首页|基于集成学习的FY-4A/GIIRS红外通道亮温偏差订正研究

基于集成学习的FY-4A/GIIRS红外通道亮温偏差订正研究

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
资料变分同化方法基于观测误差无偏的假设,故偏差订正是卫星资料质量控制的重要环节之一.开展了基于集成学习的风云四号A星(Feng-Yun 4A,FY-4A)干涉式大气垂直探测仪(Geostationary Interferometric Infrared Sounder,GIIRS)中波红外通道亮温偏差订正研究.将随机森林、极端梯度提升(eXtreme Gradient Boosting,XGBoost)、Decision Tree 和 Extra Tree 作为集成学习的基础模型.在优化基础模型的超参数后,采用广义误差极小化方法集成基础模型回归结果.基于台风"利奇马"期间的加密晴空视场点资料,对比了集成学习、基础模型和离线法的GIIRS通道亮温偏差订正效果.试验结果表明,本文所采用的订正方法均取得了好的结果.在所有方法中,集成学习的订正效果最佳.在气团预报因子中,地理(经度和纬度)信息对基础模型贡献率较大.本文方法可推广至其他资料的偏差或误差订正.
Bias Correction of Brightness Temperature in Medium Wave Channel of FY-4A/GIIRS Based on Ensemble Learning
The data variational assimilation method is based on the assumption that the observation error is unbiased,so the bias correction is one of the important links in the quality control of satellite data.In this pa-per,the research based on ensemble learning on the bias correction of the brightness temperature of the mid-wave infrared channel of FY-4A/GIIRS is carried out.Random Forest,XGBoost,Decision Tree and Extra Tree are used as the base models for the ensemble learning.After optimizing the hyperparameters of the base model,the generalized error minimization method is used to integrate the base model regression results.Based on the encrypted clear-sky field-of-view data during Typhoon Lekima,the correction effects of the ensemble learning,the base model,and the offline method on the brightness temperature bias of the GIIRS channel are compared.The experimental results show that all the correction methods used in this paper achieve good re-sults.Among all the methods,the ensemble learning has the best correction effect.Among the air mass pre-dictor,geographical(longitude and latitude)information contributes a lot to the base model.The methods in this paper can be extended to the bias or error correction of other information.

FY-4A/GIIRSbias correctionensemble learninghyperparameter optimisationTyphoon Leki-ma

王根、杜成名、蒋芸、范传宇、潘月、袁松

展开 >

巢湖学院电子工程学院,安徽合肥 238000

安徽省气象台,安徽合肥 230031

FY-4A/GIIRS 偏差订正 集成学习 超参数优化 台风"利奇马"

安徽省重点研究与开发计划项目安徽省高校杰出青年科研项目巢湖学院高层次人才科研启动经费项目巢湖学院高层次人才科研启动经费项目巢湖学院学科建设质量提升工程项目巢湖学院校级科学研究重点项目巢湖学院大学生创新创业训练省级项目安徽省教育厅高等学校科学研究重点项目安徽省教育厅高等学校科学研究重点项目国家自然科学基金项目

2022h110200022022AH020093KYQD-202211KYQD-202114kj22zsys02XLZ-202008S2021103800042023AH0521042022AH05171241805080

2024

10.3969/j.issn.1672-8785.2024.04.005

红外
中国科学院上海技术物理研究所

红外

影响因子：0.317
ISSN：1672-8785
年,卷(期)：2024.45(4)
  • 20