A Data-Driven Approach for Accurate Rainfall Prediction

Abstract

In recent years, there has been growing interest in using Precipitable Water Vapor (PWV) derived from Global Positioning System (GPS) signal delays to predict rainfall. However, the occurrence of rainfall is dependent on a myriad of atmospheric parameters. This paper proposes a systematic approach to analyze various parameters that affect precipitation in the atmosphere. Different ground-based weather features like Temperature, Relative Humidity, Dew Point, Solar Radiation, PWV along with Seasonal and Diurnal variables are identified, and a detailed feature correlation study is presented. While all features play a significant role in rainfall classification, only a few of them, such as PWV, Solar Radiation, Seasonal and Diurnal features, stand out for rainfall prediction. Based on these findings, an optimum set of features are used in a data-driven machine learning algorithm for rainfall prediction. The experimental evaluation using a four-year (2012-2015) database shows a true detection rate of 80.4%, a false alarm rate of 20.3%, and an overall accuracy of 79.6%. Compared to the existing literature, our method significantly reduces the false alarm rates.

Development of an Improved Model for Prediction of Short-Term Heavy Precipitation Based on GNSS-Derived PWV

“…The rapid developments of the GNSS tropospheric tomography in the past two decades have also made the use of this maturing technique to obtain high accuracy three-dimensional water vapor profile, which has already been used in applications of GNSS meteorology [51][52][53]. Therefore, some researchers proposed that, in addition to the threshold for GNSS-PWV, a long GNSS-PWV time series [54,55], a high temporal resolution dataset [56,57], multidimensional GNSS tomography-based water vapor profiles [58,59] and numerous other predictors obtained from GNSS observations can be used for precipitation prediction [60][61][62][63]. Among them, Benevides et al [48] analyzed the characteristics of the temporal variation in PWV during the period of 2010-2012 in Lisbon for heavy precipitation in several case studies and proposed a simple model for predicting precipitation within 6 h. The maximum rate of PWV increment was also used as a predictor in the model, and the test results of the model showed a 75% correct detection rate and a false alarm rate of 65%.…”

Basic Statistical Estimation Outperforms Machine Learning in Monthly Prediction of Seasonal Climatic Parameters

“…However these models require very large datasets with tens of thousands of images, due the data-intensive training process. For this reason, CNNs and ConvLSTMs are mainly applied to data sets with short time intervals of no more than a few minutes between data points, which are typically much larger than data sets with longer time intervals [29][30][31][32][33][34][35][36][37][38][39][40]. For single-output prediction, a wider range of ML tools and time frames have been used, from linear methods in [17,21,41,42], to ensemble methods in [43][44][45], to hybrid methods in [28,[46][47][48], to deep models in [49][50][51][52][53][54][55][56] covering time scales from minutes to years.…”

A Chaotic Approach on Solar Irradiance Forecasting

“…Medvigy and Beaulieu [4] observed arXiv:1912.07184v1 [physics.ao-ph] 16 Dec 2019 a correlation between solar irradiance and precipitation. Researchers started using this variable for predicting the onset of precipitation [5]. However, the variation of solar irradiance is quite erratic (chaotic nature) due to atmospheric conditions like cloudiness which makes its prediction difficult.…”