A seasonal autoregressive technique for forecasting PM2.5 trend in Delhi
Varsha P. Desai1, Priyanka P. Shinde2, Kavita S. Oza3 and Rajanish K. Kamat4
D Y Patil Agriculture & Technical University,Talsande, Kolhapur, Maharashtra,India1
Government College of Engineering,Karad, Maharashtra,India2
Department of Computer Science,Shivaji University, Kolhapur, Maharashtra,India3
Dr. Homi Bhabha State University,Mumbai, Maharashtra,India4
Government College of Engineering,Karad, Maharashtra,India2
Department of Computer Science,Shivaji University, Kolhapur, Maharashtra,India3
Dr. Homi Bhabha State University,Mumbai, Maharashtra,India4
Corresponding Author : Varsha P. Desai
Recieved : 17-December-2023; Revised : 28-January-2025; Accepted : 09-February-2025
Abstract
Delhi's air pollution is a severe and persistent environmental problem that frequently reaches dangerous levels. Alarmingly high particulate matter (PM2.5) levels are commonly observed in Delhi, particularly during winter. The World Health Organization (WHO) has set acceptable guidelines for PM2.5 concentrations at 10 µg/m³ for an annual average and 25 µg/m³ for a 24-hour average. However, PM2.5 concentrations in Delhi's air often significantly exceed these limits. PM2.5 pollution has a profound impact on both the environment and public health worldwide. It is a major contributor to respiratory and cardiovascular diseases, lung cancer, breathing problems, and strokes. Additionally, it harms the environment by causing acid rain, damaging vegetation, and reducing visibility. Accurate forecasting of PM2.5 concentrations is therefore essential for implementing health precautions, protecting public health, and providing decision-making guidelines to minimize exposure to its harmful effects. The seasonal autoregressive integrated moving average (SARIMA) model is a robust, adaptable, and precise method for predicting time-series data with seasonal and non-seasonal components. It is particularly useful for real-time forecasting, especially in scenarios where seasonality plays a significant role. SARIMA effectively utilizes past data to predict future PM2.5 trends. The proposed model provides valuable insights for forecasting PM2.5 concentrations in Delhi. Air quality index (AQI) data from 2015 to 2022 was used to train the model, which was developed using the SARIMA technique to predict trends for the next five years with 95% accuracy. This predictive capability enables informed decision-making to promote a sustainable environment and safeguard public well-being. By accurately forecasting PM2.5 concentrations, the model supports proactive policy decisions and helps protect residents from the adverse effects of air pollution.
Keywords
PM2.5 pollution, Air quality index (AQI), Air pollution in Delhi, SARIMA model, Time-series forecasting, Environmental health.
Cite this article
Desai VP, Shinde PP, Oza KS, Kamat RK. A seasonal autoregressive technique for forecasting PM2.5 trend in Delhi. International Journal of Advanced Technology and Engineering Exploration. 2025;12(123):287-300. DOI : 10.19101/IJATEE.2023.10102602
References
[1]
https://www.indiatoday.in/india/story/air-pollution-health-risk-india-annual-economic-cost-over-usd-150-billion-1928843-2022-03-24. Accessed 10 January 2023.
[2]
Lu F, Xu D, Cheng Y, Dong S, Guo C, Jiang X, et al. Systematic review and meta-analysis of the adverse health effects of ambient PM2.5 and PM10 pollution in the Chinese population. Environmental Research. 2015; 136:196-204.
[3]
https://www.msn.com/en-in/news/other/summer-action-plan-for-pollution-to-be-submitted-to-delhi-cm-arvind-kejriwal-on-april-24/ar-AA1a7DWL. Accessed 15 February 2023.
[4]
www.cpcb.nic.in. Accessed 20 May 2022.
[5]
Yin C, Liu K, Zhang Q, Hu K, Yang Z, Yang L, et al. SARIMA-based medium-and long-term load forecasting. Strategic Planning for Energy and the Environment. 2023; 42(2):283-306.
[6]
Pant P, Shukla A, Kohl SD, Chow JC, Watson JG, Harrison RM. Characterization of ambient PM2.5 at a pollution hotspot in New Delhi, India and inference of sources. Atmospheric Environment. 2015; 109:178-89.
[7]
https://www.outlookindia.com/,www.outlookindia.com/website/story/india-news-delhi-air-quality-will-continue-to-remain-bad-in-coming-winters-5-key-reasons/400980. Accessed 14 March 2021.
[8]
Hill W, Lim EL, Weeden CE, Lee C, Augustine M, Chen K, et al. Lung adenocarcinoma promotion by air pollutants. Nature. 2023; 616(7955):159-67.
[9]
Pope IIICA, Dockery DW. Health effects of fine particulate air pollution: lines that connect. Journal of the Air & Waste Management Association. 2006; 56(6):709-42.
