Carbon neutrality has become a global priority, and high spatio-temporal resolution data on the column-average dry-air mole fraction carbon dioxide (XCO2) is essential for tracking progress and guiding policy adjustments. However, satellite-derived XCO2exhibits significant temporal and spatial gaps due to influences such as orbital dynamics and cloud cover. Additionally, the low spatial resolution of CarbonTracker (CT) is insufficient to meet the current demands for fine-scale monitoring. Current XCO2assessment methods often rely solely on single-pixel data, overlooking the spatio-temporal correlations. In this article, we introduce a deep learning-based spatio-temporal model (DSTM) that extracts features from multiple data sources related to atmospheric transport, carbon emissions, and carbon sinks, enabling fine-scale XCO2assessments. Additionally, XCO2data from the Orbiting Carbon Observatory-2 (OCO-2) and CT were fused at a 0.1° spatial resolution to generate training labels with broader coverage and more samples, serving as fitting labels. Our approach produced daily, full-coverage 0.1° resolution XCO2maps for China from 2015 to 2020, and analyzed changes in XCO2growth trends over this period. Numerical results show that our model outperforms traditional deep learning methods. Model validation using data from four ground-based observation sites of the Total Carbon Column Observing Network (TCCON) achieved an average R² of 0.86 and an RMSE of 2.67 ppm. The extraction and fusion of spatio-temporal features from multiple data sources provide a novel approach for reconstructing missing XCO2data.

Timely detection of urban block-level changes is crucial for urban planning and smart city development. Although time series remote sensing images provide a promising approach, current methods primarily rely on shallow features like spectrum and texture, failing to leverage deep semantic information. This makes them susceptible to lighting conditions and cloud noise, distorting spectral data or obscuring object features, thus reducing the accuracy of change detection. To overcome these limitations, we propose Semantic-TemporalNet (STN), a block-level urban change detection method based on semantic coherence analysis for fine-grained monthly urban monitoring. Unlike traditional methods sensitive to spectral fluctuations, STN employs a pre-trained ResNet50 to extract semantic features, concatenates multi-month data, and uses a fully connected layer to compute the semantic coherence score — measuring land cover consistency across consecutive months. Specifically, it learns from semantic boundary labels derived from actual urban construction activities to detect significant changes, rather than relying on spectral variations, making it robust to irrelevant changes from cloud cover, spectral fluctuations, and seasonal noise. By identifying land cover changes driven by urban development rather than superficial spectral variations, STN improves detection accuracy and robustness. The STN was tested on monthly Sentinel-2 imagery from Changsha and Wuhan, China. Results show that STN achieves average spatial and temporal accuracies of 80.6% and 62.4%, outperforming existing mainstream methods. These results confirm STN’s effectiveness in timely urban change detection with robustness against cloud interference, spectral fluctuations and seasonal noise, providing a practical tool for urban governance.

Remote sensing images often suffer from substantial data loss due to factors such as thick cloud cover and sensor limitations. Existing methods for imputing missing values in remote sensing images fail to fully exploit spatiotemporal auxiliary information, which restricts the accuracy of their reconstructions. To address this issue, this paper proposes a novel deep learning-based approach called MS2TAN (Multi-Scale Masked Spatial-Temporal Attention Network) for reconstructing time-series remote sensing images. First, we introduce an efficient spatiotemporal feature extractor based on Masked Spatial-Temporal Attention (MSTA) to capture high-quality representations of spatiotemporal neighborhood features surrounding missing regions while significantly reducing the computational complexity of the attention mechanism. Second, a Multi-Scale Restoration Network composed of MSTA-based Feature Extractors is designed to progressively refine missing values by exploring spatiotemporal neighborhood features at different scales. Third, we propose a “Pixel-Structure-Perception” Multi-Objective Joint Optimization method to enhance the visual quality of the reconstructed results from multiple perspectives and to preserve more texture structures. Finally, quantitative experimental results under multi-temporal inputs on two public datasets demonstrate that the proposed method outperforms competitive approaches, achieving a 9.76%/9.30% reduction in Mean Absolute Error (MAE) and a 0.56 dB/0.62 dB increase in Peak Signal-to-Noise Ratio (PSNR), along with stronger texture and structural consistency. Ablation experiments further validate the contribution of the core innovations to imputation accuracy.

