The existing landslide recognition methods mainly focus on the use spectral bands of optical remote sensing and machine learning base classifiers, which are insufficient in landslide characterization in complex scenes, resulting in a high missed and false detection of landslides. In this article, we develop a landslide recognition framework, which combines the multidimensional feature advantages of spectral, terrain and texture of optical satellite images, and constructs a heterogeneous ensemble learning method for landslide mapping. Firstly, we construct a landslide multi-dimensional feature dataset using Sentinel-2A and advanced land observing satellite (ALOS) digital elevation model (DEM) data. Then, we construct a heterogeneous ensemble learning landslide recognition method, which combines the advantages of fully convolutional network (FCN), U-Net, and attention U-Net base classifiers to fully learn the multidimensional features of landslides. Finally, we evaluate the performance of landslide recognition framework in the Bailongjiang River Basin complex scenes. The experimental results show that integrating the multidimensional features of spectral, terrain and texture, and using the heterogeneous ensemble learning method can reduce the missed and false detection of landslides in complex scenes. Specifically, compared with using only spectral bands, integrating spectral bands, spectral indexes, terrain factors and texture indexes achieves the highest Recall, Kappa, F1-score and MIoU in testing areas, MA is reduced by 15.56%. Compared with deep learning base classifiers, the constructed heterogeneous ensemble learning demonstrates improvements in Recall ranging from 41.67% to 69.89%, MA is reduced from 52.17% to 30.11%. This study provides a new idea for high-precision landslide recognition in complex environments

Crisis maps play a significant role in emergency responses. Users are challenged to interpret a map rapidly in emergencies, with limited visual information-processing resources and under time pressure. Therefore, cartographic techniques are required to facilitate their map cognition. In this study, we analyzed the exogenous and endogenous disruptions that users needed to overcome when they were reading maps. The analysis results suggested that cartographers’ taking the stressors into consideration could promote the cognitive fit between cartographers and users, improving map cognition and spatial information supply–demand matching. This paper also elaborates the course of map visual information processing and related graphic variables to visual attention attributes. To improve the users’ map cognition in time-critical emergency situations, crisis map design principles and a methodology were proposed. We developed three fire emergency rescue road maps and performed two evaluations to verify the effectiveness of the principles. Our experiments showed that the principles could effectively facilitate the users’ rapid map perception and proper understanding, by reducing their cognitive load, and could improve the quality of the crisis maps to some extent.

The increasing proportion of night consumption in the total daily consumption means the night economy has become an indispensable part of national economic development. However, early social science research on alcohol in the night economy and social science research on the night leisure industry dominated our understanding of the night city. Few researchers have built effective mathematical statistical models to explore the spatio-temporal distribution and regional interactions of the night economy. This paper presents a method to analyze the spatial and temporal distribution pattern of the night economy based on multi-source data. Firstly, K-Means++ and DBSCAN were used to cluster OD points to identify the gathering areas of night activities. Then, the local L-function in “flow space” was used to extract the aggregated flow of each aggregation area and analyze the regional interactions. Finally, the correlation between night activity and night service facilities was calculated by using geographic detector, and night activity and lighting were coupled by the profit and loss value. The research shows that this method can identify the main areas of night activity, dig out the interrelationships at the community level, and find the new night activity gathering points and night economic growth areas in the future. This study extends the current situation that the night economy is limited to theoretical research and research in central urban areas, provides the temporal and spatial distribution of night activities and night lighting supplies from the perspective of big data, and provides a basis for future night economy research, urban planning, and relevant policy issuance.

Accurate address matching is crucial for the analysis, integration, and intelligent management of urban geospatial data and is also a key step in achieving geocoding. However, due to the complexity, diversity, and irregularity of address expression, address matching becomes a challenging task. This paper proposes a multi-semantic feature fusion method for complex address matching of Chinese addresses that formulates address matching as a classification task that directly predicts whether two addresses refer to the same location, without relying on predefined similarity thresholds. First, the address is resolved into address elements, and the Word2vec model is trained to generate word vector representations using these address elements. Then, multi-semantic features of the addresses are extracted using a Text Recurrent Convolutional Neural Network (Text-RCNN) and a Graph Attention Network (GAT). Finally, the Enhanced Sequential Inference Model (ESIM) is used to perform both local inference and inference composition on the multi-semantic features of the addresses to achieve accurate matching of addresses. Experiments were conducted using Points of Interest (POI) address data from Baidu Maps, Tencent Maps, and Amap within the Chengdu area. The results demonstrate that the proposed method outperforms existing address matching methods, with precision, recall, and F1 values all exceeding 95%. In addition, transfer experiments using datasets from five other cities including Beijing, Shanghai, Xi’an, Guangzhou, and Wuhan show that the model maintains strong generalization ability, achieving F1 values above 84% in cities such as Xi’an and Wuhan.