A Machine Learning-Reconstructed Dataset of River Discharge, Temperature, and Heat Flux into the Arctic Ocean.

ABSTRACT: Arctic rivers deliver 11% of the global river discharge volume into the Arctic Ocean, influencing ocean circulation, sea ice, and coastal ecosystems. Our understanding of these patterns is limited by substantial data gaps. To address this, we present the Reconstructed Arctic-draining river DIscharge and Temperature (RADIT) dataset, a comprehensive record of reconstructed daily discharge, temperature, and heat flux for 25 major Arctic rivers from 1950 to 2023. Based on machine learning regression methods and ERA5-Land reanalysis data, we designed distinct reconstruction frameworks for discharge and temperature, considering the different characteristics of the observational data. We achieved high reconstruction accuracy, with median Nash-Sutcliffe efficiency (NSE) values of 0.861 for dischar

SUBMITTER: Wang Z 

PROVIDER: S-EPMC12271462 | biostudies-literature | 2025 Jul

REPOSITORIES: biostudies-literature