Ground Level Ozone Prediction for Delhi using LSTM-RNN
S. Geetha1, L. Prasika2
1S. Geetha, Assistant Professor, Mepco Schlenk Engineering College, Sivakasi (Tamil Nadu), India.
2L. Prasika, Assistant Professor, Mepco Schlenk Engineering College, Sivakasi (Tamil Nadu), India.
Manuscript received on 10 December 2018 | Revised Manuscript received on 17 December 2018 | Manuscript Published on 30 December 2018 | PP: 478-480 | Volume-8 Issue- 2S December 2018 | Retrieval Number: BS2731128218/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Outdoor air pollutants are bringing adverse effects on the living being health. Air quality is deteriorating due to multi-pollutants such as sulfur dioxide (SO2 ), Nitrogen dioxide (NO2 ), Nitrogen oxide (NOx ), Ozone (O3 ), Carbon Monoxide (CO), Particulate Matter 2.5 (PM2.5), Particulate Matter 10 (PM10), etc. Out of these multi-pollutants, ground level Ozone is creating major health issues in lungs, heart, etc. Ground level Ozone is formed due to reactions between Nitrogen, vehicle emissions, Industrial emissions, and gasoline with the presence of sunlight. Recently, Deep Learning Techniques are applied in all prediction problems. Here, we proposed the Recurrent Neural Network based LSTM prediction model to predict the ground level ozone. The model is created with the historical data collected from various stations in and around Delhi. The model is providing more accuracy to predict the ground level ozone than the stare-of-art techniques. The model is evaluated with normalized mean square error and mean absolute error.
Keywords: Sulfur Dioxide (SO2 ), Nitrogen Dioxide (NO2 ), Nitrogen oxide (NOx ), Ozone (O3 ), Carbon Monoxide (CO), Particulate Matter 2.5 (PM2.5).
Scope of the Article: Building and Environmental Acoustics