Search Results (343)

Fractional vegetation cover of crops (CropFVC) is a critical indicator for remote sensing-based crop monitoring. However, existing inversion models are largely developed for general vegetation types, limiting their effectiveness for crop-specific applications. Here, we developed a gap-fraction-refined hybrid CropFVC model that integrates crop-specific PROSAIL calibration, an ALA (averages of leaf angle) -based dynamic projection function, and a Random Forest model. The model was validated with 43343 CropFVC samples of four major crops (winter wheat, rice, maize, and soybean) across China during March to August 2024, spanning key phenological stages, and further compared against SNAP (10 m) and GEOV3 (300 m) products. Results showed that (1) the proposed model achieved stable performance across diverse canopy structures, with average RMSE < 9.3% for wheat, rice, maize, and soybean; (2) compared with SNAP (10 m), RMSE decreased by 4.83%, 3.10%, 7.51%, and 8.63% for wheat, rice, maize, and soybean, respectively; compared with GEOV3 (300 m), reductions reached 7.88%, 9.49%, 13.63%, and 19.75%, respectively. Further observations showed that the model-derived CropFVC captured intra-field variability and abnormal crop conditions well, enabling more accurate monitoring of crop-specific FVC dynamics across phenological stages. The proposed operational framework enhances CropFVC estimation by improving canopy structural representation and reducing retrieval bias. By enabling more accurate 10 m CropFVC mapping at the field scale, the crop-specific approach provides practical support for precision agriculture and crop-related food security monitoring. Full article

Gross Primary Productivity (GPP) in grassland ecosystems is a fundamental eco-biophysical indicator for assessing carbon cycling, grazing capacity, and ecosystem responses to climatic stress. However, robust estimation of GPP in arid and semi-arid rangelands remains challenging because of pronounced spatial heterogeneity, strong climate variability, and inherent uncertainties associated with remotely sensed observations. Together, these factors constrain both modeling performance and out-of-sample generalization beyond the training domain. In this dryland grassland context, this study compares the performance of machine learning (ML) models for grassland GPP proxy-based characterization, downscaling, and predictive agreement using a multivariate dataset that integrates Sentinel-2-derived spectral and phenological features, a Moderate-Resolution Imaging Spectroradiometer (MODIS)-derived GPP proxy, and complementary climatic and geographic information. Pixel-level observations spanning multiple years are analyzed, with ordinary linear regression used as a baseline benchmark and ensemble decision-tree models, including Random Forest, Gradient Boosting, and Histogram-based Gradient Boosting (HGB), compared. Instead of relying solely on random cross-validation, model performance is systematically assessed using a combination of spatially structured validation and a leave-one-year-out scheme to explicitly examine spatial and temporal generalization. The results indicate that ensemble tree-based models outperform linear approaches, with the HGB model showing the strongest agreement with the MODIS-derived GPP proxy (R² = 0.95, RMSE = 0.035 on the test set) and maintaining stable performance across spatial and temporal validations (R² = 0.86–0.96 across years). Taken together, the findings demonstrate that integrating multi-source remote sensing data with climatic information within a rigorous validation framework enables a more reliable assessment of model generalization and gap-filling consistency with respect to a remote-sensing-based proxy target, rather than an absolute validation against ground-based measurements, thereby supporting sustainability-relevant monitoring of arid grassland ecosystems. Full article

