Univariate Time Series Data Forecasting of Air Pollution using LSTM Neural Network
Faqih Hamami, Iqbal Ahmad Dahlan
Abstract
Air pollution is an important issue around the world. It can threaten the human life environment and affect illness or even death. Internet of Things (IoT) is a technology that can monitor air quality. It can transmit data in real time and with good latency. Some pollutants in the air can be dangerous at high concentrations. The prediction of time series data from pollutants transmitted by IoT is one step for preventing unwanted conditions in future such as unhealthy environments or becoming uninhabitable due to dangerous air pollution. This paper proposes to build a neural network model using LSTM to forecast air pollution concentrations in the air. The model predicts five air pollution indicators including PM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">10</sub> , SO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> , CO, O <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub> , and NO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> . The results reveal that the Root Mean Square Error of LSTM model is 5.58.