Home › Categories › Science & Nature› Hydrology Modeling

Hydrology Modeling.pdf

hess-14-1943-2010.pdf

🔗 Source: hess.copernicus.org

📊 Size: 1.24 MB

📄 Pages: 19 pages

⬇️ Downloads: 223

Summary

Researchers applied various data-driven modeling techniques to five hydrology case studies, including actual evapotranspiration, soil moisture, and rainfall-runoff. Techniques used included neural networks, genetic programming, evolutionary polynomial regression, support vector machines, M5 model trees, K-nearest neighbors, and multiple linear regression. Results showed that genetic programming was the most successful technique, while neural networks were sub-optimal for some case studies. The performance of support vector machines was sensitive to kernel choice, and M5 model trees performed well with linear and semi-linear data. K-nearest neighbors was also successful in linear situations. The study highlighted the importance of selecting the appropriate modeling technique for each specific hydrological application.

Download File

Description

Researchers applied various data-driven modeling techniques to five hydrology case studies, including actual evapotranspiration, soil moisture, and...

Technical Information

File Format: PDF
File Size: 1.24 MB
Pages: 19
Language: EN
Total Downloads: 223
Last Updated: 2 days ago

Document Overview

This PDF document about Hydrology Modeling provides comprehensive information and guidance. Whether you're a beginner or advanced user, this resource offers valuable insights into Hydrology Modeling.