Search Results (27)

Fine-grained classification of urban green spaces (UGSs) is important for urban ecological assessment and management but remains challenging because of spectral similarity among vegetation types and inaccurate object delineation in complex urban environments. This study proposes a pixel-to-object framework that combines semantic segmentation-guided object construction with multi-periodic phenological modeling. A semantic green-space mask derived from 0.27 m very-high-resolution imagery constrains superpixel segmentation to generate spatially coherent, boundary-aware green space object-level patches (GSOPs). Pixel-level temporal representations are then derived from Sentinel-2 normalized difference vegetation index (NDVI) time series using TimesNet, aggregated into GSOP-level phenological features, and combined with spatial attributes to classify urban trees, grasslands, and farmlands. Applied to the built-up area of Chengdu, China, the framework achieved an overall accuracy of 91.6%, with F1-scores of 92.5%, 91.9%, and 87.6% for urban trees, grasslands, and farmlands, respectively. Ablation experiments showed that removing phenological features reduced overall accuracy by 13.1 percentage points and decreased the F1-scores of grasslands and farmlands by 16.0 and 23.0 percentage points, respectively. These results demonstrate that semantically constrained object delineation and phenological information jointly reduce boundary fragmentation and improve the discrimination of spectrally similar urban vegetation types. Full article

Since its launch in 2015, the Sentinel-2 mission has become a cornerstone of moderate-resolution vegetation monitoring, enabling spatially explicit and temporally dense observations of terrestrial ecosystems. Its combination of 10–20 m spatial resolution, a revisit interval of less than five days, and a spectral configuration including red-edge and Short-Wave Infrared (SWIR) bands has transformed optical vegetation monitoring beyond coarse-resolution greenness products. This review synthesises the use of Sentinel-2 for vegetation monitoring, with emphasis on phenology and growth dynamics, biomass and carbon estimation, vegetation stress detection, and associated methodological developments. A systematic Scopus search identified 1700 publications, of which 1097 studies were retained following thematic and methodological screening. The results reveal rapid growth in Sentinel-2-based research after 2018, reflecting its transition into a widely adopted data source supported by cloud-based processing platforms and harmonised data products. Research output is concentrated in a limited number of journals and regions, with Europe and Asia dominating contributions, while other regions remain underrepresented. Phenology and growth monitoring, biomass and carbon assessment, and vegetation stress analysis emerged as the principal application domains. Across these themes, methodological development has shifted from vegetation indices towards machine learning, hybrid radiative-transfer modelling, and multi-sensor data fusion. The reviewed evidence indicates that no single methodological approach consistently outperforms others; rather, performance depends on the target variable, ecosystem characteristics, and the treatment of observational uncertainty. Sentinel-2 has transformed vegetation monitoring by enabling spatially explicit assessment of vegetation phenology, biomass, carbon dynamics, and stress across ecosystems. However, important challenges remain, including uncertainty propagation, limited sensitivity to early physiological stress, the absence of thermal observations, and uneven validation across ecosystem types. Future progress will depend on uncertainty-aware retrieval frameworks, physically informed hybrid models, multi-sensor integration, and expanded calibration and validation across underrepresented ecosystems. Full article

