Text-to-SQL for spatial databases enables the translation of natural language questions into corresponding SQL queries, allowing non-experts to easily access spatial data, which has gained increasing attention from researchers. Previous research has primarily focused on rule-based methods. However, these methods have limitations when dealing with complicated or unknown natural language questions. While advanced machine learning models can be trained, they typically require large labeled training datasets, which are severely lacking for spatial databases. Recently, Generative Pre-Trained Transformer (GPT) models have emerged as a promising paradigm for Text-to-SQL tasks in relational databases, driven by carefully designed prompts. In response to the severe lack of datasets for spatial databases, we have created a publicly available dataset that supports both English and Chinese. Furthermore, we propose a GPT-based method to construct prompts for spatial databases, which incorporates geographic and spatial database knowledge into the prompts and requires only a small number of training samples, such as 1, 3, or 5 examples. Extensive experiments demonstrate that incorporating geographic and spatial database knowledge into prompts improves the accuracy of Text-to-SQL tasks for spatial databases. Our proposed method can help non-experts access spatial databases more easily and conveniently.

Vector road networks are vital components of intelligent transportation systems and electronic navigation maps. There is a pressing need for efficient and rapid dynamic updates for road network data. In this paper, we propose a series of methods designed specifically for geometric change detection and the topological consistency updating of multi-source vector road networks without relying on complicated road network matching. For geometric change detection, we employ buffer analysis to compare various sources of vector road networks, differentiating between newly added, deleted, and unchanged road features. Furthermore, we utilize road shape similarity analysis to detect and recognize partial matching relationships between different road network sources. For incremental updates, we define topology consistency and propose three distinct methods for merging road nodes, aiming to preserve the topological integrity of the road network to the greatest extent possible. To address geometric conflicts and topological inconsistencies, we present a fusion and update method specifically tailored for partially matched road features. In order to verify the proposed methods, a road central line network with a scale of 1:10000 from the official institution is employed to geometrically update the commercial navigation road network of a similar scale in the remote area. The experiment results indicate that our method achieves an impressive 91.7% automation rate in detecting geometric changes for road features. For the remaining 8.3% of road features, our method provides suggestions on potential geometric changes, albeit necessitating manual verification and assessment. In terms of the incremental updating of the road network, approximately 89.2% of the data can be seamlessly updated automatically using our methods, while a minor 10.8% requires manual intervention for road updates. Collectively, our methods expedite the updating cycle of vector road network data and facilitate the seamless sharing and integrated utilization of multi-source road network data.

Research on grassland monitoring based on temperature/emissivity separation based on hyperspectral thermal infrared (HTIR) remote sensing is rare. Based on the longwave TIR instrument (Hyper-CAM), this study designed two experiments to collect HTIR datasets, separate the temperature and emissivity of different vegetation of grassland, and analyze the relationship between the emissivity of vegetation and soil moisture content. First, we collected the HTIR remotely sensed dataset of different kinds of vegetation and used the temperature/emissivity separation algorithm to separate the temperature and emissivity of seven types of vegetation. The temperature and emissivity of these types of vegetation were separated. Then, the absorption characteristics of the emissivity spectral curves of each type of grass were analyzed. The distribution and differences of the temperature and specific emissivity in different parts of these seven grassland vegetation types were quantitatively analyzed, and the relationship between their changes and vegetation leaf moisture and vegetation health status was also analyzed. Second, to monitor the drought of grassland vegetation, a second experiment was designed to measure the changes in the emissivity under different soil water contents. This observation experiment took Artemisia frigida as the research object. From the results of the separation of the temperature and emissivity, we found that the emissivity of Artemisia frigida has significantly changed with the increase in the water content, and the emissivity showed an overall increasing trend. We also quantitatively analyzed the differences in the temperature and specific emissivity between Artemisia frigida and Artemisia subulata Nakai, both belonging to the genus Artemisia, under different water content conditions. The overall waveform characteristics and their similarities and differences at 850–1280 cm⁻¹ were compared and analyzed. The experimental results shows that Hyper-CAM can effectively obtain the emissivity of various types of grassland vegetation as the absorption characteristics of grassland vegetation in the thermal infrared spectral region were quite notable, which shows the significant potential ability of identification and discrimination of different types of grassland vegetation.

Synthetic aperture radar images can be used for ship target detection. However, due to the unclear ship outline in SAR images, noise and land background factors affect the difficulty and accuracy of ship (especially small target ship) detection. Therefore, based on the YOLOv5s model, this paper improves its backbone network and feature fusion network algorithm to improve the accuracy of ship detection target recognition. First, the LSKModule is used to improve the backbone network of YOLOv5s. By adaptively aggregating the features extracted by large-size convolution kernels to fully obtain context information, at the same time, key features are enhanced and noise interference is suppressed. Secondly, multiple Depthwise Separable Convolution layers are added to the SPPF (Spatial Pyramid Pooling-Fast) structure. Although a small number of parameters and calculations are introduced, features of different receptive fields can be extracted. Third, the feature fusion network of YOLOv5s is improved based on BIFPN, and the shallow feature map is used to optimize the small target detection performance. Finally, the CoordConv module is added before the detect head of YOLOv5, and two coordinate channels are added during the convolution operation to further improve the accuracy of target detection. The map50 of this method for the SSDD dataset and HRSID dataset reached 97.6% and 91.7%, respectively, and was compared with a variety of advanced target detection models. The results show that the detection accuracy of this method is higher than other similar target detection algorithms.

1. Cross-view geo-localisation aims to estimate the geographic position of a query image by establishing a matching relationship between a ground-view query image and geo-tagged reference images (L...