<i>NowDeepN</i>: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values Prediction
One of the hottest topics in today’s meteorological research is <i>weather nowcasting</i>, which is the weather forecast for a short time period such as one to six hours. Radar is an important data source used by operational meteorologists for issuing nowcasting warnings. With the main g...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/1/125 |
id |
doaj-3a1a4485f3dd4de58df6b97615572ed6 |
---|---|
record_format |
Article |
spelling |
doaj-3a1a4485f3dd4de58df6b97615572ed62020-12-25T00:05:50ZengMDPI AGApplied Sciences2076-34172021-12-011112512510.3390/app11010125<i>NowDeepN</i>: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values PredictionGabriela Czibula0Andrei Mihai1Eugen Mihuleţ2Department of Computer Science, Babeş-Bolyai University, 400084 Cluj-Napoca, RomaniaDepartment of Computer Science, Babeş-Bolyai University, 400084 Cluj-Napoca, RomaniaRomanian National Meteorological Administration, 013686 Bucharest, RomaniaOne of the hottest topics in today’s meteorological research is <i>weather nowcasting</i>, which is the weather forecast for a short time period such as one to six hours. Radar is an important data source used by operational meteorologists for issuing nowcasting warnings. With the main goal of helping meteorologists in analysing radar data for issuing nowcasting warnings, we propose <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula>, a supervised learning based regression model which uses an ensemble of <i>deep artificial neural networks</i> for predicting the values for radar products at a certain time moment. The values predicted by <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula> may be used by meteorologists in estimating the future development of potential severe phenomena and would replace the time consuming process of extrapolating the radar echoes. <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula> is intended to be a proof of concept for the effectiveness of learning from radar data relevant patterns that would be useful for predicting future values for radar products based on their historical values. For assessing the performance of <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula>, a set of experiments on real radar data provided by the Romanian National Meteorological Administration is conducted. The impact of a <i>data cleaning</i> step introduced for correcting the erroneous radar products’ values is investigated both from the computational and meteorological perspectives. The experimental results also indicate the relevance of the features considered in the supervised learning task, highlighting that the radar products’ values at a certain geographical location at a time moment may be predicted from the products’ values from a neighboring area of that location at previous time moments. An overall <i>Normalized Root Mean Squared Error</i> less than <inline-formula><math display="inline"><semantics><mrow><mn>4</mn><mo>%</mo></mrow></semantics></math></inline-formula> was obtained for <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula> on the cleaned radar data. Compared to similar related work from the nowcasting literature, <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula> outperforms several approaches and this emphasizes the performance of our proposal.https://www.mdpi.com/2076-3417/11/1/125weather nowcastingmachine learningdeep neural networksautoencodersPrincipal Component Analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Gabriela Czibula Andrei Mihai Eugen Mihuleţ |
spellingShingle |
Gabriela Czibula Andrei Mihai Eugen Mihuleţ <i>NowDeepN</i>: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values Prediction Applied Sciences weather nowcasting machine learning deep neural networks autoencoders Principal Component Analysis |
author_facet |
Gabriela Czibula Andrei Mihai Eugen Mihuleţ |
author_sort |
Gabriela Czibula |
title |
<i>NowDeepN</i>: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values Prediction |
title_short |
<i>NowDeepN</i>: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values Prediction |
title_full |
<i>NowDeepN</i>: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values Prediction |
title_fullStr |
<i>NowDeepN</i>: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values Prediction |
title_full_unstemmed |
<i>NowDeepN</i>: An Ensemble of Deep Learning Models for Weather Nowcasting Based on Radar Products’ Values Prediction |
title_sort |
<i>nowdeepn</i>: an ensemble of deep learning models for weather nowcasting based on radar products’ values prediction |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-12-01 |
description |
One of the hottest topics in today’s meteorological research is <i>weather nowcasting</i>, which is the weather forecast for a short time period such as one to six hours. Radar is an important data source used by operational meteorologists for issuing nowcasting warnings. With the main goal of helping meteorologists in analysing radar data for issuing nowcasting warnings, we propose <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula>, a supervised learning based regression model which uses an ensemble of <i>deep artificial neural networks</i> for predicting the values for radar products at a certain time moment. The values predicted by <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula> may be used by meteorologists in estimating the future development of potential severe phenomena and would replace the time consuming process of extrapolating the radar echoes. <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula> is intended to be a proof of concept for the effectiveness of learning from radar data relevant patterns that would be useful for predicting future values for radar products based on their historical values. For assessing the performance of <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula>, a set of experiments on real radar data provided by the Romanian National Meteorological Administration is conducted. The impact of a <i>data cleaning</i> step introduced for correcting the erroneous radar products’ values is investigated both from the computational and meteorological perspectives. The experimental results also indicate the relevance of the features considered in the supervised learning task, highlighting that the radar products’ values at a certain geographical location at a time moment may be predicted from the products’ values from a neighboring area of that location at previous time moments. An overall <i>Normalized Root Mean Squared Error</i> less than <inline-formula><math display="inline"><semantics><mrow><mn>4</mn><mo>%</mo></mrow></semantics></math></inline-formula> was obtained for <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula> on the cleaned radar data. Compared to similar related work from the nowcasting literature, <inline-formula><math display="inline"><semantics><mrow><mi>N</mi><mi>o</mi><mi>w</mi><mi>D</mi><mi>e</mi><mi>e</mi><mi>p</mi><mi>N</mi></mrow></semantics></math></inline-formula> outperforms several approaches and this emphasizes the performance of our proposal. |
topic |
weather nowcasting machine learning deep neural networks autoencoders Principal Component Analysis |
url |
https://www.mdpi.com/2076-3417/11/1/125 |
work_keys_str_mv |
AT gabrielaczibula inowdeepnianensembleofdeeplearningmodelsforweathernowcastingbasedonradarproductsvaluesprediction AT andreimihai inowdeepnianensembleofdeeplearningmodelsforweathernowcastingbasedonradarproductsvaluesprediction AT eugenmihulet inowdeepnianensembleofdeeplearningmodelsforweathernowcastingbasedonradarproductsvaluesprediction |
_version_ |
1724371431044677632 |