Regional spatio-temporal forecasting of particulate matter using autoencoder based generative adversarial network

Abstract

Accurate forecasting of air pollutant PM_2.5(particulate matter with diameter less than 2.5 µm) is beneficial to society. However, the non-linear spatio-temporal correlations, multi-feasible forecast values and incomplete training data due to stochasticity make it challenging for discriminative deep learning approaches to forecasting PM_2.5 data. In this paper, a generative modeling approach is proposed to overcome the challenges in forecasting PM_2.5 data by considering it as an ill-posed inverse problem. To strengthen its applicability, the proposed approach is theoretically validated. Furthermore, based on the proposed generative modeling, an Autoencoder-based generative adversarial network (GAN) named Air-GAN is developed. Air-GAN combines a convolutional neural network- long short-term memory (CNN-LSTM) based Encoder with a conditional Wasserstein GAN (WGAN) to capture non-linear correlations in the data distribution via inverse mapping from the forecast distribution. The condition vector to conditional WGAN is the novelty in Air-GAN, which employs this inverse learning and allows the WGAN’s Generator to generate accurate forecast estimates from noise distribution. The condition vector is composed of two elements: (1) the category label of the best correlated meteorological parameter with the PM_2.5 data, assigned using an efficient classifier and (2) the output of the CNN-LSTM-based Encoder which is the latent representation of the forecast. The extensive evaluation of Air-GAN for predicting the real-time PM_2.5 data of Delhi demonstrates its superior performance with an average inference error of 5.3 µg/m³, which achieves 31.7% improvement over the baseline approaches. The improved performance of Air-GAN demonstrates its efficiency to forecast stochastic PM_2.5 data by generalizing to out-of-distribution data.