Search Results (2,844)

Accurate detection of oil and gas (O&G) facilities in high-resolution remote sensing imagery is critical for infrastructure surveillance and sustainable resource management, yet conventional detectors struggle with severe class imbalance, extreme scale variation, and arbitrary orientation. In this work, we propose OGF Oriented R-CNN (Oil and Gas Facility Detection Oriented Region-based Convolutional Neural Network), an enhanced oriented detection model derived from Oriented R-CNN that integrates three improvements: (1) O&G Loss Function, (2) Class-Aware Hard Example Mining (CAHEM) module, and (3) Feature Pyramid Network with Feature Enhancement Attention (FPNFEA). Working in synergy, they resolve the coupled challenges more effectively than any standalone fix and do so without relying on rigid one-to-one matching between modules and individual issues. Evaluated on the O&G facility dataset comprising 3039 high-resolution images annotated with rotated bounding boxes across three classes (well sites: 3006, industrial and mining lands: 692, drilling: 244), OGF Oriented R-CNN achieves a mean average precision (mAP) of 82.9%, outperforming seven state-of-the-art (SOTA) models by margins of up to 27.6 percentage points (pp) and delivering a cumulative gain of +10.5 pp over Oriented R-CNN. Full article

Global water environment monitoring urgently requires remote sensing data with high temporal resolution and wide spatial coverage. However, current space-borne ocean color spectrometers still face a significant trade-off among spatial resolution, swath width, and system compactness, which limits the large-scale deployment of satellite constellations. To address this challenge, this study developed a lightweight high-resolution spectral imager (LHRSI) with a total mass of less than 25 kg and power consumption below 80 W. The visible (VIS) camera adopts an interleaved dual-field-of-view and detectors splicing fusion design, while the shortwave infrared (SWIR) camera employs a transmission-type focal plane with staggered detector arrays. Through the field-of-view (FOV) optical design, the instrument achieves swath widths of 207.33 km for the VIS bands and 187.8 km for the SWIR bands at an orbital altitude of 500 km, while maintaining spatial resolutions of 12 m and 24 m, respectively. On-orbit imaging results demonstrate that the spectrometer achieves excellent performance in both spatial resolution and swath width. In addition, preliminary analysis using index-based indicators illustrates LHRSI’s potential for observing chlorophyll-related features in water bodies. This research not only provides a high-performance, miniaturized spectrometer solution but also lays an engineering foundation for developing low-cost, high-revisit global ocean and water environment monitoring constellations. Full article

The Altai Mountains rank among the world’s most notable and valuable archaeological regions. Within the sprawling Altai Mountains area, burial mounds (kurgans) of past civilizations, which are sometimes well preserved in permafrost, are a particularly precious trove of archaeological insights. This study investigates the application of deep learning-based object detection techniques for automatic kurgan identification in high-resolution satellite imagery. We compare the performance of various object detection methods utilizing both convolutional neural network and Transformer backbones. Our results validate the effectiveness of different approaches, especially with larger models, in the challenging task of detecting small archaeological structures. Techniques addressing the class imbalance can further improve performance of off-the-shelf methods. These findings demonstrate the feasibility of employing deep learning techniques to automate kurgan identification, which can improve archaeological surveying processes. It suggests the potential of deep learning technology for constructing a comprehensive inventory of Altai Mountain kurgans, particularly relevant in the context of global warming and archaeological site preservation. Full article

