Neural Network Approach to Forecast Hourly Intense Rainfall Using GNSS Precipitable Water Vapor and Meteorological Sensors

Benevides, Pedro; Catalão, João; Nico, Giovanni

doi:10.3390/rs11080966

Cited by 76 publications

(35 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…T M = 70.2 + 0.72*T 0 (16) The water vapor pressure values (E) were calculated using the following equation by employing relative humidity values measured through in-situ observations:…”

Section: Resultsmentioning

confidence: 99%

“…Moreover, ANN is a powerful nonlinear approach in dealing with complicated problems, such as meteorological forecasts and tropospheric estimation studies. With the use of ANN algorithms based on meteorological variables, developments have been achieved in terms of tropospheric parameter estimation, the temporal prediction of ZWD, weighted mean temperature interpolation, and hourly heavy rainfall estimation [14][15][16][17][18]. Numerous studies have been conducted with different ANN architectures.…”

Section: Introductionmentioning

confidence: 99%

“…The test results showed that a combination of meteorological parameters, such as relative humidity, air pressure, wet bulb temperature, and cloudiness as an input for the ANN model could significantly improve the forecast accuracy and efficiency. In the literature, numerous ANN studies for meteorological predictions have been carried out based on MLP architecture [13,16,17,21,22]. In addition, different models have been applied for the modeling of atmospheric parameters.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spatial Interpolation of GNSS Troposphere Wet Delay by a Newly Designed Artificial Neural Network Model

Selbesoglu

2019

Applied Sciences

View full text Add to dashboard Cite

Global Navigation Satellite System (GNSS) signals arrive at the Earth in a nonlinear and slightly curved way due to the refraction effect caused by the troposphere. The troposphere delay of the GNSS signal consists of hydrostatic and wet parts. In particular, tropospheric wet delay prediction and interpolation are more difficult than those of the dry component due to the rapid temporal and spatial variation of the water vapor content. Wet delay estimation and interpolation with a sufficient accuracy is an important issue for all parameters obtained by GNSS positioning techniques. In particular, in real-time positioning applications, errors caused by interpolation of the wet troposphere delay are reflected in the height component of about 1 to 2 cm. Furthermore, the amount of water vapor in the troposphere is very important information in weather forecast applications obtained as a function of wet delay. Therefore, real-time monitoring of the troposphere can be achieved with a higher resolution and accuracy by utilizing neural network models for interpolation of the wet tropospheric delay. In addition, in the absence of the GNSS station, wet delays can be interpolated by means of the surrounding stations to the desired location. In this study, a back propagation artificial neural network (BPNN) model based on meteorological parameters obtained from The New Austrian Meteorological Measuring Network (TAWES) was used to interpolate wet troposphere delay. Analysis was carried out at 40 reference stations of the Echtzeit Positionierung Austria (EPOSA) GNSS Network covering the whole of Austria. The interpolation of zenith wet delays based on the artificial neural network was performed by using latitude, longitude, altitude and meteorological parameters (temperature, pressure, weighted mean temperature, and water vapor pressure). These parameters were then subtracted from the artificial neural network model one by one and six different artificial neural networks were designed. In addition, the linear interpolation method (LIN) and inverse distance weighted interpolation method (IDW) were used as conventional interpolation methods. In order to investigate the effect of the network density on interpolation methods, three networks, including 40, 30, and 20 reference stations, were formed and the increased distance effect on interpolation methods was evaluated. In addition, analyses were conducted in winter, spring, and summer to evaluate the seasonal effects on interpolation methods. According to the statistical analysis, the root mean square error (RMSE) values of the IDW, LIN, and BPNN methods were found to be 12.6, 13.4, and 5.9 mm, respectively.

show abstract

“…T M = 70.2 + 0.72*T 0 (16) The water vapor pressure values (E) were calculated using the following equation by employing relative humidity values measured through in-situ observations:…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Spatial Interpolation of GNSS Troposphere Wet Delay by a Newly Designed Artificial Neural Network Model

