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...

Full description

Saved in:
Bibliographic Details
Main Authors: Zihan Wang, Fengming Hui, Xiao Cheng
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05582-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849766998466101248
author Zihan Wang
Fengming Hui
Xiao Cheng
author_facet Zihan Wang
Fengming Hui
Xiao Cheng
author_sort Zihan Wang
collection DOAJ
description 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 discharge and 0.906 for temperature. The RADIT dataset, with extensive spatial and temporal coverage, is a valuable resource for understanding Arctic hydrology and its response to climate change. It will improve Arctic freshwater budget quantification, climate model calibrations, and assessments of river impacts on the Arctic Ocean, enhancing our understanding of the role of the Arctic Ocean in the global climate system.
format Article
id doaj-art-88ce4c22c4764bfdb22f05422bddf909
institution DOAJ
issn 2052-4463
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-88ce4c22c4764bfdb22f05422bddf9092025-08-20T03:04:22ZengNature PortfolioScientific Data2052-44632025-07-0112111710.1038/s41597-025-05582-9A Machine Learning-Reconstructed Dataset of River Discharge, Temperature, and Heat Flux into the Arctic OceanZihan Wang0Fengming Hui1Xiao Cheng2School of Geospatial Engineering and Science, Sun Yat-sen University, and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)School of Geospatial Engineering and Science, Sun Yat-sen University, and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)School of Geospatial Engineering and Science, Sun Yat-sen University, and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)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 discharge and 0.906 for temperature. The RADIT dataset, with extensive spatial and temporal coverage, is a valuable resource for understanding Arctic hydrology and its response to climate change. It will improve Arctic freshwater budget quantification, climate model calibrations, and assessments of river impacts on the Arctic Ocean, enhancing our understanding of the role of the Arctic Ocean in the global climate system.https://doi.org/10.1038/s41597-025-05582-9
spellingShingle Zihan Wang
Fengming Hui
Xiao Cheng
A Machine Learning-Reconstructed Dataset of River Discharge, Temperature, and Heat Flux into the Arctic Ocean
Scientific Data
title A Machine Learning-Reconstructed Dataset of River Discharge, Temperature, and Heat Flux into the Arctic Ocean
title_full A Machine Learning-Reconstructed Dataset of River Discharge, Temperature, and Heat Flux into the Arctic Ocean
title_fullStr A Machine Learning-Reconstructed Dataset of River Discharge, Temperature, and Heat Flux into the Arctic Ocean
title_full_unstemmed A Machine Learning-Reconstructed Dataset of River Discharge, Temperature, and Heat Flux into the Arctic Ocean
title_short A Machine Learning-Reconstructed Dataset of River Discharge, Temperature, and Heat Flux into the Arctic Ocean
title_sort machine learning reconstructed dataset of river discharge temperature and heat flux into the arctic ocean
url https://doi.org/10.1038/s41597-025-05582-9
work_keys_str_mv AT zihanwang amachinelearningreconstructeddatasetofriverdischargetemperatureandheatfluxintothearcticocean
AT fengminghui amachinelearningreconstructeddatasetofriverdischargetemperatureandheatfluxintothearcticocean
AT xiaocheng amachinelearningreconstructeddatasetofriverdischargetemperatureandheatfluxintothearcticocean
AT zihanwang machinelearningreconstructeddatasetofriverdischargetemperatureandheatfluxintothearcticocean
AT fengminghui machinelearningreconstructeddatasetofriverdischargetemperatureandheatfluxintothearcticocean
AT xiaocheng machinelearningreconstructeddatasetofriverdischargetemperatureandheatfluxintothearcticocean