Context: Accurate citrus crop mapping is essential for agricultural monitoring, production planning, and supply-chain management, particularly in Brazil, one of the world’s leading orange producers and the leading orange-juice exporter. Satellite image time series from Sentinel-2 provide rich spectral and temporal information for crop identification. However, citrus mapping remains challenging due to fragmented agricultural landscapes, cloud contamination, class imbalance, and spectral overlap with other vegetation classes. Problem: Conventional machine learning models often depend on handcrafted vegetation indices, while attention-based deep learning models may require larger datasets and can become unstable under geographically constrained conditions. Therefore, there is a need for a compact and robust deep learning architecture capable of extracting citrus phenological signatures directly from multispectral time-series data. Methods: This study evaluates a Spatio-Temporal Pixel-Set Encoder Convolutional Neural Network (PSE-CNN) for citrus crop classification in the immediate geographic regions of São João da Boa Vista and Mogi Guaçu, São Paulo, Brazil. MapBiomas Collection 10.1 data from 2019 to 2024 were used to derive reference polygons, and Sentinel-2 imagery was processed into cloud-masked, 15-day temporal composites using ten spectral bands. The proposed PSE-CNN was benchmarked against PSE-TAE, PSE-Transformer, Random Forest, and XGBoost using spatially grouped data partitioning and temporal test years. Results: The proposed PSE-CNN achieved the highest Unified F1-Score of $0.704$ and the lowest coefficient of variation of $3.03\%$, indicating stronger inter-annual stability across test years and random seeds among the evaluated models. It also outperformed classical models that relied on handcrafted vegetation indices and demonstrated greater overall stability than attention-based deep learning alternatives. Conclusions: The results indicate that combining pixel-set encoding with temporal convolution provides a resource-aware and stable framework for retrospective citrus crop mapping from Sentinel-2 satellite image time series. These findings suggest that PSE-CNN can support scalable agricultural monitoring, contributing to sustainable crop inventory systems in regions where labeled data and computational infrastructure are limited. Full article

Accurate diagnosis of potato nitrogen status is critical for optimized fertilizer management and sustaining productivity. We used data from nine field experiments (2010–2018) across major potato-producing regions in northern China to develop a regional critical nitrogen dilution curve via a Bayesian hierarchical model. The curve, Nc = 4.179 × DW^−0.417 (DW = whole-plant dry matter), provided the basis for calculating the nitrogen nutrition index (NNI), which was related to canopy spectral indices from a GreenSeeker sensor. Relationships between spectral indices and NNI were strongly growth-stage dependent. The tuber initiation–bulking period, approximately 29–70 days after emergence (DAE), represented the effective phenological window, with 29–55 DAE as the primary operational window for quantitative spectral diagnosis. Stage-specific ratio vegetation index (RVI) showed the most consistent association with NNI, whereas pooled whole-season models had low predictive power. The Bayesian framework quantified uncertainty, emphasizing that near-threshold NNI values require cautious interpretation. The resulting regional-average reference supports rapid field diagnosis of potato N status while accounting for cultivar, year, and site variability. These findings provide practical guidance for stage-specific N management and demonstrate the importance of growth-stage-aware spectral assessment in operational decision-making. Full article

Urban forests are widely promoted for improving air quality, yet their effectiveness is typically assessed through static green-space indicators that ignore seasonal variation in vegetation activity. This limitation is especially consequential in cold-region cities, where winter heating-season pollution peaks coincide with the leaf-off period of deciduous trees. Using a monthly panel of 15 centrally heated cities in northern China (2015–2024; N = 1464), this study develops a phenology-aware framework integrating three indicators: effective forest capacity (EFC), which combines dynamic forest area with a sigmoid leaf-on share and city-specific evergreen fraction; heating-season exposure (HI); and a binary phenology–heating mismatch (PHM) flag. City–year–month fixed-effects models show that the EFC–PM_2.5 association is directionally negative but statistically inconclusive under conservative inference (city-clustered SE: $p=0.523$; wild bootstrap: $p=0.541$), whereas associations with SO₂ and O₃ are statistically robust. The central empirical contributions are the four-quadrant heterogeneity analysis and the topographic paired comparison: four-quadrant heterogeneity analysis reveals that forest capacity shows clearer negative associations in dry semi-humid cities, whereas HI dominates in heating-dominated plain cities. A paired topographic comparison between Urumqi and Xining illustrates how terrain-induced inversions can override forest signals. The results support differentiated urban greening strategies that coordinate forest expansion with heating-system transition, evergreen species planning, and ventilation-sensitive urban design. Full article

