Scholarlink

<p>To support coordinated air quality management, this study developed a tree-based machine learning framework for multi-pollutant forecasting. We systematically evaluated the predictive performance of Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and Decision Tree (DT) models for six key pollutants: PM<sub>2.5</sub>, PM<sub>10</sub>, NO<sub>2</sub>, SO<sub>2</sub>, CO, and O<sub>3</sub>, using high-resolution environmental monitoring data (10&#xa0;km resolution) from China’s four major municipalities (2021–2024). A comprehensive feature system was constructed incorporating meteorology-emission interaction terms. SHapley Additive exPlanations (SHAP) values were employed to quantify feature contributions. Key findings demonstrate: (1) RF achieved optimal performance in particulate matter prediction (PM<sub>2.5</sub>: R2 = 0.99, RMSE = 0.11 µg/m<sup>3</sup>; PM<sub>10</sub>: R<sup>2</sup> = 0.98); (2) GBDT showed comparable accuracy to RF for NO2 (R<sup>2</sup> = 0.85) and CO (R<sup>2</sup> = 0.98) with minimal differences (ΔR<sup>2</sup> ≤ 0.03); (3) DT exhibited competitive O<sub>3</sub> prediction capability (R<sup>2</sup> = 0.88). SHAP analysis revealed critical mechanisms, such as CO’s positive synergistic effect (SHAP = 0.136) in PM<sub>2.5</sub> prediction and O<sub>3</sub> generation sensitivity to temperature (SHAP = 0.076). This research provides an interpretable, multi-pollutant forecasting framework applicable to urban air quality warning systems and offers model selection guidance for environmental regulation strategies.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Applicability analysis of tree-based ensemble learning for air pollutant prediction models

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月25日

查看全文
  • Xiaofeng Zhu,
  • Bo Li,
  • Yan Cao,
  • Qian Zhang

摘要

To support coordinated air quality management, this study developed a tree-based machine learning framework for multi-pollutant forecasting. We systematically evaluated the predictive performance of Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and Decision Tree (DT) models for six key pollutants: PM2.5, PM10, NO2, SO2, CO, and O3, using high-resolution environmental monitoring data (10 km resolution) from China’s four major municipalities (2021–2024). A comprehensive feature system was constructed incorporating meteorology-emission interaction terms. SHapley Additive exPlanations (SHAP) values were employed to quantify feature contributions. Key findings demonstrate: (1) RF achieved optimal performance in particulate matter prediction (PM2.5: R2 = 0.99, RMSE = 0.11 µg/m3; PM10: R2 = 0.98); (2) GBDT showed comparable accuracy to RF for NO2 (R2 = 0.85) and CO (R2 = 0.98) with minimal differences (ΔR2 ≤ 0.03); (3) DT exhibited competitive O3 prediction capability (R2 = 0.88). SHAP analysis revealed critical mechanisms, such as CO’s positive synergistic effect (SHAP = 0.136) in PM2.5 prediction and O3 generation sensitivity to temperature (SHAP = 0.076). This research provides an interpretable, multi-pollutant forecasting framework applicable to urban air quality warning systems and offers model selection guidance for environmental regulation strategies.