PollenNet - a deep learning approach to predicting airborne pollen concentrations

Abstract

The accurate short-term forecasting of daily airborne pollen concentrations is of great importance in public health. Various machine learning and statistical techniques have been employed to predict these concentrations. In this paper, an RNN-based method called PollenNet is introduced, which is capable of predicting the average daily pollen concentrations for three types of pollen: ragweed (Ambrosia), birch (Betula), and grass (Poaceae). Moreover, two strategies incorporating measurement errors during the training phase are introduced, making the method more robust. The data for experiments were obtained from the RealForAll project, where pollen concentrations were gathered using a Hirst-type 7-day volumetric spore trap.Additionally, five types of meteorological data were utilized as input variables. The results of our study demonstrate that the proposed method outperforms standard models typically used for predicting pollen concentrations, specifically the pollen calendar method, pollen predictions based on patterns, and the naive approach.

What factors influence Bitcoin’s daily price direction from the perspective of machine learning classifiers?

“…Usually, the grid search method is combined with a cross-validation strategy. Cross-validation can prevent overfitting and help evaluate the model performance more robustly than a simple train-test approach [7]. Due to the time series nature of the observed forecasting problem, the blocking time series split is used as the cross-validation splitting strategy.…”