The absolute radiometric calibration of a satellite sensor is an essential process that determines the coefficients required to convert the radiometric quantities of satellite images. This procedure is crucial for ensuring the applicability and enhancing the reliability of optical sensors onboard satellites. This study performs the absolute radiometric calibration of the Compact Advanced Satellite 500-1 (CAS500-1) Advanced Earth Imaging Sensor System-C (AEISS-C), a low Earth orbit satellite developed independently by Republic of Korea for precise ground observation. Field campaign using a tarp, an Analytical Spectral Devices FieldSpecIII spectroradiometer, and a MicrotopsII sunphotometer was conducted. Additionally, reflectance-based vicarious calibration was performed using observational data and the MODerate resolution atmospheric TRANsmission model (version 6) radiative transfer model (RTM). Cross-calibration was also performed using data from the Sentinel-2 MultiSpectral Instrument, RadCalNet observations, and MODIS Bidirectional nReflectance Distribution Function (BRDF) products (MCD43A1) to account for differences in spectral response functions, viewing/solar geometry, and atmospheric conditions between the two satellites. From these datasets, two correction factors were derived: the Spectral Band Adjustment Factor and the BRDF Correction Factor. CAS500-1/AEISS-C acquires satellite imagery using two Time Delay Integration (TDI) modes, and the absolute radiometric calibration coefficients were derived considering these TDI modes. The coefficient of determination (R²) ranged from 0.70 to 0.97 for the reflectance-based vicarious calibration and from 0.90 to 0.99 for the cross-calibration. For reflectance-based vicarious calibration, aerosol optical depth was identified as the primary source of uncertainty among atmospheric factors. For cross-calibration, the reference satellite and RTMs were the primary sources of uncertainty. The results of this study will support the monitoring of CAS500-1/AEISS-C, which produces high-resolution imagery with a spatial resolution of 2 m, and can serve as foundational material for absolute radiometric calibration procedures for other CAS500 satellites. Full article

Low clouds significantly impact weather, climate, and multiple environmental and economic sectors such as agriculture, fire risk management, aviation, and renewable energy. Accurate knowledge of cloud base height (CBH) is critical for optimizing crop yields, improving fire danger forecasts, enhancing flight safety, and increasing solar energy efficiency. This study evaluates a shadow-based CBH retrieval method using Moderate Resolution Imaging Spectroradiometer (MODIS) satellite visible imagery and compares the results against collocated lidar measurements from the Micro-Pulse Lidar Network (MPLNET) ground stations. The shadow method leverages sun–sensor geometry to estimate CBH from the displacement of cloud shadows on the surface, offering a practical and high-resolution passive remote sensing technique, especially useful where active sensors are unavailable. The validation results show strong agreement, with a correlation coefficient (R) = 0.96 between shadow-based and lidar-derived CBH estimates, confirming the robustness of the approach for shallow, isolated cumulus clouds. The method’s advantages include direct physical height estimation without reliance on cloud top heights or stereo imaging, applicability across archived datasets, and suitability for diurnal studies. This work highlights the potential of shadow-based retrievals as a reliable, cost-effective tool for global low cloud monitoring, with important implications for atmospheric research and operational forecasting. Full article

Coastal sandbars play a crucial role in shoreline protection, yet monitoring their dynamics remains challenging due to the cost and limited temporal coverage of traditional surveys. This study assesses the feasibility of using Sentinel-2 multispectral imagery combined with the logarithmic band ratio method to automatically detect submerged sandbar crests along three morphologically distinct beaches on the northwestern Mediterranean coast. Pseudo-bathymetry was derived from log-transformed band ratios of blue-green and blue-red reflectance used to extract the sandbar crest and validated against high-resolution in situ bathymetry. The blue-green band ratio achieved higher accuracy than the blue-red band ratio, which performed slightly better in very shallow waters. Its application across single, single/double, and double shore-parallel bar systems demonstrated the robustness and transferability of the approach. However, the method requires relatively clear or calm water conditions, and breaking-wave foam, sunglint, or cloud cover conditions limit the number of usable satellite images. A temporal analysis at a dissipative beach further revealed coherent bar migration patterns associated with storm events, consistent with observed hydrodynamic forcing. The proposed method is cost-free, computationally efficient, and broadly applicable for large-scale and long-term sandbar monitoring where optical water clarity permits. Its simplicity enables integration into coastal management frameworks, supporting sediment-budget assessment and resilience evaluation in data-limited regions. Full article

