Search Results (790)

In karst regions, sugarcane mapping faces challenges from fragmented fields, undulating terrain, spectral confusion, and persistent cloud cover, which limit traditional optical remote sensing. To address these issues, we propose a fine-scale extraction framework that integrates Sentinel-2 optical and Sentinel-1 synthetic aperture radar (SAR) imagery through image-level fusion, and introduces a UNet-DFH network with a Multi-Scale Edge Fusion (MSEF) module and an Attention-Deformable Fusion Module (ADFM). This study makes three core contributions: (1) we construct a dedicated optical–SAR collaborative sugarcane extraction dataset for typical karst regions, alleviating the scarcity of multimodal labeled samples; (2) we propose the UNet-DFH network, where MSEF enhances boundary preservation and topological detail in shallow decoding stages, while ADFM improves robustness to geometric deformation and local misalignment in deep semantic stages; (3) we demonstrate that the joint mechanism of edge-preserving filtering and deformable adaptation yields a synergistic effect in addressing the precision–recall trade-off. Experiments in a typical karst area of Guangxi, China, demonstrate that optical–SAR fusion achieves an IoU of 80.08% and an OA of 92.09% during the sugar accumulation and maturity stage. During the more challenging tillering stage, UNet-DFH maintains relatively stable performance under optical-only conditions, with an IoU of 72.98%, Recall of 82.78%, and OA of 92.12%. Moreover, optical–SAR fusion improves Recall by 5.5 percentage points over optical-only inputs (from 83.54% to 89.04%), while Precision exhibits a moderate decrease from 91.89% to 88.84%, reflecting the expected trade-off associated with speckle noise. These results confirm the complementary value of multimodal data and the effectiveness of the proposed modules in preserving fragmented plot boundaries and improving segmentation performance in complex karst terrain. The framework offers a promising approach for high-precision crop mapping in the studied karst agricultural landscape. Full article

Pests and diseases are key biological stress factors affecting crop yield and quality. Semantic segmentation enables pixel-level localization and severity characterization, but its performance and generalization are constrained by the high cost of high-quality pixel-level annotations, limited labeled samples, and class imbalance in agricultural datasets. We propose AgriUFM, an unconditional flow-matching framework for joint image–mask generation in agricultural pest and disease scenarios. By learning a unified continuous probability flow over the joint distribution, the framework is designed to promote structural co-evolution and spatial consistency between generated RGB images and masks. Across four evaluated datasets, AgriUFM achieved lower FID and rFID than the evaluated GAN- and diffusion-based comparators, whereas IS performance was dataset-dependent. Within the evaluated ablation configurations, uniform time sampling with 25 sampling steps and the midpoint ODE solver yielded the most favourable observed quality–efficiency trade-off. Under the held-out test protocol, the joint UFM strategy achieved higher image–mask correspondence than the M2I and I2M conditional variants. In the evaluated downstream settings, AgriUFM-generated augmentation improved MIoU and PA for U-Net and TransUNet. These results indicate that joint distribution modelling is a promising approach for structurally coherent generative augmentation in the agricultural imaging tasks studied. Full article

This study directly compares a photovoltaic (PV)-powered vapor-compression chiller with a solar-thermal-driven absorption chiller for localized cooling of the tomato crop zone in a 1536 m² smart greenhouse under a hot-arid climate. The principal contribution is a controlled system-level comparison of two solar-cooling pathways under the same greenhouse load, solar-aperture area, terminal equipment, rated cooling capacity, and crop-zone temperature-control constraints. The previously validated greenhouse model was transitioned from EnergyPlus 8.9 to Version 23.1, after which the two alternative plants were connected to the same base model. Base-case annual simulations produced nearly identical chiller cooling energy (1669.3 and 1668.9 MWh) and was only 4 and 5 h above 28 °C. The PV-powered system required 101.6 MWh of net grid electricity, whereas the absorption system used 202.3 MWh of electricity and 253.2 MWh of natural gas and achieved an 84.23% solar fraction. Static operational primary energy was 331.2 and 912.7 MWhPE, respectively; HSDH28 was 0.50 and 0.81 °C·h; and peak grid import was 113.46 and 63.61 kW. The absorption case additionally required 10,103.6 m³/yr of cooling-tower makeup water. Storage/EMS sensitivity changed the absorption solar fraction from 58.17% to 88.30% and natural-gas use from 187.7 to 674.0 MWh/yr without materially changing cooling service. Matched 50–100 W/m² daytime latent-load sensitivity increased annual cooling by 14.7–28.8%. At the 100 W/m² bound, HSDH28 increased to 49.32 °C·h for PV and 8.06 °C·h for absorption, while the principal energy–infrastructure trade-off remained: static primary energy was 712.4 versus 1354.2 MWhPE and peak grid import was 137.46 versus 63.96 kW. A bounded hourly primary-energy-factor stress test did not reverse the technology ranking, and balanced TOPSIS scores were 0.766 for PV and 0.234 for absorption. The results show that PV vapor compression minimizes operational primary energy and cooling-water use, whereas solar-thermal absorption reduces electrical peak demand and shows greater thermal-control resilience at the highest tested latent-load bound. Full article

