Application of Seq2Seq models for predicting the development of thunderstorm activity to enhance the pilot’s situational awareness in flight

The paper presents the results of application of Seq2seq models based on neural networks for nowcasting-forecasting with a lead time of up to 2 hours – of thunderstorm activity in order to increase situational awareness of aircraft crews. Various recurrent and convolutional recurrent models were cre...

Full description

Saved in:
Bibliographic Details
Main Authors: G. V. Kovalenko, I. A. Yadrov
Format: Article
Language:Russian
Published: Moscow State Technical University of Civil Aviation 2025-03-01
Series:Научный вестник МГТУ ГА
Subjects:
Online Access:https://avia.mstuca.ru/jour/article/view/2498
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849684919634100224
author G. V. Kovalenko
I. A. Yadrov
author_facet G. V. Kovalenko
I. A. Yadrov
author_sort G. V. Kovalenko
collection DOAJ
description The paper presents the results of application of Seq2seq models based on neural networks for nowcasting-forecasting with a lead time of up to 2 hours – of thunderstorm activity in order to increase situational awareness of aircraft crews. Various recurrent and convolutional recurrent models were created and trained on the basis of radar meteorological observations of thunderstorm cells. The results showed that convolutional recurrent neural networks (ConvRNN, ConvLSTM, ConvGRU) outperform classical recurrent models and improve the thunderstorm forecast by 25–30% in terms of RMSE (root mean square error) metric compared to the baseline model, which always selects the most recent radar image available at the time of prediction. Nevertheless, despite the fact that the convolution recurrence models can accurately represent the general trend of thunderstorm cloud shape changes, the accuracy of predicting the intensity of thunderstorm cells is usually overestimated. Application of the proposed thunderstorm activity forecasting technology can enhance the situational awareness of the flight crew improving the projection of the current situation into the near future and optimizing the decision-making process for thunderstorm avoidance by providing crew members with predictive information about thunderstorm development on the navigation display screen. Future research is expected to further optimize the model architecture and integrate the predictive technology into flight crew decision support systems.
format Article
id doaj-art-a5b2da3d455b4a298d1ff024a4eaf595
institution DOAJ
issn 2079-0619
2542-0119
language Russian
publishDate 2025-03-01
publisher Moscow State Technical University of Civil Aviation
record_format Article
series Научный вестник МГТУ ГА
spelling doaj-art-a5b2da3d455b4a298d1ff024a4eaf5952025-08-20T03:23:19ZrusMoscow State Technical University of Civil AviationНаучный вестник МГТУ ГА2079-06192542-01192025-03-01281203810.26467/2079-0619-2025-28-1-20-381542Application of Seq2Seq models for predicting the development of thunderstorm activity to enhance the pilot’s situational awareness in flightG. V. Kovalenko0I. A. Yadrov1Saint Petersburg State University of Civil Aviation named after Chief Marshal of Aviation A.A. NovikovSaint Petersburg State University of Civil Aviation named after Chief Marshal of Aviation A.A. NovikovThe paper presents the results of application of Seq2seq models based on neural networks for nowcasting-forecasting with a lead time of up to 2 hours – of thunderstorm activity in order to increase situational awareness of aircraft crews. Various recurrent and convolutional recurrent models were created and trained on the basis of radar meteorological observations of thunderstorm cells. The results showed that convolutional recurrent neural networks (ConvRNN, ConvLSTM, ConvGRU) outperform classical recurrent models and improve the thunderstorm forecast by 25–30% in terms of RMSE (root mean square error) metric compared to the baseline model, which always selects the most recent radar image available at the time of prediction. Nevertheless, despite the fact that the convolution recurrence models can accurately represent the general trend of thunderstorm cloud shape changes, the accuracy of predicting the intensity of thunderstorm cells is usually overestimated. Application of the proposed thunderstorm activity forecasting technology can enhance the situational awareness of the flight crew improving the projection of the current situation into the near future and optimizing the decision-making process for thunderstorm avoidance by providing crew members with predictive information about thunderstorm development on the navigation display screen. Future research is expected to further optimize the model architecture and integrate the predictive technology into flight crew decision support systems.https://avia.mstuca.ru/jour/article/view/2498seq2seqpredictionrecurrent neural networksconvolutional recurrent neural networkssituational awarenessthunderstorm avoidance
spellingShingle G. V. Kovalenko
I. A. Yadrov
Application of Seq2Seq models for predicting the development of thunderstorm activity to enhance the pilot’s situational awareness in flight
Научный вестник МГТУ ГА
seq2seq
prediction
recurrent neural networks
convolutional recurrent neural networks
situational awareness
thunderstorm avoidance
title Application of Seq2Seq models for predicting the development of thunderstorm activity to enhance the pilot’s situational awareness in flight
title_full Application of Seq2Seq models for predicting the development of thunderstorm activity to enhance the pilot’s situational awareness in flight
title_fullStr Application of Seq2Seq models for predicting the development of thunderstorm activity to enhance the pilot’s situational awareness in flight
title_full_unstemmed Application of Seq2Seq models for predicting the development of thunderstorm activity to enhance the pilot’s situational awareness in flight
title_short Application of Seq2Seq models for predicting the development of thunderstorm activity to enhance the pilot’s situational awareness in flight
title_sort application of seq2seq models for predicting the development of thunderstorm activity to enhance the pilot s situational awareness in flight
topic seq2seq
prediction
recurrent neural networks
convolutional recurrent neural networks
situational awareness
thunderstorm avoidance
url https://avia.mstuca.ru/jour/article/view/2498
work_keys_str_mv AT gvkovalenko applicationofseq2seqmodelsforpredictingthedevelopmentofthunderstormactivitytoenhancethepilotssituationalawarenessinflight
AT iayadrov applicationofseq2seqmodelsforpredictingthedevelopmentofthunderstormactivitytoenhancethepilotssituationalawarenessinflight