Method and experiment of rainfall intensity inversion using a microwave link based on support vector machine

Abstract

The precipitation is an important physical phenomenon. The real-time, accurate measurement of rainfall intensity has important significance in meteorological support, agriculture, weather forecasting, transportation industry and military mission. However, current methods, such as the rain gauge, the weather radar and meteorological satellite, are unable to meet the needs in all the areas above at present. The network of rain gauge is costly. Meanwhile, rain gauge has low spatial and temporal resolution. And the weather radar has a big deviation because of the ground clutter. Besides, the meteorological satellite is unable to measure the surface rainfall. Thus, a method of using the measurement of microwave rain-induced attenuation for rainfall estimation has been presented in meteorological field recently by meteorological experts and it has made some progress. The method based on microwave link has low cost because of using preexisting microwave device. There are also many preexisting microwave transmission networks, which can be used by rainfall field inversion in the future research. The method measures rainfall intensity more accurately because the propagation path of microwave is close to the surface. Many models for inversing rainfall intensity by rain-induced microwave attenuation have been put forward on account of the method advantages. The commonly used model for inversion of rain rate is given by International Telecommunication Union (ITU). However, the model presented by ITU ignores a number of meteorological factors such as temperature, humidity and air pressure, which to some degree reduces the accuracy of the rainfall inversion based on microwave link. Thus, based on the theory of support vector machine (SVM), an inversion method of the path rainfall intensity by using a microwave link is proposed. Starting from the theory of Mie scattering and the atmospheric gas absorption attenuation model, a model of rainfall intensity inversion of line-of-sight microwave links is proposed, which is based on support vector machine, the microwave rain attenuation characteristics and the Gamma drop-size distribution. One line-of-sight microwave link is designed and used to measure the microwave rain-induced attenuation and inverse rainfall. Compared with actual rainfall intensity measured by a disdrometer, inversion rainfall intensity shows a satisfactory result. The correlation coefficient of rain rate is inversed by microwave link based on SVM and that of disdrometer is higher than 0.6 mostly, and the maximum value is 0.9674; the minimum value of the root-mean-square error of the rain rate is 0.5780 mm/h; the minimum value of the error of accumulated rain amount is 0.0080 mm; the relative error of accumulated rain amount is less than 10% and its minimum value is 0.7425%. All these parameters above are superior to ITU's. Therefore, the inversion result demonstrates the validity, feasibility and accuracy of rainfall inversion model using a microwave link based on SVM. The model we present is of great significance for further improving the accuracy of inversion of rain rate based on microwave link and rainfall monitoring.