Surface litter manure can significantly increase the risk of diseases in broiler brooding houses, such as coccidiosis and colibacillosis. Indoor air quality can be deteriorated, due to the release of ammonia, hydrogen sulfide, and methane. However, existing double-crank shoveling-throwing mechanisms of surface manure cleaning have suffered from low efficiency, performance, and excessive vibration, because the key structural parameters are determined empirically without systematic multi-objective optimization. In this study, a multi-objective optimization was developed for the double-crank shoveling-throwing mechanism using an improved NSGA-II algorithm. Thereby, better performance was achieved to improve the shoveling efficiency, energy consumption, and stability. A kinematic and dynamic model of the double-crank shoveling-throwing mechanism was first established to reveal the influence of structural parameters on the shoveling trajectory and force behaviors. A coupled ADAMS-EDEM simulation model was then constructed to simulate the interaction between the mechanism and manure particles. As such, 60 sets of variable samples were generated after the optimal Latin hypercube sampling. A Gaussian process regression (GPR) surrogate model was constructed to map the relationship between six variables and the shovel throwing quality Q. The relative error between the prediction and simulation was 3.85%, indicating high prediction accuracy. An improved NSGA-II algorithm was proposed to overcome the limitations of the standard NSGA-II algorithm—namely, significant dimensional differences among the three objectives, highly nonlinear parameter-performance mapping, and discontinuous parameter space. Three improvements were introduced: (1) an adaptive normalization mechanism to eliminate dimensional effects; (2) a hybrid optimization framework with global search (NSGA-II) and local refinement (sequential quadratic programming, SQP) for the high convergence accuracy; and (3) an improved crowding distance and solution selection mechanism for the distribution uniformity of the Pareto front. The improved algorithm was compared with standard NSGA-II, NSGA-III, MOPSO, and MOEA/D, according to three performance indicators: Inverted Generational Distance (IGD), Spacing, and Hypervolume (HV). The results showed that the improved NSGA-II algorithm significantly outperformed the rest. Specifically, the IGD value decreased by 71%, 68%, and 64%, respectively, compared with standard NSGA-II, MOPSO, and MOEA/D. Spacing value decreased by 26%, compared with standard NSGA-II, whereas, the HV value increased by 16%. The better performance was achieved in the high convergence, more uniform distribution, and higher coverage of the true Pareto front. The optimal compromise solution was selected from the Pareto set using the entropy-weighted TOPSIS. The optimal parameters were recommended: l₁=70.4 mm, l₂=88.5 mm, l₃=100.2 mm, l₄=30.3 mm, b=99.7 mm, β=37.4°. A prototype was manufactured for the double-crank shoveling-throwing device, according to the optimal parameters. Field experiments were conducted in three repetitions in a brooding house in Zhouzhi County, Xi’an, Shaanxi Province, China, in December 2025. The experimental conditions were as follows: Litter layer with a thickness of 50–60 mm, chicken manure layer thickness of 10-20 mm, and manure moisture content of 30%–35%. The results demonstrated that the optimal mechanism improved shoveling efficiency by 138.24%, whereas the driving torque and the angular acceleration peak at the shovel end were reduced by 35.12%, and 35.60%, respectively. In addition, the residual rate of surface manure decreased from 18.45% to 8.13%, with a reduction of 55.99%, indicating significantly improved cleaning quality. A multi-objective optimization framework was provided for the double-crank shoveling-throwing mechanism using ADAMS-EDEM simulation, GPR surrogate modeling, and an improved NSGA-II algorithm. The dimensional differences and high nonlinearity were avoided for the low computational cost after engineering optimization. The improved NSGA-II algorithm demonstrated superior convergence and distribution performance, compared with mainstream multi-objective algorithms. The optimal mechanism was achieved to balance shoveling efficiency, energy consumption, and operational stability. The findings can offer a complete technical pathway to enhance the performance of hinge-type multi-bar mechanisms, particularly for manure cleaning equipment in the poultry industry.

