Search Results (40)

Cotton is a globally strategic crop that plays a crucial role in sustaining national economies and livelihoods. To address the challenges of accurate cotton field extraction in the complex planting environments of Xinjiang’s Alaer reclamation area, a cotton field identification model was developed that integrates multi-source satellite remote sensing data with machine learning methods. Using imagery from Sentinel-2, GF-1, and Landsat 8, we performed feature fusion using principal component, Gram–Schmidt (GS), and neural network techniques. Analyses of spectral, vegetation, and texture features revealed that the GS-fused blue bands of Sentinel-2 and Landsat 8 exhibited optimal performance, with a mean value of 16,725, a standard deviation of 2290, and an information entropy of 8.55. These metrics improved by 10,529, 168, and 0.28, respectively, compared with the original Landsat 8 data. In comparative classification experiments, the endmember-based random forest classifier (RFC) achieved the best traditional classification performance, with a kappa value of 0.963 and an overall accuracy (OA) of 97.22% based on 250 samples, resulting in a cotton-field extraction error of 38.58 km². By enhancing the deep learning model, we proposed a U-Net architecture that incorporated a Convolutional Block Attention Module and Atrous Spatial Pyramid Pooling. Using the GS-fused blue band data, the model achieved significantly improved accuracy, with a kappa coefficient of 0.988 and an OA of 98.56%. This advancement reduced the area estimation error to 25.42 km², representing a 34.1% decrease compared with that of the RFC. Based on the optimal model, we constructed a digital map of continuous cotton cropping from 2021 to 2023, which revealed a consistent decline in cotton acreage within the reclaimed areas. This finding underscores the effectiveness of crop rotation policies in mitigating the adverse effects of large-scale monoculture practices. This study confirms that the synergistic integration of multi-source satellite feature fusion and deep learning significantly improves crop identification accuracy, providing reliable technical support for agricultural policy formulation and sustainable farmland management. Full article

Hyperspectral sparse unmixing (SU) networks have recently received considerable attention due to their model hyperspectral images (HSIs) with a priori spectral libraries and to capture nonlinear features through deep networks. This method effectively avoids errors associated with endmember extraction, and enhances the unmixing performance via nonlinear modeling. However, two major challenges remain: the use of large spectral libraries with high coherence leads to computational redundancy and performance degradation; moreover, certain feature extraction models, such as Transformer, while exhibiting strong representational capabilities, suffer from high computational complexity. To address these limitations, this paper proposes a hyperspectral unmixing dual-branch network integrating an adaptive hop-aware GCN and neighborhood offset Mamba that is termed DGMNet. Specifically, DGMNet consists of two parallel branches. The first branch employs the adaptive hop-neighborhood-aware GCN (AHNAGC) module to model global spatial features. The second branch utilizes the neighborhood spatial offset Mamba (NSOM) module to capture fine-grained local spatial structures. Subsequently, the designed Mamba-enhanced dual-stream feature fusion (MEDFF) module fuses the global and local spatial features extracted from the two branches and performs spectral feature learning through a spectral attention mechanism. Moreover, DGMNet innovatively incorporates a spectral-library-pruning mechanism into the SU network and designs a new pruning strategy that accounts for the contribution of small-target endmembers, thereby enabling the dynamic selection of valid endmembers and reducing the computational redundancy. Finally, an improved ESS-Loss is proposed, which combines an enhanced total variation (ETV) with an $l_{1/2}$ sparsity constraint to effectively refine the model performance. The experimental results on two synthetic and five real datasets demonstrate the effectiveness and superiority of the proposed method compared with the state-of-the-art methods. Notably, experiments on the Shahu dataset from the Gaofen-5 satellite further demonstrated DGMNet’s robustness and generalization. Full article

In recent years, deep learning (DL) has been demonstrated remarkable capabilities in hyperspectral unmixing (HU) due to its powerful feature representation ability. Convolutional neural networks (CNNs) are effective in capturing local spatial information, but limited in modeling long-range dependencies. In contrast, transformer architectures extract global contextual features via multi-head self-attention (MHSA) mechanisms. However, most existing transformer-based HU methods focus only on spatial or spectral modeling at a single scale, lacking a unified mechanism to jointly explore spatial and channel-wise dependencies. This limitation is particularly critical for multiscale contextual representation in complex scenes. To address these issues, this article proposes a novel Spatial-Channel Multiscale Transformer Network (SCMT-Net) for HU. Specifically, a compact feature projection (CFP) module is first used to extract shallow discriminative features. Then, a spatial multiscale transformer (SMT) and a channel multiscale transformer (CMT) are sequentially applied to model contextual relations across spatial dimensions and long-range dependencies among spectral channels. In addition, a multiscale multi-head self-attention (MMSA) module is designed to extract rich multiscale global contextual and channel information, enabling a balance between accuracy and efficiency. An efficient feed-forward network (E-FFN) is further introduced to enhance inter-channel information flow and fusion. Experiments conducted on three real hyperspectral datasets (Samson, Jasper and Apex) and one synthetic dataset showed that SCMT-Net consistently outperformed existing approaches in both abundance estimation and endmember extraction, demonstrating superior accuracy and robustness. Full article

