EconPapers    
Economics at your fingertips  
 

River Flow Modeling in Semi-Arid and Humid Regions Using an Integrated Method Based on LARS-WG and LSTM Models

Kiyoumars Roushangar (kroshangar@yahoo.com) and Sadegh Abdelzad
Additional contact information
Kiyoumars Roushangar: University of Tabriz
Sadegh Abdelzad: University of Tabriz

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), 2023, vol. 37, issue 10, No 2, 3813-3831

Abstract: Abstract River flow or runoff is an important water flux that can pose great threats to water security because of changes in its timing, magnitude, and seasonality. In this study, runoff variations in two different climate conditions, including the semi-arid and humid climates, were assessed using an integrated method based on the LARS-WG and Long Short-term Memory (LSTM) models. Runoff variations were simulated for the base period of 2001–2020 and it was forecasted for the future period of 2021–2040. Climatic parameters were evaluated using the LARS-WG statistical model for the selected stations under the RCPs scenarios. Then, outputs obtained under the RCPs scenarios, including minimum temperature, maximum temperature, precipitation, and sunshine hours, were considered as the input of the LSTM model. Results showed that the amount of mean runoff in spring for semi-arid areas and in spring and winter for humid areas will decrease in the next twenty years compared to the base period. For other seasons in both climates, the amount of runoff will increase. The maximum rainfall increase under the RCP8.5 scenario was 66.66 mm for the humid region and 30.06 mm for the semi-arid region compared to the base period. Also, the maximum temperature increase for the semi-arid region was 1.18 °C under the RCP8.5 scenario, and for the humid region was 1.07 °C under the RCP2.6 scenario. Results showed that the LSTM method can successfully model the future river flow values and river flow related to the previous day has a significant impact on the modeling process.

Keywords: Deep learning method; LARS-WG; Runoff; Semi-arid region; Temperature (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11269-023-03527-8 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:waterr:v:37:y:2023:i:10:d:10.1007_s11269-023-03527-8

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11269

DOI: 10.1007/s11269-023-03527-8

Access Statistics for this article

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) is currently edited by G. Tsakiris

More articles in Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) from Springer, European Water Resources Association (EWRA)
Bibliographic data for series maintained by Sonal Shukla (sonal.shukla@springer.com) and Springer Nature Abstracting and Indexing (indexing@springernature.com).

 
Page updated 2024-12-29
Handle: RePEc:spr:waterr:v:37:y:2023:i:10:d:10.1007_s11269-023-03527-8