Beatriz Monge-Sanz

Abstract:

This work is focused on the application of neural network based models to the analysis of total ozone (TO) time series. Processes that affect total ozone are extremely non linear, especially at the considered European mid-latitudes. Artificial neural networks (ANNs) are intrinsically non-linear systems, hence they are expected to cope with TO series better than classical statistics do. Moreover, neural networks do not assume the stationarity of the data series so they are also able to follow time-changing situations among the implicated variables. These two features turn NNs into a promising tool to catch the interactions between atmospheric variables, and therefore to extract as much information as possible from the available data in order to make, for example, time series reconstructions or future predictions. Models based on NNs have also proved to be very suitable for the treatment of missing values within the data series. In this paper we present several models based on neural networks to fill the missing periods of data within a total ozone time series, and models able to reconstruct the data series. The results released by the ANNs have been compared with those obtained by using classical statistics methods, and better accuracy has been achieved with the non linear ANNs techniques. Different network structures and training strategies have been tested depending on the specific task to be accomplished. © European Geosciences Union 2004.

Abstract:

During recent years ozone depletion has been detected not only over polar regions but also over mid-latitude areas. This study analyzed daily total ozone (TO) data from three south-western European locations in order to detect long-time TO trends by means of a filtering technique. Correlation analysis with atmospheric circulation patterns was carried out to explain the decreasing trends observed. Results appear to show a strong correlation between TO decrease and the North Atlantic Oscillation and Arctic Oscillation Indices throughout recent decades. On the other hand, the trends also indicate that, at least during the last ten years, TO variations cannot be explained solely by natural atmospheric cycles over the studied area.