Enhanced early warning of extreme river discharge events in the Yangtze River Basin using atmospheric circulation signals
We develop DetRF, a machine learning model that integrates anomaly detection with a Balanced Random Forest ensemble. The model was trained and validated using ERA5 reanalysis data from 2000–2019 and independently tested with ERA5 data from 2020–2024. Its early warning performance was assessed using precipitation and runoff observations.
Authors
- Chunlei Gu (ORCID: https://orcid.org/0000-0001-7019-2392)
- Xiaojun She (ORCID: https://orcid.org/0000-0003-0605-8820)
- Yinghong Jing (ORCID: https://orcid.org/0000-0001-5788-5418)
- Yao Li (ORCID: https://orcid.org/0000-0001-8745-191X)
- xiaoke xu
- Anning Huang
- Yong Wang
- Lifu Zhang
Publication Details
- Journal
- International Journal of Applied Earth Observation and Geoinformation
- Published
- 2026-09-22
- DOI
- https://doi.org/10.1016/j.jag.2026.105590
- Primary Topic
- Hydrological Forecasting Using AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00