Marine aquaculture is a critical component of coastal socio-ecological systems and marine spatial governance. Nearshore cage farming is a primary regulatory focus because of its flexible deployment, concentrated distribution, and strong environmental interactions. As farming intensity grows and coastal space becomes contested, regulatory needs are shifting from coarse facility detection to fine-grained characterization of cage types, spatial configurations, and instance-level inventories. High-resolution remote sensing combined with deep learning–based semantic segmentation offers a scalable pathway, yet aquaculture cages are small, densely clustered, weakly bounded, and embedded in heterogeneous water and background conditions, which challenges cross-regional generalization. Moreover, most studies emphasize pixel-level accuracy, while region-scale inventory reliability remains underexamined. This study targets Dongshan–Zhao’an Bay and Meizhou Bay in Fujian Province, China, and builds a fine-grained dataset of three cage types – conventional, suspended, and deep-water cages – using 0.5-m optical imagery. Under a unified framework, eight representative models spanning convolutional neural network (CNN), Transformer, and hybrid architectures are benchmarked. We analyze the effects of input scale, training-sample ratio, and background proportion, and adopt a strict cross-region train–test strategy to evaluate transferability. Bay-scale inference and instance-level evaluation are further conducted to link pixel-level accuracy with inventory reliability. Results show that Transformer-based models achieve strong pixel-level performance under the baseline setting, with SegFormer-b5 reaching the highest mean intersection over union (mIoU) of 0.9297. However, in the Dongshan–Zhao’an Bay → Meizhou Bay bay-scale inference experiment, this pixel-level advantage did not translate into reliable instance-level inventorying. U-Net and attention U-Net achieved more balanced instance-level F1-scores of 0.7011 and 0.7188, respectively, whereas SegFormer-b5 produced 1371 predicted instances for 489 ground-truth instances and yielded a much lower F1-score of 0.3795. These findings indicate that high pixel-level accuracy does not necessarily guarantee reliable spatial statistics, highlighting the need to jointly consider pixel-level quality and instance-level reliability for robust bay-scale aquaculture governance.
Lobate scarps are small thrust faults that record the recent contractional tectonic activity of the Moon, but their subtle optical expression and narrow width, compounded by highly variable illumination across lunar remote sensing imagery, make consistent large-area mapping difficult. To address these challenges, we propose MALS-Net, a multimodal attention-enhanced semantic segmentation network for automatic detection of lunar lobate scarps from high-resolution orbital imagery. MALS-Net employs LROC NAC digital orthophoto maps (DOMs) together with monocular depth data generated by Depth Anything V2, thereby combining optical texture with structural prior. The framework comprises two key parts: an attention-augmented encoder and a small-object-oriented decoder. In the encoder, a ResNet-50 backbone with atrous spatial pyramid pooling (ASPP) captures multiscale context while efficient channel attention (ECA) adaptively weights features during multimodal fusion. In the decoder, a spatial context awareness (SCA) module and an efficient spatial channel attention (ESCA) module jointly enhance small-scale scarps by strengthening global spatial context and local edge responses. In addition, a multilevel evaluation framework is further developed that includes pixel-level, object-level, and geometric (normalized centroid distance (NCD) and compactness similarity (CS)) metrics designed for lobate scarps. Experiments on a new dataset of 11,920 multimodal samples between 60°N and 60°S show that MALS-Net outperforms representative baselines, achieving a pixel-level F1 of 92.129%, with object-level F1, NCD, and CS of 69.409%, 1.066%, and 82.966%. Ablation studies demonstrate the complementary contributions of ECA, SCA, and ESCA, and show that fusing DOM with depth features is markedly more effective than any single modality or the combination of DOM and SLDEM. Finally, when deployed over the Chang’e-7 pre-selected landing area in the south polar region, which was entirely excluded from the training dataset, MALS-Net detects six candidate lobate scarps, demonstrating generalization capability and practical potential for global mapping.
