Real-time 7-Day Forecast of Pollen Counts Using Deep Convolutional Neural Network
posterposted on 30.01.2019 by Yannic Lops, Ebrahim Eslami, Yunsoo Choi, Alqamah Sayeed
Poster sessions are particularly prominent at academic conferences. Posters are usually one frame of a powerpoint (or similar) presentation and are represented at full resolution to make them zoomable.
This study implements a deep convolutional neural network with the great potential to recognize patterns of pollen phenomena that enable the prediction of pollen concentrations. We trained the model using data from 2009 to 2015 from multiple meteorological data sets, satellite data, and processed data reflecting pollen flux as input for the model. The model forecasts pollen counts one to seven days ahead for the entire year of 2016. Comparison of daily forecasts to observations, the algorithm obtains a relatively high index of agreement and Pearson correlation coefficient of up to 0.90 and 0.88 respectively. An evaluation of categorical statistics based on defined threshold levels shows satisfactory results. Critical Success Index of the model forecasts is as high as 0.887 for weed pollen, 0.646 for tree pollen, and 0.294 for grass pollen. Compared to the conventional modeling approaches, the convolutional neural network shows a promising ability to predict pollen for multiple days. This poster was presented at the Earth Science Information Partners (ESIP) Winter Meeting in January 2019.