MVAR: MultiVariate AutoRegressive Air Pollutants Forecasting Model

TL;DR

The paper introduces MVAR, a multivariate air pollutant forecasting model that captures interactions among pollutants, efficiently utilizes data, and achieves long-term predictions, supported by a new comprehensive dataset.

Contribution

MVAR is a novel multivariate forecasting model that reduces data dependency, incorporates meteorological coupling, and provides long-term predictions, addressing limitations of existing single-pollutant approaches.

Findings

MVAR outperforms state-of-the-art methods in forecasting accuracy.

The model effectively captures interactions among multiple pollutants.

A new comprehensive dataset for air pollution forecasting in North China is constructed.

Abstract

Air pollutants pose a significant threat to the environment and human health, thus forecasting accurate pollutant concentrations is essential for pollution warnings and policy-making. Existing studies predominantly focus on single-pollutant forecasting, neglecting the interactions among different pollutants and their diverse spatial responses. To address the practical needs of forecasting multivariate air pollutants, we propose MultiVariate AutoRegressive air pollutants forecasting model (MVAR), which reduces the dependency on long-time-window inputs and boosts the data utilization efficiency. We also design the Multivariate Autoregressive Training Paradigm, enabling MVAR to achieve 120-hour long-term sequential forecasting. Additionally, MVAR develops Meteorological Coupled Spatial Transformer block, enabling the flexible coupling of AI-based meteorological forecasts while learning the interactions among pollutants and their diverse spatial responses. As for the lack of standardized datasets in air pollutants forecasting, we construct a comprehensive dataset covering 6 major pollutants across 75 cities in North China from 2018 to 2023, including ERA5 reanalysis data and FuXi-2.0 forecast data. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods and validate the effectiveness of the proposed architecture.