Accurately adjusting the feeding intake is often required in pond aquaculture of Micropterus salmoides. In this study, a dual-model progressive feeding strategy was proposed to accurately forecast the postprandial feeding status of the subsequent round using a time series model. The decrement mechanism was first triggered. Subsequently, a classification model was utilized to determine the postprandial feeding status of the current round, enabling the termination of the decrement mechanism. The experimental system consisted of three pond culture tanks stocked with Micropterus salmoides, with initial body masses of (161.47±11.02) , (204.36±17.09) , and (220.25±22.78) g, and the stocking densities of 224, 301, and 294 individuals, respectively. Feeding experiments were conducted using a multi-round feeding protocol within a single session. Audio data was collected during feeding using the digital hydrophone, while video data was obtained using a camera. Meanwhile, multimodal data including light intensity, water temperature, body mass, per-round feeding rate, and population abundance were synchronously recorded for per-round feeding. The stabilization of the cumulative feeding energy curve was adopted to determine feeding termination. A dynamic adaptive threshold segmentation was employed to accurately identify the feeding audio within the collected audio. Principal component analysis was conducted on the feeding features to extract from the feeding audio. Feature selection was employed to identify sensitive features to feeding status, which served as the inputs for model training and classification. Four models 1D convolutional neural network, Long short-term memory, gated recurrent unit, and transformer were improved to construct the feeding prediction models with time series. The optimal model was selected to predict the postprandial feeding status of the subsequent round, serving as the first-stage model of feeding strategy. Eight models k-Nearest Neighbors, decision tree, support vector machine, random forests, adaBoost, gradient boosting decision trees, extreme gradient boosting, and light gradient boosting machine (LightGBM) were employed to construct feeding status classification models. The best classification performance was selected as the feeding determination model in the second stage. Results showed that the sensitive features included overall features, light intensity, water temperature, body mass, and per-round feeding rate. A classification between the original and sensitive features demonstrated the effectiveness of the sensitive features, according to gradient boosting decision trees and random forests models. Transformer-regression-classification (transformer-RC) model outperformed the rest of the models across 1 to 3-time windows, with the accuracy from 0.93 to 0.94. The Transformer-RC model effectively predicted the postprandial feeding status of the subsequent round. All five ensemble models achieved strong classification, which outperformed the three base models. Among them, the LightGBM model achieved an accuracy of 0.98 for inputs to the classification model of feeding status in the second stage of the feeding strategy. Both the Transformer-RC and LightGBM models shared high prediction and classification after validation, with average values of four evaluation metrics exceeding 0.89 under both feeding states, indicating strong generalization. This finding can provide a strong reference to develop intelligent feeding.

Agricultural carbon emissions have been generated by human activities in vast regions. It is often required to accurately understand the status, spatiotemporal patterns, and future trends of agricultural carbon emissions. It is also crucial to optimize carbon sequestration and emission reduction against climate adaptation. However, current assessments can rely heavily on statistical data, where regions with incomplete statistical records can introduce great uncertainties in carbon accounting and forecasting. Taking Chongqing as a case study, a systematic investigation was conducted to explore the spatiotemporal patterns and future trends of agricultural carbon emissions from 2004 to 2023. Multi-source agricultural data was also combined with statistics and remote sensing monitoring at the county level. Furthermore, spatiotemporal analysis was employed to examine the evolution, including slope estimation, the Mann-Kendall test, Moran's I index, and the Getis-Ord Gi* index. While the prediction models were then constructed for the trends, such as ARIMA and three machine learning methods (support vector machine, random forest, and XGBoost). The results indicate that: 1) The feasible and reliable performance was achieved to evaluate agricultural carbon emission using multi-source data, particularly with the average annual agricultural carbon emission of 2.435 million tons. There was a significant correlation with the conventional statistical data (R²=0.932, P<0.001), thus compensating for missing county-level statistical data. The higher stability was also achieved after evaluation. 