Remote Sensing

Building polygon extraction is a critical task in remote sensing analysis and a fundamental component of modern urban management. Conventional segmentation-based methods often suffer from geometric distortions during the conversion from masks to polygons. End-to-end polygon prediction approaches (e.g., PolyWorld) alleviate this issue by directly predicting building polygons; however, existing PolyWorld-like methods remain limited in accurate corner vertex detection and polygon reasoning due to insufficient representation learning, particularly for geometry. In this work, we propose PolyGeom, an end-to-end framework equipped with a geometry-aware graph transformer for accurate and robust building polygon extraction. PolyGeom employs the Segment Anything Model (SAM) as its backbone to leverage large-scale pretrained features, thereby capturing both local and global semantics. Moreover, we propose a geometry-aware graph transformer that explicitly models geometry of building polygons, facilitating more reliable polygon reasoning. Extensive experiments on three challenging benchmarks, CrowdAI, WHU, and BONAI datasets, demonstrate that PolyGeom consistently outperforms existing methods in terms of building detection accuracy, topology correctness, and geometry alignment. Ablation studies further validate the effectiveness of the two key proposed designs in building polygon extraction.

The precise localization of small objects in UAV-captured remote sensing imagery remains a formidable challenge due to their limited spatial support, coarse resolution, and severe background clutter. These factors often cause weak target cues to be progressively overwhelmed during deep feature extraction. Existing deep learning-based detectors typically suffer from two fundamental limitations: the irreversible loss of fine-grained spatial details during hierarchical feature fusion and the scale-insensitive optimization of conventional loss functions, which inadequately emphasize hard-to-detect small targets. To address these issues, we propose a novel Spatial-Semantic Aggregation and Balancing Network (SSABNet) tailored for UAV-based small-target detection. First, a Spatial-Semantic Aggregation (SSA) module is introduced to establish a high-fidelity restoration pathway that recovers fine-grained texture and boundary information from shallow layers. By employing content-aware operators, SSA effectively reconciles the structural discrepancy between spatial details and semantic abstractions, enabling precise cross-scale feature fusion while suppressing aliasing artifacts. Second, we design a Scale-Aware Balancing Loss (SABL) to mitigate the gradient instability and vanishing-gradient issues commonly encountered when optimizing non-overlapping small targets. SABL adopts a scale-dependent modulation mechanism that smoothly transitions from Wasserstein distance for distributional alignment of small objects to Euclidean distance for geometric refinement of larger targets, thereby ensuring stable and balanced optimization across object scales. Extensive experiments on the VisDrone benchmark demonstrate that SSABNet outperforms state-of-the-art detectors, achieving gains of 1.3% in overall AP and 2.5% in ${\mathrm{AP}}_s$. Further evaluation on the UAVDT dataset confirms its strong generalization capability, yielding improvements of 0.5% in AP and 16.9% in ${\mathrm{AP}}_s$. These results validate the effectiveness of jointly addressing feature representation and scale-aware optimization for UAV small-target detection.

This study investigates the spatiotemporal variability of ambient methane (CH₄) using a drone-deployable Aeris Technologies MIRA Strato LDS midwave-infrared analyzer. Laboratory calibration with NOAA-certified gas standards and Standard Reference Material (SRM) for CH₄ demonstrated high measurement precision across a range of concentrations (R² = 0.9986, slope = 0.9678). Field validation conducted during a two-week intercomparison with a Picarro G2301 in September 2023 confirmed the MIRA Strato’s reliability under ambient conditions (R² = 0.9845; slope = 0.9438), indicating strong agreement with the reference analyzer. Diurnal patterns revealed peak CH₄ concentrations (~2.2 ppm) between 04:00–08:00 LT and minima (~2.1 ppm) between 13:00–17:00 LT, consistent with nocturnal boundary-layer stability and daytime convective mixing. Across 14 midday UAV flights from October 2023 to September 2024, CH₄–altitude slopes ranged from −3.05 × 10⁻⁴ to +1.41 × 10⁻⁴ ppm/m, reflecting variable stratification and uplift regimes. The highest flight concentration (2.23 ppm) was observed on 19 October under stable conditions, while the lowest (2.03 ppm) was observed on 14 August under elevated vertical mixing. These extremes reflect seasonal background accumulation and convective transport effects. Temperature was the most consistent predictor, with regression coefficients ranging from −0.021 to +0.008 ppm/°C, while ethane (C₂H₆) coefficients were significant but confounded due to measurements below detection limits. The analyzer maintained strong signal stability throughout (mean CV ≈ 0.0066; max = 0.0114), and remote sensing validation with TROPOMI supported observed seasonal accumulation trends. These results demonstrate the MIRA Strato’s capability to resolve near-surface CH₄ dynamics and characterize convective transport in complex atmospheric environments.