Predicting daily ragweed pollen concentrations using Computational Intelligence techniques over two heavily polluted areas in Europe.

Forecasting ragweed pollen concentration is a useful tool for sensitive people in order to prepare in time for high pollen episodes. The aim of the study is to use methods of Computational Intelligence (CI) (Multi-Layer Perceptron, M5P, REPTree, DecisionStump and MLPRegressor) for predicting daily values of Ambrosia pollen concentrations and alarm levels for 1-7 days ahead for Szeged (Hungary) and Lyon (France), respectively. Ten-year daily mean ragweed pollen data (within 1997-2006) are considered for both cities. 10 input variables are used in the models including pollen level or alarm level on the given day, furthermore the serial number of the given day of the year within the pollen season and altogether 8 meteorological variables. The study has novelties as (1) daily alarm thresholds are firstly predicted in the aerobiological literature; (2) data-driven modelling methods including neural networks have never been used in forecasting daily Ambrosia pollen concentration; (3) algorithm J48 has never been used in palynological forecasts; (4) we apply a rarely used technique, namely factor analysis with special transformation, to detect the importance of the influencing variables in defining the pollen levels for 1-7 days ahead. When predicting pollen concentrations, for Szeged Multi-Layer Perceptron models deliver similar results with tree-based models 1 and 2 days ahead; while for Lyon only Multi-Layer Perceptron provides acceptable result. When predicting alarm levels, the performance of Multi-Layer Perceptron is the best for both cities. It is presented that the selection of the optimal method depends on climate, as a function of geographical location and relief. The results show that the more complex CI methods perform well, and their performance is case-specific for ≥2 days forecasting horizon. A determination coefficient of 0.98 (Ambrosia, Szeged, one day and two days ahead) using Multi-Layer Perceptron ranks this model the best one in the literature.

Intercomparison of air quality data using principal component analysis, and forecasting of PM10 and PM2.5 concentrations using artificial neural networks, in Thessaloniki and Helsinki.

In this paper we propose a methodology consisting of specific computational intelligence methods, i.e. principal component analysis and artificial neural networks, in order to inter-compare air quality and meteorological data, and to forecast the concentration levels for environmental parameters of interest (air pollutants). We demonstrate these methods to data monitored in the urban areas of Thessaloniki and Helsinki in Greece and Finland, respectively. For this purpose, we applied the principal component analysis method in order to inter-compare the patterns of air pollution in the two selected cities. Then, we proceeded with the development of air quality forecasting models for both studied areas. On this basis, we formulated and employed a novel hybrid scheme in the selection process of input variables for the forecasting models, involving a combination of linear regression and artificial neural networks (multi-layer perceptron) models. The latter ones were used for the forecasting of the daily mean concentrations of PM10 and PM2.5 for the next day. Results demonstrated an index of agreement between measured and modelled daily averaged PM10 concentrations, between 0.80 and 0.85, while the kappa index for the forecasting of the daily averaged PM10 concentrations reached 60% for both cities. Compared with previous corresponding studies, these statistical parameters indicate an improved performance of air quality parameters forecasting. It was also found that the performance of the models for the forecasting of the daily mean concentrations of PM10 was not substantially different for both cities, despite the major differences of the two urban environments under consideration.