Fine particulate matter smaller than 2.5 μm (PM_2.5) in size can significantly affect human health, atmospheric visibility, climate, and ecosystems. PM_2.5 has become the major air pollutant in most cities of China. However, influencing factors and their interactive effects on PM_2.5 concentrations remain unclear. This study used a geographic detector method to quantify the effects of anthropogenic precursors (AP) and meteorological factors on PM_2.5 concentrations in cities of China. Results showed that impacts of meteorological conditions and AP on PM_2.5 have significant spatio-temporal disparities. Temperature was the main influencing factor throughout the whole year, which can explain 27% of PM_2.5 concentrations. Precipitation and temperature were primary impacting factors in southern and northern China, respectively, at the annual time scale. In winter, AP had stronger impacts on PM_2.5 in northern China than in other seasons. Ammonia had stronger impacts on PM_2.5 than other anthropogenic precursors in winter. The interaction between all factors enhanced the formation of PM_2.5 concentrations. The interaction between ammonia and temperature had strongest impacts at the national scale, explaining 46% (q = 0.46) of PM_2.5 concentrations. The findings comprehensively elucidated the relative importance of driving factors in PM_2.5 formation, which can provide basic foundations for understanding the meteorological and anthropogenic influences on the concentration patterns of PM_2.5.

As a trusted decentralized application, smart contracts manage a large number of digital assets on the blockchain. Vulnerability detection of smart contracts is an important part of ensuring the security of digital assets. At present, many researchers extract features of smart contract source code for vulnerability detection based on deep learning methods. However, the current research mainly focuses on the single representation form of the source code, which cannot fully obtain the rich semantic and structural information contained in the source code, so it is not conducive to the detection of various and complex smart contract vulnerabilities. Aiming at this problem, this paper proposes a vulnerability detection model based on the fusion of syntax and semantic features. The syntactic and semantic representation of the source code is obtained from the abstract syntax tree and control flow graph of the smart contract through TextCNN and Graph Neural Network. The syntactic and semantic features are fused, and the fused features are used to detect vulnerabilities. Experiments show that the detection accuracy and recall rate of this model have been improved on the detection tasks of five types of vulnerabilities, with an average precision of 96% and a recall rate of 90%, which can effectively identify smart contract vulnerabilities.

As a basic method of spatial data operation, spatial keyword query can provide meaningful information to meet user demands by searching spatial textual datasets. How to accurately understand users’ intentions and efficiently retrieve results from spatial textual big data are always the focus of research. Spatial textual big data and their complex correlation between textual features not only enrich the connotation of spatial objects but also bring difficulties to the efficient recognition and retrieval of similar spatial objects. Because there are a lot of many-to-many relationships between massive spatial objects and textual features, most of the existing research results that employ tree-like and table-like structures to index spatial data and textual data are inefficient in retrieving similar spatial objects. In this paper, firstly, we define spatial textual concept (STC) as a group of spatial objects with the same textual keywords in a limited spatial region in order to present the many-to-many relationships between spatial objects and textual features. Then we attempt to introduce the concept lattice model to maintain a group of related STCs and propose a hybrid tree-like spatial index structure, the lattice-tree, for spatial textual big data. Lattice-tree employs R-tree to index the spatial location of objects, and it embeds a concept lattice structure into specific tree nodes to organize the STC set from a large number of textual keywords of objects and their relationships. Based on this, we also propose a novel spatial keyword query, named Top-k spatial concept query (TkSCQ), to answer STC and retrieve similar spatial objects with multiple textual features. The empirical study is carried out on two spatial textual big data sets from Yelp and Amap. Experiments on the lattice-tree verify its feasibility and demonstrate that it is efficient to embed the concept lattice structure into tree nodes of 3 to 5 levels. Experiments on TkSCQ evaluate lattice from results, keywords, data volume, and so on, and two baseline index structures based on IR-tree and Fp-tree, named the inverted-tree and Fpindex-tree, are developed to compare with the lattice-tree on data sets from Yelp and Amap. Experimental results demonstrate that the Lattice-tree has the better retrieval efficiency in most cases, especially in the case of large amounts of data queries, where the retrieval performance of the lattice-tree is much better than the inverted-tree and Fpindex-tree.

The real estate price index serves as a crucial indicator reflecting the operational status of the real estate market in China. However, it often lags until mid-next month, hindering stakeholders from grasping market trends in real time. Moreover, the real estate market has an extremely complex operating mechanism, which makes it difficult to accurately assess the impact of various policy and economic factors on the real estate price index. Therefore, we hope, from the perspective of data science, to explore the emotional fluctuations of the public towards the real estate market and to reveal the dynamic relationship between the real estate price index and online news sentiment. Leveraging massive online news data, we propose a forecasting scheme for the real estate price index that abandons complex policy and economic data dependence and is solely based on common and easily obtainable online news data. This scheme involves crawling historical online real estate news data in China, employing a BERT-based sentiment analysis model to identify news sentiment, and subsequently aggregating the monthly Real Estate Sentiment (RES) index for Chinese cities. Furthermore, we construct a Vector Autoregression (VAR) model using the historical RES index and housing price index to forecast future housing price indices. Extensive empirical research has been conducted in Beijing, Shanghai, Guangzhou, and Shenzhen, China, to explore the dynamic interaction between the RES index and both the new housing price index and the second-hand housing price index. Experimental results showcase the unique features of the proposed RES index in various cities and demonstrate the effectiveness and utility of our proposed forecasting scheme for the real estate price index.