Rapidly obtaining information on the content and spatial distribution of soil organic carbon (SOC) in farmland is crucial for evaluating regional soil quality, land degradation, and crop yield. This study focuses on mountain soils in various crop cultivation areas in Shangzhou District, Shangluo City, Southern Shaanxi, utilizing ZY1-02D hyperspectral satellite imagery, field-measured hyperspectral data, and field sampling data to achieve precise inversion and spatial mapping of the SOC content. First, to address spectral bias caused by environmental factors, the Spectral Space Transformation (SST) algorithm was employed to establish a transfer relationship between measured and satellite image spectra, enabling systematic correction of the image spectra. Subsequently, multiple spectral transformation methods, including continuous wavelet transform (CWT), reciprocal, first-order derivative, second-order derivative, and continuum removal, were applied to the corrected spectral data to enhance their spectral response characteristics. For feature band selection, three methods were utilized: Variable Importance Projection (VIP), Competitive Adaptive Reweighted Sampling (CARS), and Stepwise Projection Algorithm (SPA). SOC content prediction was conducted using three models: partial least squares regression (PLSR), stepwise multiple linear regression (Step-MLR), and random forest (RF). Finally, leave-one-out cross-validation was employed to optimize the L4-CARS-RF model, which was selected for SOC spatial distribution mapping. The model achieved a coefficient of determination (R²) of 0.81, a root mean square error of prediction (RMSEP) of 1.54 g kg⁻¹, and a mean absolute error (MAE) of 1.37 g kg⁻¹. The results indicate that (1) the Spectral Space Transformation (SST) algorithm effectively eliminates environmental interference on image spectra, enhancing SOC prediction accuracy; (2) continuous wavelet transform significantly reduces data noise compared to other spectral processing methods, further improving SOC prediction accuracy; and (3) among feature band selection methods, the CARS algorithm demonstrated the best performance, achieving the highest SOC prediction accuracy when combined with the random forest model. These findings provide scientific methods and technical support for SOC monitoring and management in mountainous areas and offer valuable insights for assessing the long-term impacts of different crops on soil ecosystems.

Soil environmental protection has become a pressing issue for sustainable development. This study collected 153 topsoil samples from a typical agricultural area to evaluate the contamination characteristics of heavy metal(loid)s (HMs), identify their potential sources, and assess the associated ecological and human health risks. The results showed that the mean concentration of HMs was in the order of Zn > Cr > Ni > Pb > Cu > As > Cd > Hg; all HMs were below their background levels, except Cd. The geo-accumulation index (Igeo) and improved Nemerow index (INI) revealed that the overall pollution level was considered as no or slight contamination, while HMs posed low ecological risk according to the ecological hazard factor (E_i) and potential ecological risk index (PERI). In addition, three main sources were identified through the positive matrix factorization (PMF) model: natural source (48.2%; contributed As, Ni, Cu, Pb, and Zn), coal burning and waste disposal (24%; contributed Hg and Cd), and agricultural activities (27.8%; contributed Cr). The human health risk (HHR) assessment model and Monte Carlo simulation were applied to evaluate human health risks, and the results suggested that children faced higher health risks than adults, with 45.83% of samples exceeding the non-carcinogenic acceptable limit. As and Cr were the main contributors to non-carcinogenic and carcinogenic risks, respectively. The findings contributed to the local environmental management and sustainable development of agriculture.

The Banzhusi granite porphyry is located in the Xiong’ershan area, East Qinling orogenic belt (EQOB). This study presents an integrated whole-rock geochemistry and zircon U-Pb-Hf-O isotope analysis of the Banzhusi granite porphyry. These rocks have metaluminous, high-K alkali-calcic and shoshonitic features and show significant enrichment in light rare earth elements (LREEs) over heavy rare earth elements (HREEs) with negative Eu anomalies. These samples are also greatly enriched in Rb, Ba, K, Pb, Th and U and depleted in Nb, Ta, P and Ti, and they mostly overlap the ranges of the Taihua Group tonalite–trondhjemite–granodiorite (TTG) gneiss. Magmatic zircons from three samples of the Banzhusi granite porphyry yield U-Pb ages of 125.1 ± 0.97 Ma, 128.1 ± 1.2 Ma and 128.2 ± 1.3 Ma. The Hf-O isotope features of zircons from the three samples are very similar (δ¹⁸O_zircon = 4.84‰ to 6.51‰, εHf_(t) = −26.9 to −14.4). The co-variations of geochemical and isotopic data in these granite porphyries imply that the Banzhusi granite porphyry resulted from the mixing of the partially melted Taihua Group and mantle-derived material in a post-collisional setting from 128–125 Ma.

Rock image classification represents a challenging fine-grained image classification task characterized by subtle differences among closely related rock categories. Current contrastive learning methods prevalently utilized in fine-grained image classification restrict the model’s capacity to discern critical features contrastively from image pairs, and are typically too large for deployment on mobile devices used for in situ rock identification. In this work, we introduce an innovative and compact model generation framework anchored by the design of a Feature Positioning Comparison Network (FPCN). The FPCN facilitates interaction between feature vectors from localized regions within image pairs, capturing both shared and distinctive features. Further, it accommodates the variable scales of objects depicted in images, which correspond to differing quantities of inherent object information, directing the network’s attention to additional contextual details based on object size variability. Leveraging knowledge distillation, the architecture is streamlined, with a focus on nuanced information at activation boundaries to master the precise fine-grained decision boundaries, thereby enhancing the small model’s accuracy. Empirical evidence demonstrates that our proposed method based on FPCN improves the classification accuracy mobile lightweight models by nearly 2% while maintaining the same time and space consumption.

Cracks are a common early road defect that tends to worsen with the aging of roads, potentially leading to severe structural damage. Timely and accurate crack detection plays a crucial role in mitigating such risks and holds significant importance for infrastructure maintenance. Deep learning techniques have demonstrated excellent performance in image-based crack extraction tasks. However, challenges persist due to the presence of numerous noisy pixels in the image background and the diverse and intricate morphologies of cracks, leading to issues such as misclassification and omission. To address these issues, this paper proposes a refined pixel-level segmentation network (ANF-Net) suitable for complex crack detection scenarios with high noise levels and diverse crack morphologies. When extracting crack features, on one hand, the network introduces an attention module tailored for crack scenes to learn pixel-wise feature weights, enabling the network to focus on crack regions and thereby reducing the impact of similar background features, mitigating false positives caused by noise misclassification. On the other hand, a constrained multi-morphological convolution structure is constructed by imposing learnable continuous constraints on the deformation offsets of convolutional kernels, allowing the network to adaptively fit different crack shapes. This design enhances the network’s ability to extract cracks in morphologically diverse, narrow, and densely populated regions, effectively preventing issues such as crack extraction interruptions and omissions. Additionally, a multi-scale discrete wavelet transform enhancement module is designed to assist the network in considering frequency domain information that contains crack features, further improving its feature extraction capability. Simulations are conducted using three publicly available crack datasets, and the proposed method is compared with mainstream segmentation models. The results demonstrate that the proposed method achieves F1 scores of 87.9%, 82.5%, and 71.5% on the three datasets, respectively, all of which surpass the performance of current mainstream segmentation models. The proposed network accurately extracts road cracks and exhibits robust performance.