Prediction of Total Phosphorus Concentration in Canals by GAT-Informer Model Based on Spatiotemporal Correlations

Water, Journal Year: 2024, Volume and Issue: 17(1), P. 12 - 12

Published: Dec. 24, 2024

The accurate prediction of total phosphorus (TP) is crucial for the early detection water quality eutrophication. However, predicting TP concentrations among canal sites challenging due to their complex spatiotemporal dependencies. To address this issue, study proposes a GAT-Informer method based on correlations predict in Beijing–Hangzhou Grand Canal Basin Changzhou City. begins by creating feature sequences each site time lag relationship concentration between sites. It then constructs graph data combining real river distance and correlation sequences. Next, spatial features are extracted fusing node using attention (GAT) module. employs Informer network, which uses sparse mechanism extract temporal efficiently simulating model was evaluated R2, MAE, RMSE, with experimental results yielding values 0.9619, 0.1489%, 0.1999%, respectively. exhibits enhanced robustness superior predictive accuracy comparison traditional models.

Language: Английский

---

Runoff prediction based on the IGWOLSTM model: Achieving accurate flood forecasting and emergency management

Journal of Hydro-environment Research, Journal Year: 2024, Volume and Issue: 56, P. 28 - 39

Published: Aug. 23, 2024

Language: Английский

---

Analysis of the influence of the daily regulation of power stations on navigable flow conditions at river confluences using the LSTM model

Engineering Applications of Computational Fluid Mechanics, Journal Year: 2024, Volume and Issue: 18(1)

Published: Sept. 2, 2024

The daily operations of large hydropower stations on rivers induce frequent variations in downstream water levels and flow velocities, resulting unsteady complex hydraulic characteristics at the confluence main stream its tributaries, which adversely affect navigation safety. continuity momentum equations, along with RNG k-ϵ turbulence model VOF model, were employed to simulate river process under conditions. simulated results for velocity vector fields are good agreement experimental data. Variations characteristics, including level, velocity, longitudinal gradient analysed. indicated that level decreases when tributary merges stream. As ratio increases, fluctuations decrease. However, an increase staggered period greater within this region. Moreover, a crescent-shaped high-speed region is formed discharge relative area correspondingly enlarges, reaching maximum peak discharge, subsequently gradually diminishes as decreases. Based these simulation data, Long Short-Term Memory (LSTM) was developed effectively predict providing more convenient accurate method obtaining real-time information areas than traditional mathematical statistical approaches. This study provides novel insights into predicting areas, thereby offering basis formulating safety plans.

Language: Английский

---

Exploration and Prediction of Lake Water Levels Based on the MOACO Algorithm and CNN-LSTM Model

Published: June 12, 2024

Language: Английский

---

Unveiling key drivers of economy-water system and transforming water use pattern into sustainable development: Inner-Shaan-Ning region in the Yellow River Basin

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: unknown, P. 143651 - 143651

Published: Sept. 1, 2024

Language: Английский

---