| 基于轻量级梯度提升机的南京大气臭氧浓度预测 |
| 摘要点击 1534 全文点击 388 投稿时间：2022-08-11 修订日期：2022-10-06 |
| 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 轻量级梯度提升机(LightGBM) 地面臭氧 臭氧浓度预测 随机森林(RF) 循环神经网络(RNN) |
| 英文关键词 light gradient boosting machine (LightGBM) ground-level ozone ozone concentration prediction random forest (RF) recurrent neural networks (RNN) |
| 作者 | 单位 | E-mail | | 朱珈莹 | 南京信息工程大学, 中国气象局气溶胶-云-降水重点开放实验室, 南京 210044 | 20211203039@nuist.edu.cn | | 安俊琳 | 南京信息工程大学, 中国气象局气溶胶-云-降水重点开放实验室, 南京 210044 | junlinan@nuist.edu.cn | | 冯悦政 | 南京信息工程大学, 中国气象局气溶胶-云-降水重点开放实验室, 南京 210044 | | | 贺婕 | 南京信息工程大学, 中国气象局气溶胶-云-降水重点开放实验室, 南京 210044 | | | 张玉欣 | 青海省人工影响天气办公室, 西宁 810000 | | | 王俊秀 | 呼和浩特市气象局, 呼和浩特 010020 | |
|
| 中文摘要 |
| 采用南京地区2015年1月至2016年12月期间的空气质量数据和常规气象资料数据，分析了南京地区O3浓度变化特征，建立基于轻量级梯度提升机（LightGBM）的O3浓度预测模型，并将该模型与支持向量机、循环神经网络和随机森林等3种在空气质量预测方向上常用的机器学习方法进行了对比，验证模型的有效性和可行性.结果表明，南京地区O3浓度变化具有显著的季节性差异，浓度变化受前期浓度、气象因子和其他空气污染物浓度的共同影响.LightGBM模型较为准确地预测了南京地区地面O3浓度（R2=0.92），且该模型的预测精度和计算效率等性能优于其他模型.尤其是在容易出现臭氧污染的高温天气，该模型预测准确性明显高于其他模型，模型稳定性较好.LightGBM具有预测准确度高、稳定性好、有良好的泛化能力和运算时间短等特点，在O3浓度预测方面具有显著的优势. |
| 英文摘要 |
| Based on the air quality data and conventional meteorological data of the Nanjing Region from January 2015 to December 2016, to analyze the characteristics of O3 concentration changes in the Nanjing Region, a light gradient boosting machine (LightGBM) model was established to predict O3 concentration. The model was compared with three machine learning methods that are commonly used in air quality prediction, including support vector machine, recurrent neural network, and random forest methods, to verify its effectiveness and feasibility. Finally, the performance of the prediction model was analyzed under different meteorological conditions. The results showed that the variation in O3 concentration in Nanjing had significant seasonal differences and was affected by a combination of its pre-concentration, meteorological factors, and other air pollutant concentrations. The LightGBM model predicted the ground-level O3 concentration in the Nanjing area more precisely to a large extent (R2=0.92), and the model outperformed other models in prediction accuracy and computational efficiency. In particular, the model showed a significantly higher prediction accuracy and stability than that of other models under a high-temperature condition that was more likely prone to ozone pollution. The LightGBM model was characterized by its high prediction accuracy, good stability, satisfactory generalization ability, and short operation time, which broaden its application prospect in O3 concentration prediction. |
|
|
|
