Abstract The Congo River is one of the least studied basins although it is the world’s second largest in size (~3.7 million km2) and discharge (Q) (~40,600 m3 s−1). Using remote sensing data and a hydrologic model, previous studies have successfully estimated Q of the Congo River at Brazzaville-Kinshasa stations with an accuracy of 10–40%. However, those studies depended on only a hydrologic model or estimated Q using remotely sensed data with a single rating curve. Recently, Kim et al. (2019) has also successfully applied the ensemble learning regression method, which is one of the machine learning techniques, to estimate Q (termed as ELQ) by linearly combining several rating curves over different locations. The study has estimated Q at the Brazzaville station with relative root-mean-square error (RRMSEs) of 7.17/5.53% for training/validation datasets whose temporal resolutions are 35-day for the period from 2002 to 2010. However, ELQ still requires in-situ Q data in order to train base learners and obtain their weights. In this study, we present a study estimating daily Q by applying ELQ with satellite altimetry data and the hydrologic-hydraulic Hillslope River Routing (HRR) model for the Congo River. We parameterized our model with the HRR-derived Q ( Q ^ HRR ) in training/validation datasets without the aid of in-situ Q. ELQ-derived Q ( Q ^ ELQ ) has not been calibrated or scaled with in-situ Q data in training/validation datasets. However, the HRR model has been calibrated to mean monthly historical gauge measurements (1903–1990). Q ^ HRR showed RRMSEs of 15.72/18.00% for training/validation datasets compared with daily in-situ Q data at the Kinshasa station spanning from November 2002 to September 2010. We used the Basic Ensemble Method ( f BEM ), which employs the uniformly distributed weights in ELQ process, that can provide improved estimates of Q. Q ^ ELQ using f BEM showed RRMSE of 11.32/9.05% on average for training/validation datasets. Moreover, we introduced the method generating more accurate ELQ using the ensemble mean of f BEM ( f BEM ) which yielded RRMSEs of 7–10%. This study demonstrates that ELQ can provide more accurate daily Q using satellite altimetry data and a hydrologic model for poorly gauged river basins.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Estimating discharges for poorly gauged river basin using ensemble learning regression with satellite altimetry data and a hydrologic model


    Beteiligte:
    Kim, Donghwan (Autor:in) / Lee, Hyongki (Autor:in) / Beighley, Edward (Autor:in) / Tshimanga, Raphael M. (Autor:in)

    Erschienen in:

    Advances in Space Research ; 68 , 2 ; 607-618


    Erscheinungsdatum :

    2019-08-13


    Format / Umfang :

    12 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    EVALUATION OF THE BALTIC SEA BASIN USING SATELLITE ALTIMETRY DATA

    Pajak, Katarzyna / Birylo, Monika | British Library Conference Proceedings | 2016


    Hydro-climatology study of the Ogooué River basin using hydrological modeling and satellite altimetry

    Bogning, Sakaros / Frappart, Frederic / Paris, Adrien et al. | Elsevier | 2020


    Satellite altimetry

    Bryan, J. W. | NTRS | 1970


    Indus river water level monitoring using satellite radar altimetry

    Zaidi, Arjumand Z. / Vignudelli, Stefano / Khero, Zarif et al. | Elsevier | 2020


    Satellite Altimetry

    J. W. Bryan | NTIS | 1970