Accurate estimation of crop yield from remote sensing remains challenging due to the crop-specific nature of yield drivers and the difficulty of interpreting spectral indicators across agronomic systems. While many studies prioritise predictive accuracy through complex models, fewer explicitly examine the stability and physiological relevance of individual spectral and phenological indicators under controlled analytical conditions. This study investigates yield–spectral relationships in wheat and cotton using a unified Sentinel-2 indicator framework applied across multiple growing seasons in a Mediterranean agricultural environment. A consistent set of spectral and thermal indicators was derived from two phenologically targeted Sentinel-2 acquisitions per season and analysed using correlation analysis, univariate regression, constrained multivariate modelling, and recurrence analysis within an identical workflow for both crops. Distinct crop-specific patterns were observed. Wheat yield was most strongly associated with water-sensitive and canopy-related indicators, with NDWI-based metrics reaching Pearson correlations up to r = 0.85 and multivariate models explaining a substantial proportion of yield variability (up to R² ≈ 0.70) under controlled analytical conditions. In contrast, cotton yield variability was dominated by thermal accumulation, with growing degree day indicators showing correlations up to |r| = 0.59 and multivariate performance reaching R² = 0.74. Recurrence analysis indicated consistent recurrence of these indicator families across analytical stages under the examined conditions. Overall, the results indicate that parsimonious, physiologically interpretable indicator combinations can account for a meaningful proportion of yield variability without reliance on highly complex or high-dimensional modelling approaches, supporting crop-aware indicator selection for precision agriculture applications. Full article

Aiming at the dual dilemma in high-resolution cropland change detection, where CNNs are constrained by limited local receptive fields and Transformers suffer from heavy computational costs, we propose LiteScan-Net, a lightweight and robust network architecture incorporating scanning principles from state-space modeling. The network innovatively introduces the Multi-Directional Global Scanning (MDGS) mechanism as an efficient engineering surrogate, which simulates the selective scanning process using large-kernel 1D convolutions. This achieves global context modeling with linear complexity while avoiding the hardware limitations imposed by recurrent computations. Based on this mechanism, a three-stage collaborative architecture is constructed: the Coordinate-Aware Feature Purification (CAFP) module is designed to mitigate shallow phenological noise via coordinate sensitivity; the Context Difference Verification (CDV) module aims to alleviate pseudo-changes caused by registration errors through global alignment; and the State-Space Guided Refinement (SSGR) module promotes the generation of change masks with precise boundaries and compact interiors. To verify the model generalization, we construct a Massive Specialized Cropland Change Detection dataset named MSCC, which exhibits significant cross-scale characteristics. Experimental results demonstrate that LiteScan-Net achieves state-of-the-art (SOTA) performance across the CLCD, Hi-CNA, and MSCC datasets, with F1-scores of 79.43%, 84.82%, and 89.62%, respectively. With a low computational cost of only 1.78 GFLOPs and a real-time inference speed of 37.9 FPS, LiteScan-Net demonstrates high potential for future deployment on resource-constrained edge devices. Full article

Urban railway corridors—including abandoned, redesigned, and in-use lines—can support biodiversity and ecological connectivity in fragmented cities, yet their ecological dynamics and roles in Nature-based Solutions (NbS) remain poorly understood. Addressing this requires a context-sensitive approach that differentiates corridor types and compares their ecological functions. This study compares vegetation dynamics along railway corridors in two cities with contrasting socio-ecological contexts—Perth (Western Australia) and Beijing (China)—using a typology-based comparative approach. The results show that: (1) vegetation dynamics differ fundamentally between the two cities, with Perth characterized by vertically structured vegetation dominated by native tree layers and non-native disturbance-tolerant annual groundcover, while Beijing supports more continuous vegetation with widespread natural regeneration of native species; and (2) these differences correspond to distinct suggested NbS strategies. For Perth, NbS should combine phenology-aware management (wet versus dry seasons) with disturbance-based zoning and staged native planting strategies. In contrast, Beijing corridors are characterized by more uniform disturbance patterns but differentiated corridor typologies, indicating NbS structured around corridor-type management with a stronger emphasis on the support of native groundcover establishment and allowing for self-sustaining regeneration. These findings highlight how different contexts shape vegetation dynamics and provide comparative ecological insights for developing context-specific NbS for urban railway corridors. Full article

