A Hybrid Deep Learning Framework for Long-Term Forecasting of Climate Change Indicators Using Bi-LSTM and the LBGWA Algorithm
Keywords:
Bi-LSTM, Climate change, CO₂ forecasting, Deep learning, Global surface temperature, Hybrid optimization, LBGWA, Time series forecastingAbstract
Accurate forecasting of long-term climate trends is critical for understanding environmental changes and guiding policy responses. Traditional statistical methods such as ARIMA, VAR, and VECM often fail to capture the nonlinear, long-range dependencies inherent in climate time series data. This paper presents a hybrid deep learning framework that integrates a Bidirectional Long Short-Term Memory (Bi-LSTM) model with a Learning-Based Global Warming Analysis (LBGWA) optimizer to predict three key climate indicators CO₂ concentration, surface temperature, and population growth across a historical span from 1750 to 2023. The Bi-LSTM model captures temporal patterns in both forward and backward directions, while the LBGWA metaheuristic enhances hyperparameter tuning to improve model stability and accuracy.
The proposed framework is trained on preprocessed climate data using feature engineering and normalization techniques. Experimental results demonstrate that the Bi-LSTM + LBGWA model significantly outperforms conventional forecasting approaches in terms of Mean Absolute Error (MAE = 0.07) and Root Mean Square Error (RMSE = 0.09), indicating high precision in long-term forecasting. Comparative analyses with ARIMA, FbProphet, and VAR models confirm the effectiveness of the hybrid approach. This study establishes the viability of deep learning-based architectures for robust, long-range environmental forecasting. It also provides a foundational step toward integrating climate predictions with health risk assessment frameworks such as BenMAP and EHI-Score. The framework's reproducibility, accuracy, and scalability make it highly relevant for climate analysts, sustainability researchers, and government agencies focused on climate adaptation and public health planning.
References
K. Kumar and B. P. Pande, “Air pollution prediction with machine learning: a case study of Indian cities,” International Journal of Environmental Science and Technology, vol. 20, May 2022, doi: https://doi.org/10.1007/s13762-022-04241-5.
J. K. Sethi and M. Mittal, “Monitoring the Impact of Air Quality on the COVID-19 Fatalities in Delhi, India: Using Machine Learning Techniques,” Disaster Medicine and Public Health Preparedness, pp. 1–8, Oct. 2020, doi: https://doi.org/10.1017/dmp.2020.372.
M. Panja, T. Chakraborty, A. Biswas, and S. Deb, “E-STGCN: Extreme Spatiotemporal Graph Convolutional Networks for Air Quality Forecasting,” arXiv.org, 2024. https://arxiv.org/abs/2411.12258
S. Yarragunta, M. A. Nabi, and P. Jeyanthi, “Prediction of Air Pollutants Using Supervised Machine Learning,” 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), May 2021, doi: https://doi.org/10.1109/iciccs51141.2021.9432078.
C. Shetty, B. J. Sowmya, S. Seema, and K. G. Srinivasa, “Air pollution control model using machine learning and IoT techniques,” Advances in Computers, pp. 187–218, 2020, doi: https://doi.org/10.1016/bs.adcom.2019.10.006.
U. Mahalingam, K. Elangovan, H. Dobhal, C. Valliappa, S. Shrestha, and G. Kedam, “A Machine Learning Model for Air Quality Prediction for Smart Cities,” 2019 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET), Mar. 2019, doi: https://doi.org/10.1109/wispnet45539.2019.9032734.
S. Sur, R. Ghosal, and R. Mondal, “Air Pollution Hotspot Identification and Pollution Level Prediction in the City of Delhi,” 2020 IEEE 1st International Conference for Convergence in Engineering (ICCE), pp. 290–294, Sep. 2020, doi: https://doi.org/10.1109/icce50343.2020.9290698.
S. K. Shah, Z. Tariq, J. Lee, and Y. Lee, “Real-Time Machine Learning for Air Quality and Environmental Noise Detection,” 2020 IEEE International Conference on Big Data (Big Data), Dec. 2020, doi: https://doi.org/10.1109/bigdata50022.2020.9377939.
G. Agrawal, D. Mohan, and H. Rahman, “Ambient air pollution in selected small cities in India: Observed trends and future challenges,” IATSS Research, vol. 45, no. 1, pp. 19–30, Apr. 2021, doi: https://doi.org/10.1016/j.iatssr.2021.03.004.
K. Rani, K. S. Babu, and S. Kumar Das, “Temporal convolutional denoising autoencoder network for air pollution prediction with missing values,” Urban Climate, vol. 38, pp. 100872–100872, Jul. 2021, doi: https://doi.org/10.1016/j.uclim.2021.100872.
