Masked Training for Realtime Resilient Streamflow Forecasting: A Spatial-Temporal ML Approach for Real-World Operational Settings - Experimental Dataset
Abstract
This is the experimental dataset used in the paper "Masked Training for Realtime Resilient Streamflow Forecasting: A Spatial-Temporal ML Approach for Real-World Operational Settings", serving the purpose of open-science compliance and facilitate reproducibility in hydrology research. The dataset comprise of: (i). raw discharge data acquired from USGS Water Service API named "usgs_discharge.csv", (ii). the processed discharge data from the raw file as described in the paper named "processed_discharge.csv", (iii). the raw basin characteristics data acquired using StreamStats API named "basin_characteristics.csv", and (iv). the processed basin characteristics data named "processed_basin_chars.csv".
Fields of Study & Subjects
Hydrological Forecasting Using AI
Hydrology and Watershed Management Studies
Traffic Prediction and Management Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 24 February 2026
- Language
- EN
- Document type
- Dataset