Search Results (1,257)

Operational agricultural monitoring in the Central European lowlands requires timely parcel boundaries; however, unmarked field edges produce minimal spectral contrast in single-date imagery. Previous works demonstrated that harmonic NDVI encoding enables zero-shot field delineation using foundational models, but the influence of the spectral index choice on temporal boundaries remained unquantified. This study systematically evaluates eleven vegetation indices—NDVI, GNDVI, NDRE, EVI, EVI2, SAVI, MSAVI, NDWI, CIg, CIre, and NDYVI—within a fixed harmonic phenology encoding pipeline. A one-year PlanetScope time series (15 × 15 km, Slavonija, Croatia) was decomposed via annual sinusoidal regression to extract per-pixel phase, amplitude, and mean parameters. These harmonic descriptors were mapped to HSV colour channels and segmented using the Segment Anything Model without fine-tuning. Official agricultural parcels (PAAFRD, 2025) provided ground truth for pixel-wise, object-wise, and size-stratified evaluation. Performance stratified into three tiers based on object-wise metrics. Soil-adjusted and enhanced-greenness indices (MSAVI, EVI, EVI2, and SAVI) achieved F1 = 0.51–0.52, and mIoU = 0.70–0.71, statistically outperforming standard ratio formulations (NDVI: F1 = 0.49) and chlorophyll indices (CIg, CIre: F1 = 0.45–0.47). Pixel-wise scores remained compressed (F1 > 0.88 across all indices), indicating consistent interior coverage but index-dependent boundary precision. Error analysis revealed scale-dependent patterns: merging dominated small parcels (<10,000 m²), while fragmentation increased with parcel size. Results demonstrate that spectral formulation is a systematic design factor in phenology-based delineation, with soil background correction and dynamic range compression improving seasonal trajectory separability. The harmonic parameters generated by this framework provide feature-ready input for crop classification, suggesting that integrated boundary extraction and crop mapping workflows merit further investigation. Full article

Spring and autumn phenology jointly regulate terrestrial carbon, water, and energy exchanges, yet the mechanisms linking seasonal transitions remain debated under increasing hydroclimatic stress. Here, we integrate satellite-derived phenology with reanalysis-based indicators of land–atmosphere coupling to examine how spring onset interacts with growing season controlling factors and how these interactions shape autumn senescence at the global scale. Globally, start-of-season (SOS) and end-of-season (EOS) timings are positively coupled, with later SOS generally followed by later EOS, and this relationship becomes stronger when only later-SOS years are considered. However, SOS does not induce coherent global shifts in growing season climate limitation. Piecewise structural equation modeling reveals that SOS influences EOS primarily through a direct phenological pathway, with a mean path coefficient of ~0.4 day·day⁻¹ explaining approximately 26% of global EOS variability. In contrast, energy and water-mediated pathways contribute smaller but spatially heterogeneous effects, together accounting for ~5% of explained variance on average. SOS–EOS coupling is strongest in water-limited regimes, particularly in grasslands and shrublands. Managed croplands exhibit distinct and more heterogeneous responses, reflecting partial decoupling of phenology from natural hydroclimatic constraints. Collectively, our results indicate that spring phenology exerts a robust but spatially variable influence on autumn timing, dominated by direct effects rather than indirect mediation through growing season climate limitations, with regional modulation imposed by background hydroclimatic conditions. Full article

Urban wetlands are acoustic hotspots where vegetation structure, hydrological dynamics, and anthropogenic noise interact, yet multi-season assessments of how vegetation influences avian soundscapes are limited. This study explored bird soundscape dynamics across forest, open forest grassland, and meadow habitats in Nanjing Xinjizhou National Wetland Park, eastern China, using passive acoustic monitoring during spring and autumn 2023. Twelve sampling points (four per vegetation type) were established, and six acoustic indices were calculated, including the Acoustic Complexity Index (ACI), Acoustic Diversity Index (ADI), Acoustic Evenness Index (AEI), Bioacoustic Index (BIO), Normalized Difference Soundscape Index (NDSI), and Acoustic Entropy Index (H). were calculated from 48-h recordings each season. Random forest models and redundancy analysis assessed the relationships between acoustic indices, fine-scale vegetation parameters (e.g., crown width, tree height, species richness), and anthropogenic factors (e.g., distance to roads/trails, surface hardness). Vegetation structure, particularly crown width, was the primary driver of avian acoustic diversity, with broad-crowned forests consistently exhibiting the highest acoustic complexity. In spring, anthropogenic factors such as trail and road proximity dominated soundscape variation, suppressing biological sounds. In autumn, with reduced human presence, vegetation structure emerged as the dominant factor, while bioacoustic activity remained elevated despite reduced peaks in acoustic complexity. Proximity to roads increased low-frequency (1–2 kHz) noise and suppressed mid-frequency (4–8 kHz) bird vocalizations, but trees with crown widths ≥4 m maintained higher acoustic diversity even near disturbance sources. This study demonstrates that vegetation structure mediates both resource availability and sound propagation, buffering the effects of anthropogenic disturbance in frequency-specific ways. Multi-season sampling is crucial for understanding the dynamic interplay between vegetation phenology and human activity that shapes urban wetland soundscapes. Full article

