Lithologic unit classification is essential for resource surveys and infrastructure planning. Remote sensing provides a rapid and scalable alternative to traditional field surveys but faces challenges in vegetation-covered areas due to limited lithological information. To address this, we propose AMSNet, an attention-based multi-scale a priori knowledge-guided lithologic classification framework, which integrates Multi-Scale Enhanced Cross-Spatial Attention (MSECA) and Wavelet-Enhanced Crisscross Attention (WCCA). MSECA extracts lithologic features by aggregating multi-scale neighborhood information and introducing cross-spatial learning, while WCCA enhances long-range contextual understanding using wavelet transforms to mitigate information loss during key-query generation. Experiments on the Qichun and Tieshan datasets demonstrate that AMSNet achieves an overall accuracy (OA) of 69.03% and 83.77%, a mean intersection over union (mIoU) of 48.41% and 48.18%, and a Macro-F1 score of 63.65% and 60.68%, outperforming baseline models. Ablation studies further confirm the effectiveness of MSECA and WCCA in improving lithologic feature extraction. These findings demonstrate the potential of AMSNet to improve lithologic classification in complex terrains, contributing to advancements in geoscience applications.

Lithological unit classification (LUC) refers to the classification of different types of rocks within an area, and it has been widely used in many fields, such as resource surveys and infrastructure planning. However, traditional field surveys require a lot of resources and time. Since remote sensing technology can rapidly acquire information without regional limitations, many researchers have focused on classifying lithological units with remote sensing images. However, in an area covered by vegetation, the beneficial information directly provided by remote sensing images is limited. Moreover, lithological interpretation often requires geological prior knowledge for guidance, which cannot be provided by remote sensing images. Thus, this study designed a dual-branch deep learning model to extract geological prior knowledge from geological information, and improve the accuracy of LUC. In the process of feature transmission of the model, a Dense Attention residual - Atrous Spatial Pyramid Pooling (DA-ASPP) module was proposed to maximize the preservation of lithological units’ features. The DA-ASPP integrates the idea of dense connection into ASPP for multiscale object feature preservation and adds residual structure into the channel attention mechanism to screen out the representative features of lithological units. The study area was located in southeastern Hubei Province, China, with seven categories of lithological units. A total of seven deep-learning networks were compared. The proposed method achieved a mean Intersection over Union (IOU) of 44.61% with a Macro-F1 of 56.54%, which were better than those of comparison models. Moreover, the visualization results demonstrated the superiority of the proposed model in LUC.

Land cover classification in mining areas (LCMA) is essential for the environmental assessment of mines and plays a crucial role in their sustainable development. The shapes of mine land occupation elements are irregular, and the overall proportion of their area is relatively small. Therefore, their features may be easily lost during feature extraction, which limits the interpretation accuracy in mining areas. This study attempts to address these issues. We propose a model named EG-UNet to enhance the features of elements with few samples and to capture long-range information. The proposed EG-UNet includes two main modules. First, the edge feature enhancement module, the edges of elements of mine land occupation contain more information than other spatial locations. Hence, during the feature extraction of elements, a Sobel operator is used to extract the object boundary, which increases the weight of these features before the pooling operation for their preservation. Second, the long-range information extraction module, long-range information helps extract tiny objects, such as dumping grounds in the mining area. We present a graph convolutional network (GCN) to capture the long-range features and apply convolutional neural networks to learn the graph construction. A total of ten deep-learning networks were compared using the LCMA semantic segmentation dataset. Our model exhibited the best performance, especially in classifying classes with few samples. Furthermore, to evaluate the general ability of EG-UNet, a benchmark-Gaofen Image Dataset (GID) was used, and the result still reflected the superiority of our method.

Mountain roads are a source of important basic geographic data used in various fields. The automatic extraction of road images through high-resolution remote sensing imagery using deep learning has attracted considerable attention. But the interference of context information limited extraction accuracy, especially for roads in mountain area. Furthermore, when pursuing research in a new district, many algorithms are difficult to train due to a lack of data. To address these issues, a framework based on remote sensing road-scene neighborhood probability enhancement and improved conditional generative adversarial network (NIGAN) is proposed in this article. This framework can be divided into two sections: 1) road scenes classification section. A remote sensing road-scene neighborhood confidence enhancement method was designed for classifying road scenes of the study area to reduce the impact of nonroad information on subsequent fine-road segmentation and 2) fine-road segmentation section. An improved dilated convolution module, which is helpful in extracting small objects such as road, was added into the conditional generative adversarial network (CGAN) to increase the receptive field and pay attention to global information, and segment roads from the results of road scenes classification section. To validate the NIGAN framework, new mountain road-scene and label datasets were constructed, and diverse comparison experiments were performed. The results indicate that the NIGAN framework can improve the integrity and accuracy of mountain road-scene extraction in diverse and complex conditions. The results further confirm the validity of the NIGAN framework in small samples. In addition, the mountain road-scene datasets can serve as benchmark datasets for studying mountain road extraction.

Road information from high-resolution remote-sensing images is widely used in various fields, and deep-learning-based methods have effectively shown high road-extraction performance. However, for the detection of roads sealed with tarmac, or covered by trees in high-resolution remote-sensing images, some challenges still limit the accuracy of extraction: 1) large intraclass differences between roads and unclear interclass differences between urban objects, especially roads and buildings; 2) roads occluded by trees, shadows, and buildings are difficult to extract; and 3) lack of high-precision remote-sensing datasets for roads. To increase the accuracy of road extraction from high-resolution remote-sensing images, we propose a split depth-wise (DW) separable graph convolutional network (SGCN). First, we split DW-separable convolution to obtain channel and spatial features, to enhance the expression ability of road features. Thereafter, we present a graph convolutional network to capture global contextual road information in channel and spatial features. The Sobel gradient operator is used to construct an adjacency matrix of the feature graph. A total of 13 deep-learning networks were used on the Massachusetts roads dataset and nine on our self-constructed mountain road dataset, for comparison with our proposed SGCN. Our model achieved a mean intersection over union (mIOU) of 81.65% with an F1-score of 78.99% for the Massachusetts roads dataset, and an mIOU of 62.45% with an F1-score of 45.06% for our proposed dataset. The visualization results showed that SGCN performs better in extracting covered and tiny roads and is able to effectively extract roads from high-resolution remote-sensing images.