The FY-4B satellite, launched in June 2021 as China’s new-generation geostationary meteorological satellite, carries three identical High-Energy Particle Detectors (HEPDs) that enable multi-directional, wide-spectral measurements of energetic electrons. The three units are mounted in the zenith (−Z), flight (+X with a +Y offset of 30°), and anti-flight (−X with a −Y offset of 30°) directions, allowing simultaneous observations from nine look directions over a field of view close to 180° in the 0.4–4 MeV energy range (eight energy channels). This paper systematically presents the design principles of the HEPD electron detector, the ground calibration scheme, and preliminary in-orbit validation results. The probe employs a multi-layer silicon semiconductor telescope technique to achieve high-precision measurements of electron energy spectra, fluxes, and directional anisotropy in the 0.4–4 MeV range. Ground synchrotron calibration shows that the energy resolution is better than 16% for energies above 1 MeV, and the angular resolution is about 20°, providing a solid basis for subsequent quantitative inversion. During in-orbit operation, HEPD remains stable under both quiet conditions and strong geomagnetic storms: the measured electron fluxes, differential energy spectra, and directional distributions show good agreement with GOES-16 observations in the same energy bands during quiet periods and for the first time provide from geostationary orbit pitch-angle-resolved images of the minute-scale evolution of electron enhancement events. These results demonstrate that HEPD is capable of long-term monitoring of the geostationary radiation environment and can supply high-quality, continuous, and reliable data to support studies of radiation-belt particle dynamics, data assimilation in space weather models, and radiation warnings for satellites in orbit. Full article

The accurate monitoring of water vapor is essential for understanding the hydrological cycle and improving weather forecasting. Although the Moderate-resolution Imaging Spectroradiometer (MODIS) provides spatially continuous precipitable water vapor (PWV), validation in Hunan Province reveals a systematic underestimation, with correlations to radiosonde (RS-PWV) around 0.40 and average RMSE and MAE reaching 23.80 and 18.04 mm. To address this issue, high-accuracy PWV derived from the BeiDou Navigation Satellite System (BDS-PWV), which show high consistency with RS-PWV, were incorporated. A random forest daily-scale water vapor fusion model was developed based on the differential characteristics of dry and wet season residuals. By employing day of year (DOY), latitude, longitude, and elevation as auxiliary factors, the model establishes a seasonal fusion framework that dynamically transitions between dry and wet seasons. Validation shows that the fusion PWV aligns closely with RS-PWV, reducing average RMSE and MAE to 4.71 and 3.81 mm, corresponding to improvements of 80.21% and 78.88% over MODIS, with accuracy increases exceeding 75% at all stations. The fusion model effectively mitigates MODIS’s underestimation and weather sensitivity, producing high-accuracy, spatially continuous daily PWV fields and offering strong potential for improving precipitation and weather forecasting in complex regions such as Hunan Province. Full article

In infrared detectors, the readout circuits usually cause horizontal or vertical streak noise, whereas the infrared focal plane arrays experience triangular nonuniform fixed-pattern noise. In addition, imaging devices suffer from optically relevant fixed-pattern noise owing to the temperature. When the infrared camera is in orbit, it is affected by the photon effect, temperature change, and time drift. This makes the nonuniformity correction coefficients pertaining to the ground no longer applicable, resulting in the degradation of the nonuniformity correction effect. The existing methods are not fully applicable to triangular fixed-pattern noise or the fixed-pattern noise caused by detector optics. To address this situation, this paper proposes a nonuniformity correction method, namely infrared image sequences based on the optimization of $L_{2,1}$ group sparsity in the spatiotemporal domain. We established a nonuniformity correction model of differential operators in the spatiotemporal domain for infrared image sequences by applying the time-domain differential operator constraints to the images to denoise the image. This enables the adaptive correction of the nonuniformity of the above types of noise. We demonstrate that the proposed method is effective for triangular nonuniform and optically induced fixed-pattern noises. The proposed method was extensively evaluated using publicly available datasets and datasets containing image sequences of different scenes captured by a high-resolution infrared camera of the Qilu-2 satellite. The method has high robustness and good processing results with effective ghost suppression and significant reduction of nonuniform noise. Full article

With the advancement of remote sensing technology, high-resolution images are widely used in the field of computer vision. However, image quality is often degraded due to hardware limitations and environmental interference. This paper proposes a Residual Separable Super-Resolution Reconstruction Generative Adversarial Network (RSSRGAN) for remote sensing image super-resolution. The model aims to enhance the resolution and edge information of low-resolution images without hardware improvements. The main contributions include (1) designing an optimized generator network by improving the residual dense network and introducing depthwise separable convolutions to remove BN layers, thereby increasing training efficiency—two PatchGAN discriminators are designed to enhance multi-scale detail capture—and (2) introducing content loss and joint perceptual loss on top of adversarial loss to improve global feature representation. Experimental results show that compared to the widely used SRGAN model in remote sensing (exemplified by the satellite-specific SRGAN in this study), this model improves PSNR by approximately 18.8%, SSIM by 8.0%, reduces MSE by 3.6%, and enhances the PI metric by 13.6%. It effectively enhances object information, color, and brightness in images, making it more suitable for remote sensing image super-resolution. Full article

