Hybrid CNN-LSTM Model for Air Quality Prediction: A Case Study for Gurugram

Year 2024, Volume: 5 Issue: 1, 33 - 40, 15.06.2024

Anıl Utku

https://doi.org/10.55195/jscai.1469468

Abstract

One of the most important environmental problems brought about by rapid population growth and industrialization is air pollution. Today, air pollution is generally caused by heating, industry and motor vehicles. In addition, factors such as unplanned urbanization, topographic structure of cities, atmospheric conditions and meteorological parameters, building and population density also cause pollution to increase. Pollutants with concentrations above limit values have negative effects on humans and the environment. In order to prevent people from being negatively affected by these pollutants, it is necessary to know the pollution level and take action as soon as possible. In this study, a hybrid ConvLSTM model was developed in order to quickly and effectively predict air pollution, which has such negative effects on humans and the environment. ConvLSTM was compared with LR, RF, SVM, MLP, CNN and LSTM using approximately 4 years of air quality index data from the city of Gurugram in India. Experimental results showed that ConvLSTM was significantly more successful than the base models, with 30.645 MAE and 0.891 R2.

Keywords

Air quality, Deep learning, Machine learning, CNN, LSTM

References

• X. Tan, L. Han, X. Zhang, W. Zhou, W. Li, & Y. Qian, A review of current air quality indexes and improvements under the multi-contaminant air pollution exposure. J. Env. Manag., c. 279, 2021.
• M. Leili, A. Nadali, M. Karami, A. Bahrami, & A. Afkhami, Short-term effect of multi-pollutant air quality indexes and PM2. 5 on cardiovascular hospitalization in Hamadan, Iran: a time-series analysis. Env. Sci. and Poll. Res., c. 28, sy 38, ss. 53653-53667, 2021.
• P. Kumar, A critical evaluation of air quality index models (1960–2021). Environmental Monitoring and Assessment, c. 194, sy 5, ss. 1-45, 2022.
• R. Cao, Y. Wang, J. Huang, Q. Zeng, X. Pan, G. Li, & T. He, The construction of the air quality health index (AQHI) and a validity comparison based on three different methods. Env. Res., sy 197, 2021.
• X. Sui, K. Qi, Y. Nie, N. Ding, X. Shi, X. Wu, & W. Wang, Air quality and public health risk assessment: A case study in a typical polluted city, North China. Urban Climate, sy 36, 2021.
• Y. Wang, L. Huang, C. Huang, J. Hu, & M. Wang, High-resolution modeling for criteria air pollutants and the associated air quality index in a metropolitan city. Env. Int., sy 172, 2023.
• F. O. Abulude, I. A. Abulude, S. D. Oluwagbayide, S. D. Afolayan, & D. Ishaku, Air Quality Index: A case of 1-day monitoring in 253 Nigerian urban and suburban towns. Journal of Geovisualization and Spatial Analysis, c. 6, sy 1, 2022.
• Z. Jiang, Y. Gao, H. Cao, W. Diao, X. Yao, C. Yuan, & Y. Chen, Characteristics of ambient air quality and its air quality index (AQI) model in Shanghai, China. Sci. Total Env., sy 896, 2023.
• F. Abulude, I. Abulude, S. Oluwagbayide, S. Afolayan, & D. Ishaku, Air Quality Index: Case of One-Day Monitoring of 253 Urban and Suburban Towns in Nigeria. Env. Sci. Proc., c. 8, sy 1, 2021.
• D. P. K. Meena, & D. V. Singh, Air Quality Monitoring and Pollution Control Technologies, Int.l J. Multidiscip. Res. Sci., Eng. Tech., c. 7, sy 2, ss. 4409-4426, 2024.
• A. Sengupta, G. Govardhan, S. Debnath, P. Yadav, S. H. Kulkarni, A. N. Parde, & S. D. Ghude, Probing into the wintertime meteorology and particulate matter (PM2. 5 and PM10) forecast over Delhi. Atmos. Poll. Res., c. 13, sy 6, 2022.
• H. Nozari, J. Ghahremani-Nahr, & A. Szmelter-Jarosz, AI and machine learning for real-world problems. Adv. in Comp., sy 134, ss. 1-12, 2024.
• A. Mishra, & Y. Gupta, Comparative analysis of Air Quality Index prediction using deep learning algorithms. Spat. Inf. Res., c. 32, sy 1, ss. 63-72, 2024.
• G. Ravindiran, G. Hayder, K. Kanagarathinam, A. Alagumalai, & C. Sonne, Air quality prediction by machine learning models: A predictive study on the Indian coastal city of Visakhapatnam. Chemosphere, sy 338, 2023.
