Search

As a kind of time series data in the field of transportation, trajectory has complex multi-dimensional information. How to fully excavate the multi-dimensional information of the trajectory and analyse its complex dynamic pattern is an important problem to be solved in the classification of trajectory time series. In response to the above problems, this paper improves the existing self-attention mechanism, and proposes a trajectory time series classification algorithm based on convolutional self-attention mechanism. According to the characteristics of the trajectory data, the convolutional self-attention mechanism first extracts the characteristics of the trajectory fragments in the trajectory to obtain the flight status characteristics, and then performs the self-attention operation on these characteristics, so as to achieve a better feature extraction effect. The experimental results show that the trajectory time series classification algorithm based on the convolutional self-attention mechanism has better feature extraction ability and classification accuracy than other existing algorithms.

The rapid development of urbanization and agriculture poses serious impacts on groundwater in arid and semi-arid areas, which typically have high groundwater depletion rates. In this study, chemical and isotopic analyses combined with different data interpretation methods (diagrams, bivariate analyses, principal component analysis (PCA), and hierarchical cluster analysis (HCA)) were used to identify the major factors controlling groundwater chemistry in an arid and semi-arid region of North China. Sixty-four groundwater samples (35 from unconfined aquifer, 29 from confined aquifer) were collected in Baotou City, North China, and 17 chemical variables were detected for each sample. The complex hydrochemical types in unconfined groundwater (e.g., HCO3-Ca·Mg, HCO3·Cl-Na·Mg, SO4-Na·Mg, and Cl·SO4-Na types) may be related to anthropogenic activities, while the main hydrochemical types in confined groundwater are HCO3-Ca·Mg, HCO3-Na·Mg, HCO3·Cl-Na·Ca, SO4·HCO3-Na·Mg, and Cl·SO4-Na types. Three component models for unconfined and confined groundwater were revealed using PCA, which explained approximately 79.69% and 80.68% of the data variance, respectively, providing a deeper insight into groundwater composition controlled by geochemistry and anthropogenic activities. Three clusters were yielded from HCA. The factors and identified clusters were verified with hydrochemical investigations. Among the natural factors, the main hydrochemical processes involve the dissolution of various minerals (halite, gypsum, feldspar, fluorite, mirabilite, biotite, dolomite, and calcite), cation exchange, evaporation, and mixing. The anthropogenic factors include domestic sewage intrusion and agricultural activities, which are most likely to lead to further declines in groundwater quality. These findings may be useful for improving groundwater resource management for sustainable development in arid and semi-arid areas.