Coupling and Comparison of Physical Mechanism and Machine Learning Models for Water Level Simulation in Plain River Network Area DOI Creative Commons
Xiaoqing Gao, Yunzhu Liu, Cheng Gao

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(24), P. 12008 - 12008

Published: Dec. 22, 2024

In this study, the JiaoGang Basin in Yangtze River Delta plains of river network area was research object. A basin water level simulation model constructed based on physical mechanism and Mike software, parameters were calibrated validated. Based dataset produced by model, three types ML models, Support Vector Machine (SVM), random forest (RF), gradient boosting decision tree (GBDT), constructed, trained, validated, compared with model. The results showed that met accuracy requirements at most stations. training validation periods, RF GBDT models had root mean square errors (RMSEs) all stations less than 0.25 Nash–Sutcliffe coefficient (NSE) greater 0.7. can simulate better. considerably outperform terms peak present time errors, fluctuations (RMSE NSE) are minor to those

Language: Английский

A novel insight on input variable and time lag selection in daily streamflow forecasting using deep learning models DOI
Amina Khatun,

M.N. Nisha,

Siddharth G. Chatterjee

et al.

Environmental Modelling & Software, Journal Year: 2024, Volume and Issue: 179, P. 106126 - 106126

Published: June 25, 2024

Language: Английский

Citations

10
A state-of-the-art review of long short-term memory models with applications in hydrology and water resources DOI
Zhong-kai Feng, J. Zhang, Wen-jing Niu

et al.

Applied Soft Computing, Journal Year: 2024, Volume and Issue: unknown, P. 112352 - 112352

Published: Oct. 1, 2024

Language: Английский

Citations

9
Improved Flood Forecasting using Numerical Weather Prediction Meteorological Forecasts with Integrated Rainfall-Runoff and Hydrodynamic Model DOI

Archana Ramchandra Mohite,

Amina Khatun, Chandranath Chatterjee

et al.

Water Resources Management, Journal Year: 2025, Volume and Issue: unknown

Published: April 2, 2025

Language: Английский

Citations

1
Artificial Intelligence Algorithms in Flood Prediction: A General Overview DOI
Manish Pandey

Springer eBooks, Journal Year: 2024, Volume and Issue: unknown, P. 243 - 296

Published: Jan. 1, 2024

Language: Английский

Citations

5
High-Resolution Flow and Phosphorus Forecasting Using ANN Models, Catering for Extremes in the Case of the River Swale (UK) DOI Creative Commons
Elisabeta Cristina Timiș, Horia Hangan, Mircea Vasile Cristea

et al.

Hydrology, Journal Year: 2025, Volume and Issue: 12(2), P. 20 - 20

Published: Jan. 21, 2025

The forecasting of river flows and pollutant concentrations is essential in supporting mitigation measures for anthropogenic climate change effects on rivers their environment. This paper addresses two aspects receiving little attention the literature: high-resolution (sub-daily) data-driven modeling prediction phosphorus compounds. It presents a series artificial neural networks (ANNs) to forecast soluble reactive (SRP) total (TP) under wide range conditions, including low storm events (0.74 484 m3/s). Results show correct along stretch River Swale (UK) with an anticipation up 15 h, at resolutions 3 h. concentration improved compared previous application advection–dispersion model.

Language: Английский

Citations

0
Improved streamflow simulations in hydrologically diverse basins using physically informed deep learning models DOI
Bhanu Magotra, Manabendra Saharia,

C. T. Dhanya

et al.

Hydrological Sciences Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 27, 2025

Physically informed deep learning models, especially Long Short-Term Memory (LSTM) networks, have shown promise in large-scale streamflow simulations. However, an in-depth understanding of the relative contribution physical information models has been missing. Using a large-sample testbed 220 catchments hydrologically diverse regions Indian subcontinent, we quantify impact incremental addition on model performance using multiple variants LSTM based various combinations static catchment attributes and simulated land surface states. We found that trained with geophysics as additional input outperformed base terms nationwide median Kling-Gupta Efficiency (KGE) in-sample catchments, increasing KGE from 0.32 to 0.60. Additionally, retained significant prediction skill out-of-sample demonstrating pre-trained can be powerful tool predict data-scarce regions.