Tea garden irrigation suffers from time delays, nonlinear interference, and phenological biomass fluctuations caused by plucking, leading to the failure of traditional Proportional–Integral–Derivative (PID) and fixed-threshold models in precise water supply. This study proposes a precision irrigation system for smart tea gardens integrating Phenology-Aware Collaborative Decision-Making and an Adaptive Gain Predictive Super-Twisting Sliding Mode Control (AG-PSTC) algorithm. A “temperature–time–water” phenological reference model was constructed, and Crop Water Stress Index (CWSI) was introduced to decouple shoot density changes into phenology-driven and water stress components, realizing dynamic target soil moisture (W_target) setting. The AG-PSTC algorithm combined an improved Smith predictor for phase compensation and a barrier function-based adaptive super-twisting term for chattering elimination and finite-time convergence. Simulations showed AG-PSTC reduced rise time by 78% and steady-state error by four orders of magnitude compared with PID, with robust performance under ±40% time-delay perturbation. Field tests confirmed the system suppressed false irrigation during plucking, with soil moisture standard deviation within 1.51%. This study provides a vertical integration framework from crop physiological models to precision control, promoting the transition of tea garden irrigation from experience-based to demand-based. 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

AI-driven imaging is becoming central to crop monitoring, with proximal and unmanned aerial vehicle (UAV) platforms now routinely used for disease and stress detection, yield estimation, canopy structure, and fruit counting. Yet, as these models move from plots to farms, the main bottleneck is no longer raw accuracy but robustness under distribution shift. Systems trained in one field, season, cultivar, or sensor often fail when the scene, sensor, protocol, or timing changes in realistic ways. This review synthesizes recent advances on robustness and transferability in proximal and UAV imaging, drawing on a corpus of 42 core studies across field crops, orchards, greenhouse environments, and multi-platform phenotyping. Shift types are organized into four axes, namely scene, sensor, protocol, and time. The article also maps the empirical evidence on when RGB imaging alone is sufficient and when multispectral, hyperspectral, or thermal modalities can potentially improve robustness. This serves as a basis to synthesize acquisition and evaluation practices that often matter more than architectural tweaks, which include phenology-aware flight planning, radiometric standardization, metadata logging, and leave-one-field/season-out splits. Adaptation options are consolidated into a practical symptom/remedy roadmap, ranging from lightweight normalization and small target-set fine-tuning to feature alignment, unsupervised domain adaptation, style translation, and test-time updates. Finally, a benchmark and dataset agenda are outlined with emphasis on object-oriented splits, cross-sensor and cross-scale collections, and longitudinal datasets where the same fields are followed across seasons under different management regimes. The goal is to outline practices and evaluation protocols that support progress toward deployable and auditable systems, noting that such claims require standardized out-of-distribution testing and transparent reporting as emphasized in the benchmark specification and experiment suite proposed here. 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

The Soil and Plant Analyzer Development (SPAD) value is a reliable proxy for chlorophyll, yet conventional field measurement remains labor-intensive and spatially limited. Current remote sensing inversion models typically depend on costly multispectral sensors and rarely account for phenological changes, restricting their applicability across orchards and seasons. To overcome these limitations, this study introduces a stage-aware and low-cost SPAD inversion framework for jujube trees, integrating multi-source data fusion and an optimized ensemble model. A two-year experiment (2023–2024) combined UAV multispectral vegetation indices (VI) with RGB-derived color indices (CI) across leaf expansion, flowering, and fruit-setting stages. Rather than using static features, stage-specific predictors were systematically identified through a hybrid selection mechanism combining Random Forest Cumulative Feature Importance (RF-CFI), Recursive Feature Elimination (RFE), and F-tests. Building on these tailored features, XGBoost, decision tree (DT), CatBoost, and an Optimized Integrated Architecture (OIA) were developed, with all hyperparameters globally tuned using a genetic algorithm (GA). The RFI-CFI-OIA-GA model delivered superior accuracy (R² = 0.758–0.828; MSE = 0.214–2.593; MAPE = 0.01–0.045 in 2024) in the training dataset, and robust cross-year transferability (R² = 0.541–0.608; MSE = 0.698–5.139; MAPE = 0.015–0.058 in 2023). These results demonstrate that incorporating phenological perception into multi-source data fusion substantially reduces interference and enhances generalizability, providing a scalable and reusable strategy for precision orchard management and spatiotemporal SPAD mapping. Full article

