledge base of normal multivariate atmospheric patterns. A comprehensive feature engineering process generated temporal, physical, and statistical features, which were discretized using meteorological thresholds. The mined rules were filtered, prioritized, and integrated with hard physical constraints. The system employs a fuzzy logic mechanism for violation assessment and a weighted anomaly scoring system for classification. When validated on a synthetic dataset with injected anomalies, the method significantly outperformed traditional QC techniques, achieving an F1-score of 0.878 and demonstrating a superior ability to identify complex physical inconsistencies. Application to an independent historical dataset from a Zhenjiang tea plantation (2008–2016) successfully identified 14.6% anomalous records, confirming the temporal transferability and robustness of the approach. This framework provides an accurate, interpretable, and scalable solution for enhancing the quality of meteorological data, with direct implications for improving the reliability of frost prediction and pest management in precision agriculture. Full article

Payments for Ecosystem Services (PESs) have become a central instrument in global biodiversity finance, yet endangered species-specific PESs remain rare and poorly understood in implementation terms. Taiwan provides a revealing case: a three-year program paying farmers to conserve four threatened species—Prionailurus bengalensis, Lutra lutra, Tyto longimembris, and Hydrophasianus chirurgus—in working farmland across Taiwan and Kinmen island. Through semi-structured interviews with farmers, residents, and local conservation actors, we examine how payments are interpreted, rationalized, enacted, and emotionally experienced at the ground level. This study adopts Colaizzi’s data analysis method, the primary advantage of which lies in its ability to systematically transform fragmented and emotive interview narratives into a logically structured essential description. This is achieved through the rigorous extraction of significant statements and the subsequent synthesis of thematic clusters. Participants reported willingness to continue not only because subsidies offset losses, but because rarity, community pride, and the visible arc of “we helped this creature survive” became internalized rewards. NGOs amplified this shift by translating science into farm practice and “normalizing” coexistence. In practice, conservation work became a social project—identifying threats, altering routines, and defending habitat as a shared civic act. This study does not estimate treatment-effect size; instead, it delivers mechanistic insight at a live policy moment, as Taiwan expands PESs and the OECD pushes incentive reform. The finding is simple and strategically important: endangered-species PESs work best where payments trigger meaning—not where payments replace it. Full article

This paper presents a low-cost, fully on-premise Edge Artificial Intelligence (AI) system designed to support real-time pest and disease detection in open-field chili pepper cultivation. The proposed architecture integrates AI-Thinker ESP32-CAM module (ESP32-CAM) image acquisition nodes (“Sticks”) with a Raspberry Pi 5–based edge server (“Module”), forming a plug-and-play Internet of Things (IoT) pipeline that enables autonomous operation upon simple power-up, making it suitable for aging farmers and resource-limited environments. A Leaf-First 2-Stage vision model was developed by combining YOLOv8n-based leaf detection with a lightweight ResNet-18 classifier to improve the diagnostic accuracy for small lesions commonly occurring in dense pepper foliage. To address network instability, which is a major challenge in open-field agriculture, the system adopted a dual-protocol communication design using Hyper Text Transfer Protocol (HTTP) for Joint Photographic Experts Group (JPEG) transmission and Message Queuing Telemetry Transport (MQTT) for event-driven feedback, enhanced by Redis-based asynchronous buffering and state recovery. Deployment-oriented experiments under controlled conditions demonstrated an average end-to-end latency of 0.86 s from image capture to Light Emitting Diode (LED) alert, validating the system’s suitability for real-time decision support in crop management. Compared to heavier models (e.g., YOLOv11 and ResNet-50), the lightweight architecture reduced the computational cost by more than 60%, with minimal loss in detection accuracy. This study highlights the practical feasibility of resource-constrained Edge AI systems for open-field smart farming by emphasizing system-level integration, robustness, and real-time operability, and provides a deployment-oriented framework for future extension to other crops. Full article