Language: Английский

Citations

0
Spatio-Temporal NDVI Prediction for Rice Crop DOI
Anamika Dey,

Somrita Sarkar,

Arijit Mondal

et al.

SN Computer Science, Journal Year: 2025, Volume and Issue: 6(3)

Published: Feb. 28, 2025

Language: Английский

Citations

0
A new strategy for prediction of water qualitative and quantitative parameters by deep learning-based models with determination of modelling uncertainties DOI
Mojtaba Poursaeid, Amir Hossein Poursaeed

Hydrological Sciences Journal, Journal Year: 2023, Volume and Issue: 69(2), P. 207 - 225

Published: Dec. 19, 2023

This study presents a new method based on three types of deep learning-based models (DLM) for estimation water parameters. The DLM were recurrent neural networks (RNN), long short-term memory (LSTM), and bidirectional (BiLSTM). areas the Colorado River basin in United States Mighan Wetland Iran. electrical conductivity (EC), dissolved oxygen (DO), total solids (TDS), chloride ions (Cl), river flow rate (debi) simulated by models. Wilson score (WS) uncertainty analysis results modelling showed that LSTMdebi, RNNDO, RNNEC best simulating due to having lowest errors (Mean ei equal 0.36, −1.50, −0.59), respectively. Finally, highest value R2 index, 0.998, was achieved LSTM model debi parameter, 0.996 EC modelling, Wetland.

Language: Английский

Citations

4
Smoothed-LSTM: Advancing spatio-temporal NDVI prediction in semi-automated dataset for rice crop DOI
Anamika Dey,

Somrita Sarkar,

Debajyoti Kumar

et al.

Published: April 8, 2024

Accurate Normalized Difference Vegetation Index (NDVI) forecasting is crucial for effective agricultural planning. However, a good prediction of the same requires sufficient data, but structured data not available in public domain or open-source community. Also, most existing methods do consider spatial information. This study presents novel semi-automated dataset generation framework that utilizes Sentinel-2, POWER Data Access Viewer, and Google Earth Engine to create comprehensive time-series dataset. We propose smoothed long short-term memory (LSTM) model considering time series, historical meteorological, The proposed Smoothed-LSTM-based outperforms Traditional-LSTM models, demonstrating its effectiveness NDVI applications.

Language: Английский

Citations

1
A probabilistic integration of LSTM and Gaussian Process Regression for uncertainty-aware reservoir water level predictions DOI
Kshitij Tandon, Subhamoy Sen

Hydrological Sciences Journal, Journal Year: 2024, Volume and Issue: 70(1), P. 144 - 161

Published: Nov. 11, 2024

Reservoir-level forecasting while being crucial for optimal operation, is challenged by complex physical processes and changing climate conditions. Machine learning approaches offer deterministic predictions but often neglect system physics uncertainty. This article presents a probabilistic data-driven approach combining Long Short-Term Memory (LSTM) Gaussian Process Regression (GPR) to provide both point forecasts uncertainty estimates. The hybrid model leverages LSTM's fitting capabilities with GPR's robust Bayesian frameworks estimation in nonlinear problems, offering accurate without extensive high-fidelity modeling, avoiding frequent training parameter optimization. Evaluation real reservoir data from India shows the model's superiority over vanilla LSTM univariate multivariate scenarios. proposed achieved Nash Sutcliffe efficiency of 0.97 0.98, mean biased error -0.5634 -1.0314 10-day forecasts, continuous ranked probability score 5.80 1.87 Bhakra Pong reservoirs, respectively.

Language: Английский

Citations

0