Boulmaiz T. auteur aut IRD Hafsi R. auteur aut IRD Guermoui M. auteur aut IRD Boutaghane H. auteur aut IRD Abida H. auteur aut IRD Saber M. auteur aut IRD Kantoush S. A. auteur aut IRD Ferkous K. auteur aut IRD Tramblay Yves auteur aut IRD text journalArticle eng text/pdf born digital access A new pre-processing methodology for gridded Satellite Precipitation Products (SPPs) is developed to improve the performance of Machine Learning (ML) algorithms for runoff prediction. The developed approach was applied to capture the rainfall patterns, and to select relevant input data. This approach was tested using the FeedForward Neural Network (FFNN) and the Extreme Learning Machine (ELM) given their flexibility and ability in hydrological modelling. The methodology was tested in a semiarid transboundary watershed located in North Africa (Algeria, Tunisia) with the Integrated MultisatellitE Retrievals for Global Precipitation Measurement (GPMIMERG) and the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) products. The results demonstrate the effectiveness of the proposed approach using all employed SPPs. In terms of Nash-Sutcliffe efficiency, the suggested pre-processing technique improved the prediction ability of FFNN by 13%, and of ELM by 15%, which highlights how pre-processing techniques significantly enhance ML models with SPP data. specialized machine learning IMERG PERSIANN pre-processing rainfall runoff satellite precipitation products ALGERIE TUNISIE 062 020 126 69 10 1356-1370 2024 0262-6667 https://www.documentation.ird.fr/hor/fdi:010091171 10.1080/02626667.2024.2378108 0262-6667 [F B010091171] https://www.documentation.ird.fr/hor/fdi:010091171 https://www.documentation.ird.fr/intranet/publi/2024-09/010091171.pdf Accès réservé (Intranet de l'IRD) IRD - Base Horizon / Pleins textes 2024-09-27 2024-09-27 fdi:010091171 fre