Environmental Monitoring and Predicting Using Graph-Based Series Decomposition Model
- DOI
- 10.2991/978-94-6463-728-1_69How to use a DOI?
- Keywords
- Climate pollution prediction; PSO; EEMD; GCN; Air pollutant concentrations
- Abstract
Better methods of forecasting the concentrations of air pollution are important in developmental of sound policies and decisions at a time when environmental concerns and the need for mitigating climate change has become important. This paper describes how climate pollution can be predicted from climate data streams by the integrated design of GCNs and EEMD with PSO. The ability of the PSO-EEMD-GCN model to predict the said six major air pollutants: PM2.5, PM10, CO, NO2, O3, and SO2. Closely, the effectiveness of the current model is assessed with aid of vital parameters including RMSE, MAE, MSE, MAPE, and R-Squared. Drawing from the evaluation results, success reveals that PSO-EEMD-GCN is an efficient predictive model for climate pollution. For the Chinese consumers, the “Willingness to Pay Model” budget accuracy is 23, stated in terms of RMSE. 92 and an MAE of 16. The high correlation means explains why the correlation coefficients for SO2 and PM10 are much higher for the rural areas, and the low RMSE means that is why the RMSE for the total values is 86 for PM10, but an RMSE of 17. As for the MAE, we analyzed data derived from 85 state examination results and attained an average of 65 and an MAE of 11. 71 for PM2.5. The values of the model also show the practical significance with RMSE of 0. 28 and the MAE is 0. 16, which proves that it is appropriate at predicting the CO levels. Even for ozone (O3), which is considered as the most challenging chemical, the predictor gives a pretty good RMSE of 16.09 and an MAE of 12.17 and nitrogen dioxide with an Root Mean Square Error (RMSE) of 11.24 and an MAE of 7.50. It is seen that for sulfur dioxide (SO2) forecasts the error metrics are higher but the system remains predictive. Therefore solving, the PSO-EEMD-GCN model has shown great promise in being a helpful tool for forecasting climate pollution.
- Copyright
- © 2025 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Mughair Aslam Bhatti AU - Uzair Aslam Bhatti AU - Muhammad Aamir AU - Sarkar Sabarata Kumar AU - Maqbool Khan AU - Yonis Gulzar PY - 2025 DA - 2025/05/19 TI - Environmental Monitoring and Predicting Using Graph-Based Series Decomposition Model BT - Proceedings of the 3rd International Conference on Green Building, Civil Engineering and Smart City (GBCESC 2024) PB - Atlantis Press SP - 737 EP - 744 SN - 2352-5401 UR - https://doi.org/10.2991/978-94-6463-728-1_69 DO - 10.2991/978-94-6463-728-1_69 ID - Bhatti2025 ER -