On the Possibility of Using Neural Networks for the Thunderstorm Forecasting

Elena  Stankova; Irina O.  Tokareva; Natalia V.  Dyachenko

doi:10.1007/978-3-030-87010-2_25

On the Possibility of Using Neural Networks for the Thunderstorm Forecasting

Elena Stankova, Irina O. Tokareva, Natalia V. Dyachenko

Department of Computer Modelling and Multiprocessor Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Abstract

The paper explores the possibility of forecasting such dangerous meteorological phenomena as a thunderstorm by applying five types of neural network to the output data of a hydrodynamic model that simulates dynamic and microphysical processes in convective clouds. The ideas and the result delivered in [1] are developed and supplemented by the classification error calculations and by consideration of radial basic and probabilistic neural networks. The results show that forecast accuracy of all five networks reaches values of 90%. However, the radial basis function has the advantages of the highest accuracy along with the smallest classification error. Its simple structure and short training time make this type of neuralnetwork the best one in view of accuracy versus productivity relation.

Original language	English
Title of host publication	Computational Science and Its Applications – ICCSA 2021
Subtitle of host publication	21st International Conference, Cagliari, Italy, September 13–16, 2021, Proceedings, Part VIII
Publisher	Springer Nature
Pages	350-359
ISBN (Electronic)	978-3-030-87010-2
ISBN (Print)	978-3-030-87009-6
DOIs	https://doi.org/10.1007/978-3-030-87010-2_25
State	Published - 2021
Event	International Conference on Computational Science and Its Applications - Кальяри, Italy Duration: 13 Sep 2021 → 16 Sep 2021 Conference number: 21

Publication series

Name	Lecture Notes in Computer Science
Volume	12956

Conference

Conference	International Conference on Computational Science and Its Applications
Abbreviated title	ICCSA
Country/Territory	Italy
City	Кальяри
Period	13/09/21 → 16/09/21

Keywords

Machine learning
Neural networks
Perceptron complex
Radial basic neural network
Probabilistic neural network
Numerical model of convective cloud
Weather forecasting
Thunderstorm forecasting

Access to Document

10.1007/978-3-030-87010-2_25

Cite this

Stankova, E., Tokareva, I. O., & Dyachenko, N. V. (2021). On the Possibility of Using Neural Networks for the Thunderstorm Forecasting. In Computational Science and Its Applications – ICCSA 2021: 21st International Conference, Cagliari, Italy, September 13–16, 2021, Proceedings, Part VIII (pp. 350-359). (Lecture Notes in Computer Science; Vol. 12956). Springer Nature. https://doi.org/10.1007/978-3-030-87010-2_25

Stankova, Elena ; Tokareva, Irina O. ; Dyachenko, Natalia V. . / On the Possibility of Using Neural Networks for the Thunderstorm Forecasting. Computational Science and Its Applications – ICCSA 2021: 21st International Conference, Cagliari, Italy, September 13–16, 2021, Proceedings, Part VIII. Springer Nature, 2021. pp. 350-359 (Lecture Notes in Computer Science).

@inproceedings{39a141f66cc846d381fea374b748fb9d,

title = "On the Possibility of Using Neural Networks for the Thunderstorm Forecasting",

abstract = "The paper explores the possibility of forecasting such dangerous meteorological phenomena as a thunderstorm by applying five types of neural network to the output data of a hydrodynamic model that simulates dynamic and microphysical processes in convective clouds. The ideas and the result delivered in [1] are developed and supplemented by the classification error calculations and by consideration of radial basic and probabilistic neural networks. The results show that forecast accuracy of all five networks reaches values of 90%. However, the radial basis function has the advantages of the highest accuracy along with the smallest classification error. Its simple structure and short training time make this type of neuralnetwork the best one in view of accuracy versus productivity relation.",

keywords = "Machine learning, Neural networks, Perceptron complex, Radial basic neural network, Probabilistic neural network, Numerical model of convective cloud, Weather forecasting, Thunderstorm forecasting",

