The use of a neural network to forecast daily grass pollen concentration in a Mediterranean region: the southern part of the Iberian Peninsula

Sánchez-Mesa, Juan Antonio; Galán, Carmen Rueda; Martínez-Heras, J. A.; Hervás-Martínez, C.

doi:10.1046/j.1365-2222.2002.01510.x

Cited by 56 publications

(25 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For Szeged, MLP provides the best results for the forecasting horizon (1-7 days) that is confirmed by former studies (Sánchez-Mesa et al, 2002;Voukantsis et al, 2010). 1-day forecast indicates the best performance.…”

Section: Performance Of the Forecasting Modelssupporting

confidence: 77%

“…When forecasting, the following values of coefficient of determination (R 2 ) (i.e. squared correlations) of one day ahead forecasts were received: 0.60 for Poaceae using neural networks (Sánchez-Mesa et al, 2002); 0.93 again for Poaceae using neural networks (Rodríguez-Rajo et al, 2010); 0.45 for grass pollen (whole season) using correlation analysis (Stach et al, 2008) and 0.79 for Poaceae using Multiple Linear Regression (Voukantsis et al, 2010). Our study provides a coefficient of determination of 0.98 (Ambrosia, Szeged, one day and two days ahead) using Multi-Layer Perceptron that ranks this model the best one in the literature.…”

Section: Performance Of the Forecasting Modelsmentioning

confidence: 99%

See 1 more Smart Citation

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

Csépe

Makra

Voukantsis

et al. 2014

Science of The Total Environment

View full text Add to dashboard Cite

• 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.

show abstract

Section: Performance Of the Forecasting Modelssupporting

confidence: 77%

Section: Performance Of the Forecasting Modelsmentioning

confidence: 99%

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

Csépe

Makra

Voukantsis

et al. 2014

Science of The Total Environment

View full text Add to dashboard Cite

show abstract

“…Moreover, the effects of diverse meteorological parameters on Poaceae pollination have been dissected, with the aim of collecting useful information for the improvement of predictive models, which represent an important contribution to primary prevention strategies for susceptible individuals. Each climatic area is characterized by particular pollination patterns and weather conditions, leading to such models being widely studied across different regions (Sánchez-Mesa et al 2002;Smith and Emberlin 2006;Rodríguez-Rajo et al 2010;Piotrowska 2012, Brighetti et al 2014. Similar studies have also been carried out in other taxa (Rodríguez-Rajo et al 2003, Kasprzyk 2009, Sabariego et al 2012, Oteros et al 2013.…”

Section: Introductionmentioning

confidence: 92%

Climate change: consequences on the pollination of grasses in Perugia (Central Italy). A 33-year-long study

et al. 2016

View full text Add to dashboard Cite

Many works carried out in the last decades have shown that the pollen season for taxa flowering in winter and spring, in temperate regions, has tended to be earlier, probably due to the continuous rise in temperature. The mean annual temperature in Perugia, Central Italy, was about 0.5 °C higher in the last three decades compared with that registered from 1952 to 1981. The increase of temperature took place mainly in winter and spring, while no significant variation was recorded during the summer and autumn. This scenario shows variations in the timing and behavior of flowering of many spontaneous plants such as grasses, whose phenology is strongly influenced by air temperature. This work reports fluctuations in the airborne grass pollen presence in Perugia over a 33-year period (1982-2014), in order to study the influence of the warming registered in recent years on the behavior of pollen release of this taxon. The grass pollen season in Perugia typically lasts from the beginning of May to late July. The start dates showed a marked trend to an earlier beginning of the season (-0.4 day/year), as well as a strong correlation with the average temperatures of March and April. The peak is reached around 30th May, but the annual pollen index (API) is following a decreasing trend. The correlation between starting dates and spring temperatures could be interesting for the constitution of a forecasting model capable of predicting the presence of airborne grass pollen, helping to plan therapies for allergic people.

show abstract

“…Only few studies used advanced machine learning methods such as neural network (Sánchez-Mesa et al, 2002;Rodríguez-Rajo et al, 2010;Puc, 2012;Voukantsis et al, 2010) and random forest (Nowosad, 2016) for pollen forecasting and support vector machines are applied for related environmental studies (Voukantsis et al, 2010;Osowski and Garanty, 2007).…”

Section: Pollen Estimationmentioning

confidence: 99%

Machine Learning Applications for Earth Observation

Lary

Zewdie

Liu

et al. 2018

Earth Observation Open Science and Innovation

View full text Add to dashboard Cite

Machine learning has found many applications in remote sensing. These applications range from retrieval algorithms to bias correction, from code acceleration to detection of disease in crops, from classification of pelagic habitats to rock type classification. As a broad subfield of artificial intelligence, machine learning is concerned with algorithms and techniques that allow computers to "learn" by example. The major focus of machine learning is to extract information from data automatically by computational and statistical methods. Over the last decade there has been considerable progress in developing a machine learning methodology for a variety of Earth Science applications involving trace gases, retrievals, aerosol products, land surface products, vegetation indices, and most recently, ocean applications. In this chapter, we will review some examples of how machine learning has already been useful for remote sensing and some likely future applications.

show abstract

The use of a neural network to forecast daily grass pollen concentration in a Mediterranean region: the southern part of the Iberian Peninsula

Cited by 56 publications

References 20 publications

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

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

Climate change: consequences on the pollination of grasses in Perugia (Central Italy). A 33-year-long study

Machine Learning Applications for Earth Observation

Contact Info

Product

Resources

About