The Tibetan Plateau, known as the “Third Pole” and the “Water Tower of Asia”, has experienced significant changes in its surface water due to global warming. Accurately understanding and monitoring the spatiotemporal distribution of surface water is crucial for ecological conservation and the sustainable use of water resources. Among existing satellite data, the MODIS sensor stands out for its long time series and high temporal resolution, which make it advantageous for large-scale water body monitoring. However, its spatial resolution limitations hinder detailed monitoring. To address this, the present study proposes a dynamic endmember selection method based on phenological features, combined with mixed pixel decomposition techniques, to generate monthly water abundance maps of the Tibetan Plateau from 2000 to 2023. These maps precisely depict the interannual and seasonal variations in surface water, with an average accuracy of 95.3%. Compared to existing data products, the water abundance maps developed in this study provide better detail of surface water, while also benefiting from higher temporal resolution, enabling effective capture of dynamic water information. The dynamic monitoring of surface water on the Tibetan Plateau shows a year-on-year increase in water area, with an increasing fluctuation range. The surface water abundance products presented in this study not only provide more detailed information for the fine characterization of surface water but also offer a new technical approach and scientific basis for timely and accurate monitoring of surface water changes on the Tibetan Plateau. Full article

Hyperspectral unmixing (HU) aims to decompose mixed pixels into a set of endmembers and corresponding abundances. Deep learning-based HU methods are currently a hot research topic, but most existing unmixing methods still rely on per-pixel training or employ convolutional neural networks (CNNs), which overlook the non-local correlations of materials and spectral characteristics. Furthermore, current research mainly focuses on linear mixing models, which limits the feature extraction capability of deep encoders and further improvement in unmixing accuracy. In this paper, we propose a nonlinear unmixing network capable of extracting global spatial-spectral features. The network is designed based on an autoencoder architecture, where a dual-stream CNNs is employed in the encoder to separately extract spectral and local spatial information. The extracted features are then fused together to form a more complete representation of the input data. Subsequently, a linear projection-based multi-head self-attention mechanism is applied to capture global contextual information, allowing for comprehensive spatial information extraction while maintaining lightweight computation. To achieve better reconstruction performance, a model-free nonlinear mixing approach is adopted to enhance the model’s universality, with the mixing model learned entirely from the data. Additionally, an initialization method based on endmember bundles is utilized to reduce interference from outliers and noise. Comparative results on real datasets against several state-of-the-art unmixing methods demonstrate the superior of the proposed approach. Full article

With the growing use of hyperspectral remote sensing payloads, there has been a significant increase in the number of hyperspectral remote sensing image archives, leading to a massive amount of collected data. This highlights the need for an efficient content-based hyperspectral image retrieval (CBHIR) system to manage and enable better use of hyperspectral remote-sensing image archives. Conventional CBHIR systems characterize each image by a set of endmembers and then perform image retrieval based on pairwise distance measures. Such an approach significantly increases the computational complexity of the retrieval, mainly when the diversity of materials is high. Those systems also have difficulties in retrieving images containing particular materials with extremely low abundance compared to other materials, which leads to describing image content with inappropriate and/or insufficient spectral features. In this article, a novel CBHIR system to define global hyperspectral image representations based on a semantic approach to differentiate foreground and background image content for different retrieval scenarios is introduced to address these issues. The experiments conducted on a new benchmark archive of multi-label hyperspectral images, which is first introduced in this study, validate the retrieval accuracy and effectiveness of the proposed system. Comparative performance analysis with the state-of-the-art CBHIR systems demonstrates that modeling hyperspectral image content with foreground and background vocabularies has a positive effect on retrieval performance. Full article