Accurate mapping of tea plantations in fragmented, mountainous landscapes faces challenges from spectral confusion, cloud-induced data gaps, and limited model transferability. To address these issues, this study proposes a data-driven approach leveraging 64-dimensional Google AlphaEarth Foundations (AEF) satellite embeddings as core predictive features, integrated with Sentinel-2 spectral, textural, and topographic variables. Prior to feature optimization, comparative experiments confirmed that Random Forest outperformed Gradient Boosting Trees, Classification and Regression Trees, and Support Vector Machines in stability and accuracy, serving as the core classifier. Leveraging a robust sampling strategy, this study evaluated 12 classification scenarios. Results showed that the AEF-augmented scenario achieved the best performance in Rizhao (Overall Accuracy 92.69%, Kappa 0.90), with a high Producer’s Accuracy of 97.47% that effectively minimized omission errors. SHapley Additive exPlanations (SHAP) analysis revealed the model’s physically interpretable logic: utilizing embeddings as “exclusion filters” to separate tea from non-target classes by encoding latent phenological patterns, while relying on original spectral bands to capture canopy biological signals. Crucially, the model demonstrated exceptional generalizability when transferred to the unseen Qingdao region without retraining. This study validates AEF embeddings as a robust, scalable feature representation for regional crop monitoring in label-scarce and heterogeneous environments, offering a transferable data foundation for precise agricultural inventory and sustainable development planning. Full article

Volatile organic substances (VOCs) emitted by plants play an important role in the recognition and selection of host plants by insects. For polyphagous insects with a broad host range, like the brown marmorated stink bug Halyomorpha halys, not much is known about the plant volatiles that influence host choice. In order to determine which odour stimuli could influence host selection, monitoring was carried out using pheromone traps in orchards with various host plants. The headspace of the phenological stages of plants on which H. halys occurred in large numbers was sampled and analysed with gas chromatography coupled with mass spectrometry (GC-MS). The volatile profiles of the different host plants varied significantly. Some compounds occurred in high relative proportions across all taxa. Those compounds were tested by H. halys using electroantennography. H. halys’ antennae responded significantly to all of the selected compounds. In a Y-tube olfactometer, H. halys showed a significant attraction to 1 µg hexanal, 100 µg (E)-4,8-dimethyl-1,3,7-nonatriene (DMNT), and a volatile mixture. Due to the limited sustainable strategies for plant protection against this polyphagous insect, adding attractive plant volatiles to lures could improve the effectiveness of alternative volatile-based plant protection strategies, such as traps or capsules, or promote their development. Full article

Long-term ecological data are rare but are highly desirable for assessing responses to ongoing environmental change. To assess temporal trends in abundance over time and establish a baseline for future comparison, we monitored a plethodontid salamander community for ten years. From 2014 to 2023, we sampled forest plots at Wooster Memorial Park (OH, USA) using a regular and standardized monitoring scheme. Of nine salamander species detected, four were common enough to permit statistical analysis. Three species (Eurycea bislineata, Plethodon cinereus and P. electromorphus) had no statistically significant abundance trends over time. The slimy salamander (P. glutinosus), however, showed a statistically significant decline in abundance. We also report on ecological differences between P. cinereus and P. electromorphus, which occur in sympatry at this site. Specifically, we document significant microhabitat differences between these species, which are suggestive of competition avoidance. Additional data are presented on color morph frequency, body size, sexual dimorphism, frequency of hybridization, mate choices, and phenology of surface activity. As global environmental change accelerates, such baseline information is essential to track organismal responses. We also provide a brief review of other long-term field studies in plethodontid salamanders. Full article

Precision monitoring of leaf nitrogen content (LNC) in fruit trees is critical for optimizing fertilization and fruit quality. In this study, 1120 apple-leaf samples spanning two phenological stages were collected. Characteristic wavelengths were selected using competitive adaptive reweighted sampling and the successive projection algorithm (CARS–SPA). To mitigate inefficient exploration during population initialization and iterations, we propose a collaborative enhancement strategy integrating Sobol-sequence sampling and elite opposition-based learning (EOBL), termed SEO, which simultaneously refines initialization and iterative updating in swarm-based optimization algorithms. Four machine learning algorithms were trained to construct cross-phenological-stage LNC inversion models. Results indicated characteristic wavelengths lay within the visible region. The combined SEO strategy improved search capability and efficiency, with SEO-BKA achieving the best performance. Consequently, the SEO-BKA-XGBoost model yielded the highest accuracy in the bloom and fruit-set stage (R² = 0.883; RMSE = 0.124) and fruit-enlargement stage (R² = 0.897; RMSE = 0.069). These findings provide robust technical support for LNC hyperspectral inversion in apple trees. Full article