2) There were significant source and regional differences in agricultural carbon emissions. The primary sources were methane emissions from rice cultivation and carbon emissions from fertilizer use, with average annual emissions of 1.175 million and 0.809 million tons, respectively. The spatial agglomeration of agricultural carbon emissions was intensified year by year, with the global Moran's I index of 0.695, 0.615, and 0.64 in 2017, 2021, and 2023, respectively. Specifically, Wanzhou, Liangping, and Zhongxian were identified as emission hotspots, with average annual agricultural carbon emissions of 0.106 million, 0.105 million, and 0.089 million tons, respectively; Whereas Nan'an, Jiulongpo, and Beibei were identified as emission cold spots, with average annual emissions of 6.996 thousand, 15.694 thousand, and 29.679 thousand tons, respectively. 3) The interpretable ARIMA-XGBoost prediction model performed well on an independent test set (R²=0.936). The agricultural carbon emissions were shifted from a generally stable state to a more widespread downward trend. Total emissions were projected to gradually decrease from 2.187 million to 1.788 million tons between 2024 and 2030. More significant influencing factors were determined as the rural employees, highway mileage, and gross product in agricultural carbon emissions. Yet there was no variation in the spatially differentiated distribution over counties. Multi-source data can offer information complementarity and reliability to assess regional agricultural carbon emissions. The findings can provide a scientific foundation for low-carbon sequestration and emission reduction. A valuable reference can also serve as the low carbon strategies in similar regions.

Conventional processing cannot fully modulate multiple biological activities of bioactive Polygonatum sibiricum polysaccharides using structural modifications and complex conformational transformations. The present study aims to clarify the different effects of steaming and fermentation—two representative processing techniques, including dynamic structural evolution of the medicinally valuable polysaccharides and the subsequent precise regulation of their bioactivities. Polysaccharides were extracted and then purified from fresh Polygonatum sibiricum, conventionally three-times-steamed Polygonatum sibiricum, and steamed-then-fermented Polygonatum sibiricum. The polysaccharide samples were designated as FPP, PPP, and FMP, respectively. An analytical platform was also employed: high-performance gel permeation chromatography (HPGPC) was used to determine molecular weight distributions; high-performance liquid chromatography (HPLC) with pre-column derivatization was used to quantify monosaccharide composition; Fourier transform infrared spectroscopy (FT-IR) was used to identify characteristic functional groups and conformational transitions. Zeta potential and dynamic light scattering analysis were used to assess colloidal stability and particle size uniformity, while scanning electron microscopy (SEM) and atomic force microscopy (AFM) were used to visualize morphological and nanostructure transformations, respectively. Antioxidant and hypoglycemic activities were evaluated through in vitro assays. Specifically, the 2,2-Diphenyl-1-picrylhydrazyl (DPPH) and 2,2′-Azino-bis(3-ethylbenzothiazoline-6-sulfonic acid) (ABTS) radical scavenging capacities were determined with α-amylase and α-glucosidase inhibitory kinetics. Steaming was used to alter the structural integrity of the polysaccharides, disrupt their native triple-helix conformation, modify the monosaccharide profile, shift molecular weight distribution toward higher ranges, and dramatically increase uronic acid content. Subsequently, fermentation acted as the precise biological modification, further fine-tuning monosaccharide compositional ratios using microbial enzymatic hydrolysis. Biotransformation raised the absolute Zeta potential, electrostatic repulsion and colloidal stability, and particle size distribution, indicating the remarkable homogeneity. These conformations were visually captured by microstructural observations. In SEM imagery, morphological transitions were observed: FPP displayed a smooth, continuous sheet-like film; Steaming induced regularly arranged, protrusive structures; Fermentation generated a porous network morphology, thereby increasing structural porosity and specific surface area. According to these morphological shifts in AFM images, nanoscale transformations occurred from flexible, worm-like chains of FPP to compact, spherical chains in both PPP and FMP. The average chain height increased markedly after steaming and then decreased after fermentation. Functionally, these structural modifications were closely correlated with enhanced bioactivities. In antioxidant evaluations, PPP exhibited the most potent DPPH radical scavenging capacity. Meanwhile, FMP presented robust ABTS radical scavenging activity compared with the PPP. In hypoglycemic potential, both PPP and FMP were more effectively inhibited α-amylase than native FPP. Crucially, FMP shared the optimal inhibitory effect against α-glucosidase among all tested samples. Steaming and fermentation served as effective strategies to modulate the chemical structure, spatial conformation, and microscopic morphology of Polygonatum sibiricum polysaccharides, thereby enhancing their antioxidant and hypoglycemic activities. The processing-induced structural modifications showed a strong correlation between specific structural features and physiological functions in plant polysaccharides. Consequently, this finding can also provide a solid theoretical foundation and practical guidance for the precise, high-value industrial application of Polygonatum sibiricum resources in the functional food using traditional Chinese medicine processing.