Accurate inventories of grasslands are important for studies of greenhouse gas (GHG) dynamics, as grasslands store about one-third of the global terrestrial carbon stocks. This paper develops a framework for large-area grassland mapping based on the probability of grassland occurrence and the interactive pathways of fractional vegetation and soil-related endmember nexuses. In this study, grassland occurrence probability maps were produced based on data on bio-climate factors obtained from MODIS/Terra Land Surface Temperature (MOD11A2), MODIS/Terra Vegetation Indices (MOD13A3), and Tropical Rainfall Measuring Mission (TRMM 3B43) using the random forests (RF) method. Time series of 8-day fractional vegetation-related endmembers (green vegetation, non-photosynthetic vegetation, sand land, saline land, and dark surfaces) were generated using linear spectral mixture analysis (LSMA) based on MODIS/Terra Surface Reflectance data (MOD09A1). Time-series endmember fraction maps and grassland occurrence probabilities were employed to map grassland distribution using an RF model. This approach improved the accuracy by 5% compared to using endmember fractions alone. Additionally, based on the grassland occurrence probability maps, we identified extensive ecologically sensitive regions, encompassing 1.54 (10⁴ km²) of desert-to-steppe (D-S) and 2.34 (10⁴ km²) of steppe-to-meadow (S-M) transition regions. Among these, the D-S area is located near the threshold of 310 mm/yr in precipitation, an annual temperature of 10.16 °C, and a surface comprehensive drought index (TVPDI) of 0.59. The S-M area is situated close to the line of 437 mm/yr in precipitation, an annual temperature of 5.49 °C, and a TVPDI of 0.83. Full article

Hyperspectral unmixing, which decomposes mixed pixels into the endmembers and corresponding abundances, is an important image process for the further application of hyperspectral images (HSIs). Lately, the unmixing problem has been solved using deep learning techniques, particularly autoencoders (AEs). However, the majority of them are based on the simple linear mixing model (LMM), which disregards the spectral variability of endmembers in different pixels. In this article, we present a multi-attention AE network (MAAENet) based on the extended LMM to address the issue of the spectral variability problem in real scenes. Moreover, the majority of AE networks ignore the global spatial information in HSIs and operate pixel- or patch-wise. We employ attention mechanisms to design a spatial–spectral attention (SSA) module that can deal with the band redundancy in HSIs and extract global spatial features through spectral correlation. Moreover, noticing that the mixed pixels are always present in the intersection of different materials, a novel sparse constraint based on spatial homogeneity is designed to constrain the abundance and abstract local spatial features. Ablation experiments are conducted to verify the effectiveness of the proposed AE structure, SSA module, and sparse constraint. The proposed method is compared with several state-of-the-art unmixing methods and exhibits competitiveness on both synthetic and real datasets. Full article

Deep learning networks based on CNNs or transformers have made progress in spectral reconstruction (SR). However, many methods focus solely on feature extraction, overlooking the interpretability of network design. Additionally, models exclusively based on CNNs or transformers may lose other prior information, sacrificing reconstruction accuracy and robustness. In this paper, we propose a novel Unmixing-Guided Convolutional Transformer Network (UGCT) for interpretable SR. Specifically, transformer and ResBlock components are embedded in Paralleled-Residual Multi-Head Self-Attention (PMSA) to facilitate fine feature extraction guided by the excellent priors of local and non-local information from CNNs and transformers. Furthermore, the Spectral–Spatial Aggregation Module (S2AM) combines the advantages of geometric invariance and global receptive fields to enhance the reconstruction performance. Finally, we exploit a hyperspectral unmixing (HU) mechanism-driven framework at the end of the model, incorporating detailed features from the spectral library using LMM and employing precise endmember features to achieve a more refined interpretation of mixed pixels in HSI at sub-pixel scales. Experimental results demonstrate the superiority of our proposed UGCT, especially in the grss_d f c_2018 dataset, in which UGCT attains an RMSE of 0.0866, outperforming other comparative methods. Full article

Spectral unmixing is among one of the major hyperspectral image analysis tasks that aims to extract basic features (endmembers) at the subpixel level and estimate their corresponding proportions (fractional abundances). Recently, the rapid development of deep learning networks has provided us with a new method to solve the problem of spectral unmixing. In this paper, we propose a spatial-information-assisted spectral information learning unmixing network (SISLU-Net) for hyperspectral images. The SISLU-Net consists of two branches. The upper branch focuses on the extraction of spectral information. The input of the upper branch is a number of pixels randomly extracted from the hyperspectral image. The data are fed into the network as a random combination of different pixel blocks each time. The random combination of batches can boost the network to learn global spectral information. Another branch focuses on learning spatial information from the entire hyperspectral image and transmitting it to the upper branch through the shared weight strategy. This allows the network to take into account the spectral information and spatial information of HSI at the same time. In addition, according to the distribution characteristics of endmembers, we employ Wing loss to solve the problem of uneven distributions of endmembers. Experimental results on one synthetic and three real hyperspectral data sets show that SISLU-Net is effective and competitive compared with several state-of-the-art unmixing algorithms in terms of the spectral angle distance (SAD) of the endmembers and the root mean square error (RMSE) of the abundances. Full article

