Season Specific Sediment Rating Curve Development Using Machine Learning: A Case Study of the Mahakali River Basin, Nepal

Fuente: Zenodo
Enregistré dans:
Détails bibliographiques
Auteur principal: Katwal, kamal
Format: Recurso digital
Publié: Zenodo 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866901483015897088
author Katwal, kamal
author_facet Katwal, kamal
contents <p>Sediment transport in Himalayan rivers is highly dynamic, driven by intense monsoon rainfall, steep topography,<br>and fragile geology, posing challenges for water resource management and infrastructure sustainability. This study<br>develops season-specific sediment rating curves (SRCs) for Station 120 in the Mahakali River Basin, Nepal, using<br>machine learning (ML) models to improve sediment load estimation under varying hydrological conditions. Daily<br>discharge and suspended sediment data from 2007 to 2014 were analyzed across four seasons Pre-Monsoon,<br>Monsoon, Post-Monsoon, and Winter accounting for seasonal variability in sediment transport dynamics. Three ML<br>models K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF) were evaluated, and<br>the best-performing model for each season was selected based on R² and Mean Absolute Percentage Error (MAPE).<br>SVM outperformed others in Pre-Monsoon, Monsoon, and Winter seasons, while RF showed superior accuracy in Post-<br>Monsoon. Power-law SRCs were derived from predicted sediment concentrations, yielding equations: S=4.28×Q1.16<br>(Monsoon), S=1.21×Q1.19 (Post-Monsoon), S=3.81×Q1.17 (Pre-Monsoon), and S=826.88×Q −0.71 (Winter). Despite<br>improved accuracy, higher MAPE during the Monsoon season highlights the limitations of ML models in capturing<br>extreme events. The findings support the need for advanced deep learning approaches, as suggested by prior studies,<br>to better represent non-linear and time-dependent sediment processes. This research provides a robust, seasonally<br>adaptive framework for sediment load estimation in data-scarce Himalayan basins, supporting improved sediment<br>management.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18765917
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Season Specific Sediment Rating Curve Development Using Machine Learning: A Case Study of the Mahakali River Basin, Nepal
Katwal, kamal
Sediment rating curve (SRC), Machine learning, Seasonal variation, Suspended sediment load, Hydrological modeling, Mahakali River Basin, SVM, KNN, Random Forest
<p>Sediment transport in Himalayan rivers is highly dynamic, driven by intense monsoon rainfall, steep topography,<br>and fragile geology, posing challenges for water resource management and infrastructure sustainability. This study<br>develops season-specific sediment rating curves (SRCs) for Station 120 in the Mahakali River Basin, Nepal, using<br>machine learning (ML) models to improve sediment load estimation under varying hydrological conditions. Daily<br>discharge and suspended sediment data from 2007 to 2014 were analyzed across four seasons Pre-Monsoon,<br>Monsoon, Post-Monsoon, and Winter accounting for seasonal variability in sediment transport dynamics. Three ML<br>models K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF) were evaluated, and<br>the best-performing model for each season was selected based on R² and Mean Absolute Percentage Error (MAPE).<br>SVM outperformed others in Pre-Monsoon, Monsoon, and Winter seasons, while RF showed superior accuracy in Post-<br>Monsoon. Power-law SRCs were derived from predicted sediment concentrations, yielding equations: S=4.28×Q1.16<br>(Monsoon), S=1.21×Q1.19 (Post-Monsoon), S=3.81×Q1.17 (Pre-Monsoon), and S=826.88×Q −0.71 (Winter). Despite<br>improved accuracy, higher MAPE during the Monsoon season highlights the limitations of ML models in capturing<br>extreme events. The findings support the need for advanced deep learning approaches, as suggested by prior studies,<br>to better represent non-linear and time-dependent sediment processes. This research provides a robust, seasonally<br>adaptive framework for sediment load estimation in data-scarce Himalayan basins, supporting improved sediment<br>management.</p>
title Season Specific Sediment Rating Curve Development Using Machine Learning: A Case Study of the Mahakali River Basin, Nepal
topic Sediment rating curve (SRC), Machine learning, Seasonal variation, Suspended sediment load, Hydrological modeling, Mahakali River Basin, SVM, KNN, Random Forest
url https://doi.org/10.5281/zenodo.18765917