In this research, we present data-driven forecasting of ionospheric Total Electron Content (TEC) using the Long-Short Term Memory (LSTM) deep recurrent neural network method. The random forest machine learning method was used to perform a regression analysis and estimate the variable importance of the input parameters. The input data are obtained from satellite and ground based measurements characterizing the solar-terrestrial environment. We estimate the relative importance of 34 different parameters, including the solar flux, solar wind density and speed, the three components of interplanetary magnetic field, Lyman-alpha, the Kp, Dst and Polar Cap (PC) indices. The TEC measurements are taken with 15-second cadence from an equatorial GPS station located at Bogota, Columbia (4.7110° N, 74.0721° W). The 2008 - 2017 data set, including the five top parameters estimated using the random forest, is used for training the machine learning models, and the 2018 data set is used for independent testing of the LSTM forecasting. The LSTM method as applied to forecast the TEC up to 5 hours ahead, with 30-minute cadence. The results indicate that very good forecasts with low RMS error (high correlation) can be made in the near future and the RMS errors increase as we forecast further into the future. The data sources are satellite and ground based measurements characterizing the solar-terrestrial environment.

Allergies to airborne pollen are a significant issue affecting millions of Americans. Consequently, accurately predicting the daily concentration of airborne pollen is of significant public benefit in providing timely alerts. This study presents a method for the robust estimation of the concentration of airborne Ambrosia pollen using a suite of machine learning approaches including deep learning and ensemble learners. Each of these machine learning approaches utilize data from the European Centre for Medium-Range Weather Forecasts (ECMWF) atmospheric weather and land surface reanalysis. The machine learning approaches used for developing a suite of empirical models are deep neural networks, extreme gradient boosting, random forests and Bayesian ridge regression methods for developing our predictive model. The training data included twenty-four years of daily pollen concentration measurements together with ECMWF weather and land surface reanalysis data from 1987 to 2011 is used to develop the machine learning predictive models. The last six years of the dataset from 2012 to 2017 is used to independently test the performance of the machine learning models. The correlation coefficients between the estimated and actual pollen abundance for the independent validation datasets for the deep neural networks, random forest, extreme gradient boosting and Bayesian ridge were 0.82, 0.81, 0.81 and 0.75 respectively, showing that machine learning can be used to effectively forecast the concentrations of airborne pollen.

Airborne allergic pollen is a well known trigger for several cases of public health issues affecting millions of people. The effect is highly prevalent in the temperature region, especially in the North American region and Europe. For example, about 50 million Americans are affected by pollen caused allergy and similarly, studies show quite a significant population of Europe is affected. Contrary to the higher abundance of pollen in rural areas, pollen allergy is severe in urban areas than rural environments. Of all sources, it is the Ambrosia pollen that affects most due to its abundant production, strong allergic potency and its high prevalence near urban areas. Hence estimating the concentration of allergic pollen in the ambient atmosphere and notifying the public is crucial for people with allergies and health professionals who care for them. In this workshop, we present estimation of allergic pollen (particularly Ambrosia pollen) using advanced machine learning methods and input parameters from a suite of sources ranging from land surface to global reanalysis models and NEXRAD weather radar measurements at location of Tulsa, Oklahoma. We will present results of the machine learning model tested using an independent dataset and characterization of each atmospheric and land surface parameters’ importance for the machine learning estimation.