Good characterization of traffic interactions among urban roads can facilitate traffic-related applications, such as traffic control and short-term forecasting. Most studies measure the traffic interaction between two roads by their topological distance or the correlation between their traffic variables. However, the distance-based methods neglect the spatial heterogeneity of roads’ traffic interactions, while the correlation-based methods cannot capture the non-linear dependency between two roads’ traffic variables. In this paper, we propose a novel approach called Road2Vec to quantify the implicit traffic interactions among roads based on large-scale taxi operating route data using a Word2Vec model from the natural language processing (NLP) field. First, the analogy between transportation elements (i.e., road segment, travel route) and NLP terms (i.e., word, document) is established. Second, the real-valued vectors for road segments are trained from massive travel routes using the Word2Vec model. Third, the traffic interaction between any pair of roads is measured by the cosine similarity of their vectors. A case study on short-term traffic forecasting is conducted with artificial neural network (ANN) and support vector machine (SVM) algorithms to validate the advantages of the presented method. The results show that the forecasting achieves a higher accuracy with the support of the Road2Vec method than with the topological distance and traffic correlation based methods. We argue that the Road2Vec method can be effectively utilized for quantifying complex traffic interactions among roads and capturing underlying heterogeneous and non-linear properties.

A Geographic Knowledge Graph (GeoKG) links geographic relation triplets into a large-scale semantic network utilizing the semantic of geo-entities and geo-relations. Unfortunately, the sparsity of geo-related information distribution on the web leads to a situation where information extraction systems can hardly detect enough references of geographic information in the massive web resource to be able to build relatively complete GeoKGs. This incompleteness, due to missing geo-entities or geo-relations in GeoKG fact triplets, seriously impacts the performance of GeoKG applications. In this paper, a method with geospatial distance restriction is presented to optimize knowledge embedding for GeoKG completion. This method aims to encode both the semantic information and geospatial distance restriction of geo-entities and geo-relations into a continuous, low-dimensional vector space. Then, the missing facts of the GeoKG can be supplemented through vector operations. Specifically, the geospatial distance restriction is realized as the weights of the objective functions of current translation knowledge embedding models. These optimized models output the optimized representations of geo-entities and geo-relations for the GeoKG’s completion. The effects of the presented method are validated with a real GeoKG. Compared with the results of the original models, the presented method improves the metric Hits@10(Filter) by an average of 6.41% for geo-entity prediction, and the Hits@1(Filter) by an average of 31.92%, for geo-relation prediction. Furthermore, the capacity of the proposed method to predict the locations of unknown entities is validated. The results show the geospatial distance restriction reduced the average error distance of prediction by between 54.43% and 57.24%. All the results support the geospatial distance restriction hiding in the GeoKG contributing to refining the embedding representations of geo-entities and geo-relations, which plays a crucial role in improving the quality of GeoKG completion.

Monitoring carbon emissions is crucial for assessing and addressing economic development and climate change, particularly in regions like the nine provinces along the Yellow River in China, which experiences significant urbanization and development. However, to the best of our knowledge, existing studies mainly focus on national and provincial scales, with fewer studies on municipal and county scales. To address this issue, we established a carbon emission assessment model based on the “NPP-VIIRS-like” nighttime light data, aiming to analyze the spatiotemporal variation of carbon emissions in three different levels of nine provinces along the Yellow River since the 21st century. Further, the spatial correlation of carbon emissions at the county level was explored using the Moran’s I spatial analysis method. Results show that, from 2000 to 2021, carbon emissions in this region continued to rise, but the growth rate declined, showing an overall convergence trend. Per capita carbon emission intensity showed an overall upward trend, while carbon emission intensity per unit of GDP showed an overall downward trend. Its spatial distribution generally showed high carbon emissions in the eastern region and low carbon emissions in the western region. The carbon emissions of each city mainly showed a trend of “several”; that is, the urban area around the Yellow River has higher carbon emissions. Meanwhile, there is a trend of higher carbon emissions in provincial capitals. Moran’s I showed a trend of decreasing first and then increasing and gradually tended to a stable state in the later stage, and the pattern of spatial agglomeration was relatively fixed. “High–High” and “Low–Low” were the main types of local spatial autocorrelation, and the number of counties with “High–High” agglomeration increased significantly, while the number of counties with “Low–Low” agglomeration gradually decreased. The findings of this study provide valuable insights into the carbon emission trends of the study area, as well as the references that help to achieve carbon peaking and carbon neutrality goals proposed by China.

Geographic relation completion contributes greatly to improving the quality of large-scale geographic knowledge graphs (GeoKGs). However, the internal features of a GeoKG used in large-scale GeoKGs embedding are often limited by the weak connectivity between geographic entities (geo-entities). If there is no proper choice in the method of external semantic enhancement, this will often interfere with the representation and learning of the KG. Therefore, we here propose a geographic relation (geo-relation) prediction model based on multi-layer similarity enhanced networks for geo-relations completion (MSEN-GRP). The MSEN-GRP comprises three parts: enhancer, encoder, and decoder. The enhancer constructs semantic, spatial, structural, and attribute-similarity networks for geo-entities, which can explicitly and effectively enhance the implicit semantic associations between existing geo-entities. The encoder can obtain the long path relation dependency characteristics of geo-entities using a mixed-path sampling strategy and can support different optimization schemes for external semantic enhancement. Geo-relations prediction experiments show that the mean reciprocal ranking of this method is significantly higher than those of the traditional TransE DisMult and methods, and Hits@10 is improved by up to 57.57%. Furthermore, the spatial-similarity network has the most significant enhancement effect on geo-relations prediction. The proposed method provides a new way to perform relation completion in sparse GeoKGs.

As the largest freshwater Lake in China, Poyang Lake plays an important role in regulating the water level of Yangtze River and maintaining the ecological balance of surrounding areas. Therefore, this study utilizes Google Earth Engine (GEE) geospatial technology to acquire 124 remotely sensed images to explore the spatial and temporal changes of the four seasons of Poyang Lake from 1987 to 2019. The official statistics from relevant cities are used to quantitatively reveal the main driving factors of water body changes in Poyang Lake. Temporally, the water body area of Poyang Lake shows an obvious downward trend in general. Spatially, the water body area of Poyang Lake shows a gradual decrease from the center of the lake to the surroundings. In 1987-1998, the water body area of Poyang Lake showed an increasing trend, with an increase of about 727.90km2. From 1998 to 2006, the water body area of Poyang Lake mainly showed a decreasing trend, with a decrease of 401.58km2. The water body area of Poyang Lake increased slowly during 2006-2017. Anthropogenic factors and natural factors have influenced the changes in water body area of Poyang Lake to a certain extent. This study can provide valuable supporting data for the comprehensive environmental management and flood hazard monitoring of Poyang Lake.