The Brazilian Amazon has been endangered by agro-extractivism, a development model characterized by the expansion of the agricultural frontier to produce raw commodities embedded in power-asymmetrical commodity chains. Recently, the socio-biodiversity economy has emerged as an alternative development model, aimed at reconciling local development with nature conservation. While the environmental and social contrasts between the two models are well documented, the commercial dimension of the socio-biodiversity economy remains underexplored. These two models are typically approached as separate systems, yet their coexistence and interaction within the same actors and across interconnected value chains has not been empirically examined. In this paper, we provide a qualitative analysis of dynamics and upgrading mechanisms in two cocoa value chains in the Brazilian Amazon: raw (bulk) and fine-flavor (fino) cocoa. Through this comparison, we examine how each chain differs in terms of commercial relations and how socio-biodiversity economy and agro-extractivism interact within the commercial sphere. The research took place in three municipalities along the Transamazon highway between March and September 2024. Data were gathered through semi-structured interviews with cocoa producers, buyers, and supporting actors such as NGOs, companies, and public agencies, complemented by participant observation and participation in cocoa-related events. Findings suggest that the bulk and fino cocoa chains present distinct commercial configurations, the former displaying agro-extractivist patterns, the latter consistent with the socio-biodiversity economy. Cocoa production in the region is part of an emergent socio-biodiversity economy that remains commercially embedded in agro-extractivism. Notably, farmers engage in both chains as part of their livelihood strategies, while relying predominantly on the bulk trade. We argue that the fino cocoa chain may represent a pathway for transforming commercial relations in the region, provided that the structural conditions sustaining agro-extractivist patterns in the bulk chain are addressed. More broadly, we show that production-level transitions toward sustainable farming do not automatically translate into the transformation of commercial relations, and call for greater analytical attention to the commercial dimension of socio-biodiversity economies.

In traditional time-series image prediction tasks, both accuracy and image quality tend to deteriorate as the prediction horizon extends. To address this challenge in Shiitake mushroom fruiting body growth prediction, this study selected Shiitake mushroom strain No. 509, cultivated by the Shanghai Academy of Agricultural Sciences, as the experimental subject and proposed an enhanced model, VMRNN-DMSA, based on the Vision Mamba RNN Depth architecture. This model integrates a skip-connection mechanism with a Max Feature Map module to effectively filter and fuse features, enhancing feature representation and prediction accuracy. Additionally, a Spatial Attention Mechanism was introduced to strengthen the perception of key regions and improve spatial modeling. Furthermore, an Adaptive Kernel Convolution module with irregular context convolution kernels was incorporated to extract fine-grained local features and enhance visual quality. A weighted loss function was used to balance pixel-level accuracy, structural fidelity, and perceptual quality. This function combines Mean Squared Error Loss, Multi-Scale Structural Similarity, and Perceptual Loss. Experimental results showed that the proposed method achieved an MSE of 39.4255, an SSIM of 0.8579, and a PSNR of 22.0774. Compared with baseline models, MSE decreased by 29.05%, while SSIM and PSNR increased by 19.34% and 14.52%, respectively. These results indicate that VMRNN-DMSA significantly improves both prediction accuracy and image quality in long-term forecasting tasks, providing a reliable reference for the growth prediction of other edible fungi.

Artificial intelligence (AI)-supported agricultural disease detection has become increasingly important for addressing global food security challenges. In this study, a hybrid meta-heuristic optimization-based feature selection approach is proposed for the detection of peacock eye disease (Venturia oleaginea) on olive leaves. The proposed method combines Artificial Rabbit Optimization (ARO) and Genetic Algorithm (GA) strategies to balance global exploration and local exploitation during feature selection. Comprehensive experiments conducted on a dataset of 954 olive leaf images demonstrate that the proposed approach achieves an F1-score of 99.7% while reducing the feature dimensionality by 95%, selecting only 100 features from ResNet101. Statistical analysis confirms that the method significantly outperforms standalone GA and ARO approaches (p<0.05, paired t-tests), demonstrating superior long-term convergence behavior and a 47–56% reduction in performance variance across repeated runs. Compared to existing approaches in the literature, the proposed method attains competitive or superior accuracy with substantially fewer features, indicating a marked reduction in computational complexity. These results suggest that the proposed hybrid feature selection framework has strong potential for deployment in resource-constrained agricultural monitoring scenarios, where efficient inference and reduced model complexity are critical.

