Daily scale air quality index forecasting using bidirectional recurrent neural networks: Case study of Delhi, India

• Main Authors: Pande C.B., Kushwaha N.L., Alawi O.A., Sammen S.S., Sidek L.M., Yaseen Z.M., Pal S.C., Katipo?lu O.M.
• Other Authors: 57193547008
• Format: Article
• Published: Elsevier Ltd 2025
• Subjects: Air Pollutants; Air Pollution; Cities; Environmental Monitoring; Forecasting; India; Neural Networks, Computer; Seasons; Delhi; Air quality; Decision making; Learning systems; Mean square error; Quality assurance; Regression analysis; Air quality indices; Bidirectional recurrent neural networks; Decisions makings; Deep learning model; Delhi air pollution; Kernel ridge regressions; Learning models; Performance; Recurrent neural network model; Urban cities; air quality; artificial neural network; atmospheric pollution; forecasting method; index method; model; urban area; air pollution; article; case study; decision making; deep learning; forecasting; human; machine learning; nerve cell network; recurrent neural network; ridge regression; root mean squared error; short term memory; winter; air pollutant; city; environmental monitoring; procedures; season; Long short-term memory

This research was established to accurately forecast daily scale air quality index (AQI) which is an essential environmental index for decision-making. Researchers have projected different types of models and methodologies for AQI forecasting, such as statistical techniques, machine learning (ML), a...