Wei Zhang

Observing building changes in remote sensing images plays a crucial role in monitoring urban development and promoting sustainable urbanization. Mainstream change detection methods have demonstrated promising performance in identifying building changes. However, buildings have large intra-class variance and high similarity with other objects, limiting the generalization ability of models in diverse scenarios. Moreover, most existing methods only detect whether changes have occurred but ignore change types, such as new construction and demolition. To address these issues, we present a building change-type detection network (BCTDNet) based on the Segment Anything Model (SAM) to identify newly constructed and demolished buildings. We first construct a dual-feature interaction encoder that employs SAM to extract image features, which are then refined through trainable multi-scale adapters for learning architectural structures and semantic patterns. Moreover, an interactive attention module bridges SAM with a Convolutional Neural Network, enabling seamless interaction between fine-grained structural information and deep semantic features. Furthermore, we develop a change-aware attribute decoder that integrates building semantics into the change detection process via an extraction decoding network. Subsequently, an attribute-aware strategy is adopted to explicitly generate distinct maps for newly constructed and demolished buildings, thereby establishing clear temporal relationships among different change types. To evaluate BCTDNet’s performance, we construct the JINAN-MCD dataset, which covers Jinan’s urban core area over a six-year period, capturing diverse change scenarios. Moreover, we adapt the WHU-CD dataset into WHU-MCD to include multiple types of changing. Experimental results on both datasets demonstrate the superiority of BCTDNet. On JINAN-MCD, BCTDNet achieves improvements of 12.64% in IoU and 11.95% in F1 compared to suboptimal methods. Similarly, on WHU-MCD, it outperforms second-best approaches by 2.71% in IoU and 1.62% in F1. BCTDNet’s effectiveness and robustness in complex urban scenarios highlight its potential for applications in land-use analysis and urban planning.

Geographical named entity matching, a crucial step in address encoding, aims to enhance address resolution accuracy through the precise identification and linkage of geographical named entity data. However, existing approaches tend to ignore the spatial information of entities, leading to misclassification. Drawing on the human process of searching for addresses, this study proposes a multi-objective learning model named GNEMM that integrates the semantic and spatial information of geographical named entities. To further mimic the human cognitive process during address search, it incorporates the Retrieval-Augmented Generation (RAG) technique. By integrating newly added external address data with an advanced large language model (LLM) like GPT-4, it achieves precise address evaluation and recommendation. The model was tested using a standard geographical named entity dataset from Shandong Province, focusing on three sub-tasks: element segmentation, matching, and spatial similarity score prediction. The experimental results indicate that the method achieves a geographical named entity matching accuracy of up to 99%, with improvements of 10% and 5% in the segmentation and prediction sub-tasks. GNEMM performs best in address-matching tasks of various scales, and the vectors extracted by GNEMM perform best in the downstream retrieval and matching of various address types, which verifies its applicability in geographical named entity recommendation applications.

The precise extraction of building footprints using remote sensing technology is increasingly critical for urban planning and development amid growing urbanization. However, considering the complexity of building backgrounds, diverse scales, and varied appearances, accurately and efficiently extracting building footprints from various remote sensing images remains a significant challenge. In this paper, we propose a novel network architecture called ME-FCN, specifically designed to perceive and optimize multi-scale features to effectively address the challenge of extracting building footprints from complex remote sensing images. We introduce a Squeeze-and-Excitation U-Block (SEUB), which cascades multi-scale semantic information exploration in shallow feature maps and incorporates channel attention to optimize features. In the network’s deeper layers, we implement an Adaptive Multi-scale feature Enhancement Block (AMEB), which captures large receptive field information through concatenated atrous convolutions. Additionally, we develop a novel Dual Multi-scale Attention (DMSA) mechanism to further enhance the accuracy of cascaded features. DMSA captures multi-scale semantic features across both channel and spatial dimensions, suppresses redundant information, and realizes multi-scale feature interaction and fusion, thereby improving the overall accuracy and efficiency. Comprehensive experiments on three datasets demonstrate that ME-FCN outperforms mainstream segmentation methods.

Social media is widely used to share real-time information and report accidents during natural disasters. Named entity recognition (NER) is a fundamental task of geospatial information applications that aims to extract location names from natural language text. As a result, the identification of location names from social media information has gradually become a demand. Named entity correction (NEC), as a complementary task of NER, plays a crucial role in ensuring the accuracy of location names and further improving the accuracy of NER. Despite numerous methods having been adopted for NER, including text statistics-based and deep learning-based methods, there has been limited research on NEC. To address this gap, we propose the CTRE model, which is a geospatial named entity recognition and correction model based on the BERT model framework. Our approach enhances the BERT model by introducing incremental pre-training in the pre-training phase, significantly improving the model’s recognition accuracy. Subsequently, we adopt the pre-training fine-tuning mode of the BERT base model and extend the fine-tuning process, incorporating a neural network framework to construct the geospatial named entity recognition model and geospatial named entity correction model, respectively. The BERT model utilizes data augmentation of VGI (volunteered geographic information) data and social media data for incremental pre-training, leading to an enhancement in the model accuracy from 85% to 87%. The F1 score of the geospatial named entity recognition model reaches an impressive 0.9045, while the precision of the geospatial named entity correction model achieves 0.9765. The experimental results robustly demonstrate the effectiveness of our proposed CTRE model, providing a reference for subsequent research on location names.