Original scientific paper

https://doi.org/10.17559/TV-20240828001947

Hyb_LSTM+KCNN: Hybrid Long Short Term Memory with Kernel Convolution Neural Networks Based Time Series Forecasting for Air Quality Index Detection

Suma Sira Jacob ; Department of Artificial Intelligence and Data Science, Sri Krishna College of Technology, Coimbatore, Tamil Nadu
Ghadah Aldehim ; Department of Information Systems College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
Mashael Maashi ; Department of Software Engineering, College of Computer and Information Sciences, King Saud University, P.O. Box 103786, Riyadh 11543, Saudi Arabia
S. Dhanalakshmi ; Department of Electronics and Communication Engineering, Coimbatore Institute of Technology, Coimbatore, Tamil Nadu, India *

* Corresponding author.

Abstract

Clean air is essential for maintaining a healthy lifestyle, yet poor air quality remains a major contributor to numerous respiratory ailments. Air pollutants such as PM2.5, NOx, COx, and SOx significantly impact human health, emphasizing the need for accurate forecasting models. However, predicting air quality is challenging due to the dynamic interplay of various factors, including meteorological conditions, vehicular emissions, and industrial discharges. This study proposes a novel hybrid forecasting model, Hyb_LSTM+KCNN, which combines Long Short-Term Memory (LSTM) networks and Kernel Convolutional Neural Networks (KCNN) for time-series prediction of the Air Quality Index (AQI). The LSTM component captures temporal dependencies in air quality data, enabling effective modeling of sequential patterns over time. Meanwhile, the KCNN module enhances feature extraction by leveraging convolutional kernels to identify local data patterns. By integrating these complementary strengths, the hybrid architecture provides a more robust and accurate AQI forecasting model.The proposed model was evaluated on comprehensive datasets, incorporating various pollutant levels and meteorological parameters. Experimental results demonstrated that the Hyb_LSTM+KCNN model consistently outperforms traditional forecasting techniques, achieving higher prediction accuracy and generalization capabilities. The model effectively captures correlations between pollutants and environmental factors, leading to precise AQI forecasts even under dynamic and complex conditions. This study presents a promising solution for air quality prediction, with practical implications for environmental monitoring and public health management. Future research will explore further optimization of the model for real-time applications and investigate its performance when integrating additional data sources, such as satellite and hyperspectral imagery.

Keywords

air quality; convolution neural networks; forcasting; long short term memory; time series model

Hrčak ID:

335044

URI

https://hrcak.srce.hr/335044

Publication date:

30.8.2025.

Visits: 372 *