Accurate and timely cotton-field mapping is essential for irrigation management, water resource allocation, and regional yield assessment in arid irrigated agroecosystems. However, existing deep-learning-based crop mapping approaches generally lack interpretability and often exhibit performance variability across phenological stages, thereby limiting their reliability for operational deployment. To address these limitations, we developed an interpretable semantic segmentation framework for cotton mapping in the Wei-Ku Oasis, Xinjiang, China, under multi-source remote sensing conditions. The proposed model integrates Sentinel-2 surface reflectance, Sentinel-1 VV/VH backscatter, DEM, vegetation indices, and GLCM texture features. By incorporating a receptive-field enhancement mechanism together with an embedded feature-attribution module, the framework enables importance estimation of multi-source predictors within the network architecture, thereby providing intrinsic model interpretability. Under a unified training and evaluation protocol, the proposed model achieved an mIoU of 85.62% and an F1-score of 92.96% on the test set, outperforming U-Net, DeepLabV3+, and SegFormer baselines. Monthly classification results indicated that August provided the most discriminative acquisition window (mIoU = 85.54%, F1 = 92.83%), while June–July also maintained high recognition accuracy. Feature attribution results indicate that the importance of different predictors varies across phenological stages: Sentinel-2 red-edge bands remained highly influential throughout the growing season, NDVI/EVI exhibited increased contributions during June–August, SAR VH showed relatively higher importance during peak canopy development, and DEM maintained stable information contribution across all stages. Cross-year and cross-region experiments further demonstrated the model’s generalization capability, achieving an mIoU of 82.81% in same-region cross-year evaluation and 74.56% under cross-region transfer. Overall, the proposed segmentation framework improves classification accuracy while explicitly modeling and quantifying feature importance, providing a methodological reference for cotton-field mapping and acquisition timing selection in arid irrigated regions. Full article

This study evaluated the potential of Sentinel-2-derived NDVI (Normalized Difference Vegetation Index) for predicting within-field variability of winter wheat grain yield in central Lithuania during the 2024 growing season. Reliable within-field yield prediction remains challenging in regions with heterogeneous soils and limited region-specific models, particularly in northeastern Europe. Grain yield data were obtained from combine harvesters equipped with GPS yield monitoring across 13 fields with a total area of 283.6 ha. NDVI values were calculated for four half-monthly periods from March to May, corresponding to key phenological stages (from tillering to spike emergence). Spatial and temporal variability in NDVI–yield relationships was observed, with early May consistently showing the strongest correlations (r up to 0.49), particularly in lower-fertility fields, indicating its critical role in yield prediction. Machine learning models (Random Forest, XGBoost, and Deep Neural Networks), along with linear regression, were applied to predict yields based on NDVI from four growth stages. Random Forest achieved the highest predictive accuracy (MAE = 0.951 t/ha), outperforming the other models. The model also showed the highest correlation with observed yields (Pearson r = 0.717), indicating strong agreement between predicted and measured values. Feature importance analysis confirmed NDVI from 1 to 15 May as the most influential predictor across all models. Predicted yield maps closely matched observed patterns, with the largest discrepancies near field edges due to combine harvester effects. These findings highlight the utility of mid-season NDVI for precise estimation of within-field grain yield variability and demonstrate that Random Forest models can effectively capture the NDVI–yield relationship, particularly under heterogeneous field conditions. Full article

