In recent years, with the rapid development of urban transportation network in China, many problems have been exposed, especially in the Beijing–Tianjin–Hebei (BTH) region. Under the call of sustainable development, it is of great significance to evaluate the economic, social, and ecological (ESE) impact of transportation network in BTH urban agglomeration for promoting the sustainable development of transportation ESE in BTH urban agglomeration. In this paper, 12 indicators in the field of transportation are selected to build the evaluation index system of ESE effects of transportation network in BTH urban agglomeration. By using entropy weight TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) model and the Jenks natural breaks classification method, the ESE impacts of transportation network in 13 cities of BTH from 2013 to 2017 are analyzed from the temporal and spatial dimensions. The research shows that: (1) From 2013 to 2017, the economic impact degree of traffic network shows an annual fluctuation trend, the social impact degree increases year by year, and the ecological impact degree decreases year by year; (2) For the cities of BTH, the ESE impact assessment results of transportation network from 2013 to 2017 can be divided into seven clusters. Except Handan City, the ESE impact assessment categories of other cities’ transportation network have been improved, but the proportion of cities in the transition period is still large, especially the “Low-Low-Low” cities. The types of cities in the transitional period need to be focused. It is still a heavy burden to realize the ESE coordination and sustainable development of BTH urban agglomeration transportation network.

For the semantic segmentation of remote sensing images, most existing methods focus on directly fusing unrefined low-level features with high-level features to enhance feature representation. However, these methods often neglect the potential feature entanglement within low-level features, making it challenging to accurately extract and restore spatial details. In this article, a gradient decoupling guided network (GDGNet) is proposed to alleviate this issue. The key components of GDGNet include the hybrid gradient enhancement (HGE) module, the hierarchical gradient attention (HGA) module, and the global-local context fusion (GLCF) module. Firstly, the HGE aggregates learnable gradient convolutions to encode gradient information, enhancing the gradient features of low-level features. Then, the HGA reweights gradient decoupling masks (GDMs) to disentangle low-level features, guiding the network to focus on essential gradient regions. Finally, the GLCF fuses low-level and high-level features, generating local and global contextual features and concatenating them to achieve segmentation. We conducted comparison and ablation experiments on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen and Potsdam datasets. The experimental results demonstrate the superiority of the proposed GDGNet over several state-of-the-art methods. The codes will be available at https://github.com/wangkaiwh331/GDGNet.

Hyperspectral image (HSI) classification methods based on deep learning techniques have succeeded wildly. However, the high-dimensional non-linearity, spectral mixing, and difficulty in labeling training samples of HSI still hinder the accuracy of HSI classification. Several patch-free-based methods were proposed for HSI classification and have attracted attention. Nevertheless, recent patch-free methods have focused on low- or high-order interactions, ignoring the abundant middle-order interactions, failing to capture the multi-order interactions in the context of HSI, and difficulty extracting discriminative features when the sample data is imbalanced. In this paper, a combining multi-attention and asymmetric convolution (CMAAC) global learning framework was proposed for insufficient utilization of spectral-spatial information and imbalanced HSI samples. In CMAAC, the channel convolutional long short-term mechanism and multi-order spatial aggregation block (CLMS), which aim to capture multi-order interactions information and extract more discriminant spectral-spatial features effectively, is proposed. The pyramid-enhanced attention mechanism (PEAM) alleviates the information loss in feature flow, retains more spatial information, and better solves the challenge of scale diversity in different land-cover types. The asymmetric convolutional structure (ACS) at the end of the model highlights the influence of local key feature points and improves its representation ability. Additionally, the framework introduces a joint loss function to reduce misclassified classes caused by the imbalance between well-classified and hard-classified samples. We conducted experiments on four benchmark datasets and compared them with the state-of-the-art approaches, demonstrating the model’s effectiveness and superiority.