Stormwater utility fees (SUFs) are a user fee-based funding mechanism that provides a dedicated source of revenue for stormwater management programs. There are different ways of setting the utility fee. The most prevalent method is to use equivalent residential units (ERUs), which are derived from impervious areas. SUF rates are adjusted based on land use, with commercial and industrial areas typically charged higher than residential areas. The impervious area of a parcel is the fundamental basis for setting the SUF. Hence, the impervious area must be captured accurately and effectively. The readily available national land cover data provides impervious cover, but the resolution of the database lacks the details needed for setting accurate SUFs at a parcel level. Fortunately, emerging computer technologies have provided the opportunity to develop tools for accurate calculation of impervious areas at a finer resolution. We have developed and implemented an easy-to-use artificial intelligence (AI) based machine learning technique that processes ortho imagery in a short span for a typical municipality. The tool provides revenue generation statistics by jurisdiction to help with decision support for revenue management among different jurisdictions within a watershed-based stormwater district. This proposed presentation will provide an overview of the mechanism of SUF, rate structure, and factors to consider in establishing a stormwater utility fee. In addition, a detailed case study using the AI based SUF tool will be provided for the audience to understand the fundamentals of setting SUF and demonstrate the steps involved in the use of the tool. The approach presented can be applied everywhere when evaluating a stormwater utility fee. The presentation is intended for a technical audience, such as engineers, planners, policymakers, and those who are interested in learning more about the use of SUF for stormwater management.