2023/06/24 by Jingwei Zuo, Zuo, Jingwei, Wenbin Li +5
Earth and Planetary Sciences · Environmental Science · #Air Quality Monitoring and Forecasting #Air Quality and Health Impacts #Artificial Intelligence (cs.AI) #Atmospheric chemistry and aerosols #FOS: Computer and information sciences #Machine Learning (cs.LG)
paper · pdf · doi:10.48550/arxiv.2306.13948
openalex publication_date 2023/06/24 · openalex created_date 2023/06/28 · openalex updated_date 2026/07/28
Air quality forecasting has garnered significant attention recently, with data-driven models taking center stage due to advancements in machine learning and deep learning models. However, researchers face challenges with complex data acquisition and the lack of open-sourced datasets, hindering efficient model validation. This paper introduces PurpleAirSF, a comprehensive and easily accessible dataset collected from the PurpleAir network. With its high temporal resolution, various air quality measures, and diverse geographical coverage, this dataset serves as a useful tool for researchers aiming to develop novel forecasting models, study air pollution patterns, and investigate their impacts on health and the environment. We present a detailed account of the data collection and processing methods employed to build PurpleAirSF. Furthermore, we conduct preliminary experiments using both classic and modern spatio-temporal forecasting models, thereby establishing a benchmark for future air quality forecasting tasks.