• N. H. Van, P. Van Thanh, D. N. Tran, & D. T. Tran, A new model of air quality prediction using lightweight machine learning. Int. J. Env. Sci. Tech., c. 20, sy 3, ss. 2983-2994, 2023.
• N. N. Maltare, & S. Vahora, Air Quality Index prediction using machine learning for Ahmedabad city. Dig. Chem. Eng., sy 7, 2023.
• G. I. Drewil, & R. J. Al-Bahadili, Air pollution prediction using LSTM deep learning and metaheuristics algorithms. Measurement: Sensors, sy 24, 2022.
• G. Kurnaz, & A. S. Demir, Prediction of SO2 and PM10 air pollutants using a deep learning-based recurrent neural network: Case of industrial city Sakarya. Urban Climate, sy 41, 2022.
• E. Kristiani, H. Lin, J. R. Lin, Y. H. Chuang, C. Y. Huang, & C. T. Yang, Short-term prediction of PM2. 5 using LSTM deep learning methods. Sustainability, c. 14, sy 4, 2022.
• “Gurugram's Air Quality Index Time-Series Dataset”, Kaggle. https://www.kaggle.com/datasets/pranaii/test-aqi/data (Erişim 1 Mart 2024)
• S. Park, S. Jung, S. Jung, S. Rho, & E. Hwang, Sliding window-based LightGBM model for electric load forecasting using anomaly repair. J. Supercomp, sy 77, ss. 12857-12878, 2021.
• H. Henderi, T. Wahyuningsih, & E. Rahwanto, Comparison of Min-Max normalization and Z-Score Normalization in the K-nearest neighbor (kNN) Algorithm to Test the Accuracy of Types of Breast Cancer. Int. J. Inf Sys., c. 4, sy 1, ss. 13-20, 2021.
• X. Song, X. Liu, F. Liu, & C. Wang, Comparison of machine learning and logistic regression models in predicting acute kidney injury: A systematic review and meta-analysis. Int. J. Med. Inf., sy 151, 2021.
• S. W. Lee, Regression analysis for continuous independent variables in medical research: statistical standard and guideline of Life Cycle Committee. Life cycle, sy 2, 2022.
• M. M. Ghiasi, & S. Zendehboudi, Application of decision tree-based ensemble learning in the classification of breast cancer. Comp. Bio. Med., sy 128, 2021.
• X. Zhou, H. Wen, Y. Zhang, J. Xu, & W. Zhang, Landslide susceptibility mapping using hybrid random forest with GeoDetector and RFE for factor optimization. Geosci. Front., c. 12, sy 5, 2021.
• S. Talukdar, K. U. Eibek, S. Akhter, S. K. Ziaul, A. R. M. T. Islam, & J. Mallick, Modeling fragmentation probability of land-use and land-cover using the bagging, random forest and random subspace in the Teesta River Basin, Bangladesh. Eco. Indic., 126, 2021.
• A. Utku. Derin Öğrenme Tabanlı Trafik Yoğunluğu Tahmini: İstanbul İçin Bir Vaka Çalışması. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, c. 11, sy 3, ss. 1584-1598, 2023.
• A. Rizwan, N. Iqbal, R. Ahmad, & D. H. Kim, WR-SVM model based on the margin radius approach for solving the minimum enclosing ball problem in support vector machine classification. Appl. Sci., c. 11, sy 10, 2021.
• A. Utku. Deep Learning Based an Efficient Hybrid Model for Urban Traffic Prediction. Bilişim Teknolojileri Dergisi, c. 16, sy 2, ss. 107-117, 2023.
• H. Alla, L. Moumoun, & Y. Balouki, A multilayer perceptron neural network with selective-data training for flight arrival delay prediction. Sci. Prog., ss. 1-12, 2021.
• Y. Liu, H. Pu, & D. W. Sun, Efficient extraction of deep image features using convolutional neural network (CNN) for applications in detecting and analysing complex food matrices. Trends in Food Sci. & Tech., sy 113, ss. 193-204, 2021.
• X. Meng, N. Shi, D. Shi, W. Li, & M. Li, Photonics-enabled spiking timing-dependent convolutional neural network for real-time image classification. Optics Express, c. 30, sy 10, ss. 16217-16228, 2022.
• Q. Wang, R. Q. Peng, J. Q. Wang, Z. Li, & H. B. Qu, NEWLSTM: An optimized long short-term memory language model for sequence prediction. IEEE Access, sy 8, ss. 65395-65401, 2020.
• Y. Kaya, Z. Yiner, M. Kaya, & F. Kuncan, F. A new approach to COVID-19 detection from X-ray images using angle transformation with GoogleNet and LSTM. Measurement Science and Technology, c. 33, sy 12, 2022.