Oilseed production in the Canadian Prairies is highly sensitive to interacting climatic, soil, and landscape constraints, which has important implications for long-term agricultural sustainability under climate change. Canola and flax are economically significant Prairie oilseeds with distinct sensitivities to temperature and moisture variability; however, region-wide, crop-specific suitability assessments remain limited. In this study, we developed a machine-learning-enhanced Land Suitability Rating System (LSRS) framework to evaluate both historical and projected suitability for canola and flax across the Prairie agricultural region. Random Forest regression models were trained using spatial crop-density data in combination with observed climate normals and updated soil and terrain variables. Variable-importance scores were used to derive empirical climate–soil weighting, resulting in climate contributions of 70% for canola and 75% for flax. Model performance demonstrated strong internal agreement with observed spatial patterns (R2 ≈ 0.99). Canola suitability was primarily associated with mid- to late-season precipitation and maximum temperatures, whereas flax suitability was more strongly influenced by growing-season minimum temperatures. Future suitability was simulated using CanDCS-M6 downscaled CMIP6 projections under SSP2-4.5, SSP3-7.0, and SSP5-8.5. Projected warming and regionally variable precipitation changes produced spatially heterogeneous shifts in suitability, including localized gains in northern areas and increased climatic risk across parts of the southern Prairies under higher-emission scenarios. The proposed framework integrates empirical machine-learning insights with an interpretable suitability rating system, providing a scalable and policy-relevant tool to support climate-informed adaptation and sustainable oilseed production planning.

Water scarcity, poor soil, and low water and fertilizer utilization are major challenges on agricultural production in soil structurethe tableland region of China’s Loess Plateau. Optimizing tillage patterns and improving soil nutrient status can improve crop yield and water and fertilizer utilization efficiency. A field trial was initiated in 2005 to assess the impacts of various tillage and fertilization practices on dryland agricultural production. A split-plot design was used, with tillage practices (traditional tillage and no tillage) as the main plot treatment and fertilization management (no fertilization (CK), mineral nitrogen (N), mineral phosphorus (P), composted cow manure (M), a combination of mineral nitrogen and phosphorus (NP), and a combination of mineral nitrogen, phosphorus, and composted cow manure (NMP)) as the split-plot treatment. An experiment was conducted from 2022 to 2024. The NMP treatment resulted in lower bulk density, a lower three-soil-phase index, and higher mean weight diameter, geometric mean diameter, soil water storage, total nitrogen, and soil organic matter than the CK. In the no-tillage treatment, the crop roots were less effective at extracting water from the deep subsoil, leading to greater residual moisture at depth (especially in the 120–200 cm soil layer) and lower yield and water use efficiency than in traditional tillage. The grain yield and water use efficiency were 9.2% and 8.4% lower, respectively, under no tillage than under traditional tillage. The NMP under traditional tillage exhibited lower surface soil bulk density and a higher three-soilphase index, mean weight diameter, geometric mean diameter, soil organic matter, total nitrogen, and water use efficiency than the unfertilized control, resulting in higher grain yields. The NMP under traditional tillage is recommended to increase grain yield and water use efficiency in wheat–maize rotation systems in the tableland region of China’s Loess Plateau. Future studies should analyze the deep root architecture and the effect of weed competition on soil water depletion.

