Air Quality Prediction in Shaanxi Province: A GBDT Model Study from the Digital-Intelligent Governance Perspective
DOI:
https://doi.org/10.6919/ICJE.202512_11(12).0005Keywords:
GBDT; Air Quality Forecasting; Environmental Digital Intelligence Governance.Abstract
This study constructs an air quality machine learning prediction model based on air quality monitoring and meteorological index data from Shaanxi Province, drawing on the concept of environmental digital intelligence governance. After data cleaning, feature extraction, and standardization processing, the performance of the decision tree, random forest, and GBDT algorithm is compared. The results show that the GBDT model has the best prediction effect, with an R² of 0.9832, which can effectively capture air quality changes, and PM10, PM2.5, and SO₂ are the main air quality influencing factors. The research results can provide data support for regional environmental protection and precise pollution control, and also provide reference cases for the practical application of digital intelligence technology in environmental governance.
Downloads
References
[1] Shaanxi Provincial Market Supervision and Administration Bureau Shaanxi Continues to Deepen Air Pollution Control. Information on: https://snamr.shaanxi.gov.cn/sy/ztzl/dqwrzlzxxd/202508/t20250811_3553300.html
[2] Luo Z, Zeng R, Wang P. Air Quality Prediction Based on Quadratic Prediction Model. Learning & Education. 2022.
[3] Duan J, Gong Y, Luo J, et al. Air-quality prediction based on the ARIMA-CNN-LSTM combination model optimized by dung beetle optimizer. Scientific Reports. 2023, Vol. 13.
[4] Hua V, Nguyen T, Dao M S, et al. The impact of data imputation on air quality prediction problem. PLoS ONE. 2024, Vol. 19 (No. 9), p. 39.
[5] Gao Senhai, Ma Xu. Air pollution level prediction based on Self-Attention CNN-LSTM. Journal of Tianjin University of Technology. 2025, p. 1-7.
[6] Zhou Jianguo, Qin Yuan, Zhou Luming. Air quality index prediction model utilizing quadratic decomposition, LSTM-ELM, and error correction techniques. Journal of Safety and Environment. 2025, Vol. 25 (No. 01), p. 322-334.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Core Journal of Engineering

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