Oaxaca is one of the most biocultural diverse regions in Mexico. Although the white-nosed coati (Nasua narica L.; Procyonidae, Mammalia) is widely used by Indigenous and rural communities throughout the Neotropics, its role within subsistence hunting, traditional food systems, and local management practices in Oaxaca has remained undocumented. This study analyzes the biocultural significance of N. narica hunting and consumption among four Indigenous groups in northern Oaxaca. Data were collected through ethnographic techniques, i.e., semi-structured interviews with locals, ethnozoological field trips, and participatory workshops conducted with Zoque, Zapotec, Chinantec, and Mazatec communities. In addition, an extensive literature review was carried out to contextualize and compare the field data. N. narica hunting is predominantly diurnal and collective, frequently involving dogs (Canis lupus familiaris) and horses (Equus ferus caballus), and fulfills at least three functions, including food provisioning, crop protection, and limited wild meat trade. N. narica meat is incorporated into traditional diet and prepared in at least five culturally distinct culinary forms. The use of N. narica reflects complex ethnoecological knowledge and long-term human–fauna interactions embedded within Indigenous livelihoods. These findings underscore the relevance of a biocultural ethnoecological approach for understanding subsistence hunting, wild meat use, and rural livelihoods in Mesoamerica. Full article

Organic fertilization is a key strategy for improving soil structure and fertility in China’s Vertisols, yet the trade-offs among soil quality enhancement, grain yield performance, and nutrient use efficiency under different organic amendment regimes remain insufficiently elucidated. Based on a unique 43-year field fertilization experiment, this study systematically evaluated the effects of long-term chemical fertilization (NPK) alone, low-dose (NPKLS) and high-dose straw incorporation (NPKHS), combined chemical fertilizer with cattle manure (NPKCM), and pig manure (NPKPM) fertilization on soil physical, chemical properties, crop yields and plant nutrient utilization efficiency. The results showed that NPKCM and NPKPM significantly improved soil physical properties by reducing soil bulk density, improving soil pore structure, and enhancing soil water retention capacity and saturated hydraulic conductivity. Although long-term manure application led to slight soil salt accumulation, the rate of accumulation remained substantially lower than that associated with commercial organic fertilizers and did not approach the crop salinity damage threshold, suggesting low ecological risk. Compared with NPK treatment, manure amendment effectively counteracted soil acidification induced by prolonged chemical fertilization, while also significantly increasing soil total phosphorus and available phosphorus content, and elevated the proportion of active phosphorus (PAC). The improved soil phosphorus activation capacity and comprehensive soil quality further contributed to substantial increases in wheat grain yield under NPKCM and NPKPM treatments. Despite these agronomic benefits, the additional nitrogen and phosphorus inputs from manure resulted in soil nutrient surpluses, which considerably reduced nitrogen and phosphorus partial factor productivity as well as agronomic efficiency. In contrast, straw incorporation treatments (NPKLS, NPKHS) sustained stable crop yield without notable declines in nutrient efficiency, positioning them as a greener and more sustainable approach to balancing grain production with resource use efficiency. These findings highlight the need to integrate nutrient credits from manure into fertilization program. Given the 43-year evidence, fertilization strategy should consider not only the nutrients supplied by manure but also the quantities exported through harvested products, with adjustments based on annual soil fertility analyses. Such nutrient budgeting is essential to maximize fertilizer use efficiency, prevent excessive phosphorus accumulation, and maintain balanced soil fertility over time. Full article

