Deep Particulate Matter Forecasting Model Using Correntropy-Induced Loss

TL;DR

This paper introduces a novel forecasting model for particulate matter that employs the correntropy-induced loss function, effectively handling heavy-tailed distributions and extreme values in air pollution data.

Contribution

It applies the maximum correntropy criterion for regression to air pollution forecasting, demonstrating improved performance over traditional loss functions in capturing extreme pollution events.

Findings

MCCR loss outperforms MSE in extreme value prediction

Rigorous seasonality adjustment improves model accuracy

The approach is effective across various statistical and machine learning models

Abstract

Forecasting the particulate matter (PM) concentration in South Korea has become urgently necessary owing to its strong negative impact on human life. In most statistical or machine learning methods, independent and identically distributed data, for example, a Gaussian distribution, are assumed; however, time series such as air pollution and weather data do not meet this assumption. In this study, the maximum correntropy criterion for regression (MCCR) loss is used in an analysis of the statistical characteristics of air pollution and weather data. Rigorous seasonality adjustment of the air pollution and weather data was performed because of their complex seasonality patterns and the heavy-tailed distribution of data even after deseasonalization. The MCCR loss was applied to multiple models including conventional statistical models and state-of-the-art machine learning models. The results show that the MCCR loss is more appropriate than the conventional mean squared error loss for forecasting extreme values.