Improving Short-term Daily Streamflow Forecasting Using an Autoencoder Based CNN-LSTM Model

Umar Muhammad Mustapha Kumshe, Zakariya Muhammad Abdulhamid, Baba Ahmad Mala, Tasiu Muazu, Abdullahi Uwaisu Muhammad (), Ousmane Sangary, Abdoul Fatakhou Ba, Sani Tijjani, Jibril Muhammad Adam, Mosaad Ali Hussein Ali, Aliyu Uthman Bello and Muhammad Muhammad Bala
Additional contact information
Umar Muhammad Mustapha Kumshe: Hohai University
Zakariya Muhammad Abdulhamid: Northeastern University
Baba Ahmad Mala: Huazhong University of Science and Technology
Tasiu Muazu: Hohai University
Abdullahi Uwaisu Muhammad: Hohai University
Ousmane Sangary: Hubei University of Technology
Abdoul Fatakhou Ba: Hohai University
Sani Tijjani: Kano State Polytechnic
Jibril Muhammad Adam: Federal University Dutse
Mosaad Ali Hussein Ali: Assiut University
Aliyu Uthman Bello: Federal University Dutse
Muhammad Muhammad Bala: Kano University of Science and Technology

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), 2024, vol. 38, issue 15, No 7, 5973-5989

Abstract: Abstract Streamflow forecasting is vital for managing water resources, such as flood control, agriculture planning, hydropower generation, environmental management, drought management, and water quality management. Motivated by the success of artificial intelligence models for hydrological applications, this study proposes a model that integrates an autoencoder, the Convolutional Neural Networks (CNN), and the Long Short Term Memory (LSTM) networks. Thirty years daily dataset were served to the Autoencoder Convolutional Neural Network Long Short Term Memory (AE-CNN-LSTM) and the baseline models. To evaluate the model's accuracy, 80% of the dataset was used for training and the remaining 20% was used to test the performance of these models. Statistical metrics, for instance, the Root Mean Squared Error (RMSE), the Mean Absolute Error (MAE), the Mean Absolute Percentage Error (MAPE), the Nash–Sutcliffe Efficiency (NSE), and the Coefficient of determination (R2) were employed to evaluate the model’s performance. In terms of train RMSE, test RMSE, train MAE, test MAE, train MAPE, test MAPE, train NSE, test NSE, train R2, and test R2, the proposed model significantly obtained the best results with values of 2.6299, 2.7971, 0.1676, 0.1881, 16.76, 18.81, 0.98, 0.97, 0.98, and 0.96, respectively.

Keywords: Ala river; Autoencoder; Deep learning; Hydrology; LSTM; Streamflow (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11269-024-03937-2 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:38:y:2024:i:15:d:10.1007_s11269-024-03937-2

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

DOI: 10.1007/s11269-024-03937-2

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 () and Springer Nature Abstracting and Indexing ().