Unveiling the Potential of Hybrid Deep Learning Algorithm in Streamflow Projection DOI Open Access
Rishith Kumar Vogeti,

Rahul Jauhari,

Bhavesh Rahul Mishra

et al.

IOP Conference Series Earth and Environmental Science, Journal Year: 2024, Volume and Issue: 1409(1), P. 012001 - 012001

Published: Nov. 1, 2024

Abstract The present study aims to analyze the potential of a hybrid deep learning algorithm, GRU-RNN-LSTM, for mimicking streamflow and is evaluated using Kling Gupta Efficiency. case chosen was Lower Godavari Basin. Grid search tuning conducted algorithm. GRU-RNN-LSTM has shown good performance having Efficiency values 0.785, 0.77 in training testing segments respectively, further utilized projection by making use scenario, Shared Socioeconomic Pathway 585 (SSP585). highest, Lowest, Average streamflows expected are 2624 m 3 /s, 599.03 703.36 /s respectively. These projections could assist water resources planners initiating long-term measures.

Language: Английский

A Comparative Assessment of Machine Learning and Deep Learning Models for the Daily River Streamflow Forecasting DOI

Malihe Danesh,

Amin Gharehbaghi, Saeid Mehdizadeh

et al.

Water Resources Management, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 29, 2024

Language: Английский

Citations

6
An approach on the estimation and temporal interaction of runoff: the band similarity method DOI Creative Commons
Volkan Yılmaz, Cihangir Köyceğiz, Meral Büyükyıldız

et al.

Journal of Water and Climate Change, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 30, 2024

ABSTRACT This study is based on the investigation of performance band similarity (BS) method, which quite new in literature, prediction flow and determining memory properties phenomenon. For this purpose, models for monthly data Sarız station, located Seyhan Basin Türkiye, were produced first with particle swarm optimization (PSO) algorithm. Second, these used BS method to create BSPSO approach. Then, was made same set support vector regression (SVR). In test period, standalone PSO, BSPSO, SVR achieved most successful Nash–Sutcliffe efficiency (NSE) values 0.516, 0.691, 0.659, respectively. As a result, it seen that increased success PSO by approximately 35%.

Language: Английский

Citations

3
A surrogate model for the variable infiltration capacity model using physics-informed machine learning DOI Creative Commons
Haiting Gu, Xiao Liang, Li Liu

et al.

Journal of Water and Climate Change, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 18, 2025

ABSTRACT In this study, a physics-informed machine learning-based surrogate model (SM) for the variable infiltration capacity (VIC) was developed to improve simulation efficiency in Yarlung Tsangpo River basin. The approach combines empirical orthogonal function decomposition of low-fidelity VIC models extract spatial and temporal features, with learning techniques applied refine feature series. This allows accurate reconstruction high-fidelity simulations from results model. Using SM built 1.0°-resolution as an example, study highlights challenges solutions associated simulations. significantly improves accuracy, achieving Kling–Gupta 0.88, Nash–Sutcliffe 0.97, PBIAS value −6.21% reduced computational demands. Additionally, different methods impact performance SM, support vector regression performing best these methods. SMs varying resolutions maintain similar but higher notably enhance efficiency, reducing time by 86.31% when compared These findings demonstrate potential while requirements.

Language: Английский

Citations

0
River flood prediction through flow level modeling using multi-attention encoder-decoder-based TCN with filter-wrapper feature selection DOI

G. Selva Jeba,

P. Chitra

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 17(6), P. 5233 - 5249

Published: Aug. 22, 2024

Language: Английский

Citations

2
Unveiling the Potential of Hybrid Deep Learning Algorithm in Streamflow Projection DOI Open Access
Rishith Kumar Vogeti,

Rahul Jauhari,

Bhavesh Rahul Mishra

et al.

IOP Conference Series Earth and Environmental Science, Journal Year: 2024, Volume and Issue: 1409(1), P. 012001 - 012001

Published: Nov. 1, 2024

Abstract The present study aims to analyze the potential of a hybrid deep learning algorithm, GRU-RNN-LSTM, for mimicking streamflow and is evaluated using Kling Gupta Efficiency. case chosen was Lower Godavari Basin. Grid search tuning conducted algorithm. GRU-RNN-LSTM has shown good performance having Efficiency values 0.785, 0.77 in training testing segments respectively, further utilized projection by making use scenario, Shared Socioeconomic Pathway 585 (SSP585). highest, Lowest, Average streamflows expected are 2624 m 3 /s, 599.03 703.36 /s respectively. These projections could assist water resources planners initiating long-term measures.

Language: Английский

Citations

0