author = "Elena Stankova and Tokareva, {Irina O.} and Dyachenko, {Natalia V.}",

note = "Stankova E., Tokareva I.O., Dyachenko N.V. (2021) On the Possibility of Using Neural Networks for the Thunderstorm Forecasting. In: Gervasi O. et al. (eds) Computational Science and Its Applications – ICCSA 2021. ICCSA 2021. Lecture Notes in Computer Science, vol 12956. Springer, Cham. https://doi.org/10.1007/978-3-030-87010-2_25; null ; Conference date: 13-09-2021 Through 16-09-2021",

year = "2021",

doi = "10.1007/978-3-030-87010-2_25",

language = "English",

isbn = "978-3-030-87009-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature",

pages = "350--359",

booktitle = "Computational Science and Its Applications – ICCSA 2021",

address = "Germany",

}

Stankova, E, Tokareva, IO & Dyachenko, NV 2021, On the Possibility of Using Neural Networks for the Thunderstorm Forecasting. in Computational Science and Its Applications – ICCSA 2021: 21st International Conference, Cagliari, Italy, September 13–16, 2021, Proceedings, Part VIII. Lecture Notes in Computer Science, vol. 12956, Springer Nature, pp. 350-359, International Conference on Computational Science and Its Applications, Кальяри, Italy, 13/09/21. https://doi.org/10.1007/978-3-030-87010-2_25

On the Possibility of Using Neural Networks for the Thunderstorm Forecasting. / Stankova, Elena ; Tokareva, Irina O. ; Dyachenko, Natalia V. .

Computational Science and Its Applications – ICCSA 2021: 21st International Conference, Cagliari, Italy, September 13–16, 2021, Proceedings, Part VIII. Springer Nature, 2021. p. 350-359 (Lecture Notes in Computer Science; Vol. 12956).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

TY - GEN

T1 - On the Possibility of Using Neural Networks for the Thunderstorm Forecasting

AU - Stankova, Elena

AU - Tokareva, Irina O.

AU - Dyachenko, Natalia V.

N1 - Conference code: 21

PY - 2021

Y1 - 2021

N2 - The paper explores the possibility of forecasting such dangerous meteorological phenomena as a thunderstorm by applying five types of neural network to the output data of a hydrodynamic model that simulates dynamic and microphysical processes in convective clouds. The ideas and the result delivered in [1] are developed and supplemented by the classification error calculations and by consideration of radial basic and probabilistic neural networks. The results show that forecast accuracy of all five networks reaches values of 90%. However, the radial basis function has the advantages of the highest accuracy along with the smallest classification error. Its simple structure and short training time make this type of neuralnetwork the best one in view of accuracy versus productivity relation.

AB - The paper explores the possibility of forecasting such dangerous meteorological phenomena as a thunderstorm by applying five types of neural network to the output data of a hydrodynamic model that simulates dynamic and microphysical processes in convective clouds. The ideas and the result delivered in [1] are developed and supplemented by the classification error calculations and by consideration of radial basic and probabilistic neural networks. The results show that forecast accuracy of all five networks reaches values of 90%. However, the radial basis function has the advantages of the highest accuracy along with the smallest classification error. Its simple structure and short training time make this type of neuralnetwork the best one in view of accuracy versus productivity relation.

KW - Machine learning

KW - Neural networks

KW - Perceptron complex

KW - Radial basic neural network

KW - Probabilistic neural network

KW - Numerical model of convective cloud

KW - Weather forecasting

KW - Thunderstorm forecasting

U2 - 10.1007/978-3-030-87010-2_25

DO - 10.1007/978-3-030-87010-2_25

M3 - Conference contribution

SN - 978-3-030-87009-6

T3 - Lecture Notes in Computer Science

SP - 350

EP - 359

BT - Computational Science and Its Applications – ICCSA 2021

PB - Springer Nature

Y2 - 13 September 2021 through 16 September 2021

ER -

Stankova E, Tokareva IO, Dyachenko NV. On the Possibility of Using Neural Networks for the Thunderstorm Forecasting. In Computational Science and Its Applications – ICCSA 2021: 21st International Conference, Cagliari, Italy, September 13–16, 2021, Proceedings, Part VIII. Springer Nature. 2021. p. 350-359. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-030-87010-2_25

On the Possibility of Using Neural Networks for the Thunderstorm Forecasting

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this