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

Zoltán Csépe, L. Makra, Dimitris Voukantsis, István Matyasovszky, Gábor Tusnády, Kostas Karatzas, Michel Thibaudon

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)542-552
Number of pages11
JournalScience of the Total Environment
Volume476-477
DOIs
Publication statusPublished - Apr 1 2014

Fingerprint

Multilayer neural networks
Artificial intelligence
pollen
Factor analysis
Data structures
Europe
Neural networks
factor analysis
relief
alarm
method
climate

Keywords

  • Allergy
  • Forecasting
  • Multi-Layer Perceptron
  • Neural networks
  • Ragweed pollen
  • Tree based methods

ASJC Scopus subject areas

  • Environmental Chemistry
  • Pollution
  • Waste Management and Disposal
  • Environmental Engineering

Cite this

Predicting daily ragweed pollen concentrations using Computational Intelligence techniques over two heavily polluted areas in Europe. / Csépe, Zoltán; Makra, L.; Voukantsis, Dimitris; Matyasovszky, István; Tusnády, Gábor; Karatzas, Kostas; Thibaudon, Michel.

In: Science of the Total Environment, Vol. 476-477, 01.04.2014, p. 542-552.

Research output: Contribution to journalArticle

Csépe, Zoltán ; Makra, L. ; Voukantsis, Dimitris ; Matyasovszky, István ; Tusnády, Gábor ; Karatzas, Kostas ; Thibaudon, Michel. / Predicting daily ragweed pollen concentrations using Computational Intelligence techniques over two heavily polluted areas in Europe. In: Science of the Total Environment. 2014 ; Vol. 476-477. pp. 542-552.
@article{debe79c07c774e7aa83d3089fe26bfe0,
title = "Predicting daily ragweed pollen concentrations using Computational Intelligence techniques over two heavily polluted areas in Europe",
abstract = "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.",
keywords = "Allergy, Forecasting, Multi-Layer Perceptron, Neural networks, Ragweed pollen, Tree based methods",
author = "Zolt{\'a}n Cs{\'e}pe and L. Makra and Dimitris Voukantsis and Istv{\'a}n Matyasovszky and G{\'a}bor Tusn{\'a}dy and Kostas Karatzas and Michel Thibaudon",
year = "2014",
month = "4",
day = "1",
doi = "10.1016/j.scitotenv.2014.01.056",
language = "English",
volume = "476-477",
pages = "542--552",
journal = "Science of the Total Environment",
issn = "0048-9697",
publisher = "Elsevier",

}

TY - JOUR

T1 - Predicting daily ragweed pollen concentrations using Computational Intelligence techniques over two heavily polluted areas in Europe

AU - Csépe, Zoltán

AU - Makra, L.

AU - Voukantsis, Dimitris

AU - Matyasovszky, István

AU - Tusnády, Gábor

AU - Karatzas, Kostas

AU - Thibaudon, Michel

PY - 2014/4/1

Y1 - 2014/4/1

N2 - 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.

AB - 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.

KW - Allergy

KW - Forecasting

KW - Multi-Layer Perceptron

KW - Neural networks

KW - Ragweed pollen

KW - Tree based methods

UR - http://www.scopus.com/inward/record.url?scp=84893475521&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893475521&partnerID=8YFLogxK

U2 - 10.1016/j.scitotenv.2014.01.056

DO - 10.1016/j.scitotenv.2014.01.056

M3 - Article

VL - 476-477

SP - 542

EP - 552

JO - Science of the Total Environment

JF - Science of the Total Environment

SN - 0048-9697

ER -