|
| 基于机器学习的长株潭城市群PM2.5重污染预报 |
| Prediction of Heavy PM2.5Pollution in Chang Zhu Tan Urban Agglomeration Based on Machine Learning |
| |
| DOI： |
| 中文关键词: PM2.5 重污染预报 机器学习 可解释性 长株潭城市群 |
| 英文关键词: PM2.5 Heavy pollution prediction Machine learning Interpretability Chang ZhuTan urbanagglomeration |
| 基金项目:国家自然科学基金资助项目（No41271095）；湖南省自然科学基金资助项目（No2024JJ7649）；湖南省气象局2020年重点课题基金资助项目（XQKJ20A001）；中国气象局预报专项基金资助项目（FPZJ2024-091） |
|
| 摘要点击次数: 274 |
| 全文下载次数: 99 |
| 中文摘要: |
| 为提高PM2.5重污染的预报准确率，融合气象和环境资料、前期观测和后期数值天气预报数据、地面和高空预报因子，建立预报时效较长且准确度较高的机器学习模型库。以长株潭城市群的PM2.5重污染天气预报为例，将数据预处理、特征工程、算法优选、超参数调优等技术方法运用于模型中，建立的重污染预报机器学习模型库可预报PM2.5浓度和等级，预警4 d内的PM2.5重污染。为增强模型的透明度，对其进行可解释性研究。事前可解释性分析表明，PM2.5浓度预报模型存在事前三特性：前期要素比后期要素重要，环境要素比气象要素重要，地面要素比高空要素重要；事后可解释性分析表明，常德2022年1月18日的重污染天气过程受上游传输和本地污染累积的共同影响，其中传输的作用稍大。 |
| 英文摘要: |
| A machine learning model library with long prediction time and high accuracy was established based on meteorological and environmental data， early observation and later numerical weather forecast data， ground and high altitude forecast factors to improve the prediction accuracy of PM2.5 heavy pollution. Taking heavy PM2.5 pollution forecast in Chang Zhu Tan urban agglomeration as an example， using data preprocessing， feature engineering， algorithm optimization and hyperparameter tuning and other technologies， this model library could predict the concentration and grade of PM2.5， and warn heavy PM2.5 pollution within 4 days. Interpretability of the model was studied to enhance its transparency. Ex ante interpretability analysis showed that 〖JP〗PM2.5 concentration prediction model had three ex ante characteristics: 〖JP3〗preceding factors were more import〖JP〗ant than 〖JP〗late factors， environmental factors were more important than meteorological factors， and ground factors were more important than high altitude factors. Post interpretability analysis showed that the heavy pollution weather process on January 18， 2022 in Changde was influenced by upstream transmission and local pollution 〖JP3〗accumulation， in which transmission played a larger role. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
