Prediction of convective clouds formation using evolutionary neural computation techniques

Research areas:

• Applications - Weather forecasting

Year:

2020

Type of Publication:

Article

Keywords:

Convection initialization prediction, machine learning algorithms, neural networks, unbalanced databases

Authors:

• Guijo-Rubio, David
• Gutiérrez, Pedro Antonio
• Casanova-Mateo, Carlos
• Fernández, Juan Carlos
• Gómez-Orellana, Antonio Manuel
• Salvador-González, Pablo
• Salcedo-Sanz, Sancho
• Hervás-Martínez, César

Journal:

Neural Computing and Applications

Volume:

32

Pages:

13917-13929

Month:

February

ISSN:

0941-0643

BibTex:

@article{NCAA2020, author = "David Guijo-Rubio and Pedro Antonio Guti{\'e}rrez and Carlos Casanova-Mateo and Juan Carlos Fern{\'a}ndez and Antonio Manuel G{\'o}mez-Orellana and Pablo Salvador-Gonz{\'a}lez and Sancho Salcedo-Sanz and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "The prediction of convective clouds formation is a very important problem in different areas such as agriculture, natural hazards prevention or transport-related facilities, among others. In this paper we evaluate the capacity of different types of evolutionary artificial neural networks to predict the formation of convective clouds, tackling the problem as a classification task. We use data from Madrid-Barajas airport, including variables and indices derived from the Madrid-Barajas airport radiosonde station. As objective variable, we use the cloud information contained in the METAR and SPECI meteorological reports from the same airport and we consider a prediction time-horizon of 12 hours. The performance of different types of evolutionary artificial neural networks has been discussed and analysed, including three types of basis functions (Sigmoidal Unit, Product Unit and Radial Basis Function), and two types of models, a mono-objective evolutionary algorithm with two objective functions and a multi-objective evolutionary algorithm optimised by the two objective functions simultaneously. We show that some of the developed neuro-evolutionary models obtain high quality solutions to this problem, due to its high unbalance characteristic.", awards = "JCR(2020): 5.606 Position: 31/140 (Q1) Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE", comments = "JCR(2020): 5.606 Position: 31/140 (Q1) Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE", issn = " 0941-0643", journal = "Neural Computing and Applications", keywords = "Convection initialization prediction, machine learning algorithms, neural networks, unbalanced databases", month = "February", note = "JCR(2020): 5.606 Position: 31/140 (Q1) Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE", pages = "13917-13929", title = "{P}rediction of convective clouds formation using evolutionary neural computation techniques", url = "doi.org/10.1007/s00521-020-04795-w", volume = "32", year = "2020", }

Note:

JCR(2020): 5.606 Position: 31/140 (Q1) Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Abstract:

The prediction of convective clouds formation is a very important problem in different areas such as agriculture, natural hazards prevention or transport-related facilities, among others. In this paper we evaluate the capacity of different types of evolutionary artificial neural networks to predict the formation of convective clouds, tackling the problem as a classification task. We use data from Madrid-Barajas airport, including variables and indices derived from the Madrid-Barajas airport radiosonde station. As objective variable, we use the cloud information contained in the METAR and SPECI meteorological reports from the same airport and we consider a prediction time-horizon of 12 hours. The performance of different types of evolutionary artificial neural networks has been discussed and analysed, including three types of basis functions (Sigmoidal Unit, Product Unit and Radial Basis Function), and two types of models, a mono-objective evolutionary algorithm with two objective functions and a multi-objective evolutionary algorithm optimised by the two objective functions simultaneously. We show that some of the developed neuro-evolutionary models obtain high quality solutions to this problem, due to its high unbalance characteristic.

Comments:

JCR(2020): 5.606 Position: 31/140 (Q1) Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE