Pulse Brain · Growing Health Evidence Index
Tier 3 — Observational / field trialPeer-reviewed

Can artificial intelligence and data-driven machine learning models match or even replace process-driven hydrologic models for streamflow simulation?: A case study of four watersheds with different hydro-climatic regions across the CONUS

Taereem Kim, Tiantian Yang, Shang Gao, Lujun Zhang, Ziyu Ding, Xin Wen, Jonathan J. Gourley, Yang Hong

Journal of Hydrology · 2021

Read source ↗ All evidence

Summary

This comparative study evaluates whether data-driven machine learning approaches can match or exceed the predictive performance of established process-based hydrologic models for streamflow simulation. The analysis spans four watersheds across diverse hydro-climatic zones in the continental United States, suggesting that AI-driven methods may offer competitive or complementary alternatives to traditional mechanistic modelling approaches. The findings inform methodological choices in hydrological prediction and watershed management.

Regional applicability

Whilst the study focuses on United States watersheds, the methodological comparison between machine learning and process-based hydrologic models is transferable to United Kingdom river basin management and flood forecasting applications, particularly where diverse hydro-climatic conditions are encountered across different regions.

Key measures

Streamflow simulation accuracy, model performance metrics across different hydro-climatic regions

Outcomes reported

The study compared the performance of artificial intelligence and machine learning models against traditional process-driven hydrologic models for streamflow simulation across four watersheds in different hydro-climatic regions of the continental United States.

Theme
Measurement & metrics
Subject
Measurement methods & nutrient profiling
Study type
Research
Study design
Comparative modelling study
Source type
Peer-reviewed study
Status
Published
Geography
United States
System type
Other
DOI
10.1016/j.jhydrol.2021.126423
Catalogue ID
SNmqopettp-r5zbdx

Topic tags

Pulse AI · ask about this record

Dig deeper with Pulse AI.

Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.