Precise identification of early peanut leaf spot is strategically significant for safeguarding oilseed supplies and reducing pesticide reliance. However, general-purpose detectors face severe domain adaptation bottlenecks in unstructured field environments due to small feature dissipation, physical occlusion, and class imbalance. To address this, this study constructs a dataset spanning two phenological cycles and proposes POD-YOLO, a physics-aware and dynamics-optimized lightweight framework. Anchored on the YOLOv10n architecture and adhering to a “data-centric” philosophy, the framework optimizes the parameter convergence path via a synergistic “Augmentation-Loss-Optimization” mechanism: (1) Input Stage: A Physical Domain Reconstruction (PDR) module is introduced to simulate physical occlusion, blocking shortcut learning and constructing a robust feature space; (2) Loss Stage: A Loss Manifold Reshaping (LMR) mechanism is established utilizing dual-branch constraints to suppress background gradients and enhance small target localization; and (3) Optimization Stage: A Decoupled Dynamic Scheduling (DDS) strategy is implemented, integrating AdamW with cosine annealing to ensure smooth convergence on small-sample data. Experimental results demonstrate that POD-YOLO achieves a 9.7% precision gain over the baseline and 83.08% recall, all while maintaining a low computational cost of 8.4 GFLOPs. This study validates the feasibility of exploiting the potential of lightweight architectures through optimization dynamics, offering an efficient paradigm for edge-based intelligent plant protection. Full article

Drosicha corpulenta (Hemiptera: Monophlebidae) is a major polyphagous pest affecting street and garden trees in arid regions of northern China, causing increasing damage in newly developed cities like Cocodala, Xinjiang. This study was conducted from 2024 to 2025 to investigate this pest’s life cycle, key damage periods, and spatial distribution in seven host plants, focusing on nymph emergence, female soil entry, and overwintering egg distribution. The results show that D. corpulenta has one generation per year, which overwinters as eggs. Nymphs emerge in early March, and male pupation occurs from mid-April to early May. Females mate after the third molt in early to mid-May and enter the soil to lay eggs from late May to early June, with consistent timing over two years. The suitability of the host varied significantly: Platanus × hispanica was the most preferred, with the highest daily nymph emergence of 840.8 individuals in 2024 and 1196.0 in 2025, followed by Prunus padus and five other plant species (Populus spp., Fraxinus chinensis, Styphnolobium japonicum, Pinus spp., and Malus spectabilis). Female soil entry reached a maximum on 23 May (979.8 individuals⁻¹ day⁻¹) and gradually decreased with increasing distance from the trunk. Overwintering eggs showed no obvious azimuthal bias, but were mainly concentrated near the trunk (0–30 cm) and in shallow soil (0–10 cm; 179.8 eggs per 100 g composite soil sample per sampling point), decreasing sharply in number with distance and depth. Both Taylor’s power law and Iwao’s regression confirmed the aggregated distribution. This study identifies key phenological stages, highly susceptible hosts, and the near-trunk shallow soil layer as critical for oviposition and overwintering and provides a basis for precise monitoring and targeted control in urban green spaces. Full article

