基于随机森林模型的南海大气CO2柱浓度估算模型构建及其检验与应用

周芳成; 刘少军; 田光辉; 韩秀珍; 甘业星

###

DOI:10.7519/j.issn.1000-0526.2024.061701

气象:2024,50(12):1542-1550

查看/发表评论过刊浏览高级检索 HTML

←前一篇 | 后一篇→

码上扫一扫！

下载全文

基于随机森林模型的南海大气CO2柱浓度估算模型构建及其检验与应用

周芳成，刘少军，田光辉，韩秀珍，甘业星

(国家卫星气象中心/国家空间天气监测预警中心，北京 100081；许健民气象卫星创新中心，北京 100081；海南省气象科学研究所，海南省南海气象防灾减灾重点实验室，海口 570203；中国气象局三沙海洋气象野外科学试验基地,海南，三沙 573199；海南省南海海洋气象野外科学观测研究站，海南，三沙 573199)

Construction, Test and Application of Atmospheric CO2 Column Concentration Estimation Model over the South China Sea Based on Random Forest Model

ZHOU Fangcheng,LIU Shaojun，TIAN Guanghui，HAN Xiuzhen,GAN Yexing

(National Satellite Meteorological Centre/National Center for Space Weather, Beijing 100081； Innovation Center for FengYun Meteorological Satellite (FYSIC), Beijing 100081； Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province, Hainan Institute of Meteorological Science, Haikou 570203； Sansha Marine Meteorology Field Experiment Station of CMA, Hainan, Sansha 573199； South China Sea Marine Meteorology Hainan Observation and Research Station, Hainan, Sansha 573199)

摘要

图/表

参考文献

相似文献

本文已被：浏览 28次下载 20次
投稿时间：2023-12-24 修订日期：2024-08-22

中文摘要: 利用多源宽幅卫星的叶绿素a浓度、瞬时光和有效辐射、颗粒无机碳、颗粒有机碳、海面温度、风速、风向7个参数,基于随机森林模型建立了南海大气CO2柱浓度估算模型，以2020年数据验证模型精度，偏差为0.27 ppm（1 ppm=10-6），决定系数为0.59，均方根误差为1.00 ppm，整体精度较高。研究发现，南海大气CO2柱浓度呈现明显的季节特征，表现为春季＞夏季＞冬季＞秋季。造成南海大气CO2柱浓度季节差异的主要影响因素呈随时间变化特征，风向是1月和4月的主要影响因素，风速和风向是影响7月最大的2个因素，海温成为10月最主要影响因素。基于宽幅多源遥感数据建立的方法，可实现对南海大气CO2柱浓度的高频次、全覆盖监测。

中文关键词: 南海，随机森林模型，大气CO2柱浓度，估算模型，季节变化特征

Abstract:In this study, a random-forest-based model of atmospheric CO2 column concentration over the South China Sea was built with the data of chlorophyll-a concentration, instantaneous photosynthetically active radiation, particulate inorganic carbon, particulate organic carbon, sea surface temperature, wind speed and wind direction, which were from multisource satellite remote sensing data. The accuracy of the model was verified by the data in 2020, with Bias being 0.27 ppm, R2 being 0.59 and RMSE being 1.00 ppm. The results show that the atmospheric CO2 column concentration in the South China Sea pre-sents obvious seasonal characteristics, with the highest value in spring, followed by that in summer, winter and autumn in sequence. Moreover, the main impact factors for the seasonal differences of atmospheric CO2 column concentration in the South China Sea vary with time. In January and April, it is affected mainly by wind direction. In July, wind speed and wind direction are the two major impact factors. In October, sea surface temperature is the major factor. This method established based on the multisource satellite remote sensing data can realize the high-frequency and full-coverage monitoring of atmospheric CO2 column concentration in the South China Sea.

keywords: the South China Sea, random forest model, atmospheric CO2 column concentration, estimation model, seasonal variation characteristic

文章编号： 中图分类号： 文献标志码：

基金项目:国家自然科学基金青年基金项目（42001309）、中国气象局风云卫星应用先行计划（2022）(FY-APP-2022.0308)和海南省气象局科研项目（HNQXJS202214）共同资助

作者	单位
周芳成	国家卫星气象中心/国家空间天气监测预警中心，北京 100081；许健民气象卫星创新中心，北京 100081
刘少军	海南省气象科学研究所，海南省南海气象防灾减灾重点实验室，海口 570203；中国气象局三沙海洋气象野外科学试验基地,海南，三沙 573199；海南省南海海洋气象野外科学观测研究站，海南，三沙 573199
田光辉	海南省气象科学研究所，海南省南海气象防灾减灾重点实验室，海口 570203；中国气象局三沙海洋气象野外科学试验基地,海南，三沙 573199；海南省南海海洋气象野外科学观测研究站，海南，三沙 573199
韩秀珍	国家卫星气象中心/国家空间天气监测预警中心，北京 100081；许健民气象卫星创新中心，北京 100081
甘业星	海南省气象科学研究所，海南省南海气象防灾减灾重点实验室，海口 570203；中国气象局三沙海洋气象野外科学试验基地,海南，三沙 573199；海南省南海海洋气象野外科学观测研究站，海南，三沙 573199

Author Name	Affiliation
ZHOU Fangcheng	National Satellite Meteorological Centre/National Center for Space Weather, Beijing 100081； Innovation Center for FengYun Meteorological Satellite (FYSIC), Beijing 100081
LIU Shaojun	Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province, Hainan Institute of Meteorological Science, Haikou 570203； Sansha Marine Meteorology Field Experiment Station of CMA, Hainan, Sansha 573199； South China Sea Marine Meteorology Hainan Observation and Research Station, Hainan, Sansha 573199
TIAN Guanghui	Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province, Hainan Institute of Meteorological Science, Haikou 570203； Sansha Marine Meteorology Field Experiment Station of CMA, Hainan, Sansha 573199； South China Sea Marine Meteorology Hainan Observation and Research Station, Hainan, Sansha 573199
HAN Xiuzhen	National Satellite Meteorological Centre/National Center for Space Weather, Beijing 100081； Innovation Center for FengYun Meteorological Satellite (FYSIC), Beijing 100081
GAN Yexing	Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province, Hainan Institute of Meteorological Science, Haikou 570203； Sansha Marine Meteorology Field Experiment Station of CMA, Hainan, Sansha 573199； South China Sea Marine Meteorology Hainan Observation and Research Station, Hainan, Sansha 573199

引用文本：
周芳成,刘少军,田光辉,韩秀珍,甘业星,2024.基于随机森林模型的南海大气CO2柱浓度估算模型构建及其检验与应用[J].气象,50(12):1542-1550.
ZHOU Fangcheng,LIU Shaojun,TIAN Guanghui,HAN Xiuzhen,GAN Yexing,2024.Construction, Test and Application of Atmospheric CO2 Column Concentration Estimation Model over the South China Sea Based on Random Forest Model[J].Meteor Mon,50(12):1542-1550.