Lithium (Li) is growing in importance and demand in several industrial applications, such as portable electric devices, electric vehicles, and hybrid electric vehicles. Li-rich pegmatites are one of the main sources of Li production in the world, so low-cost and high-efficiency exploration using remote sensing has become an important means for promoting the discovery of Li resources. Although imaging spectroscopy has great potential for Li-rich pegmatites identification and regional delineation, due to the limitations of resolution and data acquisition, the exploration of the Earth’s surface at various scales on a variety of platforms requires further research. The purpose of this study is to use a ground-based HySpex imaging hyperspectrometer to map pegmatite zones directly, developing a new approach for mineralized pegmatite exploration. To achieve this, we present the minimum wavelength mapper (MWM), which combines the position and depth information of the deepest absorption feature, to give a per-pixel overview map of the Jingerquan Li–Be–Nb–Ta pegmatite deposit pit and heap. The results show that images between 2100 and 2450 nm provide useful information about mineral assemblages that display strong spectral features, such as Li-rich pegmatites, Li-poor pegmatites and alteration, and their spatial distribution at the surface in areas covered by the imagery. The wavelength position and the depth of Al–OH can provide an overview of the mineral assemblages and abundances, to rapidly classify possible regions of interest for further analysis.

Geological environment remote sensing (GERS) interpretation contributes to lithological mapping, disaster prediction, soil erosion monitoring, and so on. However, the rich diversity, complex distribution, interclass similarities, and uncertainties in data quality of geological elements pose challenges to GERS interpretation. In addition, current automatic feature extraction of GERS elements, which rely on deep learning (DL) and remote sensing (RS) information process technologies, often require sufficient labeled data. Due to the enormous labor cost and specialized expertise needed, labeled GERS samples are limited to training the data-driven models. To tackle the above challenges, we introduce the semi-supervised dual-model progressive self-training (DM-ProST) framework. This framework employs two DL networks with different initializations as evaluator models to correct each other. A sample filtering strategy is then implemented to evaluate the quality of unlabeled samples, selecting high-quality and reliable ones to expand the training set. In addition, a fully connected conditional random field (CRF) module is incorporated to optimize DL network prediction maps, thereby enhancing the boundary performance of segmentation results. The framework utilizes a multitask loss function that combines consistency loss with cross-entropy, enabling the models to learn discriminative GERS features. This process accurately generates pseudo-labels and achieves precise lithology mapping of GERS with a small amount of annotation samples. Finally, we conducted an experimental evaluation on the Landsat 8 dataset in Xinjiang, China, and massive experiments proved the effectiveness of DM-ProST.

Due to the complex and highly heterogeneous land cover in urban areas, the single-temporal pixel-wise and parcel-wise classification cannot realize high-precision recognition of ground objects. Semantic segmentation of satellite image time series (SITS), can distinguish objects with similar spectral reflection and temporal evolution. But optical SITS have problems of uneven time-frequency distribution and incomplete, which makes it impossible to directly use existing models to carry out time series semantic segmentation. This study proposes a semantic segmentation network that combines optical and radar SITS, named Multi-Source Temporal Attention Fusion-Based Temporal-Spatial Transformer (MTAF-TST), to achieve high-precision land cover classification in urban areas. Firstly, MTAF-TST uses the Transformer spatial semantic segmentation module to extract the spatial context information of ground objects to realize pixel-level land cover classification, which relieves the salt-and-pepper phenomenon that is easy to occur in traditional pixel-by-pixel classification in complex scenes. Secondly, MTAF-TST uses the Transformer time feature extraction module to mine long-range time-dependent and high-level semantic information, overcoming the drawbacks of traditional convolutional and recurrent neural networks that cannot mine long-range time-dependent features of SITS. Finally, MTAF-TST uses a multi-source temporal attention fusion module to fuse the depth features of optical and radar SITS, which overcomes the shortcomings of traditional direct feature stitching methods that cannot make full use of time-correlated features, achieving high-precision land cover classification. The experimental results show that the MTAF-TST can realize the complementarity of radar and optical SITS in terms of timing integrity, color, texture, etc., and effectively improve the accuracy of SITS classification.

