Suspended sediment load modeling using Hydro-Climate variables and Machine learning

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 633, P. 130948 - 130948

Published: March 1, 2024

Language: Английский

---

A newly developed multi-objective evolutionary paradigm for predicting suspended sediment load

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 634, P. 131090 - 131090

Published: March 21, 2024

Language: Английский

---

Regional scale simulations of daily suspended sediment concentration at gauged and ungauged rivers using deep learning

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 133111 - 133111

Published: April 1, 2025

Language: Английский

---

A comparison of machine learning models for suspended sediment load classification

Engineering Applications of Computational Fluid Mechanics, Journal Year: 2022, Volume and Issue: 16(1), P. 1211 - 1232

Published: May 24, 2022

The suspended sediment load (SSL) is one of the major hydrological processes affecting sustainability river planning and management. Moreover, sediments have a significant impact on dam operation reservoir capacity. To this end, reliable applicable models are required to compute classify SSL in rivers. application machine learning has become common solve complex problems such as modeling. present research investigated ability several data. This investigation aims explore new version classifiers for classification at Johor River, Malaysia. Extreme gradient boosting, random forest, support vector machine, multi-layer perceptron k-nearest neighbors been used values divided into multiple discrete ranges, where each range can be considered category or class. study illustrates two different scenarios related number categories, which five 10 with time scales, daily weekly. performance proposed was evaluated by statistical indicators. Overall, achieved excellent data under various scenarios.

Language: Английский

---

Optimizing sediment transport models by using the Monte Carlo simulation and deep neural network (DNN): A case study of the Riba-Roja reservoir

Environmental Modelling & Software, Journal Year: 2024, Volume and Issue: 175, P. 105979 - 105979

Published: Feb. 20, 2024

This study emphasizes the importance of accurate calibration in sediment transport models and highlights transformative role artificial intelligence (AI), specifically machine learning, improving accuracy computational efficiency. Extensive experiments were carried out Riba-Roja reservoir, which is located northeastern Iberian Peninsula. The accumulated volume (ASV) curve was used to calibrate these experiments. optimal ASV found be very close experimental data, with only minor differences upstream areas. results revealed a consistent rate settling. Furthermore, investigated capabilities deep neural networks (DNNs) predicting curves observing variable performance. In essence, AI's potential for enhancing models.

Language: Английский

---

Evaluation of deep learning algorithm for inflow forecasting: a case study of Durian Tunggal Reservoir, Peninsular Malaysia

Natural Hazards, Journal Year: 2021, Volume and Issue: 109(1), P. 351 - 369

Published: June 15, 2021

Language: Английский

---

Development of prediction model for phosphate in reservoir water system based machine learning algorithms

Ain Shams Engineering Journal, Journal Year: 2021, Volume and Issue: 13(1), P. 101523 - 101523

Published: July 2, 2021

Phosphate (PO4) is a major component of most fertilizers, and when erosion runoff occur, large amounts it enter the water bodies, causing several problems such as eutrophication. Feitsui reservoir, primary source supply to Taipei, reported half reservoir's pollutants from nonpoint-source pollution. The value PO4 in body fluctuates highly nonlinear stochastic patterns. However, conventional modeling techniques are no longer sufficiently effective predicting accurately patterns concentrations water. Therefore, this study proposes different machine learning algorithms: artificial neural network (ANN), support vector (SVM), random forest (RF), boosted trees (BT) predict concentration PO4. Monthly measured data between 1986 2014 were used train test accuracy these models. performances models examined using statistical indices. Hyperparameters optimization cross-validation was performed enhance precision Five quality parameters input proposed Different combinations explored optimize precision. findings revealed that ANN outperformed other three capture changes with high where RMSE equal 1.199, MAE 0.858, R2 0.979, MSE 1.439, finally, CC 0.9909. developed model could be reliable means for managing eutrophication problems.

Language: Английский

---

Application of long short-term memory neural network technique for predicting monthly pan evaporation

Scientific Reports, Journal Year: 2021, Volume and Issue: 11(1)

Published: Oct. 20, 2021

Abstract Evaporation is a key element for water resource management, hydrological modelling, and irrigation system designing. Monthly evaporation (Ep) was projected by deploying three machine learning (ML) models included Extreme Gradient Boosting, ElasticNet Linear Regression, Long Short-Term Memory; two empirical techniques namely Stephens-Stewart Thornthwaite. The aim of this study to develop reliable generalised model predict throughout Malaysia. In context, monthly meteorological statistics from weather stations in Malaysia were utilised training testing the on basis climatic aspects such as maximum temperature, mean minimum wind speed, relative humidity, solar radiation period 2000–2019. For every approach, multiple formulated utilising various combinations input parameters other factors. performance assessed standard statistical measures. outcomes indicated that outclassed could considerably enhance precision Ep estimate even with same inputs. addition, assessment showed Memory Neural Network (LSTM) offered most precise estimations all studied both stations. LSTM-10 measures (R 2 = 0.970, MAE 0.135, MSE 0.027, RMSE 0.166, RAE 0.173, RSE 0.029) Alor Setar 0.986, 0.058, 0.005, 0.074, 0.120, 0.013) Kota Bharu.

Language: Английский

---

Soil water erosion assessment in Morocco through modeling and fingerprinting applications: A review

Heliyon, Journal Year: 2022, Volume and Issue: 8(8), P. e10209 - e10209

Published: Aug. 1, 2022

During the last century, a great deal of effort has been directed toward determining soil erosion rates using various methods under wide range climatic conditions, types, land uses, topography, and among others. Therefore, to better understand studies in Morocco, country with diverse physiography variations we undertook an analysis national data several modeling fingerprinting. The approach used for this research is review scientific articles, conference papers thesis on erosion, focusing more categorization different models other applied. results reveal very interesting information as follows: (i) distribution frequency level fingerprinting applications; focus was north country: (Rif 32.89%, High Atlas Occidental Meseta 18.43% Middle 10.53%), (ii) (R) USLE remain most widely (51,32%) (iii) support practice factor severely lacking across country, (iv) highest rate concentrated Rif mountains; (v) positive relationship between geological features, slope, climate, use cover, plus environmental characteristics, well measurement negative study areas size scale. Even though overall show high degree variability, which cannot be explained by combination factors, but at minimum partly related experimental conditions. This overview database are designed assist future assessment help define priorities providing state art focused comprehensive analyses address issue Morocco.

Language: Английский

---

Combining Radial Basis Function Neural Network Models and Inclusive Multiple Models for Predicting Suspended Sediment Loads

Water Resources Management, Journal Year: 2022, Volume and Issue: 36(11), P. 4313 - 4342

Published: July 26, 2022

Language: Английский

---