Ecosystem services supply and demand can coordinate the socioeconomic and environmental systems for the regional ecological security. Their spatiotemporal dynamics can be used to identify the complex interactions among services under anthropogenic disturbance. In this study, six ecosystem services were assessed in Chongqing from 2005 to 2023. The InVEST model and Spearman correlation analysis were employed to quantify carbon sequestration, grain production, soil conservation, water yield, habitat quality, as well as recreation and leisure. Furthermore, a systematic analysis was also conducted on the spatiotemporal dynamics of their supply-demand relationships and trade-offs/synergies over urbanization zoning. The results indicate that: (1) Although Chongqing maintained a surplus of ecosystem services, the margin of the surplus consistently narrowed over the study period. The supply-demand ratio was slight but persistently declined. High supply-demand ratios for carbon sequestration, water yield, soil conservation, habitat quality, as well as recreation and leisure were concentrated in the northeastern and southeastern areas of Chongqing, whereas the low ratios were clustered in the key districts of the main metropolitan area. High values of grain production were distributed in the peripheral counties of the metropolitan region, with deficits in the urban, the northeastern, and southeastern parts of Chongqing. (2) Urbanization exhibited a monocentric-polycentric structure with the west-east gradient, which was characterized by urban expansion and concomitant rural contraction. There was an outstanding spatial gradient in the supply and demand of ecosystem services. Among them, the demand increased progressively from rural to urban areas, while the supply exhibited the inverse pattern. The rural areas were positioned as primary provisioning zones, while the urban as persistent deficit zones. Supply-demand ratios declined for most services; Urban expansion zones transitioned from a balance to a deficit, with the notable exceptions of soil conservation and water yield, indicating the increased surpluses. (3) Static relationships among ecosystem services in rural areas were dominated by strong, stable trade-offs or synergies. In urban-rural transition zones, the weak synergies prevailed and fluctuated significantly, whereas urban expansion zones exhibited a trade-off between synergy dominance. Only five service pairs exhibited consistent trade-off or synergy relationships with the minimal temporal variation in urban areas. Habitat quality was persistently synergistic with recreation and leisure over all urbanization zones. While water yield consistently traded off with recreation and leisure. Most dynamic relationships among services were not statistically significant in rural and urban areas. There was a pronounced differentiation in the urban-rural transition zones, whereas the trade-offs and synergies were in urban expansion zones; Soil conservation and water yield remained synergistic over the period. The strength of the synergy increased in urbanization intensity, whereas habitat quality and water yield remained persistently in trade-off. (4) Differentiated strategies were proposed to realize the divergent patterns of ecosystem services supply-demand and their interactions in the urbanization zones. In urban areas, ecological potential should prioritize enhancing the ecological network connectivity. Urban expansion and urban-rural transition zones are required for the enforcement of ecological redlines, particularly with context-specific natural restoration and topographic constraints. In rural areas, ecotourism and carbon sink markets can be coupled with the urban-rural ecological compensation. Ecological assets can also be translated into tangible values. Differentiation of urbanization zones in the mountainous metropolitan can be used to examine the spatial heterogeneity of ecosystem service dynamics along the urban-rural gradient. This finding can provide a robust scientific foundation to inform urban spatial and sustainable ecosystems in Chongqing.

