| 基于可解释性机器学习的西安市臭氧浓度影响因子分析 |
| 摘要点击 840 全文点击 42 投稿时间：2025-06-23 修订日期：2025-09-16 |
| 查看HTML全文
查看全文 查看/发表评论 下载PDF阅读器 |
| 中文关键词 臭氧（O3） 机器学习 XGBoost模型 影响因子 SHAP模块 |
| 英文关键词 ozone（O3） machine learning XGBoost model influencing factors SHAP module |
| DOI 10.13227/j.hjkx.202506272 |
|
| 中文摘要 |
| 基于 2020~2024年西安市大气污染物与气象监测数据，利用XGBoost等机器学习模型，结合 SHAP 可解释性算法，量化解析了臭氧（O3）浓度的关键影响因子. 结果表明，XGBoost模型预测性能较优，R2达0.92，平均绝对误差（MAE）为9.52 μg·m-3、均方根误差（RMSE）为13.19 μg·m-3，同时对高浓度O3（>160 μg·m-3）预测的离散度明显低于其他模型. 通过SHAP模型分析显示，气象因素对O3的生成起主导作用，其贡献率为61.7%，其中气温、相对湿度、太阳辐射和海平面气压为主要驱动因子；大气污染物贡献率为39.3%，其中二氧化氮（NO2）贡献率为73.8%. 各因素对O3生成贡献的季节差异表现为夏季高温主导（气温贡献率为36.4%），冬季则因供暖排放导致NO2增多起主要贡献，贡献率达30.2%. 气温、太阳辐射和PM2.5与O3呈非线性正相关，NO2和相对湿度与O3呈非线性负相关. 气温>20℃，ρ（NO2）<17 μg·m-3，相对湿度<65%，太阳辐射> 1×105 J·m-2，ρ（PM2.5）在100~200 μg·m-3时对O3生成的正向贡献显著. 白天时段太阳辐射和气温，协同激活光化学反应，NO2光解转为前体物，共同驱动O3增长，对应 SHAP 散点的 “高贡献区间” 与日变化图的 “峰值时段”，而PM2.5对O3的正向贡献在中午前后（11：00~15：00）较显著，其他时段则转为负向影响. |
| 英文摘要 |
| Based on the atmospheric pollutant and meteorological monitoring data of Xi'an from 2020 to 2024， this study uses machine learning models such as XGBoost and combines with the SHAP interpretability algorithm to quantitatively analyze the key influencing factors of ozone （O3） concentration. The results showed that the XGBoost model had excellent prediction performance， with a determination coefficient （R2） of 0.92， mean absolute error （MAE） of 9.52 μg·m-3， and root mean square error （RMSE） of 13.19 μg·m-3. Meanwhile， its prediction deviation for high-concentration O3 （>160 μg·m-3） was significantly lower than that of other models. Analysis via the SHAP model indicated that meteorological factors played a dominant role in O3 formation， contributing 61.7%， among which temperature， relative humidity， solar radiation， and sea level pressure were the main driving factors. Atmospheric pollutants contributed 39.3%， with nitrogen dioxide （NO2） accounting for 73.8%. Seasonal differences in the contribution of various factors to O3 formation showed that high temperature dominated in summer （temperature contributed 36.4%）， while NO2 made the main contribution in winter due to increased heating emissions， with a contribution rate of 30.2%. The temperature， solar radiation， and PM2.5 showed non-linear positive correlations with O3， while NO2 and relative humidity showed non-linear negative correlations with O3. When the temperature >20℃， the NO2 concentration <17 μg·m-3， relative humidity <65%， solar radiation >1×105 J·m-2， and PM2.5 concentration was in the range of 100-200 μg·m-3， and the positive contribution to O3 formation was significant. During the daytime， solar radiation and temperature synergistically activated photochemical reactions， NO2 underwent photolysis to produce precursors， and these processes together drove the increase in O3 concentration. This process corresponded to the “high-contribution interval” in SHAP scatter plots and the “peak period” in diurnal variation charts. In contrast， the positive contribution of PM2.5 to O3 was relatively significant around midday （11：00-15：00）， while it shifted to a negative impact during other time periods. |
