Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 7 min ago
Peer-reviewedCC BY 4.0Scientific Data

GLORIF1, a global river flow dataset created by integrating process-based modelling and machine learning

  • Sümeyye Büşra Işık1,2,3
  • Oriol Pomarol Moya1
  • Michele Magni1
  • Madlene Nussbaum1
  • Derek Karssenberg1
  • Edwin H. Sutanudjaja1
  1. 1Department of Physical Geography, Faculty of Geosciences, Utrecht University, Utrecht, The Netherlands
  2. 2Istanbul Technical University, Istanbul, Türkiye
  3. 3State Hydraulic Works, Ankara, Türkiye
Read full textDOICite

Abstract

Accurate streamflow data are essential for managing water resources and enhancing climate resilience worldwide. Yet, existing global streamflow datasets often lack accuracy or rely on sparse observations. To address these challenges, we present GLORIF1 (GLObal RIver Flow version 1), a comprehensive monthly river discharge dataset spanning 1979-2019. GLORIF1 is generated using a hybrid modeling approach that integrates the PCR-GLOBWB (PCRaster GLOBal Water Balance) hydrological model with a Random Forest (RF) algorithm. The dataset is trained on observation data from the Global River Discharge (GRDC) and validated with the independent data from the GSIM (Global Streamflow Indices and Metadata Archive) and RSEG (Remote Sensing-based Extension for the GRDC). With its global coverage and public accessibility, GLORIF1 can be used to support more accurate hydrological and water-related studies, making it a valuable resource for global hydrology studies.

Related

  1. Metagovernance as scaffolding: strategies promoting co-created learning and innovation for sustainability transitions
    Alexander L. Q. Chen-Florea, Eva Sørensen, Mohd Sallehuddin Mat Noor +2
    Environmental Innovation and Societal TransitionsPeer-reviewedCC BY5 citedClimate scienceOpenAlex
  2. Dataset and methodological framework for land-use change scenario modelling in Uruguay using the Land Change Modeler.
    Melanie Schweikart, Leonardo R Ramírez, Ina Säumel
    Data in briefPeer-reviewedCC BYFull textClimate scienceEurope PMC
  3. Integrating ecohydrological modelling and participatory processes to co-design multifunctional forest management
    Javier Pérez-Romero, Javier Pérez-Romero, Laura Blanco-Cano +5
    Frontiers in Forests and Global ChangePeer-reviewedCC BYFull textEnvironmental science & pollutionDOAJ
  4. Machine-learning modelling of regional landslide susceptibility in eThekwini, South Africa
    Cher Petersen, Paidamwoyo Mhangara, Laven Naidoo +1
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEnvironmental science & pollutionCrossref
  5. Integrating rapid 3D structural validation into interpretation: forward modelling of the Katnook Graben, Otway Basin
    Paul John Lyon, Peter J Boult
    EarthArXivPreprintCC BY 4.0Full textGeophysics & seismologyEarthArXiv

Cite

BibTeXRIS
BibTeX
@article{isık2026glorif1,
  title = {{GLORIF1, a global river flow dataset created by integrating process-based modelling and machine learning}},
  author = {Sümeyye Büşra Işık and Oriol Pomarol Moya and Michele Magni and Madlene Nussbaum and Derek Karssenberg and Edwin H. Sutanudjaja},
  journal = {Scientific Data},
  year = {2026},
  month = jul,
  doi = {10.1038/s41597-026-07658-6},
  url = {https://doi.org/10.1038/s41597-026-07658-6},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - GLORIF1, a global river flow dataset created by integrating process-based modelling and machine learning
AU  - Sümeyye Büşra Işık
AU  - Oriol Pomarol Moya
AU  - Michele Magni
AU  - Madlene Nussbaum
AU  - Derek Karssenberg
AU  - Edwin H. Sutanudjaja
PY  - 2026
DA  - 2026/07/04
JO  - Scientific Data
DO  - 10.1038/s41597-026-07658-6
UR  - https://doi.org/10.1038/s41597-026-07658-6
AB  - Accurate streamflow data are essential for managing water resources and enhancing climate resilience worldwide. Yet, existing global streamflow datasets often lack accuracy or rely on sparse observations. To address these challenges, we present GLORIF1 (GLObal RIver Flow version 1), a comprehensive monthly river discharge dataset spanning 1979-2019. GLORIF1 is generated using a hybrid modeling approach that integrates the PCR-GLOBWB (PCRaster GLOBal Water Balance) hydrological model with a Random Forest (RF) algorithm. The dataset is trained on observation data from the Global River Discharge (GRDC) and validated with the independent data from the GSIM (Global Streamflow Indices and Metadata Archive) and RSEG (Remote Sensing-based Extension for the GRDC). With its global coverage and public accessibility, GLORIF1 can be used to support more accurate hydrological and water-related studies, making it a valuable resource for global hydrology studies.
SN  - 2052-4463
ER  -