Visualizing the associated data of urban geological disasters can better describe the urban spatial information and provide technical support for analyzing geological disasters and upper-level decision-making. Aiming at the multi-source data with various types and complex structures in the urban space, how to integrate, organize, and visualize them is a critical technical problem for the urban geological disaster big data system. This paper deeply researched and discussed the visualization technology and implementation methods of multiple data types related to urban geological disasters. At the same time, we developed a visualization analysis system for urban geological disasters, which realized the integrated visualization of multi-source data in urban space and simulation visualization of geological disasters process. In addition, it can also provide users with related analysis functions of urban geological disasters based on the visualization system.

The rapid growth of earth observation (EO) data poses a challenge to the way of data management. An efficient framework based on big data technology can bring new solutions. Some excellent frameworks have been proposed, which provide efficient organization and management of EO data. However, they are not optimized for data distribution in the storage environment. In this paper, an optimized EO data management strategy is proposed. Different horizontal scaling strategies are designed to explore the optimal scheme of EO data distribution. The MapReduce parallel computing model was used to test the performance of data retrieval in the experiment. The results show that the proposed strategy contributes to the efficient organization and arrangement of data. Remote sensing (RS) data blocks can be evenly distributed to different shards according to the time characteristics and hash characteristics of the strategy, and the logical index of the data reduces the time consumed by the routing process. This distributed management mode that achieves load balancing provides a framework foundation for parallel computing. Therefore, the framework with an efficient strategy can improve the performance of data management.

Urban informal settlements (UIS) are high-density population settlements with low standards of living and supply. UIS semantic segmentation, which identifies pixels corresponding to informal settlements in remote sensing images, is crucial to the estimation of poor communities, urban management, resource allocation, and future planning, particularly in megacities. However, most studies on informal settlement mapping are either based on parcels (image classification) or pixels (semantic segmentation). Few studies utilize object information to improve UIS mapping. Since informal settlements are formed by buildings (objects), utilizing object information can improve UIS semantic segmentation. Furthermore, current UIS mapping studies mainly focus on using single-modality remote sensing images, and there is a lack of related research on using multimodal data. Due to the spatial heterogeneity of informal settlements, using only a single modality of remote sensing image features limits the effectiveness and accuracy of informal settlements semantic segmentation. Aiming at achieving fine-scale UIS mapping results, this paper proposes a UIS semantic segmentation method, namely UisNet, that utilizes a transformer-based block to receive multimodal data, including high-spatial-resolution remote sensing images (parcel- and pixel-level) and building polygon data (object-level) to identify UIS. The experiments were conducted in Shenzhen City, and they confirmed the superior performance of UisNet, which achieved an overall accuracy (OA) of 94.80% and a mean intersection over union (mIoU) of 85.51% in the testing set of the manually labeled UIS semantic segmentation dataset (UIS-Shenzhen dataset) and outperformed the best models on semantic segmentation tasks. Besides, we add a set of experiments on a public dataset (GID dataset) and compare our method with the current state-of-the-art semantic segmentation methods. Experiments show that the proposed UisNet improves mIoU by 1.64% to 7.58% compared to other methods. This work will be available at https://github.com/RunyuFan/.