No-till precision seeding is an important component of conservation tillage, but stable operation remains constrained by compacted undisturbed soil, dense crop residues, and uneven field surfaces. This review examines the evolution of no-till precision seeding equipment from mechanical soil–residue interaction to cyber–physical closed-loop regulation. It first summarizes how soil resistance and residue interference affect furrow opening, seed placement, and seed–soil contact. It then examines the development of residue-management, furrow-opening, covering, and compaction mechanisms, highlighting the transition from passive structural optimization toward active and adaptive operation. Advances in multi-source sensing, electric-drive metering, downforce control, and vibration suppression are further reviewed as enabling technologies for improving seeding stability under variable and high-speed conditions. Despite these advances, persistent trade-offs remain among residue-removal capacity, soil disturbance, energy demand, component durability, system complexity, and operational stability. Emerging approaches based on digital twins, adaptive damping, and cooperative autonomous systems may support further improvements, but their practical implementation still requires robust field performance and effective system integration. Overall, no-till seeding equipment is progressing toward perception-assisted and closed-loop intelligent regulation while continuing to face important mechanical and implementation challenges. Full article

Immune-mediated inflammatory diseases (IMIDs) arise from interactions among genetic susceptibility, epithelial barrier function, microbiota, diet, and other environmental exposures. Modern diets influence mucosal immunity not only through fibre intake, food processing, and microbiota composition, but also through a less explored exposure layer: plant-derived molecules with potential immune activity. Crop breeding, intensive agriculture, global trade, gluten-free substitutes, and plant-based food technologies have changed the spectrum, dose, concentration, and matrix in which plant defence proteins, antinutritional factors, endogenous toxicants, and novel plant antigens reach the intestinal surface. In this structured, hypothesis-generating narrative review, we propose dietary adjuvanticity as a mechanistic framework for considering how selected food-derived molecules may amplify mucosal immune responsiveness, modify antigen presentation, disturb barrier function, or lower tolerance thresholds without necessarily acting as classical autoantigens. The framework differs from general food-derived immunomodulation, nutritional exposomics, and diet-microbiota-host interaction models by focusing specifically on adjuvant-like immune amplification at the intestinal mucosa. The ASIA concept is used only in Shoenfeld’s functional sense, as an analogy for exogenous immune amplification through innate activation, danger signalling, bystander activation, epitope spreading, and loss of tolerance in susceptible hosts; it is not applied as a dietary diagnosis. Wheat amylase-trypsin inhibitors, gluten epitopes, lectins, potato glycoalkaloids, saponins, quinoa prolamins, emerging legume proteins, L-canavanine, and tolerance-promoting plant substrates are discussed with explicit separation of established clinical evidence, strong mechanistic evidence, preclinical/ex vivo evidence, and speculative disease-modifier hypotheses. Overall, plant-derived exposures are best interpreted as potential modifiers within the IMID exposome, not as primary causes of autoimmunity. Testing this model will require defined exposures, food-matrix and processing studies, biomarkers of barrier and immune activation, patient stratification, and controlled human studies. Full article

Cacao (Theobroma cacao L.) is a crop of great economic importance in Peru; however, the presence of cadmium (Cd) in cacao-growing soils limits its production and international trade. The objective of this study was to evaluate the effect of Solanum nigrum (black nightshade) and Bidens pilosa (cobbler’s pegs) on Cd removal in cacao-producing areas of northeastern Peru. The research was conducted using a completely randomized block design (CRBD) with two factors: the phytoremediation species and planting distance (30, 50, and 70 cm), in four production areas: La Concordia 01, La Concordia 02, La Lluhuana, and La Chorrera. The reduction in Cd in soil, roots, and cacao beans was evaluated, as well as the accumulation of the metal in leaves (30, 60, 120, and 150 days) and roots (120 and 150 days) of the phytoextracting species, in addition to the bioconcentration factor (BCF) and translocation factor (TF). Cd reductions were recorded in the soil, with a maximum decrease from 0.81 to 0.03 mg kg⁻¹ (La Chorrera). In roots, the greatest reduction was from 1.79 to 0.69 mg kg⁻¹ (La Concordia 02), while in beans it was from 1.65 to 1.08 mg kg⁻¹ (La Chorrera). BCF values ranged from 1.12 to 6.97, with TF > 1, showing differences among the evaluated sites. Overall, the study findings demonstrate that the phytoextractive response was more related to site conditions than to the species used or the planting distance. Full article

