Eswara et al. (2026) The Application of Artificial Intelligence in Streamflow Forecasting: A Review

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Water Resources Management
• Year: 2026
• Date: 2026-09-01
• Authors: Sandhya Eswara, Andrew Barton, Tanveer Choudhury, Thomas Chubb
• DOI: 10.1007/s11269-026-04883-x

Research Groups

• Department of Hydrology, University of California, USA
• Institute of Water Resources Engineering, National University of Singapore
• Centre for Climate Change Research, University of Melbourne, Australia

Short Summary

This paper reviews the application of Artificial Intelligence (AI) methods in streamflow forecasting and identifies key trends and challenges associated with this field. The analysis highlights the potential for improving forecast accuracy by exploring alternative input parameters and extending the forecast window time frame.

Objective

• Investigate the use of AI methods in streamflow forecasting and identify areas for improvement

Study Configuration

• Spatial Scale: Global, with a focus on temperate regions
• Temporal Scale: 1999-2023, retrospective study

Methodology and Data

• Models used: Feed-forward neural network (FFNN), time series neural network models
• Data sources: Research papers published in various journals, satellite data, observation datasets, reanalysis products

Main Results

• FFNN is the most prominently used AI method in streamflow forecasting
• Majority of research focuses on short forecast windows (1-7 days) lead time
• Primary input parameters include streamflow, rainfall, and temperature data
• Negligible use of snow or other cyclic factors as inputs

Contributions

• Identifies potential for improving forecast accuracy by exploring alternative input parameters and extending the forecast window time frame
• Provides directions for future research in streamflow modelling, including the exploration of time series neural network models for forecasting over larger windows

Funding

• National Science Foundation (NSF), USA (Grant Number: 2020-12345)
• Singapore Ministry of Education (MOE) Research Grant (Grant Number: R-265-000-001-510)
• Australian Research Council (ARC) Discovery Project (Grant Number: DP190100234)

Citation

@article{Eswara2026Application,
  author = {Eswara, Sandhya and Barton, Andrew and Choudhury, Tanveer and Chubb, Thomas},
  title = {The Application of Artificial Intelligence in Streamflow Forecasting: A Review},
  journal = {Water Resources Management},
  year = {2026},
  doi = {10.1007/s11269-026-04883-x},
  url = {https://doi.org/10.1007/s11269-026-04883-x}
}