Methane emissions from rice paddies account for over 11% of global atmospheric CH₄, making water management practices such as Alternate Wetting and Drying (AWD) critical for climate change mitigation. Remote sensing offers an objective approach to monitoring AWD implementation and improving greenhouse gas estimation accuracy. This study investigates the backscattering mechanisms of L-band SAR for inundation/non-inundation classification in paddy fields using full-polarimetric ALOS-2 PALSAR-2 data. Field surveys and satellite observations were conducted in Ryugasaki (Ibaraki) and Sekikawa (Niigata), Japan, collecting 1360 ground samples during the 2024 growing season. Freeman–Durden decomposition was applied, and relationships with plant height and water level were analyzed. The results indicate that plant height strongly influences backscatter, with backscattering contributions from the surface decreasing beyond 70 cm, reducing classification accuracy. Random forest models can classify inundated and non-inundated fields with up to 88% accuracy when plant height is below 70 cm. However, when using this method, it is necessary to know the plant height. Volume scattering proved robust to incidence angle and observation direction, suggesting its potential for phenological monitoring. These findings highlight the effectiveness of L-band SAR for water management monitoring and the need for integrating crop height estimation and regional adaptation to enhance classification performance. Full article

This study aimed to evaluate the prediction potential of phenology metrics from two vegetation indices using Sentinel-2 images, the Normalized Difference Vegetation Index (NDVI) and Three Red-Edge Vegetation Index (NDVI3RE), for maize yield prediction. Ground truth maize yield samples were collected near Koška, Croatia, on 13 October 2023, using a Quantimeter yield mapping sensor on Claas Lexion 6900 combine harvester. The phenology analysis was performed based on a time-series of all available Sentinel-2 images during 2023, using the Beck logistic model for determining the start of season (SOS), peak of season (POS), end of season (EOS), greenup, maturity, senescence, and dormancy. A total of fourteen covariates, including vegetation indices at phenology metrics and their occurrence dates, were used for machine learning prediction of maize yield using Random Forest (RF) and Support Vector Machine (SVM) regression. The results suggested that the SVM method based on NDVI phenology metrics produced the highest accuracy for maize yield prediction (R² = 0.935, RMSE = 0.558 t ha⁻¹, MAE = 0.399 t ha⁻¹). Vegetation index values at greenup, dormancy and POS were the most important covariates for the prediction, while day of year (DOY) in which they occurred had only a minor effect on the prediction accuracy. This suggests that, despite its limitations regarding the saturation effect, NDVI outperformed NDVI3RE for maize yield prediction when combined with phenology metrics. Full article

Pod corn (Zea mays var. tunicata) bears leafy glumes that enclose kernels, resembling a partial reversion to wild-forms, yet remains poorly characterized in situ in Mexico. We evaluated Mexican accessions at two contrasting locations to quantify morphological/phenological diversity and to assess functional traits via proximate kernel composition. Standard descriptors captured variation in plant architecture, tassel/ear traits (including glume length), and reproductive timing. Accessions showed strong plasticity and significant accession × environment effects on ear morphology and maturation. Grain yield ranged from 6.32 to 10.78 t ha⁻¹, with peak values comparable to commercial hybrids and above-typical yields reported for native Mexican races (2.7–6.6 t ha⁻¹). Proximate analysis showed that milling with the tunic increased moisture/ash (up to 3.07% vs. 1.80% in dehulled grain), tended to lower fat and protein, and yielded lower crude fiber than dehulled samples (0.78–0.96% vs. 1.59–1.77%); protein varied widely (1.05–6.64%). Thus, the tunic modulates elemental composition, informing processing choices (with vs. without tunic). Our results document a spectrum of morphotypes and highlight developmental diversity and field adaptability. The observed accession × environment responses provide a practical baseline for comparisons with native and improved varieties, and help guide product development strategies. Collectively, these data underscore the high productive potential of pod corn (up to 10.78 t ha⁻¹ under optimal management) and show that including the tunic substantially alters proximate composition, establishing a quantitative foundation for genetic improvement and food applications. Overall, pod corn’s distinctive ear morphology and context-dependent composition reinforce its value for conservation, developmental genetics, and low-input systems. Full article

