The increasing occurrences of global flood events, amidst climate change, highlight the need for hydrological data availability over large geographical domains for robust decision-making. Hydrological rating curves translate fluvial stage to streamflow and play a pivotal role in various applications, including flood inundation modeling and river geomorphology. Power law is an appropriate proxy for the nonlinear relationship between stage and discharge in natural systems. This study aims to develop a hierarchical data-driven approach to compute the power-law rating curve parameters (α, β) across the stream networks of CONtiguous United States (CONUS). The development of rating curve models is motivated by our interest in exploring a unifying solution linking rating curve parameters with hydro-climatological and geomorphological characteristics across CONUS. These can be applied to operational hydrological forecastins, such as the NOAA Office of Water Prediction NextGen framework, to enhance river routing and flood inundation mapping efforts. We used HYDRoacoustics in support of the Surface Water Oceanographic Topography (HYDRoSWOT), National Hydrography (NHDPlus v2.1), and STREAM-CATCHMENT (STREAMCAT) datasets for model development. Four empirical models—Multivariate regression, eXtreme Gradient boosting (XGBoost), Random Forest, Support Vector regression are compared. The first tier of models offers high accuracy but is limited to gauges, while the second-tier models offer a good compromise between accuracy and applicability across CONUS. We found XGBoost yielded R² of 0.67 and 0.55 for α, and 0.74 and 0.70 for β in the first and second-tier models. The spatial distribution of predicted α and β indicates sensitivity to elevation, aridity, and rainfall patterns.

Widely adopted models for estimating channel geometry attributes rely on simplistic power-law (hydraulic geometry) equations. This study presents a new generation of channel geometry models based on a hybrid approach combining traditional statistical methods (Multi-Linear Regression (MLR)) and advanced tree-based Machine Learning (ML) algorithms (Random Forest Regression (RFR) and eXtreme Gradient Boosting Regression (XGBR)), utilizing novel datasets. To achieve this, a new preprocessing method was applied to refine an extensive observational dataset, namely the HYDRoacoustic dataset supporting Surface Water Oceanographic Topography (HYDRoSWOT). This process improved data quality and identified observations representing bankfull and mean-flow conditions. A compiled dataset, combining the preprocessed dataset with datasets containing additional catchment attributes like the National Hydrography Dataset Plus (NHDplusv2.1), was then used to train a suite of models to predict channel width and depth under bankfull and mean-flow conditions. The analysis shows that tree-based ML algorithms outperform traditional statistical methods in accuracy and handling the data but face limitations in prediction capabilities for streams with characteristics outside the training range. Consequently, a hybrid method was selected, combining XGBR for streams within the dataset range and MLR for those outside it. Two tiers of models were developed for each attribute using discharges derived from distinct sources (HYDRoSWOT and NHDPlusV2.1, respectively), where the second tier of models offers applicability across approximately 2.6 million streams within NHDplusv2.1. Comprehensive independent evaluations are conducted to assess the capability of the developed models in providing stream/reach-averaged (rather than at-a-station) predictions for locations outside the training and testing datasets.