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 … Show more
“…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%.…”
Nowadays, the Global Navigation Satellite Systems (GNSS) have become an effective atmospheric observing technique to remotely sense precipitable water vapor (PWV) mainly due to their high spatiotemporal resolutions. In this study, from an investigation for the relationship between GNSS-derived PWV (GNSS-PWV) and heavy precipitation, it was found that from several hours before heavy precipitation, PWV was probably to start with a noticeable increase followed by a steep drop. Based on this finding, a new model including five predictors for heavy precipitation prediction is proposed. Compared with the existing 3-factor model that uses three predictors derived from the ascending trend of PWV time series (i.e., PWV value, PWV increment and rate of the PWV increment), the new model also includes two new predictors derived from the descending trend: PWV decrement and rate of PWV decrement. The use of the two new predictors for reducing the number of misdiagnosis predictions is proposed for the first time. The optimal set of monthly thresholds for the new five-predictor model in each summer month were determined based on hourly GNSS-PWV time series and precipitation records at three co-located GNSS/weather stations during the 8-year period 2010â2017 in the Hong Kong region. The new model was tested using hourly GNSS-PWV and precipitation records obtained at the above three co-located stations during the summer months in 2018 and 2019. Results showed that 189 of the 198 heavy precipitation events were correctly predicted with a lead time of 5.15 h, and the probability of detection reached 95.5%. Compared with the 3-factor method, the new model reduced the FAR score by 32.9%. The improvements made by the new model have great significance for early detection and predictions of heavy precipitation in near real-time.
“…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%.…”
Nowadays, the Global Navigation Satellite Systems (GNSS) have become an effective atmospheric observing technique to remotely sense precipitable water vapor (PWV) mainly due to their high spatiotemporal resolutions. In this study, from an investigation for the relationship between GNSS-derived PWV (GNSS-PWV) and heavy precipitation, it was found that from several hours before heavy precipitation, PWV was probably to start with a noticeable increase followed by a steep drop. Based on this finding, a new model including five predictors for heavy precipitation prediction is proposed. Compared with the existing 3-factor model that uses three predictors derived from the ascending trend of PWV time series (i.e., PWV value, PWV increment and rate of the PWV increment), the new model also includes two new predictors derived from the descending trend: PWV decrement and rate of PWV decrement. The use of the two new predictors for reducing the number of misdiagnosis predictions is proposed for the first time. The optimal set of monthly thresholds for the new five-predictor model in each summer month were determined based on hourly GNSS-PWV time series and precipitation records at three co-located GNSS/weather stations during the 8-year period 2010â2017 in the Hong Kong region. The new model was tested using hourly GNSS-PWV and precipitation records obtained at the above three co-located stations during the summer months in 2018 and 2019. Results showed that 189 of the 198 heavy precipitation events were correctly predicted with a lead time of 5.15 h, and the probability of detection reached 95.5%. Compared with the 3-factor method, the new model reduced the FAR score by 32.9%. The improvements made by the new model have great significance for early detection and predictions of heavy precipitation in near real-time.
“…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.…”
Section: Literature Review and Scope Of The Researchmentioning
Machine learning (ML) has been utilized to predict climatic parameters, and many successes have been reported in the literature. In this paper, we scrutinize the effectiveness of five widely used ML algorithms in the monthly prediction of seasonal climatic parameters using monthly image data. Specifically, we quantify the predictive performance of these algorithms applied to five climatic parameters using various combinations of features. We compare the predictive accuracy of the resulting trained ML models to that of basic statistical estimators that are computed directly from the training data. Our results show that ML never significantly outperforms the statistical baseline, and underperforms for most feature sets. Unlike previous similar studies, we provide error bars for the relative performance of different predictors based on jackknife estimates applied to differences in predictive error magnitudes. We also show that the practice of shuffling data sequences which was employed in some previous references leads to data leakage, resulting in over-estimated performance. Ultimately, the paper demonstrates the importance of using well-grounded statistical techniques when producing and analyzing the results of ML predictive models.
“…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.…”
Section: Chaos Theory On Solar Irradiancementioning
We analyse the time series of solar irradiance measurements using chaos theory.The False Nearest Neighbour method (FNN), one of the most common methods of chaotic analysis is used for the analysis. One year data from the weather station located at Nanyang Technological University (NTU) Singapore with a temporal resolution of 1 minute is employed for the study. The data is sampled at 60 minutes interval and 30 minutes interval for the analysis using the FNN method. Our experiments revealed that the optimum dimension required for solar irradiance is 4 for both samplings. This indicates that a minimum of 4 dimensions is required for embedding the data for the best representation of input. This study on obtaining the embedding dimension of solar irradiance measurement will greatly assist in fixing the number of previous data required for solar irradiance forecasting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citationsâcitations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.