Address matching is a crucial step in geocoding, which plays an important role in urban planning and management. To date, the unprecedented development of location-based services has generated a large amount of unstructured address data. Traditional address matching methods mainly focus on the literal similarity of address records and are therefore not applicable to the unstructured address data. In this study, we introduce an address matching method based on deep learning to identify the semantic similarity between address records. First, we train the word2vec model to transform the address records into their corresponding vector representations. Next, we apply the enhanced sequential inference model (ESIM), a deep text-matching model, to make local and global inferences to determine if two addresses match. To evaluate the accuracy of the proposed method, we fine-tune the model with real-world address data from the Shenzhen Address Database and compare the outputs with those of several popular address matching methods. The results indicate that the proposed method achieves a higher matching accuracy for unstructured address records, with its precision, recall, and F1 score (i.e., the harmonic mean of precision and recall) reaching 0.97 on the test set.

Population spatialization reveals the distribution and quantity of the population in geographic space with gridded population maps. Fine-scale population spatialization is essential for urbanization and disaster prevention. Previous approaches have used remotely sensed imagery to disaggregate census data, but this approach has limitations. For example, large-scale population censuses cannot be conducted in underdeveloped countries or regions, and remote sensing data lack semantic information indicating the different human activities occurring in a precise geographic location. Geospatial big data and machine learning provide new fine-scale population distribution mapping methods. In this paper, 30 features are extracted using easily accessible multisource geographic data. Then, a building-scale population estimation model is trained by a random forest (RF) regression algorithm. The results show that 91% of the buildings in Lin’an District have absolute error values of less than six compared with the actual population data. In a comparison with a multiple linear (ML) regression model, the mean absolute errors of the RF and ML models are 2.52 and 3.21, respectively, the root mean squared errors are 8.2 and 9.8, and the R² values are 0.44 and 0.18. The RF model performs better at building-scale population estimation using easily accessible multisource geographic data. Future work will improve the model accuracy in densely populated areas.

Toponyms serve as symbols of regional culture and thus reflect the history, habitat and environment of a place. This study aims to (1) visualize the distributions of the four ethnic groups and landscape features in Guangdong of China using a toponym mapping method, of which results were presented at 1:6,400,000 scale and (2) to explore the changes by comparing contemporary data, of which results were presented at 1:3,200,000 scale. These maps provide a toponymic aspect to explore the historical evolution of ethnic groups and landscape features.

Urban landmarks play an important role as spatial references in spatial cognition, navigation, map design and urban planning. However, the current landmark extraction methods do not consider the imbalance between the landmark and non-landmarknon-landmark samples in a dataset, so the extraction results are biased toward the class with the majority of sample data, resulting in poor classification performance for the class with the fewest sample data. This study introduces a random forest (RF) classifier combined with cost-sensitive learning to extract urban landmarks automatically from a basic spatial database. First, the optimal feature set is determined according to the importance of features. Next, a cost-sensitive RF algorithm is applied to extract landmarks, which determines the misclassification cost according to the class distribution, and each decision tree is weighted by the classification results. The method has good performance, with a recall and area under the ROC curve (AUC) greater than 90%, and the model is also applicable to small sample sets, which can reduce the cost of manual labor.

Low-sampling-rate floating car data (FCD) are more challenging than those with high-sampling-rate FCD for map matching (MM) algorithms. Some MM algorithms for low-sampling-rate FCD lack sufficient efficiency nor accuracy, especially related to complex urban road networks. This paper proposes a new method named the trajectory restoration algorithm, which is based on geometry MM algorithms to ensure efficiency and accuracy. The proposed algorithm adopts the modified A* shortest path algorithm to reduce the number of function calls and fully considers road network topology and historical matched points to improve its accuracy. We test the efficiency and accuracy of the trajectory restoration algorithm with FCD data for the complex urban road networks in Beijing. The results have strong continuity which greatly improves the utilization of FCD. We show that the proposed algorithm outperforms related MM methods in efficiency and accuracy and its robustness to restore trajectories of both high and low sampling rates in complex urban road networks.