Timely and accurate urban change detection is vital for sustainable urban development, infrastructure management, and disaster response. Traditional two-dimensional approaches often overlook vertical and structural variations in dense urban areas. This study proposes a three-dimensional (3D) change detection framework that integrates high-resolution optical imagery and Digital Surface Models (DSMs) from two time points to capture both horizontal and vertical transformations. The method is based on a deep learning architecture combining a ResNet34 encoder with a UNet++ decoder, enabling the joint learning of spectral and elevation features. The research was carried out in two stages. First, a binary classification model was trained to detect areas of change and no-change, allowing direct comparison with conventional methods such as Principal Component Analysis (PCA), Change Vector Analysis (CVA) with thresholding, K-Means clustering, and Random Forest classification. In the second stage, a multi-class model was developed to categorize the types of structural changes, including new building construction, complete destruction, building height increase, and height decrease. Experiments conducted on a high-resolution urban dataset demonstrated that the proposed CNN-based framework significantly outperformed traditional methods, achieving an overall accuracy of 96.58%, an F1-score of 96.58%, and a recall of 96.7%. Incorporating DSM data notably improved sensitivity to elevation-related changes. Overall, the ResNet34–UNet++ architecture offers a robust and accurate solution for 3D urban change detection, supporting more effective urban monitoring and planning. Full article

Vegetation segmentation in Very High-Resolution (VHR) satellite imagery has become an essential task for ecological monitoring, supporting diverse applications such as large-scale vegetation conservation and detailed segmentation of small local areas. In particular, multi-class vegetation segmentation, which distinguishes various vegetation types beyond simple binary segmentation of vegetation and non-vegetation, enables detailed analysis of subtle ecosystem changes and has gained increasing importance. However, the annotation of VHR satellite imagery requires extensive time and effort, resulting in a lack of datasets for vegetation segmentation, especially those including multi-class annotations. To address this limitation, this study proposes MultiVeg, a deep learning dataset based on VHR satellite imagery for detailed multi-class vegetation segmentation. MultiVeg includes preprocessed 0.5 m resolution images collected by the KOMPSAT-3 and 3A satellites from 2014 to 2023, covering diverse environments such as urban, agricultural, and forest regions. Each image was carefully annotated by experts into three semantic classes, which are Background, Tree, and Low Vegetation, and validated through a structured quality check process. To verify the effectiveness of MultiVeg, seven representative semantic segmentation models, including convolutional neural network and Transformer-based architectures, were trained and comparatively analyzed. The results demonstrated consistent segmentation performance across all classes, confirming that MultiVeg is a high-quality and reliable dataset for deep learning-based multi-class vegetation segmentation research using VHR satellite imagery. The MultiVeg will be publicly available through GitHub (release v1.0), serving as a valuable resource for advancing deep leaning-based vegetation segmentation research in the remote sensing field. Full article

