Discovering Geographical Flock Patterns of CO2 Emissions in China Using Trajectory Mining Techniques

Abstract

Carbon dioxide (CO2) emissions are considered a significant factor that results in climate change. To better support the formulation of effective policies to reduce CO2 emissions, specific types of important emission patterns need to be considered. Motivated by the flock pattern that exists in the domain of moving object trajectories, this paper extends this concept to a geographical flock pattern and aims to discover such patterns that might exist in CO2 emission data. To achieve this, a spatiotemporal graph (STG)-based approach is proposed. Three main parts are involved in the proposed approach: generating attribute trajectories from CO2 emission data, generating STGs from attribute trajectories, and discovering specific types of geographical flock patterns. Generally, eight different types of geographical flock patterns are derived based on two criteria, i.e., the high–low attribute values criterion and the extreme number–duration values criterion. A case study is conducted based on the CO2 emission data in China on two levels: the province level and the geographical region level. The results demonstrate the effectiveness of the proposed approach in discovering geographical flock patterns of CO2 emissions and provide potential suggestions and insights to assist policy making and the coordinated control of carbon emissions.