Year: 2025
Type: article
Abstract: ir pollution is a significant concern in Izmir, the third-largest city in Turkey, and it has serious adverse effects on human health and the environment. The city faces air quality issues due to industrial activities and heavy traffic. The Internet of Things (IoT) technology enables continuous monitoring and measurement of factors that diminish air quality. Utilizing IoT to predict air pollution is crucial in mitigating potential adverse effects. In this study, air pollution predictions were conducted using machine learning, deep learning, and time series analysis methods. Data on PM10 and SO2 levels were collected from seven locations in Izmir from 1996 to 2024. The models used for evaluating PM10 and SO2 measurements included Support Vector Regression (SVR), Seasonal Autoregressive Integrated Moving Average (SARIMA), Long Short-Term Memory (LSTM), and Extended Long-Term Memory (xLSTM). Among these models, xLSTM demonstrated the best overall performance for predicting both PM10 and SO2 levels, achieving the lowest error metrics despite slightly lower R² scores than the LSTM model.
Source: Journal of Computational Design
Authors: Kübra Öztürk, Zuhal Can
Institution: Eskişehir Osmangazi University
Language: English
Subfield: Environmental Engineering
Field: Environmental Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4414630293