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.