A Novel Machine Learning Algorithm for Cloud Detection Using AERI Measurement Data

Infrared hyperspectral remote sensing has been widely used in the field of meteorology. Many scientists have carried out research on inversion methods of meteorological elements such as thermodynamic profile, boundary layer height, cloud base height, etc. In this study, a method based on machine learning for cloud detection using ground-based infrared hyperspectral radiation data is proposed. The features of outliers, the cloudy and cloud-free data of Atmospheric Emitted Radiance Interferometer (AERI) radiation are extracted. The “reference values” of cloudy and cloud-free are determined based on the observation data of Vaisala CL31 ceilometer within the time range of 8 min before the corresponding time of AERI. A support vector machine (SVM) algorithm is used for training. The dataset comes from the Atmospheric Radiation Measurement (ARM) Southern Great Plains (SGP) site and North Slope Alaska (NSA) site from 2015 to 2017, and the ARM West Antarctic Radiation Experiment (AWARE) site in 2016 is also analyzed. The instruments used in this paper include AERI, ceilometer, etc. The experimental results reveal that the agreement of cloud detection results between the proposed algorithm and ceilometer is about 93% at each site. However, for high clouds or optically thin clouds, the agreement will decrease.

Dust Climatology of Turkey as a Part of the Eastern Mediterranean Basin via 9-Year CALIPSO-Derived Product

Turkey is located in the heart of complex transition geography between Eurasia and the Middle East. In the grand scheme, the so-called eastern Mediterranean Basin is located almost in the middle of the dusty belt, and is a hot spot of climate change. The downstream location of dust-carrying winds from close desert sources reveals Turkey as an open plane to particulate matter exposure throughout the year. In order to clarify this phenomenon, this paper aims to determine the desert dust climatology of Turkey via CALIPSO onboard Lidar. This prominent instrument enables us to understand clouds, aerosols and their types, and related climatic systems, with its valuable products. In this study, a 9-year CALIPSO-derived pure dust product dataset was formed to explain horizontal and vertical distributions, transport heights and case incidences. The results indicated that the pure dust extinction coefficient increased as the location shifted from west to east. Moreover, in the same direction of west to east, the dominant spring months changed to summer and autumn. Mountain range systems surrounding Anatolia were the main obstacles against lofted and buoyant dust particles travelling to northern latitudes. Even if high ridges accumulated mass load on the southern slopes, they also enabled elevated particles to reach the ground level of the inner cities.