Streamflow forecasting using a hybrid LSTM-PSO approach: the case of Seyhan Basin

Bulent Haznedar (), Huseyin Cagan Kilinc (), Furkan Ozkan () and Adem Yurtsever ()
Additional contact information
Bulent Haznedar: Gaziantep University
Huseyin Cagan Kilinc: Istanbul Aydın University
Furkan Ozkan: Hasan Kalyoncu University
Adem Yurtsever: İstanbul University-Cerrahpaşa

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2023, vol. 117, issue 1, No 29, 701 pages

Abstract: Abstract The conditions which affect the sustainability of water cause a number of serious environmental and hydrological problems. Effective and correct management of water resources constitutes an effective and important issue among scales. In this sense, a precise estimation of streamflow time series in rivers is one of the most important issues in optimal management of surface water resources. Therefore, a hybrid method combining particle swarm algorithm (PSO) and long short-term memory networks (LSTM) are proposed to predict flow with data obtained from different flow measurement stations. In this respect, the data gathered from three Flow Measurement Stations (FMS) from Zamanti and Eğlence rivers located on Seyhan Basin are utilized. Besides, the proposed LSTM-PSO method is compared to an adaptive neuro-fuzzy inference system (ANFIS) and the LSTM benchmark model to demonstrate the performance achievement of proposed method. The prediction performances of the developed hybrid model and the others are tested on the determined stations. The forecasting performances of the models are determined with RMSE, MAE, MAPE, SD, and R2 metrics. The comparison results indicated that the LSTM-PSO method provides highest results with values of R2 (≈ 0.9433), R2 (≈ 0.6972), and R2 (≈ 0.9273) for the Değirmenocağı, Eğribük, and Ergenusagi FMS data, respectively.

Keywords: Forecasting; Streamflow; ANFIS; LSTM; PSO; Time Series (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11069-023-05877-3 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:117:y:2023:i:1:d:10.1007_s11069-023-05877-3

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

DOI: 10.1007/s11069-023-05877-3

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 ().