This study investigates the dynamic changes in wheat canopy spectral characteristics across seven critical growth stages (Tillering, Pre-Jointing, Jointing, Post-Jointing, Booting, Flowering, and Ripening) using UAV-based multispectral remote sensing. By analyzing four key spectral bands—green (G), red (R), red-edge (RE), and near-infrared (NIR)—and their combinations, we identify spectral features that reflect changes in canopy activity, health, and structure. Results show that the green band is highly sensitive to chlorophyll activity and low canopy coverage during the Tillering stage, while the NIR band captures structural complexity and canopy density during the Jointing and Booting stages. The combination of G and NIR bands reveals increased canopy density and spectral concentration during the Booting stage, while the RE band effectively detects plant senescence and reduced spectral uniformity during the ripening stage. Time-series analysis of spectral data across growth stages improves the accuracy of growth stage identification, with dynamic spectral changes offering insights into growth inflection points. Spatially, the study demonstrates the potential for identifying field-level anomalies, such as water stress or disease, providing actionable data for targeted interventions. This comprehensive spatio-temporal monitoring framework improves crop management and offers a cost-effective, precise solution for disease prediction, yield forecasting, and resource optimization. The study paves the way for integrating UAV remote sensing into precision agriculture practices, with future research focusing on hyperspectral data integration to enhance monitoring models.

Hyperspectral imaging (HSI) plays a pivotal role in modern agriculture by capturing fine-grained spectral signatures that support crop classification, health assessment, and land-use monitoring. However, the transition from raw spectral data to reliable semantic understanding remains challenging—particularly under fragmented planting patterns, spectral ambiguity, and spatial heterogeneity. To address these limitations, we propose UniHSFormer-X, a unified transformer-based framework that reconstructs agricultural semantics through prototype-guided token routing and hierarchical context modeling. Unlike conventional models that treat spectral–spatial features uniformly, UniHSFormer-X dynamically modulates information flow based on class-aware affinities, enabling precise delineation of field boundaries and robust recognition of spectrally entangled crop types. Evaluated on three UAV-based benchmarks—WHU-Hi-LongKou, HanChuan, and HongHu—the model achieves up to 99.80% overall accuracy and 99.28% average accuracy, outperforming state-of-the-art CNN, ViT, and hybrid architectures across both structured and heterogeneous agricultural scenarios. Ablation studies further reveal the critical role of semantic routing and prototype projection in stabilizing model behavior, while parameter surface analysis demonstrates consistent generalization across diverse configurations. Beyond high performance, UniHSFormer-X offers a semantically interpretable architecture that adapts to the spatial logic and compositional nuance of agricultural imagery, representing a forward step toward robust and scalable crop classification.

Forest ecosystem water conservation is an important ecohydrological regulating service for sustaining mountain watersheds under climate change. This study assessed water-conservation services in the eastern Dabie Mountains of China by integrating the InVEST Water Yield module under the Budyko framework, a Coupling Coordination Degree (CCD) model, and pixel-scale Theil–Sen, Mann–Kendall, and Ordinary Least Squares analyses. The study covered 1985–2024 through ten benchmark years (1985, 1990, 1995, 2000, 2005, 2010, 2015, 2020, 2022, and 2024). Mean water-conservation capacity across the benchmark-year maps was 362.7 mm. The OLS slope was 1.40 mm/a, while the two-sided MK test was non-significant (Z_MK = 0.54, p = 0.592), indicating a weak positive tendency in the benchmark-year sequence. Year-to-year variation was closely associated with hydroclimatic conditions, with canopy interception, litter storage, soil-water storage, and flow attenuation providing process pathways within the model framework. Water-conservation capacity reached 534.4 mm in the wet 2020 benchmark year, declined to 268.2 mm during the 2022 drought, and recovered to 369.6 mm in 2024. Comparison with area-scaled official bulletin surface-water references for seven overlapping years yielded a mean absolute percentage error of 5.21% and absolute relative errors of 0.00%–17.62%. High-value service areas were concentrated in the central forested massif, whereas low-value and coordination-imbalance areas were more common along agricultural and urbanizing margins. The integrated framework links service intensity, coordination status, and historical tendency to support differentiated watershed management and to identify spatial contrasts together with benchmark-year hydroclimatic responses.

Mountain–hill–plain transition zones combine terrain sensitivity, agricultural land use, and construction pressure and therefore require spatially differentiated management. This study develops a pressure-oriented framework that distinguishes composite ecological vulnerability from soil-erosion pressure and translates their multi-period co-occurrence into management demand. Using multi-source raster data for 2000, 2005, 2010, 2015, and 2020 on a common 30 m reference grid, we constructed an ecological vulnerability index (EVI) from 14 ecological, environmental, and human-activity indicators using a sensitivity–resilience–pressure framework, combined analytic hierarchy process (AHP)–entropy weighting, and unified natural breaks. Soil erosion intensity was estimated with the Revised Universal Soil Loss Equation (RUSLE) using digital elevation model (DEM)-derived flow accumulation, a capped effective slope length, and a fractional vegetation cover (FVC)-based cover-management factor. The EVI and RUSLE dimensions were integrated through a two-dimensional pressure matrix, a Coupled Pressure Index (CPI), and an Integrated Management Demand Index (IMDI). High vulnerability was concentrated in northern, urban-fringe, and selected agricultural areas, whereas moderate-or-above erosion was concentrated on slopes, in gullies, and on hilly farmland; areas subject to both pressures were spatially selective. The largest EVI weights were assigned to mean annual precipitation (0.3841), mean annual temperature (0.1727), ecosystem type (0.0820), biological abundance (0.0810), and built-up land ratio (0.0746). Non-vulnerable and slightly vulnerable areas increased from 40.62% to 64.27%, whereas highly and extremely vulnerable areas decreased from 38.98% to 23.29%. Moderate-or-above soil erosion accounted for 13.56% in 2020. The five-zone comprehensive management classification comprised stable conservation (40.19%), soil and water conservation priority (13.73%), ecological vulnerability regulation (27.94%), integrated management priority (1.48%), and transition management (16.66%). By linking ecological diagnosis, erosion-pressure identification, persistence analysis, and county-level zoning, the framework provides an interpretable spatial basis for prioritizing ecological conservation, soil and water conservation, and land-use management in mountain–hill–plain transition regions.