Extreme rainfall is a primary contributor to flooding with detrimental global impacts on society in a changing climate. One key challenge with understanding and predicting flooding from extreme rainfall is the need for very high resolution (less than 1 km) global coupled Earth system (atmosphere-ocean-land) models, which are not yet available. How can the relatively coarse resolution model rainfall be best used to predict and understand the extreme rainfall - flooding relationship? This study builds on the PI team’s early work on estimating flooding potential using the extreme rainfall multiplier (ERM). ERM has mainly been used in tropical cyclone rainfall over the central and eastern US. In particular, Machine Learning (ML) is effective at predicting flooding impacts (NOAA flood stages) over the mid-Atlantic region from Hurricane Irene and Tropical Storm Lee (2010) using ERM calculated from observations and the Unified Wave Interface-Coupled Model (Kerns and Chen 2022, 2023). This study extends these results to the continental US for different types of weather phenomena (e.g., atmospheric rivers and remnant tropical cyclones) and to the global domain using the pre-industrial control (piControl, 500 years) and historical (1850 - 2014) runs of E3SM. It aims to establish a baseline toward better understand extreme rainfall and flooding globally. Multiple observational and model-based products at a variety of spatial resolutions (4 km to ~100 km) are included along with coarse resolution regridded data. Flooding is determined in several ways: NOAA flood stages data, NOAA severe weather reports, and the Global Flood Database. ML provides a probabilistic prediction of flooding without using a hydrologic model. For coarser resolutions, the predictions are less confident but nevertheless skillful. The different ML predictions of flooding from the piControl and historical E3SM experiments as well as the beginning versus the end portion of the historical model runs provide an estimate of how extreme rainfall and flooding is being affected by climate change.