Figure - available from: Remote Sensing
This content is subject to copyright.
The locations of Automatic Weather Stations (dots) within the radar observation range of the MYN radar. Black circles denote radar range rings with a 50 km interval.
Source publication
Estimating precipitation area is important for weather forecasting as well as real-time application. This paper aims to develop an analytical framework for efficient precipitation area estimation using S-band dual-polarization radar measurements. Several types of factors, such as types of sensors, thresholds, and models, are considered and compared...
Similar publications
Temperature is used to indicate variability and climate changes that indicate the process which is been carried out within the ecosystem and its services. The lack of knowledge about temperature affects human lives in terms of agriculture, transportation, mining, etc. temperature forecasting is used to predict atmospheric conditions based on parame...
Recently, Big Data has become an increasingly important source to support traditional credit scoring. Personal credit evaluation based on machine learning approaches focuses on the application data of clients in open banking and new banking platforms with challenges about Big Data quality and model risk. This paper represents a PySpark code for com...
Citations
... The application of machine learning models in meteorological studies, particularly in the remote sensing area, is gaining more focus. Such models could be used to partition areas into non-rain, convective, or stratiform based on satellite data [63,64], and ground-based radar data [65,66]. However, ML models need to be performed carefully as they do not necessarily outperform other statistical models [67]. ...
Rain type classification into convective and stratiform is an essential step required to improve quantitative precipitation estimations by remote sensing instruments. Previous studies with Micro Rain Radar (MRR) measurements and subjective rules have been performed to classify rain events. However, automating this process by using machine learning (ML) models provides the advantages of fast and reliable classification with the possibility to classify rain minute by minute. A total of 20,979 min of rain data measured by an MRR at Das in northeast Spain were used to build seven types of ML models for stratiform and convective rain type classification. The proposed classification models use a set of 22 parameters that summarize the reflectivity, the Doppler velocity, and the spectral width (SW) above and below the so-called separation level (SL). This level is defined as the level with the highest increase in Doppler velocity and corresponds with the bright band in stratiform rain. A pre-classification of the rain type for each minute based on the rain microstructure provided by the collocated disdrometer was performed. Our results indicate that complex ML models, particularly tree-based ensembles such as xgboost and random forest which capture the interactions of different features, perform better than simpler models. Applying methods from the field of interpretable ML, we identified reflectivity at the lowest layer and the average spectral width in the layers below SL as the most important features. High reflectivity and low SW values indicate a higher probability of convective rain.
... This could be helpful in many fields where accurate identification of the precipitation area is important such as transportation, agriculture, hydrology, and atmospheric science. To examine the evaporation or sublimation, one can utilize polarimetric variables [51][52][53][54] or/and the humidity profile from the NWP model [55]. Our study suggests that HGT can also be one of the useful factors in identifying the presence of precipitation on the ground (Figure 11c) without explicit representation of evaporation or sublimation. ...
An accurate classification of the precipitation type is important for forecasters, particularly in the winter season. We explored the capability of three supervised machine learning (ML) methods (decision tree, random forest, and support vector machine) to determine ground precipitation types (no precipitation, rain, mixed, and snow) for winter precipitation. We provided information on the particle characteristics within a radar sampling volume and the environmental condition to the ML model with the simultaneous use of polarimetric radar variables and thermodynamic variables. The ML algorithms were optimized using predictor selection and hyperparameter tuning in order to maximize the computational efficiency and accuracy. The random forest (RF) had the highest skill scores in all precipitation types and outperformed the operational scheme. The spatial distribution of the precipitation type from the RF model showed a good agreement with the surface observation. As a result, RF is recommended for the real-time precipitation type classification due to its easy implementation, computational efficiency, and satisfactory accuracy. In addition to the validation, this study confirmed the strong dependence of precipitation type on wet-bulb temperature and a 1000–850 hPa layer thickness. The results also suggested that the base heights of the radar echo are useful in discriminating non-precipitating area.
... Gagin et al. [18] and Tsonis et al. [19] used ground-based radar data to study the relationship between the area of rain clusters and precipitation. Song et al. [20] estimated efficient areas of precipitation using S-band dual-polarization radar measurements and yielded a rigorous comparison in statistical and machine learning. Capsoni et al. [21] and Awaka [22] found a relationship between the characteristic radius and peak rainfall rates of rain clusters. ...
Continuous observations from geostationary satellites can show the morphology of precipitation cloud systems in quasi-real-time, but there are still large deviations in the inversion of precipitation. We used binary-connected area recognition technology to identify meso-β-scale rain clusters over Hainan Island from 1 June 2000 to 31 December 2018, based on Global Precipitation Measurement (GPM) Integrated Multi-satellitE Retrievals for GPM data. We defined and statistically analyzed the parameters of rain clusters to reveal the typical morphological and precipitation characteristics of rain clusters, and to explore the relationship between the parameters and rainfall intensity of rain clusters. We found that the area and long axis of rain clusters over land were larger than those over the ocean, and that continental rain clusters were usually square in shape. Rain clusters with a larger area and longer axis were concentrated on the northern side of the mountains on Hainan Island and the intensity of rain was larger on the northern and eastern sides of the mountains. The variation of continental rain clusters over time was more dramatic than the variation of oceanic clusters. The area and long axis of rain clusters was larger between 14:00 and 21:00 from April to September and the long axis of the oceanic rain clusters increased in winter. There were clear positive correlations between the area, long axis and shape of the rain clusters and the maximum rain rate. The area and long axis of continental rain clusters had a higher correlation with the rain rate than those of oceanic clusters. The establishment of a relationship between the morphology of rain clusters and precipitation helps us to understand the laws of precipitation and improve the prediction of precipitation in this region.