Persistent cloud cover during the growing season and mosaic cropping patterns introduce temporal gaps and mixed pixels, undermining the reliability of large-scale crop identification and acreage statistics. To address these issues, we develop a high spatiotemporal-resolution remote-sensing approach tailored to heterogeneous farmlands. First, an improved Spatiotemporal Adaptive Reflectance Fusion Model (STARFM) is used to fuse Landsat, Sentinel-2, and MODIS observations, reconstructing a continuous Normalized Difference Vegetation Index (NDVI) time series at 30 m spatial and 8-day temporal resolution. Second, at the field scale, we derive phenological descriptors from the reconstructed series—key phenophase timing, amplitude, temporal trend, and growth rate—and use a Random Forest (RF) classifier for detailed crop discrimination. We further integrate SHapley Additive exPlanations (SHAP) to quantify each feature’s class-discriminative contribution and signed effect, thereby guiding feature-set optimization and threshold refinement. Finally, we generate a 2024 crop distribution map and conduct comparative evaluations. Relative to baselines without fusion or without phenological variables, the fused series mitigates single-sensor limitations under frequent cloud/rain and irregular acquisitions, enhances NDVI continuity and robustness, and reveals inter-crop temporal phase shifts that, when jointly exploited, reduce early-season confusion and improve identification accuracy. Independent validation yields an overall accuracy (OA) of 90.78% and a Cohen’s kappa(κ) coefficient of 0.882. Coupling dense NDVI reconstruction with phenology-aware constraints and SHAP-based interpretability demonstrably improves the accuracy and reliability of cropping-structure extraction in complex agricultural regions and provides a reusable pathway for regional-scale precision agricultural monitoring. Full article

Mountain forests play a key role in buffering local climate, yet their climate sensitivity is seldom mapped in a way that is directly usable for spatial planning. This study investigates how phenological thermal and vegetation variability are organized within the forested landscape of Namyangju, a mountainous region in central Korea, and derives spatial indicators of forest climate sensitivity. Using monthly, cloud-screened Landsat-8/9 land surface temperature (LST) and normalized difference vegetation index (NDVI) images over a recent multi-year period, we calculated phenological coefficients of variation for 34,123 forest grid cells and applied local clustering analysis to identify belts of high and low variability. Forest areas where LST and NDVI variability simultaneously occupied the upper tail of their distributions (top 5%/10%/20%) were interpreted as climate-sensitivity hotspots, whereas co-located coldspots were treated as microclimatic refugia. Across the mountainous terrain, sensitivity hotspots formed continuous belts along high-elevation ridges and steep, dissected slopes, while coldspots were concentrated in sheltered valley floors. Notably, the most sensitive belts were dominated by high-elevation conifer stands, despite the limited seasonal fluctuation typically expected in evergreen canopies. This pattern suggests that elevation strongly amplifies the coupling between thermal responsiveness and vegetation health, whereas valley-bottom forests act as stabilizers that maintain comparatively constant microclimatic and phenological conditions. We refer to these patterns as “forest climate-sensitivity belts,” which translate satellite observations into spatially explicit information on where climate-buffering functions are most vulnerable or resilient. Incorporating climate-sensitivity belts into forest plans and adaptation strategies can guide elevation-aware species selection in new afforestation, targeted restoration and fuel-load management in upland sensitivity zones, and the protection of valley refugia that support biodiversity, thermal buffering, and hydrological regulation. Because the framework relies on standard satellite products and transparent calculations, it can be updated as new imagery becomes available and transferred to other seasonal, mountainous regions, providing a practical basis for climate-resilient forest planning. Full article