We present a novel approach to determine spatially distributed routing parameters for the distributed hydrological Hillslope Link Model (HLM), an ordinary differential equations‐based streamflow forecasting model implemented and tested in Iowa. We being by developing a technique to determine two model parameters that control the channel routing equation in gauged catchments draining less than 1,300 km2. Then, we implement a parameter regionalization methodology using machine learning classification techniques and a bootstrap procedure, in which we trained 400 Random Forests (RFs) using physical and geomorphological features for classification. We made a regional interpolation using an ensemble of selected RF realizations that exhibited the best performance. We used as benchmark of our results a more straightforward interpolation technique based on USGS Hydrological Units Codes. We performed simulations of the HLM over the entire state of Iowa between 2012 and 2018 using the two regionalization methods, comparing them to the operational model used by the Iowa Flood Center, which applies a single set of parameter values to the entire domain. After evaluating the results at 148 USGS stations, the Random‐Forest approach captures the value of observed peak flows more precisely without losing performance in terms of the Kling Gupta Efficiency index. The improvements obtained using our proposed strategy that uses data, hydrological modeling, and a machine learning technique to identify and regionalize routing parameters are modest, indicating that the parameters that control the rainfall‐runoff transformation dominate uncertainty in our flood forecast model. Plain Language Summary We present a novel strategy to estimate the routing parameters for a regional hydrological model that forecasts floods in Iowa. In the strategy, we use a model setup that dynamically controls runoff and a machine learning technique. We applied the runoff controlled modeling setup to estimate the routing parameters over 48 gauged small watersheds in Iowa. Then, we trained multiple random forests using hydrological features and the estimated routing parameters of each small gauged watershed. After the training, we regionalize the routing parameters using the results from the random forests with the best performance. We also interpolate the routing parameters using the USGS Hydrological Unit Codes (HUCs). We ran Hillslope Link Model between 2012 and 2018 using the random forest ensemble and HUCs interpolations and a set of fixed parameters. Using the random forest ensemble, we found a set of parameters that follow the Iowa landforms and improves estimation of the peak flow magnitude and timing. Key Points The distribution of routing‐related parameters in the Hillslope Link Model (HLM) has a significant impact on estimating peak flow magnitude and timing We developed a runoff controller that separates hillslope and routing processes allowing the identification of routing‐related parameters Our machine learning procedure obtained routing parameters that match the Iowa landforms and improved HLM peak flow estimation