Remote Sensing

Accurate road extraction from high-resolution satellite imagery is important for transportation planning, infrastructure monitoring, and geospatial updating, but blurred boundaries and fragmented segments still limit practical large-area applications. This study proposes EORENet, an edge-optimized road extraction network for 2 m GF-1 imagery and large-area road product generation. EORENet decouples road-surface segmentation and road-edge delineation into task-specific branches, introduces deformable convolution for adaptive spatial aggregation, and uses a dual-task cross-feature fusion module to exchange semantic and boundary cues. A GF-1 road sample set, the Cangling Road Dataset, was constructed and evaluated together with the Ottawa and DeepGlobe Road datasets. Compared with eight representative methods, EORENet achieved the best overall IoU, F1 score, and edge-buffered F1 score; on the Cangling dataset, it reached 55.11% IoU, 71.06% F1, and 56.21% edge-buffered F1. The trained model was then applied to a spatially independent large-area GF-1 inference collection. Scene-stratified product-level assessment with 1200 independently annotated 512 × 512 patches showed systematic scene-dependent differences, with F1 scores ranging from 62.80% in mountainous forest areas to 74.57% in high-density urban cores and a balanced scene-wise mean F1 of 69.48%. City-scale extraction over four metropolitan regions further visually illustrated the workflow’s potential for large-area road-surface product generation.

Leaf radiative transfer models provide a physical basis for leaf trait retrieval, but compensating parameter effects and measurement discrepancies constrain estimation accuracy and uncertainty characterization. This study proposes Training-Informed Differentiable Bayesian Inference (TI-DBI). This method integrates training-derived joint lognormal priors, wavelength-specific spectral biases, and residual scales into a differentiable PROSPECT-D model, enabling joint parameter inference via the No-U-Turn Sampler (NUTS). Evaluated on multi-source datasets, TI-DBI yields relative root mean square errors (rRMSEs) of 27.31%, 33.72%, 16.22%, and 37.66% for chlorophyll (C_ab), carotenoids (C_ar), equivalent water thickness (C_w), and leaf dry mass per area (C_m). Outperforming an uncalibrated Markov chain Monte Carlo (MCMC) baseline for all traits and partial least squares regression (PLSR) for C_ab, C_ar, and C_w, these results confirm the specific value of the data-informed probabilistic framework. Beyond point-estimation, TI-DBI substantially improves uncertainty characterization. It yields narrower interval widths and lower interval scores than the uncalibrated baseline, with prediction interval coverage probability (PICP) of the 95% highest density intervals (HDIs) reaching 93.14%, 96.46%, 89.62%, and 86.22% for Cab, Car, Cw, and Cm, respectively. Ablation and sensitivity studies confirm that both the learned priors and spectral error calibration drive these performance gains across varying training fractions and spectral configurations. TI-DBI strictly preserves the forward model’s physical structure while providing a robust, practical framework for jointly evaluating trait estimation accuracy and posterior uncertainty.

The use of Earth Observation data for monitoring of aquatic and coastal ecosystems has expanded significantly, yet gaps remain in the spectral and thermal capabilities needed to detect and characterize liquid discharges. This study evaluates the potential of simulated pre-launch CHIME and LSTM observations, integrated with operational Sentinel-2 and Landsat 8/9 data, for water-quality anomaly detection across diverse aquatic environments, demonstrating that the simulated datasets are sufficiently realistic to reproduce key water-quality and thermal indicators and support pre-operational application development prior to mission launch. A multi-stage workflow was applied: initial anomaly detection with multispectral imagery, thermal verification using LSTM-simulated brightness temperatures processed via linear and quadratic split-window algorithms, and spectral characterization of turbidity and spectral signatures with atmospherically corrected CHIME-simulated data. Results showed consistent spatial patterns of turbidity and surface temperature between simulated and operational products, with CHIME resolving finer spectral features of suspended matter and the quadratic LSTM model achieving low RMSE relative to Landsat thermal references. These findings demonstrate the cross-sensor consistency and complementary information provided by simulated CHIME and LSTM products, supporting their use in the pre-launch development of future multisensor workflows for detecting and characterizing optical and thermal water anomalies. Identification of specific contaminants and attribution of anomalies to individual discharge sources were not assessed in this study.