Freeze–thaw cycles on the Qinghai–Tibetan Plateau inhibit microbial activity and challenge silage preservation. This paper aimed to elucidate how an indigenous, freeze–thaw-resistant Lactobacillus plantarum strain (LP160) improves oat silage quality under such stress. Oats were ensiled for 60 days under constant 20 °C (t) or freeze–thaw cycles (12 h at 20 °C/−5 °C; s) with or without LP160 inoculation. Samples after ensiling and 5-day aerobic exposure were analyzed for fermentation parameters, nutrients, microbiome, and non-targeted metabolomics using liquid chromatography–tandem mass spectrometry (LC-MS/MS). LP160 inoculation improved silage quality, as shown by the lower pH, ammoniacal nitrogen, neutral detergent fiber, acid detergent fiber contents as well as the greater amount of lactic acid. Key findings demonstrated that LP160 inoculation significantly enhanced Lactobacillus dominance, effectively curbed the growth of detrimental bacteria like Mucor, and regulated the microbial structure. During the aerobic exposure phase, the microbial community structures and successions varied under different temperature treatments. When inoculated under freeze–thaw conditions, the genus Bacillus increased, while Paenibacillus was not impeded. A total of 943 metabolites were identified, predominantly comprising amino acids, fatty acids, and the like. The expressions of metabolites with antioxidant and antibacterial properties were upregulated with LP160 inoculation. This led to the inhibition of protein hydrolysis and a reduction in ammonia–nitrogen production. The results of correlation analysis indicated that inoculating LP160 suppressed the proliferation of Mucor and enhanced the abundance of Torulaspora; meanwhile, the expression of L-palmitoylcarnitine involved in the fatty acid degradation pathway and fatty acid metabolism pathway was inhibited along with the generation of ammonia–nitrogen. Consequently, the degradation of fatty acids and proteins was restrained. The results of this paper provided new insights into the silage under freeze–thaw conditions.

The behavior of phosphorus (P) fertilizers in soil is governed not only by fertilizer solubility, but also by P mobility and vertical redistribution within the soil profile under contrasting water regime. This study aimed to investigate the combined effects of water regime, fertilizer type, and soil properties on the vertical redistribution of ammonium acetate–lactate extractable phosphorus (P-AL) in the surface soil layer under controlled pot conditions. Experiments were conducted using three soils with contrasting chemical properties: AC-LO (acidic loam, pH 5.9), NE-CL (neutral clay loam, pH 6.8), and AL-SL (alkaline sandy loam, pH 8.0). Four simulated rainfall regimes were applied at a constant rate of 25 mm day−1, corresponding to cumulative water inputs of 0 mm (W0), 50 mm (W50), 100 mm (W100), and 150 mm (W150). Fertilizer treatments included an unfertilized control (NF), a liquid NP 4–18 fertilizer applied at a low dose (L1), a liquid NP 4–18 fertilizer applied at a high dose (L2), and a solid NPK 15–15–15 fertilizer (S). Water regime exerted the strongest control on P mobility, with P-AL increasing by approximately 40–60% from W0 to W150, depending on soil type. In AC-LO, strong P fixation under low moisture minimized differences among fertilizer treatments, whereas under higher moisture (W100–W150), liquid fertilizers—particularly L2—resulted in P-AL levels approximately 10–30% higher than those of the solid fertilizer. In NE-CL, P mobility was moderate and, under W100–W150, L2 produced P-AL values approximately 10–15% higher than the solid fertilizer, promoting a more uniform P redistribution within the 2–8 cm layer. In AL-SL, the response under wet conditions depended on the water regime: at W100, L2 generated P-AL values comparable to the solid fertilizer, whereas at W150, L2 increased P-AL by approximately 11% relative to the solid form. Overall, the results indicate that soil chemical properties primarily regulate the extent of phosphorus redistribution, while water regime controls its intensity and fertilizer form influences the initial spatial configuration of P within the surface soil layer. The findings provide mechanistic insight into short-range phosphorus transport in soil, without allowing direct inferences regarding agronomic efficiency or crop response.

