# Unleashing Realistic Air Quality Forecasting: Introducing the Ready-to-Use PurpleAirSF Dataset

arXiv: https://arxiv.org/abs/2306.13948 · HTML: https://mlsanity.com/paper/2306.13948/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 15 references that are in the map.
- First posted on arXiv 24 Jun 2023.

## Builds on (most cited first, 6 of 6)

- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [A review on outlier/anomaly detection in time series data](https://mlsanity.com/paper/2002.04236/) (2020)
- [AirFormer: Predicting Nationwide Air Quality in China with Transformers](https://mlsanity.com/paper/2211.15979/) (2022)
- [Conditional Local Convolution for Spatio-temporal Meteorological Forecasting](https://mlsanity.com/paper/2101.01000/) (2021)
- [SMATE: Semi-Supervised Spatio-Temporal Representation Learning on Multivariate Time Series](https://mlsanity.com/paper/2110.00578/) (2021)
- [Graph Convolutional Networks for Traffic Forecasting with Missing Values](https://mlsanity.com/paper/2212.06419/) (2022)

## Built on by (most cited first, 2 of 2)

- [Indoor Air Quality Dataset with Activities of Daily Living in Low to Middle-income Communities](https://mlsanity.com/paper/2407.14501/) (2024)
- [Opportunistic Air Quality Monitoring and Forecasting with Expandable Graph Neural Networks](https://mlsanity.com/paper/2307.15916/) (2023)

## Abstract (arXiv)

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.