Application of random forest (RF) for flood levels prediction in Lower Ogun Basin, Nigeria

O. O. Aiyelokun (), O. D. Aiyelokun and O. A. Agbede
Additional contact information
O. O. Aiyelokun: University of Ibadan
O. D. Aiyelokun: Olivearc Solutions
O. A. Agbede: University of Ibadan

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2023, vol. 119, issue 3, No 43, 2179-2195

Abstract: Abstract This study evaluates the performance of random forest (RF) for predicting flood levels in the Lower Ogun Basin, Southwest Nigeria. Daily flood levels for a period of 36 years (1981 to 2016), recorded at Mokoloki weir, were obtained from the Ogun–Oshun River Basin Development Authority (OORBDA). Descriptive statistics were employed to provide concise information on the flood levels, and trend and autocorrelation assessments were performed using the Mann–Kendall test and the Ljung–Box test, respectively, at 95% confidence level. Antecedent daily flood levels of up to 7 days were selected as input features for the RF model to predict daily flood levels. To develop the RF model, the dataset was divided into train (70%), validation (15%), and test (15%). The performance of the RF model was evaluated using Mean Absolute Error (MAE), coefficient of determination (R2), Nash–Sutcliffe Efficiency Coefficient (NSEC), and Kling-Gupta efficiency (KGE). The study reveals that the highest flood level was 9.5 m, while 75% of the records were less or equal to 7.04 m. The flood level had a significant positive trend (tau = 0.19, 2-sided p value

Keywords: Early warning systems; Flood risk management; Random forest; Computational modeling (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11069-023-06211-7 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:nathaz:v:119:y:2023:i:3:d:10.1007_s11069-023-06211-7

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11069

DOI: 10.1007/s11069-023-06211-7

Access Statistics for this article

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards is currently edited by Thomas Glade, Tad S. Murty and Vladimír Schenk

More articles in Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards from Springer, International Society for the Prevention and Mitigation of Natural Hazards
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().