Sweet cherry (Prunus avium L.) is a high-value horticultural crop; however, winter freezing injury significantly limits its introduction and stable production in cold-temperate regions. In this study, annual shoots of 16 major sweet cherry cultivars were collected during the dormancy phase and subjected to a simulated low-temperature gradient. Eight physiological indicators, namely, relative electrolyte conductivity (REC), malondialdehyde (MDA) content, osmoregulatory substances, and antioxidant enzyme activities, were systematically measured along with the poststress recovery growth percentage (RP). The semilethal temperature (LT₅₀) was calculated using a logistic equation, and a multidimensional comprehensive evaluation system for cold tolerance was constructed using the membership function method, principal component analysis (PCA), and cluster analysis. The results indicated that low-temperature stress significantly induced membrane lipid peroxidation and osmotic compensation in the shoots. PCA revealed four principal components—osmoregulation potential, cell membrane damage threshold, cold-protective protein synthesis, and membrane stability—with a cumulative variance contribution rate of 79.47%. Correlation analysis revealed no significant correlation between LT₅₀ (reflecting thermodynamic survival capacity) and the recovery growth percentage (reflecting poststress regenerative capacity), suggesting that “passive endurance” and “active recovery” in sweet cherries are two relatively independent physiological processes. The comprehensive evaluation model classified the 16 cultivars into four cold-tolerance tiers: High Tolerance (Russia 8, Reid, Pacific Red, and Brooks); Moderate-High Tolerance (Tieton, Jiahong, Sandra Rose, and Rivedel); Moderate-Low Tolerance (Luyu, Rocket, Tamara, Lapins, Frisco, and Taisho-nishiki); and Sensitive (Summit and Kordia). The four-dimensional evaluation model developed in this study provides a scientific basis for cultivar selection in cold regions and offers a theoretical reference for the trade-off of traits in future molecular breeding for cold resistance in cherries. Full article

Wild arrowhead (Sagittaria trifolia L.) often occurs as isolated plants or compact clusters in paddy fields, yet these states are difficult to distinguish in unmanned aerial vehicle (UAV) imagery because they share similar color, texture, and leaf morphology. This study presents a two-stage framework in which an unchanged YOLOv8n detector localizes candidate targets and a dedicated Patch-cls network refines the single- or multiple-plant label. The classifier combines multi-level features, local multi-scale enhancement, and channel attention; a GhostConv variant is also evaluated to examine the efficiency trade-off. Annotation-box and detector-generated-box results are reported separately, followed by a complete-system evaluation that retains missed targets, false positives, duplicate detections, localization errors, and classification errors. Across three random seeds, the proposed Patch-cls obtained 94.00 ± 0.34% accuracy, 83.81 ± 1.19% Macro-F1, and 73.18 ± 3.91% multiple-class Recall. In the complete test pipeline, Macro-F1 increased from 0.5459 to 0.5539 and multiple-class F1 from 0.4224 to 0.4384, while mean average precision at an intersection over union (IoU) of 0.50 (mAP50) decreased slightly from 0.7023 to 0.7016. The optimized pipeline achieved 88.89 frames per second (FPS) on an NVIDIA RTX A4000 with approximately 1.62 GB peak allocated graphics processing unit (GPU) memory. The results indicate that Patch-cls can improve category balance under detector-generated crops, although the overall gain is modest and does not replace the need for stronger localization and dense-target separation. Full article

Improper disposal of coffee-processing by-products can cause environmental pollution, greenhouse gas emissions, and resource loss, whereas their reuse in coffee plantations may support sustainable production. This review systematically examines the material properties, stabilization methods, field application pathways, agronomic effects, quality responses, and environmental risks of coffee-pulp-type by-products in cultivation. Relevant studies published up to June 2026 were retrieved from Web of Science, Scopus, ScienceDirect, SpringerLink, Google Scholar, and CNKI and qualitatively synthesized along the soil–plant–quality continuum. Current evidence suggests that properly stabilized materials, applied at appropriate rates, can improve soil organic matter, structure, water and nutrient retention, microbial activity, plant growth, photosynthesis, and crop yield in plantations. They may also indirectly influence green bean quality by regulating sugars, amino acids, chlorogenic acids, and caffeine. However, these effects depend strongly on material properties, maturity, application rate, coffee genotype, soil and climatic conditions, and management practices. Excessive or insufficiently decomposed materials may cause soil acidification, phytotoxicity, oxygen depletion, nutrient imbalance, and yield–quality trade-offs. Overall, recycling within plantations can turn processing waste into farm inputs, reinforce on-farm carbon and nutrient cycles, ease disposal burdens, and advance BCG and wider circular-economy principles in practice. Full article

