Abstract

Accurately determining the height of the planetary boundary layer (PBL) is important since it can affect the climate, weather, and air quality. Ground-based infrared hyperspectral remote sensing is an effective way to obtain this parameter. Compared with radiosonde measurements, its temporal resolution is much higher. In this study, a method to retrieve the PBL height (PBLH) from the ground-based infrared hyperspectral radiance data is proposed based on machine learning. In this method, the channels that are sensitive to temperature and humidity profiles are selected as the feature vectors, and the PBLHs derived from radiosonde are taken as the true values. The support vector machine (SVM) is applied to train and test the data set, and the parameters are optimized in the process. The data set collected at the Atmospheric Radiation Measurement (ARM) program Southern Great Plains (SGP) from 2012 to 2015 is analyzed. The instruments used in this letter include Atmospheric Emitted Radiance Interferometer (AERI), Vaisala CL31 ceilometer, and radiosonde. It shows that the root mean square error (RMSE) between the PBLHs calculated by the proposed method using AERI data and those from radiosonde data can be within 370 m, and the square correlation coefficient (SCC) is greater than 0.7. Compared with the PBLHs derived from the ceilometer, it can be found that the new method is more stable and less affected by clouds.

Highlights

  • T HE planetary boundary layer (PBL) is the lowest layer of the troposphere, which is a physically mixed layer due to the effects of shear-induced turbulence and convective overturning near the Earth’s surface [1]

  • root mean square error (RMSE) AND square correlation coefficient (SCC) OF PBLHS DERIVED FROM AERI radiance (AERIRAD), Vaisala CL31 ceilometer (VCEIL), AND AERIPROF OF THE WHOLE DAY FROM 2012 TO 2015

  • AERIRAD uses the radiance of selected bands to retrieve PBL height (PBLH), which is consistent with the thermodynamic profile method

Read more

Summary

INTRODUCTION

T HE planetary boundary layer (PBL) is the lowest layer of the troposphere, which is a physically mixed layer due to the effects of shear-induced turbulence and convective overturning near the Earth’s surface [1]. The profile is oversmoothed at higher altitudes so that the important features within the retrieved profiles are missing, such as vertical gradients of temperature and water vapor that used to do PBLH estimation [9]. Another challenge is how to reconcile PBLH from aerosol as a tracer and that from thermodynamic profiles. We do not carry out the inversion of thermodynamic profiles but directly use the AERI radiance (AERIRAD) data to estimate PBLH.

ESTABLISHMENT OF DATA SET
INVERSION OF PBLH BASED ON SVM
Channel Selection
Support Vector Machine
Proposed Algorithm for PBLH Estimation
EVALUATION OF PBLH INVERSION ALGORITHM
Evaluation When a Cloud Is in the Field of View
Diurnal Cycle
Seasonal Cycle
Edge Cases
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call