Air quality improvement represents a critical challenge for the European Union, with particulate matter (PM) being the most harmful pollutant in urban areas. Urban Green Infrastructures (UGIs) provide essential ecosystem services that mitigate air pollution, notably through PM₁₀ removal via deposition on leaf surfaces, reducing health risks associated with poor air quality. This study quantifies the PM₁₀ removal supplied by urban forests in the Bydgoszcz–Toruń area (Poland) using a spatially explicit modeling framework. Remotely sensed Leaf Area Index, vegetation cover, and PM₁₀ concentration data were integrated within a GIS environment, with all analyses conducted on a seasonal basis to capture temporal variability in vegetation phenology and pollutant levels. Resulting maps of mean seasonal PM₁₀ removal efficiency (kg/ha) reveal distinct functional group patterns: deciduous broadleaves reach peak efficiency in summer, whereas conifers provide a more consistent year-round contribution, resulting in the highest annual removal. Monetary valuation was performed using externality costs from the European Environmental Agency. Overall, urban forests remove 3360.40 Mg of PM₁₀ annually, corresponding to an estimated value of 255.69 M€. Integrating biophysical and economic perspectives supports urban planning and highlights UGIs as nature-based solutions to enhance air quality, protect public health and promote ecosystem biodiversity and resilience. Full article

Olive cultivation is widespread throughout the Mediterranean basin, where the world’s main producing countries are located. Regions such as Extremadura are considered to be at high risk from the effects of climate change in the near future. In particular, olive cultivation is highly sensitive to climate change and can suffer profound effects on phenology and yield. This crop depends directly on variables such as maximum and minimum temperatures and rainfall. In this study, we have analysed how olive cultivation could be affected by calculating two bioclimatic indices, the Dryness Index (DI) and the Cool Night Index (CI), for three future periods. The methodology used projected ten combinations of climate models in two scenarios, RCP 4.5 and RCP 8.5. The results showed significant variations in the bioclimatic indices over the periods, which were used to calculate the water stress and extreme temperatures that these crops could suffer. They indicate that most of Extremadura will continue to be suitable for cultivation in the near future (2006–2035), while by the middle of the century (2036–2065) 67% of the area will remain temperate, where 72% of the olive groves are located, with a Dryness Index of 18% in the very dry category. By the end of the century (2066–2095), the zone will be 60–34% warm and very dry, with a Dryness Index of 72%. These results show that it will probably be necessary to create new areas suitable for olive cultivation and new varieties. Full article

Straw burning is a major source of regional air pollution. However, its reliable remote sensing detection faces problems in distinguishing agricultural fires from non-agricultural thermal anomalies, adequately leveraging burning seasonality, and overcoming the scarcity of pixel-level annotations. To comprehensively address these issues, this study proposes an end-to-end framework for straw burning identification that integrates spatio-temporal weighting and semi-supervised learning. The framework introduces a data-driven spatial weight optimization method to automatically learn discriminative weights for diverse land cover types (e.g., farmland, industry), replacing subjective empirical settings. Furthermore, a temporal weighting model, developed using Kernel Density Estimation, dynamically adjusts classification confidence according to historical burning seasonality, enhancing recall during peak seasons while suppressing off-season false positives. Finally, an adapted Dual-Backbone Dynamic Mutual Training (DB-DMT) strategy collaboratively leverages both limited labeled (24.5%) and abundant unlabeled (75.5%) high-resolution imagery, significantly improving model generalization in label-scarce scenarios. Validation across five representative regions of China demonstrated the framework’s superior performance, achieving a semantic segmentation mean Intersection over Union (mIoU) improvement of 3.33% (to 71.92%) and increasing precision in Henan from 95.21% to 97.71%. Crucially, the framework effectively reduced the off-season false positive rate (FPR) from 5.14% to a mere 0.23% in highly industrialized regions like Tianjin. By systematically mitigating both spatial geolocation bias and seasonal phenology confusion, our approach offers a robust and scalable solution for straw burning monitoring and a transferable paradigm for other environmental remote sensing applications. Full article

Accurate and early prediction of crop yield at the sub-field scale is essential for precision-agriculture and food-system planning. This study evaluates a phenology-based machine learning framework for winter wheat yield prediction using Sentinel-2 satellite imagery, climate reanalysis data, and field-level yield data. Phenological metrics derived from the normalised difference vegetation index (NDVI), the normalised difference water index (NDWI), and the normalised difference red-edge index (NDRE) were combined with accumulated seasonal rainfall and seasonal potential evapotranspiration, and multiple modelling strategies were assessed using a leave-one-field-out cross-validation (LOFO CV) scheme to ensure spatial generalisation. Among the evaluated models, the Random Forest (RF) algorithm achieved the highest overall performance, explaining up to 73% of the yield variability with a root mean square error (RMSE) of 0.88 t ha⁻¹ at optimal prediction timing (day of year 160–175). Integrating phenological and climatic covariates consistently improved prediction accuracy compared to models based only on phenological variables, while the inclusion of soil properties provided limited additional benefit at the examined spatial scale. Phenological metrics based on red-edge data, particularly the maximum NDRE, were the most influential predictors, highlighting the added value of red-edge spectral information beyond traditional red–near-infrared indices. Uncertainty analysis revealed spatially heterogeneous prediction uncertainty, particularly near field boundaries and in areas of complex spatial patterns. Overall, the proposed framework enables robust, early, and interpretable yield prediction at the sub-field scale, supporting uncertainty-aware decision-making in precision agriculture and offering a scalable foundation for regional crop monitoring. Full article

