在创新、协调、绿色、开放、共享的新发展理念下,为探索完善PM_(2.5)污染预报预警、应急预案以及县域精细化管控等领域的理论体系与应用视角,基于SHAP(SHapley Additive exPlanations)和随机森林(RF)构建SHAP-RF预报模型,通过分析成都市...在创新、协调、绿色、开放、共享的新发展理念下,为探索完善PM_(2.5)污染预报预警、应急预案以及县域精细化管控等领域的理论体系与应用视角,基于SHAP(SHapley Additive exPlanations)和随机森林(RF)构建SHAP-RF预报模型,通过分析成都市2018−2021年国控/省控监测站点数据,结合欧洲中期天气预报中心细网格模式预报资料,实现对PM_(2.5)特征因子重要性动态识别与筛选,生成县域本地化特征因子集,并开展未来1~10 d PM_(2.5)浓度预报研究。结果表明:①识别出成都市影响PM_(2.5)浓度变化的关键特征因子以起报天CO浓度、起报天NO_(2)浓度、起报天PM_(2.5)浓度、气温、位势高度等变量为主。②所构建的SHAP-RF预报模型对未来1~10 d的PM_(2.5)逐日浓度预报准确性较好,预报未来1 d PM_(2.5)浓度的均方根误差(RMSE)为9.25~17.93μg/m^(3),拟合优度(R^(2))为0.67~0.84;预报未来1~3 d时,RMSE为10.60~20.45μg/m^(3),R^(2)为0.57~0.74;预报未来4~10 d时,RMSE为12.50~23.48μg/m^(3),R^(2)为0.42~0.69。③单站点长时间序列PM_(2.5)浓度逐日预报检验显示,模型能较好地捕捉到PM_(2.5)浓度秋冬高、春夏低的季节性波动特征和逐日变化特征。④PM_(2.5)污染超标预报检验显示,模型对于各站点污染超标预报准确率为89.59%~97.26%,且随着预报时效的增加,对于单站点污染超标预报准确率并没有明显减小。研究显示,SHAP值在预报模型中不仅能实现对模型可解释性的可视化呈现,同时可实现特征识别,显示特征因子重要性分布特征,SHAP-RF预报模型在实际应用中能较好地实现对未来1~10 d PM_(2.5)污染过程的预报预警。展开更多
Land-sea breeze(LSB)is an atmospheric mesoscale circulation that occurs in the vicinity of the coast and is caused by uneven heating resulting from the difference in specific heat capacity between the sea and land sur...Land-sea breeze(LSB)is an atmospheric mesoscale circulation that occurs in the vicinity of the coast and is caused by uneven heating resulting from the difference in specific heat capacity between the sea and land surfaces.The circulation structure of LSB was quantitatively investigated with a Doppler wind lidar Windcube100s on the west coast of the Yellow Sea for the first time.The time of observation was 31 August to 28 September 2018.It was found that the height of LSB development was 700 m to 1300 m.The duration of conversion of LSB was between 6 h and 8 h.The biggest average horizontal sea-breeze wind speed at 425 m was 5.6 m s^(-1),and at 375 m it was 4.5 m s^(-1).During the conversion process from sea breeze to land breeze,the maximum wind shear exponent was 2.84 at 1300 m altitude.During the conversion process from land breeze to sea breeze,the maximum wind shear exponent was 1.28 at 700 m altitude.The differences in wind shear exponents between sea-breeze and landbreeze systems were between 0.2 and 3.6 at the same altitude.The maximum value of the wind shear exponent can reflect the height of LSB development.展开更多