As global warming raises ambient temperatures, plant growth and productivity are being profoundly affected. Although the impacts of extreme heat stress have received extensive attention, the developmental consequences of moderately elevated temperatures remain less understood. As sessile organisms, plants rely on developmental plasticity to adjust their growth and development in response to warm environments. Understanding how plants sense temperature and convert this signal into developmental outputs is crucial for determining their adaptive strategies to climate change and for applying this knowledge to breed climate-resilient crops. Here, we review current advances in understanding how moderately elevated temperatures regulate developmental plasticity throughout the plant life cycle, including the perception of moderate warmth, the resulting developmental plasticity during vegetative and reproductive growth, and the coordination and trade-offs between these two phases. We also highlight major unanswered questions in this field and propose strategies for manipulating developmental plasticity to breed climate-resilient crops. Full article

Recent advances in Earth observation and machine learning have significantly enhanced the capacity to monitor agricultural systems and terrestrial vegetation across spatial and temporal scales. This editorial synthesizes the contributions of eleven studies published in the Special Issue ‘Machine Learning for Applications in Agriculture and Vegetation Using Remote Sensing’. These contributions highlight emerging methodological trends, as well as persistent challenges in remote sensing for agriculture and vegetation measurement and monitoring, and reflect the growing dominance of deep learning in high-resolution mapping and segmentation. An increasing importance of multi-sensor data fusion, integrating multi- and hyperspectral satellites, UAV, and environmental data, is found. Deep learning is emerging as an effective approach for retrieving key biophysical parameters such as biomass, crop height, and yield. The collected studies also emphasize the critical role of sensor characteristics and scale, particularly the trade-offs between spectral, spatial, and temporal resolution in vegetation analysis. Despite notable progress, several limitations remain. Model transferability across regions and sensors is still constrained and multi-source data integration often lacks standardized frameworks. Empirical approaches still dominate the retrieval of biophysical variables, limiting robustness and physical interpretability. The contributions also reveal a persistent gap between high-resolution, small-scale analyses and their scalability to regional or global applications. Therefore, this editorial argues for a transition towards hybrid modeling approaches that combine physical knowledge with data-driven machine learning methods, the adoption of formal data assimilation frameworks for multi-source integration, and the development of scalable and uncertainty-aware workflows. The broader scientific context of the contributions is given by providing a critical perspective on the current state of the field and outlining the key research directions necessary to advance remote sensing in agriculture and ecosystem monitoring. Full article

To address inaccurate weed segmentation under crop overlap, occlusion, and complex field backgrounds, this study developed a combined method integrating DViT-YOLOv8-seg with confidence-guided SLIC voting. The dataset contained 1872 field images (800 × 600 pixels) of Guangzhou soft-stem lettuce and four common weed species: Eleusine indica, Digitaria sanguinalis, Portulaca oleracea, and Amaranthus blitum. All weed species were merged into one weed class, while lettuce, soil, and other field regions were treated as non-weed. Real-ESRGAN and data augmentation enhanced the training samples; Dual-ViT strengthened global–local feature interaction; GSConv reduced redundant computation; BiFPN improved multi-scale fusion; and SLIC refined ambiguous boundaries. After super-resolution preprocessing and three-fold expansion, baseline mPA increased by 10.9 percentage points. The improved network achieved 88.3% mPA at 7.9 GFLOPs, corresponding to +3.6 percentage points and -1.0 GFLOPs relative to the baseline. SLIC voting increased FWIoU to 95.6%, 4.1 percentage points above the network without SLIC. Compared with YOLOv5-seg and Fast-SCNN, mPA improved by 2.0 and 6.5 percentage points, respectively; GFLOPs were 87.7% and 95.5% lower than those of YOLOv5-seg and DeepLabv3+, respectively. The method therefore provides a favorable trade-off between segmentation accuracy and theoretical network computation for complex lettuce field imagery. Full article