Benefiting from powerful feature extraction capabilities, convolutional neural networks (CNNs) have gained prominence in hyperspectral image (HSI) classification. Nevertheless, with restricted receptive fields of convolution kernels, CNN-based methods fail to learn complex characteristics of long-range sequences. Meanwhile, vision transformer allows us to learn long-range dependencies in a global view, but local region features are ignored. To overcome these limitations, we propose a novel method entitled global-local three-dimensional convolutional transformer network (GTCT), where 3-D convolution is embedded in a dual-branch transformer to simultaneously capture global-local associations in both spectral and spatial domains. In particular, the global-local spectral convolutional transformer (GECT) is designed to exploit global spectral sequence signatures and local spectral relationships between bands. Symmetrically, the global-local spatial convolutional transformer (GACT) is devised to exploit local spatial context features and global interactions among different pixels. In addition, multiscale global-local spectral-spatial information is adaptively fused with trainable weights by the weighted multiscale spectral-spatial feature interaction (WMSFI) module. It is worth noting that a spectral-spatial global attention mechanism (SSGAM) is incorporated into multi-head convolutional attention to further integrate discriminative spectral-spatial information. Extensive experiments on four HSI datasets, including GF-5 and ZY1-02D satellite hyperspectral images, demonstrate the superiority of the proposed GTCT method over other state-of-the-art algorithms with fewer parameters and lower floating-point operations (FLOPs) in practical applications.

Satellite hyperspectral imagery is an important data source for large-scale refined land cover classification and mapping, but the high spatial heterogeneity and spectral variability at low spatial resolution and the high computation cost for massive data remain challenges in the research community. In recent years, convolutional neural network (CNN) models with the capability for feature extraction have been widely used in hyperspectral image classification. However, incomplete feature extraction, inappropriate feature fusion, and high time consumption are still the major problems for CNN applications in large-scale fine land cover mapping. In this study, a Spatial-Convolution Spectral-Transformer Interactive Network (SCSTIN) was proposed to integrate 2D-CNN and Transformer into a dual-branch network to enhance feature extraction capabilities by exploring spatial context information and spectral sequence signatures in a targeted manner. In addition, spatial-spectral interactive fusion (SSIF) units and category-adaptive weighting (CAW) as two feature fusion modules were also adopted between and after the two feature extraction branches to improve efficiency in feature fusion. The ZY1-02D hyperspectral imagery was collected to conduct the experiments in the study area of the eastern foothills of the Helan Mountains (EFHLM), covering an area of about 8800 km², which is the largest hyperspectral dataset as far as we know. To explore the potential of the proposed network in terms of accuracy and efficiency, SCSTIN models with different depths (SCSTIN-4 and SCSTIN-2) were performed. The results suggest that compared with the previous eight advanced hyperspectral image classifiers, both SCSTIN models achieved satisfactory performance in accuracy and efficiency aspects with low complexity, where SCSTIN-4 achieved the highest accuracy and SCSTIN-2 obtained higher efficiency. Accordingly, the SCSTIN models are reliable for large-scale fast refined land cover classification and mapping. In addition, the spatial distribution pattern of diverse ground objects in EFHLM is also analyzed.

To address the difficulty of separating background materials from similar materials associated with the use of “single-spectral information” for hyperspectral anomaly detection, a fast hyperspectral anomaly detection algorithm based on what we term the “greedy bilateral smoothing and extended multi-attribute profile” (GBSAED) method is proposed to improve detection precision and operation efficiency. This method utilizes “greedy bilateral smoothing” to decompose the low-rank part of a hyperspectral image (HSI) dataset and calculate spectral anomalies. This process improves the operational efficiency. Then, the extended multi-attribute profile is used to extract spatial anomalies and restrict the shape of anomalies. Finally, the two components are combined to limit false alarms and obtain appropriate detection results. This new method considers both spectral and spatial information with an improved structure that ensures operational efficiency. Using five real HSI datasets, this study demonstrates that the GBSAED method is more robust than eight representative algorithms under diverse application scenarios and greatly improves detection precision and operational efficiency.