Deep learning-based crop mapping from hyperspectral satellite data offers immense potential for capturing subtle phenological differences, yet leveraging sparse time series remains a major methodological challenge. This study evaluates the ability of the EnMAP sensor to identify nine major crop types in the intensive agricultural landscape of Southeastern Hungary. We utilized a limited time series (November, March, August) to benchmark two modeling strategies: a single-date dual-stream spatial–spectral 2D-CNN (DSS-2D) and a multi-temporal 3D-SE-ResNet. Model performance was assessed using parcel-level spatial cross-validation to ensure realistic accuracy estimates and reduce spatial autocorrelation bias. The results demonstrate that the DSS-2D model achieved superior single-date accuracy (OA > 97%), significantly outperforming pixel-based baselines. Furthermore, the multi-temporal 3D-SE-ResNet achieved a robust seasonal accuracy of 92.9%, effectively compensating for temporal sparsity by exploiting the deep spectral information of the SWIR domain. This study confirms that treating hyperspectral data as a 3D volume enables the extraction of phenological traits even from limited observations. These findings provide a strong proof-of-concept for the operational feasibility of future missions such as Copernicus CHIME for continental-scale food security monitoring. Full article

Accurate field-scale crop disease detection is crucial for precise decisions and for highly efficient multi-scale collaboration. UAV-based multispectral imaging technology offers advantages in terms of high efficiency and low cost. Deep learning shows potential for deep representation and fusion of spectral and spatial features. However, traditional manual disease surveys are limited by efficiency and cost, making it difficult to meet the large sample sizes required by deep learning. Therefore, we proposed a method for rice bacterial leaf blight detection using UAV-based multispectral imagery. This method integrates a cross-scale sample-label transfer, and a spectral–spatial dual-branch feature fusion architecture (DualRiceNet). We first used RTK positioning to transfer disease labels from near-ground RGB images to high-altitude multispectral images, effectively expanding the dataset and alleviating the scarcity of labeled samples. DualRiceNet employed a cross-attention mechanism to couple its spectral and spatial branches, thereby isolating disease-specific spatial–spectral patterns from complex interference from the farmland background. DualRiceNet achieved an overall accuracy (OA) of 92.3% on the same-distribution test set. In an independent scenario test set spanning multiple differences in geography, time, phenology, and variety, the model maintained the highest OA of 80.0%. Our method demonstrated an excellent generalization ability to real-world environmental variations in rice fields. Full article

The grapevine (Vitis vinifera L.) is one of the most economically valuable horticultural crops worldwide and is cultivated across a wide range of agroclimatic regions. The objective of this study was to develop a predictive model to estimate the yield of the cultivar Treixadura as a function of meteorological, phenological, aerobiological, and phytopathological variables. The study was conducted in a vineyard located within the Ribeiro Designation of Origin (Spain) over 21 consecutive growing seasons. During the period from 2004 to 2023, grapevine yield exhibited pronounced interannual variability, with the lowest yield recorded in 2018 and the highest in 2023. Correlation analysis showed that grapevine yield was significantly and positively associated with temperature, airborne pollen and the Plasmopara viticola pathogen, and negatively with rainfall and the Botrytis pathogen. Yield was predicted using a model that included rainfall in the first ten days of April, airborne pollen concentration, and Plasmopara viticola from the third ten-days of April as explanatory variables. This model accounted for approximately 70% of the observed variability in yield. The achieved predictive performance enables the anticipation of harvest outcomes several months in advance, thereby supporting more effective viticultural planning. Furthermore, the results highlight the importance of disease control in vineyards, as pathogen incidence not only reduces yield directly but may also compromise the accuracy of yield prediction models. Full article