A. J. Kunnathettu and S. L. Varma, “Comparative Analysis of Neural Network and Machine Learning Techniques for Air Quality Prediction,” 2020 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), pp. 724–729, Dec. 2020, doi: https://doi.org/10.1109/icacccn51052.2020.9362806.
D. AL-Najjar, H. AL-Najjar, N. Al-Rousan, and H. F. Assous, “Developing Machine Learning Techniques to Investigate the Impact of Air Quality Indices on Tadawul Exchange Index,” Complexity, vol. 2022, pp. 1–12, Oct. 2022, doi: https://doi.org/10.1155/2022/4079524.
X. Wang S. Zhang, Y. Chen, “Air quality forecasting using a spatiotemporal hybrid deep learning model based on VMD–GAT–BiLSTM,” Scientific Reports, vol. 14, no. 1, Aug. 2024, doi: https://doi.org/10.1038/s41598-024-68874-x.
A. Makhdoomi, M. Sarkhosh, and S. Ziaei, “PM2.5 concentration prediction using machine learning algorithms: an approach to virtual monitoring stations,” Scientific Reports, vol. 15, no. 1, p. 8076, Aug. 2025, doi: https://doi.org/10.1038/s41598-025-92019-3.
M. Pandey, V. Jain, N. Godhani, S. N. Tripathi, and P. Rai, “Spatio-Temporal Forecasting of PM2.5 via Spatial-Diffusion guided Encoder-Decoder Architecture,” arXiv.org, 2024. https://arxiv.org/abs/2412.13935 (accessed Aug. 29, 2025).
S. Ameer, M. A. Shah, A. Khan, “Comparative Analysis of Machine Learning Techniques for Predicting Air Quality in Smart Cities,” IEEE Access, vol. 7, pp. 128325–128338, 2019, doi: https://doi.org/10.1109/ACCESS.2019.2925082.
A. Aggarwal and D. Toshniwal, “A hybrid deep learning framework for urban air quality forecasting,” Journal of Cleaner Production, vol. 329, p. 129660, Dec. 2021, doi: https://doi.org/10.1016/j.jclepro.2021.129660.
Q. Zhang, Y. Han, V. O. K. Li, and J. C. K. Lam, “Deep-AIR: A Hybrid CNN-LSTM Framework for Fine-Grained Air Pollution Estimation and Forecast in Metropolitan Cities,” IEEE Access, vol. 10, pp. 55818–55841, 2022, doi: https://doi.org/10.1109/access.2022.3174853.
Z. Qi, T. Wang, G. Song, W. Hu, X. Li, and Z. Zhang, “Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-Grained Air Quality,” IEEE Transactions on Knowledge and Data Engineering, vol. 30, no. 12, pp. 2285–2297, Dec. 2018, doi: https://doi.org/10.1109/tkde.2018.2823740.
F. Karagulian, “Contributions to cities’ ambient particulate matter (PM): A systematic review of local source contributions at global level,” Atmospheric Environment, vol. 120, pp. 475–483, Nov. 2015, doi: https://doi.org/10.1016/j.atmosenv.2015.08.087.
S. Garg and H. Jindal, “Evaluation of Time Series Forecasting Models for Estimation of PM2.5 Levels in Air,” Arxiv (Cornell University), Apr. 2021, doi: https://doi.org/10.1109/i2ct51068.2021.9418215.
IPCC, “Climate Change 2021: The Physical Science Basis,” IPCC, 2021. https://www.ipcc.ch/report/ar6/wg1/
NASA, “Sea Level | NASA Global Climate Change,” Climate Change: Vital Signs of the Planet, Dec. 2025. https://climate.nasa.gov/vital-signs/sea-level/?intent=121
World Health Organization, “WHO global air quality guidelines: particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide,” www.who.int, 2021. https://www.who.int/publications/i/item/9789240034228
D. Huppmann, “The MESSAGE Integrated Assessment Model and the ix modeling platform (ixmp): An open framework for integrated and cross-cutting analysis of energy, climate, the environment, and sustainable development,” Environmental Modelling & Software, vol. 112, pp. 143–156, Feb. 2019, doi: https://doi.org/10.1016/j.envsoft.2018.11.012.
K. Davidson, A. Hallberg, D. McCubbin, and B. Hubbell, “Analysis of PM2.5Using the Environmental Benefits Mapping and Analysis Program (BenMAP)∗,” Journal of Toxicology and Environmental Health, Part A, vol. 70, no. 3–4, pp. 332–346, Feb. 2007, doi: https://doi.org/10.1080/15287390600884982.
E. Coffman, A. G. Rappold, R. Nethery, J. Anderton, “Quantifying Multipollutant Health Impacts Using the Environmental Benefits Mapping and Analysis Program–Community Edition (BenMAP-CE): A Case Study in Atlanta, Georgia,” Environmental Health Perspectives, vol. 132, no. 3, Mar. 2024, doi: https://doi.org/10.1289/ehp12969.
