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

Abstract

• For Szeged, MLP and tree-based models, while for Lyon only MLP performs well for predicting pollen concentration.• When predicting alarm levels, the performance of MLP is the best for both cities.• When forecasting high pollen episodes, the more complex CI methods prove better for both cities.• The selection of the optimal method depends on climate, as a function of geographical location and relief. a b s t r a c t a r t i c l e i n f o 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.

A parlagfű okozta légzőszervi allergiás megbetegedések előfordulása Magyarországon

“…Fontos tennivaló az orvoshoz nem forduló betegek felis merése, a súlyos tünetek kezelése. Több a tennivaló a megelőzés terén, ami elsősorban a parlagfű irtását jelenti, de a betegek egy része talán tudná hasznosítani a magas pollenszámra figyelmeztető információkat is [18][19][20][21].…”

Differences in Reporting the Ragweed Pollen Season Using Google Trends across 15 Countries

“…It is therefore essential to be able to forecast the onset of the pollen season as well as to characterise seasons in different places. Sentinel networks offer the potential to meet this need [4-7]. Pollen counts can forecast the exposure to pollen [8].…”

“…However, more data are required. Combining several sources of information using advanced data engineering may also be important, but the data generated are complex and not yet available for all pollen species [4-7, 11]. …”

Machine Learning Applications for Earth Observation

“…For example, Csépe et al (2014) In this study we used random forests, neural networks, and support vector machines to estimate daily Ambrosia pollen concentration at Tulsa, Oklahoma (location: 36:1511 ı N, 95:9446 ı W). We used a combination of environmental parameters and NEXRAD radar measurements.…”

“…After pollen is produced in the plant anthers its emission dispersion and deposition is influenced by meteorological variables such as the temperature, wind speed, and direction and pressure (Kasprzyk, 2008;Csépe et al, 2014;Howard and Levetin, 2014). Other meteorologic parameters such as dew point, humidity, rainfall sunshine duration are also known to affect pollen emission and distribution (Kasprzyk, 2008).…”