Checking for non-preferred file/folder path names (may take a long time depending on the number of files/folders) ...

Dataset for Predicting Event-Scale Runoff Coefficients Using Support Vector Regression


Authors:
Owners: This resource does not have an owner who is an active HydroShare user. Contact CUAHSI (help@cuahsi.org) for information on this resource.
Type: Resource
Storage: The size of this resource is 8.4 MB
Created: Jul 07, 2026 at 2:28 a.m. (UTC)
Last updated: Jul 07, 2026 at 10:09 p.m. (UTC) (Metadata update)
Published date: Jul 07, 2026 at 10:09 p.m. (UTC)
DOI: 10.4211/hs.ed81b766ae6a4c949b902935fc2ee05f
Citation: See how to cite this resource
Content types: CSV Content 
Sharing Status: Published
Views: 49
Downloads: 3
+1 Votes: Be the first one to 
 this.
Comments: No comments (yet)

Abstract

The event-based runoff coefficient (ERC) is a pivotal hydrological metric that quantifies the relationship between rainfall and resultant runoff, offering valuable insights for effective water resource management and flood risk assessment. This study investigates the performance of Support Vector Regression (SVR) in predicting ERC and the impact of temporal and spatial controls on the ERC prediction. Utilizing data from the Ohio and Mid-Atlantic region, ERC predictions are derived from historical rainfall and runoff data using SVR. Results suggest that SVR demonstrates promising predictive accuracy, with model performance varying by temporal and spatial controls. While previous studies using models such as random forests, gradient-boosted decision trees (GBDT), or regression trees reported R² values up to 0.67, the present study attained R² values exceeding this benchmark for many watersheds, with the highest R² reaching 0.89. Temporally, watersheds that are predominantly influenced by climatic controls exhibit greater predictive difficulty compared to those governed by pre-event controls. Spatially, watersheds with extensive urbanization and higher elevations generally yield less accurate predictions, likely due to increased complexity in runoff dynamics. Additional research is needed to further refine the model’s adaptability to urban and mountainous environments to enhance predictive robustness across diverse landscapes.

Subject Keywords

Content

How to Cite

Xu, T. (2026). Dataset for Predicting Event-Scale Runoff Coefficients Using Support Vector Regression, HydroShare, https://doi.org/10.4211/hs.ed81b766ae6a4c949b902935fc2ee05f

This resource is shared under the Creative Commons Attribution CC BY.

http://creativecommons.org/licenses/by/4.0/
CC-BY

Comments

There are currently no comments

New Comment

required