The rapid advancement of high-resolution remote sensing technology has significantly expanded observational capabilities in the oil and gas sector, enabling more precise identification of petroleum infrastructure. Remote sensing now plays a critical role in providing real-time, continuous monitoring. Manual interpretation remains the predominant approach, yet is plagued by multiple limitations. To overcome the limitations of manual interpretation in large-scale monitoring of upstream petroleum assets, this study develops an end-to-end, deep learning-driven framework for intelligent extraction of key oilfield targets from high-resolution remote sensing imagery. Specific aims are as follows: (1) To leverage temporal diversity in imagery to construct a representative training dataset. (2) To automate multi-class detection of well sites, production discharge pools, and storage facilities with high precision. This study proposes an intelligent monitoring framework based on deep learning for the automatic extraction of petroleum-related features from high-resolution remote sensing imagery. Leveraging the temporal richness of multi-temporal satellite data, a geolocation-based sampling strategy was adopted to construct a dedicated petroleum remote sensing dataset. The dataset comprises over 8000 images and more than 30,000 annotated targets across three key classes: well pads, production ponds, and storage facilities. Four state-of-the-art object detection models were evaluated—two-stage frameworks (Faster R-CNN, Mask R-CNN) and single-stage algorithms (YOLOv3, YOLOv4)—with the integration of transfer learning to improve accuracy, generalization, and robustness. Experimental results demonstrate that two-stage detectors significantly outperform their single-stage counterparts in terms of mean Average Precision (mAP). Specifically, the Mask R-CNN model, enhanced through transfer learning, achieved an mAP of 89.2% across all classes, exceeding the best-performing single-stage model (YOLOv4) by 11 percentage points. This performance gap highlights the trade-off between speed and accuracy inherent in single-shot detection models, which prioritize real-time inference at the expense of precision. Additionally, comparative analysis among similar architectures confirmed that newer versions (e.g., YOLOv4 over YOLOv3) and the incorporation of transfer learning consistently yield accuracy improvements of 2–4%, underscoring its effectiveness in remote sensing applications. Three oilfield areas were selected for practical application. The results indicate that the constructed model can automatically extract multiple target categories simultaneously, with average detection accuracies of 84% for well sites and 77% for production ponds. For multi-class targets over 100 square kilometers, manual detection previously required one day but now takes only one hour. Full article

Continuous global monitoring of volcanic activity from space requires balancing spatial and temporal resolution, a long-standing trade-off between polar-orbiting and geostationary satellites. Polar sensors such as MODIS, VIIRS, and SLSTR provide high spatial resolution (375 m–1 km) but with limited temporal coverage. In contrast, geostationary sensors like SEVIRI offer high temporal resolution (5–15 min) but with coarser spatial detail (~3 km), often missing lower-intensity thermal events. The recently launched Flexible Combined Imager (FCI) aboard the geostationary Meteosat Third Generation (MTG-I) satellite represents a major improvement, providing images every 10 min with a spatial resolution of 1–2 km, comparable to that of polar orbiters. Here, we adapted the established Remote Sensing Data Fusion (RSDF) algorithm to exploit the enhanced capabilities of FCI for detecting volcanic thermal anomalies and estimating Volcanic Radiative Power (VRP). The algorithm was applied to Mount Etna during three different eruptive phases that occurred in 2025. The VRP derived from FCI data was compared with that obtained from the geostationary SEVIRI and the polar-orbiting MODIS, SLSTR, and VIIRS sensors. The results show that FCI provides a more detailed and continuous characterization of volcanic thermal output than SEVIRI, while maintaining close agreement with polar sensors. These findings confirm the capability of FCI to deliver high-frequency, high-resolution thermal monitoring, representing a major step toward operational, near-real-time volcanic surveillance from space. Full article

Precise lagoon bathymetry remains scarcely available for most tropical islands despite its importance for navigation, resource assessment, spatial planning, and numerical hydrodynamic modeling. Hydrodynamic models are increasingly used for instance to understand the ecological connectivity between marine populations of interest. Island remoteness and shallow waters complicate in situ bathymetric surveys, which are substantially costly. A multisource strategy using historical point sounding, multibeam surveys and well calibrated satellite-derived bathymetry (SDB) can offer the possibility to map entirely extensive and geomorphologically complex lagoons. The process is illustrated here for the rugose complex lagoon of Gambier Islands in French Polynesia. The targeted bathymetry product was designed to be used in priority for numerical larval dispersal modeling at 100 m spatial resolution. Spatial gaps in in situ data were filed with Sentinel-2 satellite images processed with the Iterative Multi-Band Ratio method that provided an accurate bathymetric model (1.42 m Mean Absolute Error in the 0–15 m depth range). Processing was optimized here, considering the specifications and the constraints related to the targeted hydrodynamic modeling application. In the near future, a similar product, possibly at higher spatial resolution, could improve spatial planning zoning scenarios and resource-restocking programs. For tropical island countries and for French Polynesia, in particular, the needs for lagoon hydrodynamic models remain high and solutions could benefit from such multisource coverage to fill the bathymetry gaps. Full article