An evaluation of random forest based input variable selection methods for one month ahead streamflow forecasting

In the development of data-driven models for streamflow forecasting, choosing appropriate input variables is crucial. Although random forest (RF) has been successfully applied to streamflow forecasting for input variable selection (IVS), comparative analysis of different random forest-based IVS (RF-...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2024-11, Vol.14 (1), p.29766-12, Article 29766
Main Authors: Fang, Wei, Ren, Kun, Liu, Tiejun, Shang, Jianan, Jia, Shengce, Jiang, Xiangxiang, Zhang, Jie
Format: Article
Language:English
Subjects:
704/172
704/242
Algorithms
Artificial intelligence
Camelids
Comparative analysis
Feature selection
Forecasting
Humanities and Social Sciences
Hydroelectric power
Long short-term memory
Machine learning
multidisciplinary
Precipitation
Regression analysis
Science
Science (multidisciplinary)
Stream discharge
Stream flow
Streamflow forecasting
Time series
Variables
Water resources
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the development of data-driven models for streamflow forecasting, choosing appropriate input variables is crucial. Although random forest (RF) has been successfully applied to streamflow forecasting for input variable selection (IVS), comparative analysis of different random forest-based IVS (RF-IVS) methods is yet absent. Here, we investigate performance of five RF-IVS methods in four data-driven models (RF, support vector regression (SVR), Gaussian process regression (GP), and long short-term memory (LSTM)). A case study is implemented in the contiguous United States for one-month-ahead streamflow forecasting. Results indicate that RF-IVS methods enable to acquire enhanced performance in comparison to widely used partial Pearson correlation and conditional mutual information. Meanwhile, performance-based RF-IVS methods appear to be superior to test-based methods, and the test-based methods tend to select redundant variables. The RF with a forward selection strategy is finally recommended to connect with GP model as a promising combination having potential to yield favorable performance.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-024-81502-y