Variability and forecasting of air temperature in Elqui Valley (Chile)
- PDF / 1,663,726 Bytes
- 15 Pages / 595.224 x 790.955 pts Page_size
- 95 Downloads / 160 Views
RESEARCH ARTICLE
Variability and forecasting of air temperature in Elqui Valley (Chile) ´ 1,2 Juan A. Lazzus
· Pedro Vega-Jorquera1 · Ignacio Salfate1 · Fernando Cuturrufo1 · Luis Palma-Chilla1
Received: 27 January 2020 / Accepted: 31 August 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract A method to forecast air temperature TA in Elqui Valley (south of Chile’s Atacama Desert) using an artificial neural network (ANN) and meteorological time series data relevant to this zone, is proposed. This zone has one of the most sensitive climates in South America due to the influence of phenomena such as El Ni˜no/La Ni˜na, the Southeast Pacific Subtropical Anticyclone, Humboldt Current, and Madden–Julian Oscillation, in addition to the complex topography of Chilean east-west transverse valleys, and the Andes. We used a method that combines ANN and genetic algorithm (GA) for forecasting TA 1, 3, and 6 hours ahead. GA is introduced to optimize the weights update process in the proposed method. Our database contains 457,969 data, from 2004–2017, taken from eight stations throughout the valley and divided into three datasets: training set with 50% of overall data of each station, validation set with the subsequent 25% of data of each station, and prediction set with the last 25% of data. Several architectures were evaluated using the root-mean-square error (RMSE), mean absolute error (MAE) and correlation coefficient (R). The results show that the ANN+GA method represents a powerful technique for forecasting TA with RMSE from 0.99 to 4.51 [◦ C], MAE from 0.52 to 3.07 [◦ C], and R from 0.86 to 0.96. Also, we use the values obtained by ANN+GA method to investigate the spatial TA variability in elevation from the coast ∼30 [masl] to the Andean zone of this valley ∼5,000 [masl]. Keywords Air temperature · Seasonal trends · Time series forecasting · Artificial neural netwok · Atacama desert · Semi-arid climate
Introduction Weather forecasting is crucial in meteorology and climate science (Inness and Dorling 2013). The needed physical parameters for weather forecasting are complex because they depend on many local and global factors. Among
Communicated by: H. Babaie Electronic supplementary material The online version of this article (https://doi.org/10.1007/s12145-020-00519-9) contains supplementary material, which is available to authorized users. Juan A. Lazz´us
[email protected] 1
Departamento de F´ısica, Universidad de La Serena, Casilla 554, La Serena, Chile
2
Instituto de Investigaci´on Multidisciplinario en Ciencias y Tecnolog´ıa, Universidad de La Serena, Casilla 554, La Serena, Chile
these factors, air temperature (TA ) is relevant for many environmental/meteorological/climatological studies and management of the Earth’s resources (for some examples, see Vasquez 2006). Air temperature is a measurement of the mean kinetic energy of chaotic air molecules’ motion (Gli´nski et al. 2011). It is an intensive physical property that represents a measure of the thermal energy per particle of matt
Data Loading...
