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.

Temperature and humidity profiles in the atmospheric boundary layer are essential for climate studies. The ground-based infrared hyperspectral spectrometer has the advantage of measuring radiances emitted from the atmosphere at a high temporal and moderate vertical resolution. In this article, the retrieval of temperature and humidity profiles from ground-based infrared hyperspectral observations is exploited. Although existing inversion algorithms based on physical models or statistical learning have made some progress, they still suffer from high computational complexity or poor performance. Motivated by the strength of the deep learning, we present a deep retrieval architecture (DReA) by skillfully designing a light-weight one-dimensional convolution neural network (CNN) to retrieve the temperature and humidity profiles. Experiments were conducted using atmospheric emitted radiance interferometer (AERI) and radiosonde data to demonstrate the superiority of the proposed DReA. The validation of the DReA with the radiosonde, using 802 profiles with 37 layers below 3 km, presents an excellent retrieval ability with a root mean square error (RMSE) of 0.87 K for the temperature and 1.06 g/kg for the water vapor mixing ratio. Furthermore, a thorough comparison with commonly used inversion methods such as the traditional back propagation (BP) and the eigenvector (EV) regression method, shows that our proposed DReA method obtains a leading solution in retrieving temperature and humidity profiles.

Blowing snow is a common weather phenomenon in Antarctica and plays an important role in the water vapor cycle and ice sheet mass balance. Although it has a significant impact on the climate of Antarctica, people do not know much about this process. Fog events are difficult to distinguish from blowing snow events using existing detection algorithms by a ceilometer. In this study, based on ceilometer, the meteorological parameters observed by surface meteorology systems are further combined to detect blowing snow and fog using the AdaBoost algorithm. The weather phenomena recorded by human observers are ‘true’. The dataset is collected from 1 January 2016 to 31 December 2016 at the AWARE site. Among them, three-quarters of the data are used as the training set and the rest of the data as the testing set. The classification accuracy of the proposed algorithm for the testing set is about 94%. Compared with the Loeb method, the proposed algorithm can detect 89.12% of blowing snow events and 76.10% of fog events, while the Loeb method can only identify 64.29% of blowing snow events and 31.87% of fog events.

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.

High-precision retrieval of rainfall over large areas is of great importance for the research of atmospheric detection and the social life. With the rapid development of communication satellite constellations and 5G communication networks, the use of widely distributed networks of earth–space links (ESLs) and horizontal microwave links (HMLs) to retrieve rainfall over large areas has great potential for obtaining high-precision rainfall fields and complementing traditional instruments of rainfall measurement. In this paper, we carry out the research of combining multiple ESLs with HMLs to retrieve rainfall fields. Firstly, a rainfall detection network for retrieving rainfall fields is built based on the atmospheric propagation model of ESL and HML. Then, the ordinary Kriging interpolation (OK) and radial basis function (RBF) neural network are applied to the reconstruction of rainfall fields. Finally, the performance of the joint network of ESLs and HMLs to retrieve rainfall fields in the area is validated. The results show that the joint network of ESLs and HMLs based on OK algorithm and RBF neural network is capable of retrieving the distribution of rain rates in different rain cells with high accuracy, and the root mean square error (RMSE) of retrieving the rain rates of real rainfall fields is lower than 0.56 mm/h, and the correlation coefficient (CC) is higher than 0.996. In addition, the CC for retrieving stratiform rainfall and convective rainfall by the joint network of ESLs and HMLs is higher than 0.949, indicating that the characteristics of the two different types of rainfall events can be accurately monitored.

A new cloud-base height (CBH) inversion algorithm based on infrared hyperspectral radiation using a machine learning algorithm is proposed in this paper. We use the LBLRTM and DISORT model for forward research. The minimal-redundancy-maximal-relevance (mRMR) algorithm is used to extract the sensitive channels of CBH as the feature vectors. The CBHs measured by Vaisala CL31 ceilometer (VCEIL) are taken as the reference values. The artificial neural network (ANN) method with two hidden layers of 50 and 10 respective is applied to construct the mapping relationship between AERI radiation and CBH (ANN-CBH algorithm). The dataset is collected during the period from January 2012 to December 2017 at the ARM SGP site and NSA site. Among them, the data from 2012 to 2014 are used as the training set, while the data of 2015, 2016, 2017 of each site are respectively used as the testing set. Compared with the traditional physical algorithm, the ANN-CBH algorithm has higher accuracy. The correlation coefficients (CCs) between the inversion results of CBH from the ANN-CBH algorithm and the measurement results of the VCEIL are about 0.9 at SGP site and 0.85 at NSA site, while the CC of the CBH inversion results between CO2 slicing algorithm and VCEIL is only about 0.7 and 0.65, respectively. In addition, the experimental results indicate that the ANN-CBH algorithm is less affected by precipitable water vapor (PWV).