[10]
Singh T, Kaur A, Katyal SK, Walia SK, Dhand G, Sheoran K, et al. Exploring the relationship between air quality index and lung cancer mortality in India: predictive modeling and impact assessment. Scientific Reports. 2023; 13(1):1-12.
[11]
https://www.indiaspend.com/pollution/india-has-9-of-worlds-10-most-polluted-cities-but-few-air-quality-monitors-792521. Accessed 14 March 2021.
[12]
Selokar A, Ramachandran B, Elangovan KN, Varma BD. PM 2.5 particulate matter and its effects in Delhi/NCR. Materials Today: Proceedings. 2020; 33:4566-72.
[13]
Kumar K, Pande BP. Air pollution prediction with machine learning: a case study of Indian cities. International Journal of Environmental Science and Technology. 2023; 20(5):5333-48.
[14]
Kothandaraman D, Praveena N, Varadarajkumar K, Madhav RB, Dhabliya D, Satla S, et al. Intelligent forecasting of air quality and pollution prediction using machine learning. Adsorption Science & Technology. 2022; 2022:1-15.
[15]
Sharma R, Shilimkar G, Pisal S. Air quality prediction by machine learning. International Journal of Scientific Research in Science and Technology. 2021; 8:486-92.
[16]
Desai VP, Kamat RK, Oza KS. Rainfall modeling and prediction using neural networks: a case study of Maharashtra. Disaster Advances. 2022; 15(3):39-43.
[17]
Zhu D, Cai C, Yang T, Zhou X. A machine learning approach for air quality prediction: model regularization and optimization. Big Data and Cognitive Computing. 2018; 2(1):1-15.
[18]
Sharma E, Deo RC, Prasad R, Parisi AV. A hybrid air quality early-warning framework: an hourly forecasting model with online sequential extreme learning machines and empirical mode decomposition algorithms. Science of the Total Environment. 2020; 709:135934.
[19]
https://weather.com/en-IN/india/pollution/news/2022-07-07-pollution-in-delhi-patna-5-times-higher-than-cpcb-safe-limits. Accessed 25 December 2022.
[20]
Tiwari S, Kumar A, Mantri S, Dey S. Modelling ambient PM2.5 exposure at an ultra-high resolution and associated health burden in megacity Delhi: exposure reduction target for 2030. Environmental Research Letters. 2023; 18(4):1-12.
[21]
Chae S, Shin J, Kwon S, Lee S, Kang S, Lee D. PM10 and PM2.5 real-time prediction models using an interpolated convolutional neural network. Scientific Reports. 2021; 11(1):1-9.
[22]
Subramaniam S, Raju N, Ganesan A, Rajavel N, Chenniappan M, Prakash C, et al. Artificial intelligence technologies for forecasting air pollution and human health: a narrative review. Sustainability. 2022; 14(16):1-36.
[23]
Raubitzek S, Corpaci L, Hofer R, Mallinger K. Scaling exponents of time series data: a machine learning approach. Entropy. 2023; 25(12):1-45.
[24]
Ansari M, Alam M. An intelligent IoT-cloud-based air pollution forecasting model using univariate time-series analysis. Arabian Journal for Science and Engineering. 2024; 49(3):3135-62.
[25]
Zhang H, Srinivasan R. A systematic review of air quality sensors, guidelines, and measurement studies for indoor air quality management. Sustainability. 2020; 12(21):1-38.
[26]
Abhilash MS, Thakur A, Gupta D, Sreevidya B. Time series analysis of air pollution in Bengaluru using ARIMA model. In Ambient communications and computer systems 2017 (pp. 413-26). Springer Singapore.
[27]
Shah HN, Khan Z, Merchant AA, Moghal M, Shaikh A, Rane P. IOT based air pollution monitoring system. International Journal of Scientific & Engineering Research. 2018; 9(2):62-6.
[28]
Arif M, Katafygiotou M, Mazroei A, Kaushik A, Elsarrag E. Impact of indoor environmental quality on occupant well-being and comfort: a review of the literature. International Journal of Sustainable Built Environment. 2016; 5(1):1-11.
[29]
Sokhi RS, Moussiopoulos N, Baklanov A, Bartzis J, Coll I, Finardi S, et al. Advances in air quality research–current and emerging challenges. Atmospheric Chemistry and Physics Discussions. 2021; 2021:1-33.
[30]
Mane MV, Kumar D, Agarwal K. Detection and prediction of air pollution using machine learning and deep learning techniques. In international conference on computing, communication, and intelligent systems 2022 (pp. 145-50). IEEE.
[31]
Liu X, Lu D, Zhang A, Liu Q, Jiang G. Data-driven machine learning in environmental pollution: gains and problems. Environmental Science & Technology. 2022; 56(4):2124-33.