Maize is susceptible to rapid quality deterioration and fungal infection due to complex environmental fluctuations during "North-to-South Grain Transfer" strategies. However, conventional detection is often time-consuming, destructive, and labor-intensive under different storage and transportation environments. It is an urgent need to non-destructively and rapidly identify the mold ratio, and then continuously predict the quality index. In this study, a synchronous prediction was proposed for maize mold ratio and storage/transportation quality using advanced image processing and deep learning technologies. Maize samples with a controlled gradient mold ratio ranging from 0 to 12% were selected as the research objects. A systematic simulation was conducted on typical temperature and humidity environments of both waterway and overland transportation routes. Key quality indices of the maize were measured to quantify the deterioration rates in the simulated storage and transportation periods, including moisture content, fatty acid value, and electrical conductivity. Simultaneously, maize images were collected using a standard smartphone. Digital image processing was also integrated with the Vision Transformer (ViT) deep learning model and statistical modeling. The mold ratio was then detected to precisely predict the quality indices. The results indicated that the high-humidity environment of waterway transportation accelerated the deterioration of maize kernel quality (P<0.05). Specifically, the moisture content of the waterway samples rapidly exceeded the threshold of 14% in the national safe storage standard when the mold ratio reached 2%. In contrast, the moisture content of the overland transportation samples remained stable in the safe range of 12.207% to 12.772%. Furthermore, the fatty acid value and electrical conductivity increased by 57.070% and 38.357%, respectively, under waterway conditions, as the maize mold ratio increased progressively. These deterioration rates were higher than those under overland conditions, indicating the lower increases of 29.035% and 27.714%, respectively. In terms of the deep learning algorithms, the ViT architecture achieved exceptionally high precision in identifying moldy maize kernels, reaching an impressive overall accuracy of 99.00%. Subsequently, a Mean Absolute Error (MAE) of only 0.52% was achieved, indicating the accurate and reliable prediction of the overall maize mold ratio. Visual features were extracted and further screened to construct Multiple Linear Regression (MLR) models for quality evaluation. In the waterway samples, the coefficients of determination (R²) of the prediction models reached 0.859, 0.955, and 0.942, respectively, for moisture content, fatty acid value, and electrical conductivity. In the overland samples, the R² values of prediction models were 0.930 and 0.937, respectively, for the fatty acid value and electrical conductivity, indicating accurate prediction for the quality of maize during storage and transportation. In conclusion, the dynamic quality deterioration of moldy maize can provide a low-cost, easy-to-operate, and entirely non-destructive pathway for maize quality detection. This finding can also offer an effective and practical analytical tool to dynamically monitor quality and safety for risk early warning during the complex grain circulation.

Accurate perception of tomato inflorescences and flower states can often be required to support key operations in greenhouse tomato production, such as pollination and topping at the flowering and fruiting stage. However, inflorescences and flowers are characterized by small target size, dense spatial distribution, complex backgrounds, and frequent occlusion by leaves and stems in practical greenhouse environments. Single-stage detection models cannot simultaneously realize stable inflorescence localization and high-precision flower state recognition when operating on whole-plant images. In this study, a two-stage cascaded framework of visual perception was developed to detect tomato inflorescence and flower states using an improved YOLO version 11 network. A “spatial localization followed by fine-grained recognition” strategy was adopted to decompose the overall perception task into two sequential subtasks. In the first stage, an inflorescence detection model was constructed to enhance the baseline YOLO version eleven network with a Deformable Large Kernel Attention mechanism and a Dynamic Head detection structure. Deformable Large Kernel Attention Mechanism also employed large convolutional kernels with deformable convolution to capture long-range contextual information between inflorescences and adjacent peduncles, while morphological variations were also considered at different growth stages and plant structures. The dynamic head module incorporated scale- and spatial-aware feature modeling, thereby enabling the detector to robustly handle inflorescences of varying sizes for the complex regions, where inflorescences and leaves overlapped. The output precise spatial regions corresponded to inflorescences, which served as reliable regions of interest for subsequent analysis. In the second stage, a flower state recognition model was designed to operate exclusively within the inflorescence regions in the first stage. A lightweight backbone network, MobileNetV4, was