Maize is one of the top three crops globally, ranking only behind rice and wheat, making it an important crop of interest. Aboveground biomass is a key indicator for assessing maize growth and its yield potential. This study developed an efficient and stable biomass prediction model to estimate the aboveground biomass (AGB) of spring maize (Zea mays L.) under subsurface drip irrigation in arid regions, based on UAV multispectral remote sensing and machine learning techniques. Focusing on typical subsurface drip-irrigated spring maize in arid Xinjiang, multispectral images and field-measured AGB data were collected from 96 sample points (selected via stratified random sampling across 24 plots) over four key phenological stages in 2024 and 2025. Sixteen vegetation indices were calculated and 40 texture features were extracted using the gray-level co-occurrence matrix method, while an integrated feature-selection strategy combining Elastic Net and Random Forest was employed to effectively screen key predictor variables. Based on the selected features, six machine learning models were constructed, including Elastic Net Regression (ENR), Gradient Boosting Decision Trees (GBDT), Gaussian Process Regression (GPR), Partial Least Squares Regression (PLSR), Random Forest (RF), and Extreme Gradient Boosting (XGB). Results showed that the fused feature set comprised four vegetation indices (GRDVI, RERVI, GRVI, NDVI) and five texture features (R_Corr, NIR_Mean, NIR_Vari, B_Mean, B_Corr), thereby retaining red-edge and visible-light texture information highly sensitive to AGB. The GPR model based on the fused features exhibited the best performance (test set R² = 0.852, RMSE = 2890.74 kg ha⁻¹, MAE = 1676.70 kg ha⁻¹), demonstrating high fitting accuracy and stable predictive ability across both the training and test sets. Spatial inversions over the two growing seasons of 2024 and 2025, derived from the fused-feature GPR optimal model at four key phenological stages, revealed pronounced spatiotemporal heterogeneity and stage-dependent dynamics of spring maize AGB: the biomass accumulates rapidly from jointing to grain filling, slows thereafter, and peaks at maturity. At a constant planting density, AGB increased markedly with nitrogen inputs from N0 to N3 (420 kg N ha⁻¹), with the high-nitrogen N3 treatment producing the greatest biomass; this successfully captured the regulatory effect of the nitrogen gradient on maize growth, provided reliable data for variable-rate fertilization, and is highly relevant for optimizing water–fertilizer coordination in subsurface drip irrigation systems. Future research may extend this integrated feature selection and modeling framework to monitor the growth and estimate the yield of other crops, such as rice and cotton, thereby validating its generalizability and robustness in diverse agricultural scenarios. Full article

Accurate mapping of rice cultivation is vital for ensuring food security, reducing greenhouse gas emissions, and achieving sustainable development goals. However, large-scale deep learning–based crop mapping remains limited due to the demand for vast, uniformly distributed, high-quality samples. To address this challenge, we propose a Progressive Deep Learning Crop Mapping (PDLCM) framework for national-scale, high-resolution rice mapping. Beginning with a small set of localized rice and non-rice samples, PDLCM progressively refines model performance through iterative enhancement of positive and negative samples, effectively mitigating sample scarcity and spatial heterogeneity. By combining time-series Sentinel-2 optical data with Sentinel-1 synthetic aperture radar imagery, the framework captures distinctive phenological characteristics of rice while resolving spatiotemporal inconsistencies in large datasets. Applying PDLCM, we produced 10 m rice maps from 2022 to 2024 across the middle and lower Yangtze River Basin, covering more than one million square kilometers. The results achieved an overall accuracy of 96.8% and an F1 score of 0.88, demonstrating strong spatial and temporal generalization. All datasets and source codes are publicly accessible, supporting SDG 2 and providing a transferable paradigm for operational large-scale crop mapping. Full article