[32]
Mahendra HN, Mallikarjunaswamy S, Kumar DM, Kumari S, Kashyap S, Fulwani S, et al. Assessment and prediction of air quality level using ARIMA model: a case study of surat city, Gujarat State, India. Nature Environment & Pollution Technology. 2023; 22(1):199-210.
[33]
Molaei SN, Salajegheh A, Khosravi H, Nasiri A, Abadi AR. Prediction of hourly PM10 concentration through a hybrid deep learning-based method. Earth Science Informatics. 2024; 17(1):37-49.
[34]
Sarkar P, Saha M. Machine learning-based detection of sudden air pollutant level changes: impacts on public health. International Journal of Information Technology. 2024:1-9.
[35]
Mehmood K, Bao Y, Cheng W, Khan MA, Siddique N, Abrar MM, et al. Predicting the quality of air with machine learning approaches: current research priorities and future perspectives. Journal of Cleaner Production. 2022; 379:134656.
[36]
Ghazali S, Ismail LH. Air quality prediction using artificial neural network. In proceedings of the international conference on civil environmental engineering sustainability, Johor Bahru, Malaysia 2012 (pp. 1-15).
[37]
Maleki H, Sorooshian A, Goudarzi G, Baboli Z, Tahmasebi BY, Rahmati M. Air pollution prediction by using an artificial neural network model. Clean Technologies and Environmental Policy. 2019; 21:1341-52.
[38]
Natarajan SK, Shanmurthy P, Arockiam D, Balusamy B, Selvarajan S. Optimized machine learning model for air quality index prediction in major cities in India. Scientific Reports. 2024; 14(1):1-18.
[39]
Athira V, Geetha P, Vinayakumar R, Soman KP. Deepairnet: applying recurrent networks for air quality prediction. Procedia Computer Science. 2018; 132:1394-403.
[40]
Lin YC, Lee SJ, Ouyang CS, Wu CH. Air quality prediction by neuro-fuzzy modeling approach. Applied Soft Computing. 2020; 86:105898.
[41]
Bhatt K, Sarangi RK, Kambli M. Comparative analysis of ocean color forecasting models: a case study on Indian southern Peninsula using Sarima and deep learning approaches. International Research Journal of Modernization in Engineering Technology and Science. 2023; 5(11):3167-75.
[42]
Parviz L. Comparative evaluation of hybrid sarima and machine learning techniques based on time varying and decomposition of precipitation time series. Journal of Agricultural Science and Technology. 2020; 22(2):563-78.
[43]
Huang W, Li T, Liu J, Xie P, Du S, Teng F. An overview of air quality analysis by big data techniques: monitoring, forecasting, and traceability. Information Fusion. 2021; 75:28-40.
[44]
Guo Q, He Z, Li S, Li X, Meng J, Hou Z, et al. Air pollution forecasting using artificial and wavelet neural networks with meteorological conditions. Aerosol and Air Quality Research. 2020; 20(6):1429-39.
[45]
Yu R, Yang Y, Yang L, Han G, Move OA. RAQ–a random forest approach for predicting air quality in urban sensing systems. Sensors. 2016; 16(1):1-18.
[46]
Ukachukwu M, Uzoamaka N, Elochukwu N. Application of machine learning to air pollution studies: a systematic review. Journal of Energy Research and Reviews. 2023; 15(2):1-11.
[47]
Terbuch A, O’leary P, Khalili-motlagh-kasmaei N, Auer P, Zöhrer A, Winter V. Detecting anomalous multivariate time-series via hybrid machine learning. IEEE Transactions on Instrumentation and Measurement. 2023; 72:1-11.
[48]
Suri RS, Jain AK, Kapoor NR, Kumar A, Arora HC, Kumar K, et al. Air quality prediction-a study using neural network based approach. Journal of Soft Computing in Civil Engineering. 2023; 7(1):93-113.
[49]
Mohamad AF, Jasin AM, Asmat A, Canda R, Ismail J, Soom AB. Sales analytics dashboard with ARIMA and SARIMA time series model. In 13th symposium on computer applications & industrial electronics (ISCAIE) 2023 (pp. 106-12). IEEE.
[50]
Dubey AK, Kumar A, García-díaz V, Sharma AK, Kanhaiya K. Study and analysis of SARIMA and LSTM in forecasting time series data. Sustainable Energy Technologies and Assessments. 2021; 47:101474.
[51]
Al-alola SS, Alkadi II, Alogayell HM, Mohamed SA, Ismail IY. Air quality estimation using remote sensing and GIS-spatial technologies along Al-Shamal train pathway, Al-Qurayyat city in Saudi Arabia. Environmental and Sustainability Indicators. 2022; 15:1-10.