Areal interpolation is widely used to disaggregate census population from administrative units to finer spatial units. With the growing availability of residential building data, building-based dasymetric mapping is an important approach for fine-scale population estimation. However, many existing models rely on single morphological variables, such as building footprint or gross floor area, and assume uniform population density across residential areas. This study develops a typology-based dasymetric mapping model (TBM) that introduces residential building typology as an intermediate layer to differentiate population-density parameters. The analysis covers seven subdistricts in Qinhuai District, Nanjing, and is evaluated using population data for 37 communities. Residential types are identified through PCA–GMM clustering across candidate morphological feature combinations. Type-specific density parameters are estimated from subdistrict-level population and housing-area constraints, followed by subdistrict-level calibration and redistribution to residential plots. To avoid circular validation, feature combinations are selected using only the training subdistricts in each outer fold, and the resulting TBM is evaluated on the held-out subdistrict. Uniform footprint-based model (UFBM) and uniform GFA-based model (UGFM) assess typology gains, all-feature clustering model (AFCM) assesses feature selection, and WorldPop (WP) provides an external gridded reference. Under the available validation conditions, TBM shows modest improvements over AFCM and UFBM, with RMSE and MAE reductions below 2.2% and Mean RE differences below 0.3% points. Larger differences are observed relative to UGFM and WP, while TBM shares the highest Spearman’s ρ with AFCM. These results suggest that residential typology provides a measurable but limited improvement over strong building-based baselines. Given the limited sample of 37 communities and the mismatch between community-level validation and subdistrict-level modeling populations, the reported errors should be interpreted as relative comparison indicators rather than strict measures of absolute accuracy. Within these constraints, the workflow provides an interpretable link between residential morphology, density calibration, and plot-level redistribution, offering supplementary fine-scale population information where suitable data are available.
High-precision global navigation satellite system (GNSS) positioning fundamentally relies on reliable integer ambiguity resolution (IAR). Conventional validation methods are inherently sensitive to measurement noise magnitude. At elevated noise levels characteristic of urban canyons and other GNSS-degraded environments, these standard approaches struggle to achieve reliable IAR, fundamentally limiting their applicability in high-noise scenarios. This paper proposes a noise-resilient approach that achieves IAR by exploiting the geometric invariance of normalized correlation matrices. Unlike standard integer least-squares methods depending on covariance magnitudes, the proposed framework derives fixed validation criteria from correlation matrix structure, which encodes only geometric relationships between ambiguities. By analyzing extremal statistics of the correlation matrix, specifically column maxima and row minima, we establish discrimination criteria invariant across varying measurement noise conditions. To further enhance both computational efficiency and candidate separability, a randomized satellite subset selection strategy is introduced. The method utilizes a validation threshold that can be established without prior noise knowledge. Extensive real-time kinematic (RTK) experiments on controlled synthetic datasets with noise addition ranging from 2 mm to 20 mm and real outdoor scenarios demonstrate that the correlation-based method reliably validates ambiguities within 2 min at 10 mm noise, approximately three times faster than the ratio test. At noise levels as high as 20 mm, the method maintains robust performance when conventional methods become impractically slow or unreliable. This approach is particularly suited for post-processed kinematic applications and autonomous navigation systems where measurement uncertainties cannot be fully characterized a priori.
Natural resources, particularly forests, are vital for ecosystem regulation but face threats like wildfires, increasingly common in Sub-Saharan Africa (SSA). This study evaluates wildfire intensity in central Cameroon (Yoko and Nanga-Eboko) from 2003 to 2023 using geospatial techniques, based on burned area (MCD64A1) and active fire (MCD14DL and Near Real-Time, NRT) images classification. Remote sensing tools like Google Earth Engine (GEE), Moran’s I, and Getis-Ord [Formula: see text] hotspot analysis identified vulnerable areas. Results reveal fire intensities of 49.5–2651.7 ha, with densities of 0–10.89 fires/km2. Temporal trends show increasing burned areas but declining active fires, confirmed by Mann-Kendall and Sen’s slope tests. Anomalies highlight increases of 3.5 ha and two additional fires during specific periods. Fire-prone months are October, November, and December, with an average monthly burned area of 1629.70 ha. Spatial analyses reveal clustering of high-intensity zones, especially outside protected areas (Moran’s I = 0.009081; p < 0.001). These findings highlight the urgent need for improved fire mitigation strategies and landscape restoration to safeguard ecosystems.