In response to significant shifts in dietary and lifestyle preferences, the global demand for fruits has increased dramatically, especially for apples, which are consumed worldwide. Growing apple orchards of more productive and higher quality with limited land resources is the way forward. Precise planting age identification and yield prediction are indispensable for the apple market in terms of sustainable supply, price regulation, and planting management. The planting age of apple trees significantly determines productivity, quality, and yield. Therefore, we integrated the time-series spectral endmember and logistic growth model (LGM) to accurately identify the planting age of apple orchard, and we conducted planting age-driven yield prediction using a neural network model. Firstly, we fitted the time-series spectral endmember of green photosynthetic vegetation (GV) with the LGM. By using the four-points method, the environmental carrying capacity (ECC) in the LGM was available, which serves as a crucial parameter to determine the planting age. Secondly, we combined annual planting age with historical apple yield to train the back propagation (BP) neural network model and obtained the predicted apple yields for 12 counties. The results show that the LGM method can accurately estimate the orchard planting age, with Mean Absolute Error (MAE) being 1.76 and the Root Mean Square Error (RMSE) being 2.24. The strong correlation between orchard planting age and apple yield was proved. The results of planting age-driven yield prediction have high accuracy, with the MAE up to 2.95% and the RMSE up to 3.71%. This study provides a novel method to accurately estimate apple orchard planting age and yields, which can support policy formulation and orchard planning in the future. Full article

The Dynamic World product is a discrete land cover classification of Sentinel 2 reflectance imagery that is global in extent, retrospective to 2015, and updated continuously in near real time. The classifier is trained on a stratified random sample of 20,000 hand-labeled 5 × 5 km Sentinel 2 tiles spanning 14 biomes globally. Since the training data are based on visual interpretation of image composites by both expert and non-expert annotators, without explicit spectral properties specified in the class definitions, the spectral characteristics of the classes are not obvious. The objective of this study is to quantify the physical distinctions among the land cover classes by characterizing the spectral properties of the range of reflectance present within each of the Dynamic World classes over a variety of landscapes. This is achieved by comparing both the eight-class probability feature space (excluding snow) and the maximum probability class assignment (label) distributions to continuous land cover fraction estimates derived from a globally standardized spectral mixture model. Standardized substrate, vegetation, and dark (SVD) endmembers are used to unmix nine Sentinel 2 reflectance tiles from nine spectral diversity hotspots for comparison between the SVD land cover fraction continua and the Dynamic World class probability continua and class assignments. The variance partition for the class probability feature spaces indicates that eight of these nine hotspots are effectively five-dimensional to 95% of variance. Class probability feature spaces of the hotspots all show a tetrahedral form with probability continua spanning multiple classes. Comparison of SVD land cover fraction distributions with maximum probability class assignments (labels) and probability feature space distributions reveal a clear distinction between (1) physically and spectrally heterogeneous biomes characterized by continuous gradations in vegetation density, substrate albedo, and structural shadow fractions, and (2) more homogeneous biomes characterized by closed canopy vegetation (forest) or negligible vegetation cover (e.g., desert, water). Due to the ubiquity of spectrally heterogeneous biomes worldwide, the class probability feature space adds considerable value to the Dynamic World maximum probability class labels by offering users the opportunity to depict inherently gradational heterogeneous landscapes otherwise not generally offered with other discrete thematic classifications. Full article