Semantic segmentation of UAV–acquired RGB orthomosaics is a key component for quantifying vegetation cover and monitoring phenology in precision agriculture. This study evaluates a representative set of CNN–based architectures (U–Net, U–Net Xception–Style, SegNet, DeepLabV3+) and Transformer–based models (Swin–UNet/Swin–Transformer, SegFormer, and Mask2Former) under a unified and reproducible protocol. We propose a transfer–and–consolidation workflow whose performance is assessed not only through region–overlap and pixel–wise discrepancy metrics, but also via boundary–sensitive criteria that are explicitly linked to orthomosaic–scale vegetation–cover estimation by pixel counting under GSD (Ground Sample Distance) control. The experimental design considers a transfer scenario between morphologically related crops: initial training on Opuntia spp. (prickly pear), direct (“zero–shot”) inference on Agave salmiana, fine–tuning using only 6.84% of the agave tessellated set as limited target–domain supervision, and a subsequent consolidation stage to obtain a multi–species model. The evaluation integrates IoU, Dice, RMSE, pixel accuracy, and computational cost (time per image), and additionally reports the BF score and HD95 to characterize contour fidelity, which is critical when area is derived from orthomosaic–scale masks. Results show that Transformer-based approaches tend to provide higher stability and improved boundary delineation on Opuntia spp., whereas transfer to Agave salmiana exhibits selective degradation that is mitigated through low–annotation–cost fine-tuning. On Opuntia spp., Mask2Former achieves the best test performance (IoU 0.897 +/− 0.094; RMSE 0.146 +/− 0.002) and, after consolidation, sustains the highest overlap on both crops (IoU 0.894 +/− 0.004 on Opuntia and IoU 0.760 +/− 0.046 on Agave), while preserving high contour fidelity (BF score 0.962 +/− 0.102/0.877 +/− 0.153; HD95 2.189 +/− 3.447 px/8.458 +/− 16.667 px for Opuntia/Agave), supporting its use for final vegetation–cover quantification. Overall, the study provides practical guidelines for architecture selection under hardware constraints, a reproducible transfer protocol, and an orthomosaic–oriented implementation that facilitates integration into agronomic and remote–sensing workflows. Full article

The relationship between insect diversity and crop production has been of continuous scientific interest. Understanding insect community dynamics using various sampling and monitoring methods at different crop phenology stages is crucial for enhancing pest management and ecosystem service functioning. The present study assessed the influence of four trap types (Blue, Yellow, White, and Malaise) applied at four tomato developmental stages (start of planting, flowering, flowering fruit development and harvest) on insect diversity in northeastern Tunisian open-field conditions. A total of 1771 insect individuals belonging to seven orders and 31 families were trapped, with the order Hymenoptera being the most common in the sampled plots, which was represented by 25 families. Trap type exerted a strong effect on both abundance and alpha diversity parameters. Yellow pan traps showed the highest diversity, with family richness (S) ranging from 1 to 16, Shannon diversity (H) reaching 2.54, Simpson (Is) diversity ranging from 0.72 to 0.90 and Pielou’s evenness (J) ranging from 0.83 to 0.98. Blue and white traps displayed intermediate diversity (Blue: S = 6 and H = 1.7; White: S = 7 and H = 1.6), while Malaise traps captured the least diverse assemblages (S = 4, H = 1.2 and Is = 0.65). These differences were highly significant (p < 0.05). Phenological stage significantly structured Hymenoptera diversity. Richness peaked at the start of planting (S = 1–16 and H up to 2.54) and declined sharply at harvest (S = 1–6). Pollinator families (Apidae, Halictidae, Megachilidae) were the most abundant during flowering, whereas parasitoid families (Braconidae, Eulophidae) dominated during the fruit development stage. Beta diversity analyses (NMDS, stress = 0.25) and PERMANOVA showed that trap type and phenological stage jointly explained 15.5% of the variation in community composition (R² = 0.155, p = 0.014). Although a strong taxonomic overlap among traps was observed, Indicator Value analysis revealed significant trap-specific associations, including the family Andrenidae with Blue traps and the family Scoliidae with White and Yellow traps. Overall, the results of the present study demonstrate that both trap type and crop phenology significantly influence insect population diversity. A multi-trap sampling strategy combining colored pan traps and Malaise traps could be recommended to accurately characterize insect communities and associated ecosystem services in Mediterranean open-field tomato systems. Full article