本文采用吸湿性串联差分式电迁移粒径谱仪(Hygros-copicity Tandem Diferential Mobility Analyzer,H-TDMA)和气溶胶组分监测仪(S-611EG),对成都市2019年1—2月气溶胶粒子吸湿增长因子(GF)、气溶胶液态含水量(ALWC)、气溶胶谱分布(PNSD...本文采用吸湿性串联差分式电迁移粒径谱仪(Hygros-copicity Tandem Diferential Mobility Analyzer,H-TDMA)和气溶胶组分监测仪(S-611EG),对成都市2019年1—2月气溶胶粒子吸湿增长因子(GF)、气溶胶液态含水量(ALWC)、气溶胶谱分布(PNSD)、粒子化学组分进行观测,并结合气象要素分析了成都市大气气溶胶吸湿效应及其对能见度的影响。结果表明:(1)成都冬季40~200 nm的非吸湿模态粒子(GF_(NH))的吸湿增长因子随粒径增大而减小,强(弱)吸湿模态粒子的吸湿增长因子(GFMH,LH)均随粒径增大而增大,非(弱)吸湿性粒子比例(NF_(NH,LH))随粒径增大而减少。(2)成都冬季气溶胶液态含水量由爱根核模态和积聚模态粒子占主导,其中爱根核模态对ALWC贡献最大。相对湿度(RH)、细颗粒物(PM_(2.5))对ALWC的影响力依次降低,高PM_(2.5)且高RH是高ALWC的充分条件。(3)不利气象条件是成都此次雾霾过程的主要成因,低能见度在低RH时由PM_(2.5)积累所致,而气溶胶吸湿增长效应在高RH时主导能见度下降。展开更多
文摘在创新、协调、绿色、开放、共享的新发展理念下,为探索完善PM_(2.5)污染预报预警、应急预案以及县域精细化管控等领域的理论体系与应用视角,基于SHAP(SHapley Additive exPlanations)和随机森林(RF)构建SHAP-RF预报模型,通过分析成都市2018−2021年国控/省控监测站点数据,结合欧洲中期天气预报中心细网格模式预报资料,实现对PM_(2.5)特征因子重要性动态识别与筛选,生成县域本地化特征因子集,并开展未来1~10 d PM_(2.5)浓度预报研究。结果表明:①识别出成都市影响PM_(2.5)浓度变化的关键特征因子以起报天CO浓度、起报天NO_(2)浓度、起报天PM_(2.5)浓度、气温、位势高度等变量为主。②所构建的SHAP-RF预报模型对未来1~10 d的PM_(2.5)逐日浓度预报准确性较好,预报未来1 d PM_(2.5)浓度的均方根误差(RMSE)为9.25~17.93μg/m^(3),拟合优度(R^(2))为0.67~0.84;预报未来1~3 d时,RMSE为10.60~20.45μg/m^(3),R^(2)为0.57~0.74;预报未来4~10 d时,RMSE为12.50~23.48μg/m^(3),R^(2)为0.42~0.69。③单站点长时间序列PM_(2.5)浓度逐日预报检验显示,模型能较好地捕捉到PM_(2.5)浓度秋冬高、春夏低的季节性波动特征和逐日变化特征。④PM_(2.5)污染超标预报检验显示,模型对于各站点污染超标预报准确率为89.59%~97.26%,且随着预报时效的增加,对于单站点污染超标预报准确率并没有明显减小。研究显示,SHAP值在预报模型中不仅能实现对模型可解释性的可视化呈现,同时可实现特征识别,显示特征因子重要性分布特征,SHAP-RF预报模型在实际应用中能较好地实现对未来1~10 d PM_(2.5)污染过程的预报预警。
基金supported by the National Key Research and Development Program of China[Grant number 2016YFC0202001]the Chinese Academy of Sciences Strategic Priority Research Program[Grant number XDA23020301]the National Natural Science Foundation of China[Grant number 41375036]。
文摘Land-sea breeze(LSB)is an atmospheric mesoscale circulation that occurs in the vicinity of the coast and is caused by uneven heating resulting from the difference in specific heat capacity between the sea and land surfaces.The circulation structure of LSB was quantitatively investigated with a Doppler wind lidar Windcube100s on the west coast of the Yellow Sea for the first time.The time of observation was 31 August to 28 September 2018.It was found that the height of LSB development was 700 m to 1300 m.The duration of conversion of LSB was between 6 h and 8 h.The biggest average horizontal sea-breeze wind speed at 425 m was 5.6 m s^(-1),and at 375 m it was 4.5 m s^(-1).During the conversion process from sea breeze to land breeze,the maximum wind shear exponent was 2.84 at 1300 m altitude.During the conversion process from land breeze to sea breeze,the maximum wind shear exponent was 1.28 at 700 m altitude.The differences in wind shear exponents between sea-breeze and landbreeze systems were between 0.2 and 3.6 at the same altitude.The maximum value of the wind shear exponent can reflect the height of LSB development.