Climate change exerts an increasing impact on the health and resilience of honey bees through a combination of rising temperatures, altered precipitation patterns, and intensified parasitic and infectious pressure. The present study aims to analyze climatic conditions in Bulgaria for the period 2021–2024 and to evaluate the results of a national survey conducted among beekeepers, focusing on winter colony losses during the 2023/2024 season and the feeding strategies applied. The survey was carried out in 2024 among 70 beekeepers from 20 administrative regions of the country, managing a total of 8935 bee colonies. The data were analyzed using descriptive statistics and stratified by region. The reported average winter mortality was 2.22% (198 colonies), with pronounced territorial variability. The most frequently indicated self-reported probable cause of losses was bee diseases, with varroosis identified as the dominant factor. Analysis of management practices revealed widespread application of combined feeding schemes based on plant-derived supplementary feeds, primarily administered in spring (March–April) and late summer (August–September). The obtained results differ from published national data for 2024, according to which total colony losses reached 16.3%, while losses associated with mortality or severe demographic collapse accounted for 11.6%. Despite the limitations inherent to the survey-based approach and self-reported data, the results suggest that integrated management combining parasite control with targeted nutritional support through the use of Bulgarian herbal supplementary feeds may coincide with the winter survival patterns reported within the surveyed sample.

To address the problems of low picking efficiency, high pot-breaking rate, and poor stability in the pick-up and drop mechanisms of existing automatic vegetable transplanters, this paper describes the design of a whole-row mechanical two-claw seedling-picking mechanism. A “reciprocating common-rail”-type seedling picking trajectory is introduced. A whole-row mechanical two-claw seedling-picking mechanism composed of a planetary gear-linkage mechanism and a gripping mechanism is designed. The coordination method between seedling feeding and seedling picking is determined, and the parameters of the supporting seedling-feeding mechanism are established, completing the design and modelling of key parameters. Through single-factor simulation experiments, the optimal combination of key parameter levels for the seedling-picking claws was selected. A three-factor three-level orthogonal experiment was conducted to determine the optimal combination of working parameters. Seedling-picking performance tests were carried out on peppers, tomatoes, and broccoli. The test results meet relevant national standards, indicating that the pick-up and drop mechanism exhibits strong stability and good versatility, fulfilling the design requirements. This study lays a solid foundation for the design of seedling-picking mechanisms in automatic transplanters.

Enhancing the livelihood resilience of smallholder farmers has become a critical challenge in China’s contemporary agricultural development strategy. Agricultural machinery socialization services represent an important policy measure for facilitating smallholder farmers’ integration into modern agriculture and alleviating practical development constraints; however, as a substantial adjustment to farmer livelihood activities, such services may also disrupt smallholder farmers’ existing livelihood equilibria. Using survey data from smallholder farmers in the major corn-producing regions of Northeast China, this study examines the effects of agricultural machinery socialization services on smallholders’ livelihood resilience and explores the underlying mechanisms. The results show that both the breadth and depth of agricultural machinery socialization services significantly enhance smallholders’ livelihood resilience. These effects operate mainly through two pathways: an empowerment mechanism driven by farmland scale management and the professional division of labor in agriculture, and a capacity expansion mechanism driven by the extension and application of agricultural technologies and the development of social networks. Moreover, the influence of agricultural machinery socialization services on smallholders’ livelihood resilience is positively moderated by both internal perceived value and external policy incentives. Heterogeneity analysis further indicates that these services exert stronger effects on smallholder farmers’ buffering and learning capacities than on self-organizing capacity, with more pronounced impacts in plains areas than in hilly and mountainous regions. Accordingly, policy efforts should focus on the core needs of smallholder farmers by accelerating the development of a diversified, differentiated, and multi-tiered agricultural machinery socialization service system, expanding service coverage, improving service quality, and refining service mechanisms to promote sustained improvements in smallholders’ livelihood resilience.