Land surface temperature (LST) is widely used in the field of time-series remote sensing. However, due to the influence of cloud cover, the large area of LST data observation is missing, which seriously affects the later data analysis. In the past research, various effective interpolation methods have been developed, but they usually cannot effectively interpolate the image data with large observation missing. In this article, a new method for interpolating these missing data called Hilbert tensor rearrangement with Bayesian temporal tensor factorization (HTR-BTTF) is proposed. This method requires tensor rearrangement of remote sensing data, combined with BTTF method for interpolation. In order to evaluate the performance of our method, we select three real study areas with different climates, Wuhan, Harbin, and Kunming LST data during day and night, and add cloud covers with different sizes to the cold and warm season layers each year. BTTF, inverse distance weighted (IDW), harmonic analysis of time series (HANTS), and GapFill are used as comparison methods. Root-mean-square error (RMSE) is a comprehensive evaluation index of interpolation results. Experiments have shown that HTR-BTTF is an effective method for interpolating missing observations, which is better than other methods. In the simulation experiment of the largest cloud cover size, on average, the RMSE of the data filled using the HTR-BTTF method was 17.2% lower than that of BTTF and 54.9% lower than that of the GapFill method, and it shows good robustness and high accuracy.

Dense time-series remote sensing images have transformed the traditional bitemporal land-cover change detection to continuous monitoring. Previous work mostly employs linear fitting, prediction, or decomposition methods, and the detection accuracy is not high. The latest progress of deep learning (DL) shows its advantages in time-series change monitoring. However, DL models are computationally expensive and require lots of labeled samples, resulting in often employed prediction-threshold-based unsupervised change detection method. However, the determination of a reasonable threshold has always been a big problem. Therefore, we proposed the similarity-measurement-based deep transfer learning for time-series adaptive change detection (SDTL-TSACD) model. First, a standard dynamic time warping (SDTW) distance was proposed and used to cluster large-scale time series into multiple subcategories with high time-series similarity. Second, a time convolutional network (TCN) was used for nonlinear time-series fitting and prediction, and an early stop strategy was used to prevent overfitting. Then, the trained TCN model would be transferred and performed pixel-by-pixel time-series prediction within the same category, and the SDTW was also used to evaluate the prediction accuracy. Finally, the Otsu adaptive threshold was used to detect change points, and the spatial neighbor relationship was used to eliminate the pseudo-change points. Change detection results using 132 benchmark datasets showed that the SDTL-TSACD performed well in both accuracy and efficiency. In addition, the MOD13Q1-EVI images from 2001 to 2020 were used to study the land-cover change of the Loess Plateau, and the SDTL-TSACD also showed a good ability to solve practical problems.

This research is based on Australian Data Cube Data Organization and Management Framework. Through data cleaning, data segmentation and data index, remote sensing observation data collected in Wuhan from 2000 to 2017, are organized into a data cube with time series as the Z-axis. Then, extraction of MODIS-NDVI data about 414 tile images. The mean value and standard deviation value of the tile matrix were calculated to detect the areas with frequent changes in vegetation coverage in Wuhan during the 18 consecutive years. The vegetation coverage curve was extracted using the time series as the z-axis to further explore the specific time nodes and change process of vegetation coverage. The experiment results show that: (1)During the period from 2000 to 2010, the area covered by vegetation in Wuhan decreased dramatically when the city expanded; (2)After 2010, due to the followup of green work in the later stages of urban development, the area of green space in Wuhan was restored; (3)In recent years, with the large-scale transportation projects carried out in Wuhan, to a certain extent, it has affected the existing green areas.

In this paper, the blind restoration of a degraded image with an auxiliary image from another sensor is considered. In a typical multispectral satellite imaging system, multiple images from different sensors of the same area are available. When one of those images in a multiple image set is degraded, another image in the set can be used as a prior image for restoration. A hybrid algorithm based on the sparse representation using an auxiliary image is proposed in this paper. In this approach, the cost function for regularization has two terms: regularization from the degraded image being restored and the regularization from the auxiliary image. The amount of prior information from the auxiliary image to be used in the hybrid algorithm is determined based on the similarity between the auxiliary image and the degraded image. The proposed algorithm is applied to both simulated and real multispectral images, and the performance of the proposed algorithm is compared with those of other image restoration algorithms. In both quantitative and qualitative comparisons, the proposed algorithm performed better than other algorithms.