Prediction of convective clouds formation using evolutionary neural computation techniques
- PDF / 1,006,078 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 93 Downloads / 211 Views
(0123456789().,-volV)(0123456789().,-volV)
ORIGINAL ARTICLE
Prediction of convective clouds formation using evolutionary neural computation techniques David Guijo-Rubio1 • Pedro A. Gutie´rrez1 • Carlos Casanova-Mateo2 • Juan Carlos Ferna´ndez1 • Antonio Manuel Go´mez-Orellana1 • Pablo Salvador-Gonza´lez3 • Sancho Salcedo-Sanz4 • Ce´sar Herva´s-Martı´nez1 Received: 6 July 2019 / Accepted: 17 February 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
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. 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 h. 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. Keywords Convection initialisation prediction Machine learning algorithms Neural networks Unbalanced databases
1 Introduction Convective weather conditions can significantly affect many strategic economical areas such as electric supply, communications, logistic services and transport, especially air traffic. The identification of atmospheric situations that favours the initiation of convection as well as the accurate prediction of its timing and location is still a difficult task
& David Guijo-Rubio [email protected] 1
Department of Computer Science and Numerical Analysis, University of Co´rdoba, Rabanales Campus, Albert Einstein Building 3rd Floor, 14071 Co´rdoba, Spain
2
Department of Civil Engineering: Construction, Infrastructure and Transport, Universidad Polite´cnica de Madrid, Madrid, Spain
3
LATUV, Remote Sensing Laboratory, Universidad de Valladolid, Valladolid, Spain
4
Department of Signal Processing and Communications, Universidad de Alcala´, Alcala´ de Henares, Spain
for the operational weather forecasters [1]. The basic ingredients for convection to occur stated by Johns and Doswell [2] (a sufficiently moist and deep layer in the low or mid-atmosphere, conditional instability and a triggering mechanism) are still the base of many tools and applications developed to support the forecast of convection init
Data Loading...
