Short-term streamflow forecasting using the feature-enhanced regression model

Bai, Yun (avtor), Bezak, Nejc (avtor), Lebar, Klaudija (avtor), Klun, Mateja (avtor), Zhang, Jin (avtor)

Reservoir inflow forecasting is extremely important for the management of a reservoir. In practice, accurate forecasting depends on the feature learning performance. To better address this issue, this paper proposed a feature-enhanced regression model (FER), which combined stack autoencoder (SAE) with long short-term memory (LSTM). This model had two constituents: (1) The SAE was constructed to learn a representation as close as possible to the original inputs. Through deep learning, the enhanced feature could be captured sufficiently. (2) The LSTM was established to simulate the mapping between the enhanced features and the outputs. Under recursive modeling, the patterns of correlation in the short term and dependence in the long term were considered comprehensively. To estimate the performance of the FER model, two historical daily discharge series were investigated, i.e., the Yangtze River in China and the Sava Dolinka River in Slovenia. The proposed model was compared with other machine-learning methods (i.e., the LSTM, SAE-based neural network, and traditional neural network). The results demonstrated that the proposed FER model yields the best forecasting performance in terms of six evaluation criteria. The proposed model integrates the deep learning and recursive modeling, and thus being beneficial to exploring complex features in the reservoir inflow forecasting. Moreover, for smaller catchments with significant torrential characteristics, more data are needed (e.g., at least 20 years) to effectively train the model and to obtain accurate flood-forecasting results.

• Jezik: Angleški jezik
• Ključne besede: long short-term memory, stack autoencoder, feature enhanced, daily reservoir inflow, forecast
• Vrsta gradiva: Znanstveno delo
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FGG - Fakulteta za gradbeništvo in geodezijo
• Status publikacije: V tisku
• Različica publikacije: Recenzirani rokopis
• Založnik: Springer Nature B. V.
• Leto izida: 2019
• Št. strani: Str. 4783-4797
• Številčenje: Letn.33, št. nov.
• PID: 20.500.12556/RUL-114378
• UDK: 626/627
• ISSN pri članku: 0920-4741
• DOI: 10.1007/s11269-019-02399-1
• COBISS.SI-ID: 8969057
• Datum objave v RUL: 24.02.2020

Gradivo je del revije

• Naslov: Water resources management
• Skrajšan naslov: Water resour. manag.
• Založnik: Reidel
• ISSN: 0920-4741
• COBISS.SI-ID: 512526105

Licence

• Licenca: CC BY-NC-ND 4.0, Creative Commons Priznanje avtorstva-Nekomercialno-Brez predelav 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by-nc-nd/4.0/deed.sl
• Opis: Najbolj omejujoča licenca Creative Commons. Uporabniki lahko prenesejo in delijo delo v nekomercialne namene in ga ne smejo uporabiti za nobene druge namene.
• Začetek licenciranja: 24.02.2020

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: hidrotehnika, dolgotrajni kratkoročni spomin, avtoenkoder, vhodna spremenljivka, dnevni vtok v rezervoar, napovedi

Projekti

• Financer: ARRS - Agencija za raziskovalno dejavnost Republike Slovenije
• Številka projekta: P2-0180
• Naslov: Vodarstvo in geotehnika: orodja in metode za analize in simulacije procesov ter razvoj tehnologij.