Aquaculture plays a vital role in global food production, with fish pond water quality directly impacting aquatic product quality. The Guangdong-Hong Kong-Macao Greater Bay Area (GBA) serves as a key producer of aquatic products in South China. Monitoring environmental changes in fish ponds serves as an indicator of their health. This study employed the extreme gradient boosting tree (BST) model of machine learning, utilizing Landsat imagery data, to assess Chlorophyll-a (Chl-a) concentration in GBA fish ponds from 2013 to 2022. The study also examined the corresponding spatiotemporal variations in Chl-a concentration. Key findings include: (1) clear seasonal fluctuations in Chl-a concentration, peaking in summer (56.7 μg·L⁻¹) and reaching lows in winter (43.5 μg·L⁻¹); (2) a slight overall increase in Chl-a concentration over the study period, notably in regions with rapid economic development, posing a heightened risk of eutrophication; (3) influence from both human activities and natural factors such as water cycle and climate, with water temperature notably impacting summer Chl-a levels; (4) elevated Chl-a levels in fish ponds compared to surrounding natural water bodies, primarily attributed to human activities, indicating an urgent need to revise breeding practices and address eutrophication. These findings offer a quantitative assessment of fish pond water quality and contribute to sustainable aquaculture management in the GBA.

Early-season sugarcane identification plays a pivotal role in precision agriculture, enabling timely yield forecasting and informed policy-making. Compared to post-season crop identification, early-season identification faces unique challenges, including incomplete temporal observations and spectral ambiguity among crop types in early seasons. Previous studies have not systematically investigated the capability of optical and synthetic aperture radar (SAR) data for early-season sugarcane identification, which may result in suboptimal accuracy and delayed identification timelines. Both the timing for reliable identification (≥90% accuracy) and the earliest achievable timepoint matching post-season level remain undetermined, and which features are effective in the early-season identification is still unknown. To address these questions, this study integrated Sentinel-1 and Sentinel-2 data, extracted 10 spectral indices and 8 SAR features, and employed a random forest classifier for early-season sugarcane identification by means of progressive temporal analysis. It was found that LSWI (Land Surface Water Index) performed best among 18 individual features. Through the feature set accumulation, the seven-dimensional feature set (LSWI, IRECI (Inverted Red-Edge Chlorophyll Index), EVI (Enhanced Vegetation Index), PSSRa (Pigment Specific Simple Ratio a), NDVI (Normalized Difference Vegetation Index), VH backscatter coefficient, and REIP (Red-Edge Inflection Point Index)) achieved the earliest attainment of 90% accuracy by 30 June (early-elongation stage), with peak accuracy (92.80% F1-score) comparable to post-season accuracy reached by 19 August (mid-elongation stage). The early-season sugarcane maps demonstrated high agreement with post-season maps. The 30 June map achieved 88.01% field-level and 90.22% area-level consistency, while the 19 August map reached 91.58% and 93.11%, respectively. The results demonstrate that sugarcane can be reliably identified with accuracy comparable to post-season mapping as early as six months prior to harvest through the integration of optical and SAR data. This study develops a robust approach for early-season sugarcane identification, which could fundamentally enhance precision agriculture operations through timely crop status assessment.

Accurate phenological information on sugarcane is crucial for guiding precise cultivation management and enhancing sugar production. Remote sensing offers an efficient approach for large-scale phenology retrieval, but most studies have primarily focused on staple crops. The methods for retrieving the sugarcane phenology—the germination, tillering, elongation, and maturity stages—remain underexplored. This study addresses the challenge of accurately monitoring the sugarcane phenology in complex terrains by proposing an optimized strategy integrating spatiotemporal fusion data. Ground-based validation showed that the change detection method based on the Double-Logistic curve significantly outperformed the threshold-based approach, with the highest accuracy for the elongation and maturity stages achieved at the maximum slope points of the ascending and descending phases, respectively. For the germination and tillering stages with low canopy cover, a novel time-windowed change detection method was introduced, using the first local maximum of the third derivative curve (denoted as Point A) to establish a temporal buffer. The optimal retrieval models were identified as 25 days before and 20 days after Point A for germination and tillering, respectively. Among the six commonly used vegetation indices, the NDVI (normalized difference vegetation index) performed the best across all the phenological stages. Spatiotemporal fusion using the ESTARFM (Enhanced Spatial and Temporal Adaptive Reflectance Fusion Model) significantly improved the monitoring accuracy in heterogeneous agricultural landscapes, reducing the RMSE (root-mean-squared error) by 21–46%, with retrieval errors decreasing from 18.25 to 12.97 days for germination, from 8.19 to 4.41 days for tillering, from 19.17 to 10.78 days for elongation, and from 19.02 to 15.04 days for maturity, highlighting its superior accuracy. The findings provide a reliable technical solution for precision sugarcane management in heterogeneous landscapes.