Abstract
Haze has become a frequent disastrous weather condition in China. Its formation consists of evolution process of several pollutants in certain meteorological conditions with complex relationships among these factors of haze formation. How to explore the complex relationships among these multi-dimensional factors as well as effectively predict them have become a key issue in research community. The research in this paper presents a method to quantitatively reveal causality in the formation of haze, which can be used to effectively predict haze pollution. In order to make the complicated relationship among different factors be interpretable, an PS-FCM (Primary Sub-Fuzzy Cognitive Maps) model is proposed and its multi-dimensional causality solution is demonstrated. By considering the formation of haze as an evolving process with time, we explore and discover the causality based on time series data of haze pollution with PS-FCM. Thus, a multi-dimensional time series data mining method based on the PS-FCM is developed to investigate the formation of haze. We validate our model by comparing with other machine learning method via experimental data and discuss the performance of PS-FCM under different transformation functions. The results explicitly show the quantitative causality among the different factors in haze formation.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
