The increase of consumer income has resulted in the rapid development of the retail industry in China, which provides high market potential for retail companies worldwide. However, site selection for retail shops has been a confusing business issue in practical business decisions. In this study, a two-step hybrid model in site selection for small retail shops was proposed. The two steps were spatial accessibility evaluation and market potential estimation. The spatial accessibility of target regions was evaluated based on the improved gravity model to determine regions that lack retail shops. Then, a PCA (principal component analysis)–BP (backpropagation network) model was established to estimate the market potential in the target regions. The two-step model could determine sites with the most market potential and low competition. We conducted the experiment in Guiyang, China and considered 18 socioeconomic factors to make the site selection convincing. Through the experiment, 42 locations were determined with high business value; the locations were recommended to the new retail shops. The accuracy of the PCA–BP model was then proven satisfactory by comparing it with other regression methods. The proposed model could guide retail chains in enhancing business location planning and formulating regional development policies.

As an informative proxy measure for a range of socio-economic variables, satellite-derived night-time light (NTL) data have been widely used to investigate the diverse anthropogenic activities and reveal urbanization development. Due to the rapid increase of Chinese urbanization rate, from 25.3% in 1987 to 58.5% in 2017, and ‘crazy expansion’ of city space, the sick phenomenon – ‘Ghost Town’ – has been brought out, generally defined as places with high housing vacancy rate (HVR), which will cause the huge waste of the limited land source in China. To investigate the HVR of urban areas in China, this study attempts to establish a hybrid model combining data derived from National Polar-Orbiting Partnership–Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) NTL sensors with OpenStreetMap (OSM) data. By distinguishing non-residential areas and introducing detailed residential building information, we proposed a novel HVR estimation model, thus realizing the estimation of HVR in 31 Chinese provincial cities with different development levels (Tier 1–Tier 3). The results showed the average HVR of Tier 2 cities (0.204) was higher than that of Tier 1 cities (0.189) and Tier 3 cities (0.233). The model was proven more accurate (root mean square error of approximation (RMSE) = 0.022) when compared with previous models. To explore the reasons causing different HVRs in these provincial cities, the relationship between HVR and typical socio-economic factors – gross domestic product (GDP), population, and housing price – was also revealed. Through correlation verification and built of a regression model, HVR was found positively correlated with housing price (0.409), however, negatively correlated with population (−0.829) and GDP (−0.356). The research is an indication of the applicability of using data derived from NPP-VIIRS NTL sensors in reflecting HVR and an exploration to distinguish socio-economic factors influencing HVR in different cities. The model we proposed can potentially provide guidance for urban planners to formulate better land-use plan and rental measures.

Previous studies have attempted to disaggregate census data into fine resolution with multisource remote sensing data considering the importance of fine-resolution population distribution in urban planning, environmental protection, resource allocation, and social economy. However, the lack of direct human activity information invariably restricts the accuracy of population mapping and reduces the credibility of the mapping process even when external facility distribution information is adopted. To address these problems, the present study proposed a novel population mapping method by combining International Space Station (ISS) photography nighttime light data, point of interest (POI) data, and location-based social media data. A similarity matching model, consisting of semantic and distance matching models, was established to integrate POI and social media data. Effective information was extracted from the integrated data through principal component analysis and then used along with road density information to train the random forest (RF) model. A comparison with WordPop data proved that our method can generate fine-resolution population distribution with higher accuracy ( $R^2=0.91$ ) than those of previous studies ( $R^2=0.55$ ). To illustrate the advantages of our method, we highlighted the limitations of previous methods that ignore social media data in handling residential regions with similar light intensity. We also discussed the performance of our method in adopting social media data, considering their characteristics, with different volumes and acquisition times. Results showed that social media data acquired between 19:00 and 8:00 with a volume of approximately 300,000 will help our method realize high accuracy with low computation burden. This study showed the great potential of combining social sensing data for disaggregating fine-resolution population.

With the rapid development of remote sensing (RS) observation technology over recent years, the high-level semantic association-based cross-modal retrieval of RS images has drawn some attention. However, few existing studies on cross-modal retrieval of RS images have addressed the issue of mutual interference between semantic features of images caused by “multi-scene semantics”. Therefore, we proposed a novel cross-attention (CA) model, called CABIR, based on regional-level semantic features of RS images for cross-modal text-image retrieval. This technique utilizes the CA mechanism to implement cross-modal information interaction and guides the network with textual semantics to allocate weights and filter redundant features for image regions, reducing the effect of irrelevant scene semantics on retrieval. Furthermore, we proposed BERT plus Bi-GRU, a new approach to generating statement-level textual features, and designed an effective temperature control function to steer the CA network toward smooth running. Our experiment suggested that CABIR not only outperforms other state-of-the-art cross-modal image retrieval methods but also demonstrates high generalization ability and stability, with an average recall rate of up to 18.12%, 48.30%, and 55.53% over the datasets RSICD, UCM, and Sydney, respectively. The model proposed in this paper will be able to provide a possible solution to the problem of mutual interference of RS images with “multi-scene semantics” due to complex terrain objects.

In recent years, there has been a growing interest in remote sensing image–text cross-modal retrieval due to the rapid development of space information technology and the significant increase in the volume of remote sensing image data. Remote sensing images have unique characteristics that make the cross-modal retrieval task challenging. Firstly, the semantics of remote sensing images are fine-grained, meaning they can be divided into multiple basic units of semantic expression. Different combinations of basic units of semantic expression can generate diverse text descriptions. Additionally, these images exhibit variations in resolution, color, and perspective. To address these challenges, this paper proposes a multi-task guided fusion encoder (MTGFE) based on the multimodal fusion encoding method, the progressiveness of which has been proved in the cross-modal retrieval of natural images. By jointly training the model with three tasks: image–text matching (ITM), masked language modeling (MLM), and the newly introduced multi-view joint representations contrast (MVJRC), we enhance its capability to capture fine-grained correlations between remote sensing images and texts. Specifically, the MVJRC task is designed to improve the model’s consistency in joint representation expression and fine-grained correlation, particularly for remote sensing images with significant differences in resolution, color, and angle. Furthermore, to address the computational complexity associated with large-scale fusion models and improve retrieval efficiency, this paper proposes a retrieval filtering method, which achieves higher retrieval efficiency while minimizing accuracy loss. Extensive experiments were conducted on four public datasets to evaluate the proposed method, and the results validate its effectiveness.