adopted to reduce computational complexity for inference efficiency, while preserving feature representation. An Adaptive Task-aligned Focal Loss function was introduced to balance sample distribution among different flower developmental states. This loss function dynamically adjusted category weights, according to classification difficulty and sample frequency, thereby enhancing recognition performance for the minority and easily confused flower states under occlusion and cluttered backgrounds. Experiments were conducted on a greenhouse tomato image dataset at multiple growth stages and complex environments. In the inflorescence task, the first-stage model achieved substantial improvements in performance, compared with the baseline network, with the precision, recall, mean average precision at an intersection-over-union threshold of 0.5, and F1-score increasing by 4.02, 5.25, 8.49, and 4.66 percentage point, respectively. These results demonstrated that the attention and detection head enhancements significantly improved small-target detection stability in complex scenes. In the flower state recognition task, the second-stage model further improved precision, recall, mean average precision at the same threshold, and F1-score by 5.24, 2.97, 5.31, and 4.07 percentage point, respectively, indicating stronger identification for fine-grained flower state classification. The cascaded framework achieved an average processing speed of 38.4 frames per second under a single-input condition, fully meeting the real-time requirements of continuous greenhouse monitoring and online agricultural operations. The cascaded framework effectively balanced detection accuracy and computational efficiency to decouple spatial localization from fine-grained recognition. The reliable inflorescence and flower state recognition from whole-plant images can provide a practical visual perception for pollination, topping, and intelligent operations in greenhouse tomato production.

Quantitative evaluation standards are often required to accurately predict sprouting regeneration, particularly for cutting quality. However, the coppicing surface targets cannot be recognized in complex fields during Caragana korshinskii shrub coppicing in the arid regions of Northwest China. In this study, a quantitative evaluation was proposed for sprouting regeneration, according to the synergistic association between cutting morphologies and agronomic traits. Accurate recognition of coppicing surfaces was achieved in unstructured field environments. A segmentation network was constructed, named WoodGrainNet. Firstly, the global context modelling and target localization were enhanced via a semantic stream using a lightweight Transformer architecture. Secondly, a frequency-domain stream was incorporated with the Haar discrete wavelet transform to effectively suppress abiotic background interference for the texture representation of the targets. Simultaneously, a shape stream was combined with a differentiable Sobel operator. Explicit constraints were also applied to high-frequency gradient regions. Thereby, the adjacent cut boundaries were delineated to effectively alleviate the adhesion of dense targets. Three-stream features were synergistically simulated for the deep integration. The WoodGrainNet significantly improved the segmentation robustness and instance discrimination of the improved model in complex scenes, particularly at the level of underlying physical feature representation. Accurate segmentation was achieved to automatically extract a key geometric phenotypic indicator for coppicing quality—coppicing surface circularity (C). Accordingly, the coppicing quality grading and sprouting prediction were established after evaluation. The experimental results demonstrate that the better performance of WoodGrainNet was achieved to balance high accuracy and real-time processing, with a mean Intersection over Union (mIoU) of 86.99% and an inference speed of 51.78 frames/s. The performance was significantly superior to mainstream networks, such as DeepLabV3+, effectively recognizing tiny coppicing targets. In terms of agronomic analysis, statistical results revealed that there was a significant positive correlation between the morphological quality of the coppicing surface and the sprouting potential of lateral branches. Notably, the coefficient of determination (R²) between the coppicing surface circularity (C) and the number of lateral branch sprouts reached 0.764 at the 5th week (N). The circularity served as an important morphological indicator to evaluate coppicing quality and sprouting regeneration. Field tests were conducted to verify its feasibility for engineering applications. The improved model was deployed on a mobile intelligent system. A discrimination accuracy of 90.8% was achieved for coppicing quality grades under mobile working conditions. Sprouting prediction trend was highly consistent with the measured ones, indicating its potential to replace manual inspection and subjective empirical judgment. The pixel-level phenotypic analysis of the coppicing surface was effectively transformed to predict the single-plant regeneration. The finding can provide a theoretical basis and technical support for the quality evaluation, parameter monitoring, and precise detection of ecological shrub forests in arid regions.