Selbesoglu

2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In our previous research [56], a model containing 5 predictors derived from the PWV time series for predicting heavy precipitation was proposed, which correctly predicted 95.5% of heavy precipitation with a lead time of 5.15 h, and the false alarms were also reduced by the model to 28.9%. Apart from the predictors derived from PWV time series, a myriad of predictors obtained from other GNSS observations were also utilized in the model construction in previous studies [57]− [59].…”

Section: Introductionmentioning

confidence: 99%

An Improved Model for Detecting Heavy Precipitation Using GNSS-Derived Zenith Total Delay Measurements

Wang

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In recent years, precipitable water vapor (PWV) have been widely used in heavy precipitation prediction, which is obtained from a conversion of the zenith total delay (ZTD) of the GNSS signal. Since the parameter directly estimated for the tropospheric delay from GNSS data processing is the ZTD, this study investigated the feasibility of directly using ZTD to predict heavy precipitation. Based on the finding that, prior to a heavy precipitation events, ZTD was likely to start with a duration of continuous rise followed by a sharp drop, a new heavy precipitation detection model containing seven predictors derived from ZTD was established. The seven predictors reflect not only the ascending and descending trends, but also long-term and short-term variations in the ZTD time series. Three criteria, representing differnet situations for the formation of heavy precipitation, were also constructed using the predictors to detect heavy precipitation. The optimal set of thresholds for the seven predictors for each summer month were determined based on hourly ZTD and precipitation records at a pair of co-located GNSS/weather station−HKSC-KP in Hong Kong over the period 2010−2017. The model was evaluated using the predictions in 2018 and 2019 to compare against the corresponding precipitation records. Results showed that the new model correctly predicted 98.8% of the heavy precipitation events, with a mean lead time of 4.37 h. Compared with the existing models, the new model also reduced the false alarms by 32.3%. Similar results were also

show abstract

“…With the increase in the number of successful cases of application of deep learning in real life, such as in autonomous driving, healthcare, and smart cities [1][2][3][4][5][6][7][8][9], various attempts have been made to apply deep learning to weather-related fields using numerical models [10] to improve the performance of weather forecasting [11][12][13][14][15]. In the field of meteorology, nowcasting is a popular research topic in which deep learning techniques are being actively applied to the analysis of spatiotemporal data, such as radar and satellite data [16][17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step

et al. 2021

View full text Add to dashboard Cite

Nowcasting is an important technique for weather forecasting because sudden weather changes significantly affect human life. The encoding-forecasting model, which is a state-of-the-art architecture in the field of data-driven radar extrapolation, does not particularly focus on the latest data when forecasting natural phenomena. This paper proposes a weighted broadcasting method that emphasizes the latest data of the time step to improve the nowcasting performance. This weighted broadcasting method allows the most recent rainfall patterns to have a greater impact on the forecasting network by extending the architecture of the existing encoding-forecasting model. Experimental results show that the proposed model is 1.74% and 2.20% better than the existing encoding-forecasting model in terms of mean absolute error and critical success index, respectively. In the case of heavy rainfall with an intensity of 30 mm/h or higher, the proposed model was more than 30% superior to the existing encoding-forecasting model. Therefore, applying the weighted broadcasting method, which explicitly places a high emphasis on the latest information, to the encoding-forecasting model is considered as an improvement that is applicable to the state-of-the-art implementation of data-driven radar-based precipitation nowcasting.

show abstract

Neural Network Approach to Forecast Hourly Intense Rainfall Using GNSS Precipitable Water Vapor and Meteorological Sensors

Cited by 76 publications

References 28 publications

Spatial Interpolation of GNSS Troposphere Wet Delay by a Newly Designed Artificial Neural Network Model

Spatial Interpolation of GNSS Troposphere Wet Delay by a Newly Designed Artificial Neural Network Model

An Improved Model for Detecting Heavy Precipitation Using GNSS-Derived Zenith Total Delay Measurements

Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step

Contact Info

Product

Resources

About