The North Yellow Sea, located at the intersection of the Eurasian continent and North Pacific Ocean at mid-latitudes, is a sensitive area subjected to the joint actions of the ocean, land, and monsoons. On its southern shore, loess and paleosol sedimentary sequences were widely developed during the last interglacial period, which is of great significance for revealing patterns of climate change and dynamic conditions. In this paper, we focus on the Zhifu section (ZFS) on Zhifu Island within the Shandong Province of China. The optically stimulated luminescence (OSL) dating method was used to construct our chronological framework. Grain size and its endmember (EM) components were then analyzed; EM1 is a clay component EM, which represents a weak dynamic environment and strong weathering pedogenesis, while EM2 and EM3 are silt and very fine sand component EMs, respectively, representing a strong dynamic environment and weak weathering pedogenesis. Maximum EM1, mean grain size, clay content, and pH values occur in the paleosol layers (ZF4, ZF6, and ZF8), with minimum values in the loess layers (ZF5 and ZF7); EM3 values show the opposite pattern. This indicates that the ZF4, ZF6, and ZF8 layers represent warm and humid environments with abundant precipitation, where the East Asian summer monsoon (EASM) was enhanced, corresponding to Marine Isotope Stages (MIS) 5a, 5c, and 5e. In contrast, ZF5 and ZF7 represent sub-warm and humid environments with less precipitation, where the EASM was weakened, corresponding to MIS 5b and 5d. Among these stages, MIS5e is the warmest and wettest. These climatic events reveal the pattern of climate fluctuation over a ten-thousand-year timescale; they are synchronous with climate changes recorded in other geological repositories, such as cave stalagmites in southern China and sea-level fluctuations in the Yellow-Bohai Sea, which result from changes in global solar radiation. Full article

In the semiarid coast of northeast Brazil, climate change and changes in land use in drainage basins affect river hydrodynamics and hydrochemistry, modifying the estuarine environment and its biogeochemistry and increasing the mobilization of mercury (Hg). This is particularly relevant to the largest semiarid-encroached basin of the region, the Jaguaribe River. Major Hg sources to the Jaguaribe estuary are solid waste disposal, sewage and shrimp farming, the latter emitting effluents directly into the estuary. Total annual emission reaches 300 kg. In that estuary, the distribution of Hg in sediment and suspended particulate matter decreases seaward, whereas dissolved Hg concentrations increase sharply seaward, suggesting higher mobilization at the marine-influenced, mangrove-dominated portion of the estuary, mostly in the dry season. Concentrations of Hg in rooted macrophytes respond to Hg concentrations in sediment, being higher in the fluvial endmember of the estuary, whereas in floating aquatic macrophytes, Hg concentrations followed dissolved Hg concentrations in water and were also higher in the dry season. Animals (fish and crustaceans) also showed higher concentrations and bioaccumulation in the marine-influenced portion of the estuary. The variability of Hg concentrations in plants and sediments agrees with continental sources of Hg. However, Hg fractionation in water and contents in the animals respond to higher Hg availability in the marine-dominated end of the estuary. The results suggest that the impact of anthropogenic sources on Hg bioavailability is modulated by regional and global environmental changes and results from a conjunction of biological, ecological and hydrological characteristics. Finally, increasing aridity due to global warming, observed in northeast Brazil, as well as in other semiarid littorals worldwide, in addition to increased water overuse, augment Hg bioavailability and environmental risk and exposure of the local biota and the tradition of human populations exploiting the estuary’s biological resources. Full article

The large-scale quantification of accurate evapotranspiration (ET) time series has substantially been developed in recent decades using automated approaches based on remote sensing data. However, there are still several model-related uncertainties that require precise assessment. In this study, the Surface Energy Balance Algorithm for Land (SEBAL) and meteorological data from the Global Land Data Assimilation System (GLDAS) were used to estimate long-term daily actual ET based on three endmember selection procedures: two land cover-based models, one with (WF) and the other without (WOF) morphological functions, and the Allen method (with the default percentiles) for 2270 Landsat images. Models were evaluated for 23 flux tower sites with four main vegetation cover types as well as different climate types. Results showed that endmember selection with morphological functions (WF_ET) generally performed better than the other endmember approaches. Climate-based classification assessment provided the clearest discrimination between the performance of the different endmember selection approaches for the humid category. For humid zones, the land cover-based methods, especially WF, appropriately outperformed Allen. However, the performance of the three approaches was similar for sub-humid, semi-arid and arid climates together; the Allen approach was therefore recommended to avoid the need for dependency on land cover maps. Tower-by-tower validation also showed that the WF approach performed best at 12 flux tower sites, the WOF approach best at 5 and the Allen approach best at 6, suggesting that the use of land cover maps alone does not explain the differences between the performance of the land cover-based models and the Allen approach. Additionally, the satisfactory error metrics results when comparing the EC estimations with EC measurements, with root mean square error (RMSE) ≈ 0.91 and 1.59 mm·day⁻¹, coefficient of determination (R²) ≈ 0.71 and 0.41, and bias percentage (PBias) ≈ 2% and 60% for crop and non-crop flux tower sites, respectively, supports the use of GLDAS meteorological forcing datasets with the different automated ET estimation approaches. Overall, given that the thorough evaluation of different endmember selection approaches at large scale confirmed the validity of the WF approach for different climate and land cover types, this study can be considered an important contribution to the global retrieval of long time series of ET. Full article