Forecasting of Total Column Ozone using Regression Analysis and LSTM-RNN Machine Learning Approach

T M Anu; K Elampari

doi:10.17485/IJST/v15i29.730

Article

Forecasting of Total Column Ozone using Regression Analysis and LSTM-RNN Machine Learning Approach

VIEWS 1457
PDF 191

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v15i29.730

Year: 2022, Volume: 15, Issue: 29, Pages: 1420-1428

Original Article

Forecasting of Total Column Ozone using Regression Analysis and LSTM-RNN Machine Learning Approach

T M Anu^1*, K Elampari²

¹Research Scholar, Reg. No. 18113152132030, Physics Research Centre, S.T. Hindu College, Nagercoil, Affiliated to Manonmaniam Sundaranar University, Abishekapatti, Tirunelveli, 627012, Tamil Nadu, India
²Associate Professor, Department of Physics, S.T. Hindu College, Nagercoil, Manonmaniam Sundaranar University, Abishekapatti, Tirunelveli, 627 012, Tamil Nadu, India

*Corresponding Author
Email: [email protected]

Received Date:31 March 2022, Accepted Date:17 June 2022, Published Date:27 March 2022

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Objectives: Atmospheric Ozone plays an important role in global climate change, human health and environmental conditions. Accurate and timely prediction of variation in Total Column Ozone (TCO) concentration is very important for both climatology and environment. In this context, the present study aims to utilize the advancement of Artificial Intelligence in Machine learning and a conventional method to develop models for the prediction of TCO concentration using historical time series data over a tropical region, India. Methods: Long Short-Term Memory (LSTM) deep learning networks are very useful in classifying, processing and making predictions based on time series data. In this work, Multiple Linear Regression (MLR) model, Long Short-Term Memory (LSTM) models are developed for forecasting TCO over a tropical region. The Statistical Parameters such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) were used to analyze and evaluate the performance of the proposed models. Findings: In the present study the TCO concentration varied between 217.4 DU and 288.6 DU. The performances of MLR and LSTM model were compared. From the results, it is evident that the values of RMSE, MAE and MAPE of the MLR model are 3.807924, 2.93766, 1.15 respectively whereas the values for LSTM model are 3.074492, 2.574, 1.01 respectively. LSTM was found to be the accurate model for the study data set and the predicted TCO concentration has a very good correlation with the actual observations and it does not rely on the meteorological parameters. Novelty: The LSTM models are usually employed in the field of machine translation, speech recognition and for the prediction of traffic levels, stock levels and air pollutants. This work utilizes the fast numerical machine learning computing library Tensorflow and a high level neural network library Keras that runs on top of Tensorflow to develop a LSTM network model for the prediction of the concentration levels of TCO.

Keywords: Total Column Ozone; Regression; Forecasting; Climate Change; Long Short-Term Memory

