Comparing random forest flood frequency analysis with regional flood frequency, Creager and SCS in Doab-Qazanchi, Kermanshah
Due to climate change and rising global temperature, the occurrence of extreme floods and drought events has intensified. In this regard, in 2019, heavy rainfall occurred in Kermanshah province. The Gharasoo river runs through the city of Kermanshah in western Iran. The Doab-Qazanchi area is located...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Razi University
2025-06-01
|
| Series: | Journal of Applied Research in Water and Wastewater |
| Subjects: | |
| Online Access: | https://arww.razi.ac.ir/article_3775_d8a9243c082541e78f59092b72d3d24f.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Due to climate change and rising global temperature, the occurrence of extreme floods and drought events has intensified. In this regard, in 2019, heavy rainfall occurred in Kermanshah province. The Gharasoo river runs through the city of Kermanshah in western Iran. The Doab-Qazanchi area is located on the Gharasoo River at the crossroads of the Razavar and mereg Rivers to the Gharasoo River and there is no hydrometric station in this area. In this research, floods with different return periods of 2, 5, 20, 50, 100, 200, 500 and 1000 years with Creager and regional flood frequency analysis (RFFA), and the random forest machine learning method using the physical and hydrological characteristics of the surrounding watersheds are predicted. The SCS method was implemented for the flood on 03/04/2019 and it showed that the occurred flood is equivalent to a 25-year flood in this region. The predicted values estimated a lower discharge than the soil conservation service (SCS) method. The random forest (RF) method, as a machine learning method compared to old statistical methods, has a good performance in predicting the flood discharge using the physical and hydrological indicators of the catchment area, and by determining the priority of different features, it predicts the flood discharge well. |
|---|---|
| ISSN: | 2476-6283 |