Optimizing nitrogen (N) fertilization is essential for sustaining durum wheat yield and grain quality while reducing the environmental impacts associated with N over-application. Hyperspectral sensing provides a rapid and non-destructive approach for monitoring crop N status. However, high-dimensional data, phenology-dependent spectral responses, and spatial autocorrelation in field measurements limit robust nitrogen classification and interpretation. This study evaluated hyperspectral-based nitrogen status classification in durum wheat under Mediterranean field conditions and identified key spectral regions using explainable artificial intelligence. A field experiment was conducted in Southern Italy using ten N fertilization rates (0–180 kg N ha⁻¹). Canopy reflectance was acquired at the booting and heading stages from georeferenced sampling locations. Three nitrogen stratification strategies (binary Low–High, Extreme, and three-level) were evaluated using Random Forest, SVM-RBF, and XGBoost classifiers. Model performance was assessed using spatially independent Leave-One-Plot-Out cross-validation at both the sample and plot levels, with plot-level predictions derived through majority voting. Classification robustness was strongly influenced by the stratification strategy and phenological stage. The binary Low–High stratification achieved the highest sample-level accuracy, with a maximum of 0.78 at booting (SVM-RBF) and 0.75 at heading (SVM-RBF), whereas the Extreme stratification produced intermediate performance, with maximum accuracies of 0.73 at booting (SVM-RBF) and 0.63 at heading (XGBoost). Plot-level aggregation improved performance, reaching up to 0.90 at booting and 1.00 at heading. SHAP analysis highlighted red, red-edge, and near-infrared wavelengths as the dominant contributors, with increased reliance on longer wavelengths at the heading. Overall, explainable machine learning provides a robust framework for hyperspectral nitrogen monitoring in durum wheat. Full article

Interannual variability in climatic conditions represents a major source of uncertainty in cool-climate viticulture, highlighting the need for cultivar-specific assessments of climate–quality relationships. A multi-year on-farm experiment with six monitoring sites has been conducted in vineyards representative of the Tokaj wine region to monitor and assess vintage effect. This study, as the first part of a broader research project evaluating must components, quantifies relationships between climatic indices and key yield- and sugar-related traits (berry weight, total soluble solids, and total dry extract) in Vitis vinifera L. cv. Furmint grown in the Tokaj wine region over three contrasting vintages. Thermal, radiative, and water-availability variables were calculated for discrete phenological phases and statistically analyzed to identify climatic predictors of berry growth and must composition. Berry weight exhibited pronounced vintage sensitivity, showing consistent associations with precipitation-related variables during early developmental stages. In contrast, total soluble solids and total dry extract displayed weaker and less consistent responses to interannual climatic variability. Several widely used heat-accumulation indices showed limited explanatory power, indicating a moderate climatic sensitivity of sugar-related traits in this cultivar. Overall, the results suggest that early-season climatic conditions exert a stronger influence on berry growth than late-season thermal extremes, while compositional parameters related to sugar accumulation remain comparatively stable. These findings highlight the need to incorporate cultivar-specific response functions into statistical models that assess projected climate-change effects on grape quality. Full article

While climate change shifts plant phenology, conventional satellite-based studies often overlook intra-individual variations due to spatial averaging. This study utilized high-resolution UAV imagery and Digital Surface Models (DSMs) to investigate how intra-crown microclimatic heterogeneity affects the spatiotemporal patterns of flowering and autumn leaf senescence. Rhododendron yedoense f. poukhanense (H.Lév.) M. Sugim (RY) and Acer triflorum Kom. (AT) were monitored at the Korea National Arboretum, with 23 time-series images acquired between April and November 2025. Cumulative solar duration was calculated for 0.5 m intra-crown grids, and phenological events were detected using derivative analysis of vegetation indices (Red Chromatic Coordinate [RCC] and Green Chromatic Coordinate [GCC]). The results confirmed asynchrony in phenological events within single individuals depending on crown sectors. However, the linear relationship between intra-crown microclimatic heterogeneity and phenological duration was statistically weak ($\rho$ > 0.05), suggesting that strong physiological buffering mitigates the direct impact of spatial light variation. Despite this buffering, species-specific response patterns were observed: RY exhibited spatially independent flowering responses, whereas AT maintained relatively higher synchrony. Furthermore, AT showed a “Phenological Velocity” gap, where sunlit sectors tended to experience senescence approximately 1.12 days later than shaded areas**, while RY showed no significant directional lag.** This research demonstrates that phenological responses can be spatially dispersed even within an individual, and the buffering mechanisms against environmental variability differ by crown structure and growth form. These findings highlight the necessity of individual-level spatial resolution in understanding plant responses to climate change. Full article