Atmospheric pollution has recently drawn significant attention due to its proven adverse effects on public health and the environment. This concern has been aggravated specifically in Southeast Asia due to increasing vehicular use, industrial activity, and agricultural burning practices. Consequently, elevated PM_2.5 concentrations have become a matter of intervention for national authorities who have addressed the needs of monitoring air pollution by operating ground stations. However, their spatial coverage is limited and the installation and maintenance are costly. Therefore, alternative approaches are necessary at national and regional scales. In the current paper, we investigated interpolation models to fuse PM_2.5 measurements from ground stations and satellite data in an attempt to produce spatially continuous maps of PM_2.5 nationwide over Thailand. Four approaches are compared, namely the inverse distance weighted (IDW), ordinary kriging (OK), random forest (RF), and random forest combined with OK (RFK) leveraging on the NO₂, SO₂, CO, HCHO, AI, and O₃ products from the Sentinel-5P satellite, regulatory-grade ground PM_2.5 measurements, and topographic parameters. The results suggest that RFK is the most robust, especially when the pollution levels are moderate or extreme, achieving an RMSE value of 7.11 μg/m³ and an R² value of 0.77 during a 10-day long period in February, and an RMSE of 10.77 μg/m³ and R² and 0.91 during the entire month of March. The proposed approach can be adopted operationally and expanded by leveraging regulatory-grade stations, low-cost sensors, as well as upcoming satellite missions such as the GEMS and the Sentinel-5.

Many studies on synthetic aperture radar automatic target recognition (SAR ATR) have aimed to enhance recognition accuracy. Using across-track interferometry (XTI) provides height information of targets, and the 3D structure of targets in 2D SAR images can be effectively employed to improve target recognition accuracy. Therefore, this study aims to enhance target detection and recognition accuracy by simultaneously using both conventional amplitude images and XTI interferograms from simulation data in training. The research compared target detection and recognition accuracy between training with only single-band amplitude images generated by RaySAR and training with dual-band images combining amplitude images and XTI interferograms. The results showed that dual-band images significantly outperformed single-band images, with an overall 15.53% increase in F ₁ score. This advancement enhances the practical applicability of SAR ATR in various conditions and for various targets, especially with the increasing availability of satellites capable of operating XTI.

This paper describes a community effort to improve earlier versions of the full-text corpus of Genomics & Informatics by semi-automatically detecting and correcting PDF-to-text conversion errors and optical character recognition errors during the first hackathon of Genomics & Informatics Annotation Hackathon (GIAH) event. Extracting text from multi-column biomedical documents such as Genomics & Informatics is known to be notoriously difficult. The hackathon was piloted as part of a coding competition of the ELTEC College of Engineering at Ewha Womans University in order to enable researchers and students to create or annotate their own versions of the Genomics & Informatics corpus, to gain and create knowledge about corpus linguistics, and simultaneously to acquire tangible and transferable skills. The proposed projects during the hackathon harness an internal database containing different versions of the corpus and annotations.

Bridge detection from Synthetic Aperture Radar (SAR) is of great significance for infrastructure management, disaster prevention, and navigation automation. Although high-resolution SAR is increasingly accessible, exploiting Sentinel-1 remains advantageous due to its global coverage and accessibility. However, low spatial resolution of 20 m in Sentinel-1 products poses challenges in detecting small and indistinct bridges. To enhance bridge detection in low-resolution Sentinel-1 imagery, we propose a novel architecture that incorporates CycleGAN as an edge detector. CycleGAN generates detailed boundaries using 5 m land use maps, with enhanced bridge saliency. Since bridges often connect distinct edges like riverbanks and roads, this edge information assists Poly-YOLOv8, our chosen detector, in accurately localizing bridges. Our approach then integrates edge information through feature fusion module and feature alignment loss. Accordingly, the proposed SAR-EdgeYOLO achieves a precision of 98.2%, recall of 91.7%, and mAP of 94.8% at IoU 0.5, marking improvements of 3.9, 3.8, and 3.1 percentage points respectively over the baseline. The results demonstrate that CycleGAN-aided edge extraction effectively addresses the limitations of low-resolution remote sensing data, improving bridge detection accuracy and multi-class localization. This research can further contribute to the advancement of time-series infrastructure monitoring with wide applicability and higher accuracy.

Small-sized satellite constellations equipped with very-high-resolution synthetic aperture radar (SAR) sensors provide frequent revisit times and diverse viewing geometries. These properties create opportunities for real time monitoring of unidentified artificial structures through 3D positioning. SAR radargrammetry provides a practical means to achieve this by estimating the 3D position of targets from multiple SAR acquisitions. However, traditional radargrammetric techniques face challenges in target matching due to significant appearance differences caused by varying viewing geometries. Moreover, they often relied on external topographic data, which can introduce distortion or mismatches—particularly when used with sub-meter-resolution SAR imagery. In order to address these limitations, this study proposes a novel 3D positioning technique that leveraged only SAR images, without requiring external data. The core of the method involved converting zero-Doppler image patches using a reference ellipsoid model, enabling robust target matching by aligning targets into a common representation. A pixel-wise look-up table (LUT) was constructed to establish spatial correspondences between the original and generated images, allowing precise extraction of Doppler centroid frequencies and slant ranges for each target pixel. The 3D position was subsequently estimated via radargrammetric stereo processing. Validation using corner reflector (CR) arrays and real-world applications involving infrastructure targets and mountainous terrain confirmed the robustness and accuracy of the proposed approach. The results demonstrated that the technique enables reliable object level positioning.