References

Salawitch RJ, Fahey DW, Hegglin MI, Mcbride LA, Tribett WR, Doherty SJ. Twenty Questions and Answers About the Ozone Layer: 2018 Update, Scientific Assessment of Ozone Depletion: 2018, World Meteorological Organization, Geneva, Switzerland. Geneva, Switzerland. 2019.
Nasser IM, Abu-Naser SS. Artificial Neural Network for Predicting Animals Category. International Journal of Academic and Applied Research. 2019;3(2):18–24. Available from: http://dstore.alazhar.edu.ps/xmlui/handle/123456789/182
Merayo D, Rodríguez-Prieto A, Camacho AM. Prediction of Mechanical Properties by Artificial Neural Networks to Characterize the Plastic Behavior of Aluminum Alloys. Materials. 2020;13(22):5227. Available from: https://doi.org/10.3390/ma13225227
Corte I, Acevedo S, Arlego M, Lamas CA. Exploring neural network training strategies to determine phase transitions in frustrated magnetic models. Computational Materials Science. 2021;198:110702. Available from: https://doi.org/10.1016/j.commatsci.2021.110702
He QQ, Wu C, Si YW. LSTM with Particle Swam Optimization for Sales Forecasting. Electronic Commerce Research and Applications. 2022;51:101118. Available from: https://doi.org/10.1016/j.elerap.2022.101118
Shih Y, Lin M. A LSTM Approach for Sales Forecasting of Goods with Short-Term Demands in E-Commerce. Intelligent Information and Database Systems. 2019;p. 244–256. Available from: https://doi.org/10.1007/978-3-030-14799-0_21
Narmadha S, Vijayakumar V. Spatio-Temporal vehicle traffic flow prediction using multivariate CNN and LSTM model. Materials Today: Proceedings. 2021. Available from: https://doi.org/10.1016/j.matpr.2021.04.249
Shams SR, Jahani A, Kalantary S, Moeinaddini M, Khorasani N. The evaluation on artificial neural networks (ANN) and multiple linear regressions (MLR) models for predicting SO2 concentration. Urban Climate. 2021;37:100837. Available from: https://doi.org/10.1016/j.uclim.2021.100837
Shams SR, Jahani A, Moeinaddini M, Khorasani N, Kalantary S. Forecasting Ozone Density in Tehran Air Using a Smart Data-Driven Approach. Journal of Health and Safety at Work. 2021;10(4):406–408. Available from: http://jhsw.tums.ac.ir/article-1-6415-en.html
Mani G, Volety R. A comparative analysis of LSTM and ARIMA for enhanced real-time air pollutant levels forecasting using sensor fusion with ground station data. Cogent Engineering. 2021;8(1):1936886. Available from: https://doi.org/10.1080/23311916.2021.1936886
Garg S, Jindal H. Evaluation of Time Series Forecasting Models for Estimation of PM2.5 Levels in Air. 2021 6th International Conference for Convergence in Technology (I2CT). 2021;p. 1–8. Available from: https://doi.org/10.1109/I2CT51068.2021.9418215
Xayasouk T, Lee H, Lee G. Air Pollution Prediction Using Long Short-Term Memory (LSTM) and Deep Autoencoder (DAE) Models. Sustainability. 2020;12(6):2570. Available from: https://doi.org/10.3390/su12062570
Yatish HR, Swamy SR. Recent Trends in Time Series Forecasting- A Survey. International Research Journal of Engineering and Technology. 2020;7(4). Available from: https://www.irjet.net/archives/V7/i4/IRJET-V7I41059.pdf
Turabieh H, Sheta A, Braik M, Kovac-Andric E. A Layered Recurrent Neural Network for Imputing Air Pollutants Missing Data and Prediction of NO2,O3, PM10, and PM2.5 . In: Forecasting in Mathematics - Recent Advances, New Perspectives and Applications, IntechOpen. 2021.
Chen Y, Cui S, Chen P, Yuan Q, Kang P, Zhu L. An LSTM-based neural network method of particulate pollution forecast in China. Environmental Research Letters. 2021;16(4):044006. Available from: https://doi.org/10.1088/1748-9326/abe1f5
Moscoso-López JA, González-Enrique J, Urda D, Ruiz-Aguilar JJ, Turias IJ. Hourly pollutants forecasting using a deep learning approach to obtain the AQI. Logic Journal of the IGPL. 2022. Available from: https://doi.org/10.1093/jigpal/jzac035
Liu B, Zhang L, Wang Q, Chen J. A Novel Method for Regional NO2 Concentration Prediction Using Discrete Wavelet Transform and an LSTM Network. Computational Intelligence and Neuroscience. 2021;2021:1–14. Available from: https://doi.org/10.1155/2021/6631614
Lei F, Dong X, Ma X. Prediction of PM2.5 concentration considering temporal and spatial features: A case study of Fushun, Liaoning Province. Journal of Intelligent & Fuzzy Systems. 2020;39(5):8015–8025. Available from: https://doi.org/10.3233/JIFS-201515
Chang YS, Chiao HT, Abimannan S, Huang YP, Tsai YT, Lin KM. An LSTM-based aggregated model for air pollution forecasting. Atmospheric Pollution Research. 2020;11(8):1451–1463. Available from: https://doi.org/10.1016/j.apr.2020.05.015
Moolayil J. An introduction to deep learning and keras. Learn Keras for Deep Neural Networks. (Vol. 2019, pp. 1-16) Apress, Berkeley, CA. .
Heydari A, Nezhad MM, Garcia DA, Keynia F, Santoli LD. Air pollution forecasting application based on deep learning model and optimization algorithm. Clean Technologies and Environmental Policy. 2022;24(2):607–621. Available from: https://doi.org/10.1007/s10098-021-02080-5
Shin S, Lee Y, Kim M, Park J, Lee S, Min K. Deep neural network model with Bayesian hyperparameter optimization for prediction of NOx at transient conditions in a diesel engine. Engineering Applications of Artificial Intelligence. 2020;94. Available from: https://doi.org/10.1016/j.engappai.2020.103761

Copyright

© 2022 Anu & Elampari. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee)