Predicting Haze Phenomenon using Chaos Theory in Industrial Area in Malaysia

Abstract

Predicting the occurrence of haze is of great importance due to its negative impact on human health, the environment, and the economy. This study aims to develop a model for predicting haze using chaos theory. The data were taken from an industrial area, Klang, Selangor Malaysia during Southwest Monsoon. The model is trained using historical data on haze occurrences and the accuracy of the prediction is evaluated using a testing dataset. A chaos model, namely local mean approximation method (LMAM) will be used to predict the haze phenomenon. Results show that the chaos-based approach is effective in forecasting the onset and duration of haze events. The predicting model can provide early warnings for policymakers and relevant authorities, enabling them to take proactive measures to mitigate the effects of haze on public health and the environment. The model also presents a promising alternative to traditional forecasting techniques and highlights the potential applications of chaos theory in atmospheric science.