A CONUS-wide Monthly Baseflow Dataset (1982-2022) for HUC8 Basins Derived from Random Forest Modeling

Read full text
Authors: Qiang Li, Hongli Chen
Cited by: 0

Abstract

This dataset provides continuous monthly baseflow estimates for 2,185 Hydrologic Unit Code 8 (HUC8) basins across the contiguous United States (CONUS) spanning 41 years from 1982 to 2022. The data were generated using an optimized Random Forest machine learning model trained on observed baseflow measurements, incorporating 31 predictor variables including static watershed attributes (topography, soil properties), dynamic environmental variables (climate, vegetation, snow dynamics), and human activity indicators (land use proportions).

Fields of Study & Subjects

Hydrology and Watershed Management Studies Hydrological Forecasting Using AI Environmental Monitoring and Data Management

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
15 January 2026
Document type
Dataset