Performance Comparison of an LSTM-based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting

Water Resources Management, Journal Year: 2021, Volume and Issue: 35(12), P. 4167 - 4187

Published: Aug. 16, 2021

Language: Английский

---

Suspended sediment load prediction using sparrow search algorithm-based support vector machine model

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: June 5, 2024

Abstract Prediction of suspended sediment load (SSL) in streams is significant hydrological modeling and water resources engineering. Development a consistent accurate prediction model highly necessary due to its difficulty complexity practice because transportation vastly non-linear governed by several variables like rainfall, strength flow, supply. Artificial intelligence (AI) approaches have become prevalent resource engineering solve multifaceted problems modelling. The present work proposes robust incorporating support vector machine with novel sparrow search algorithm (SVM-SSA) compute SSL Tilga, Jenapur, Jaraikela Gomlai stations Brahmani river basin, Odisha State, India. Five different scenarios are considered for development. Performance assessment developed analyzed on basis mean absolute error (MAE), root squared (RMSE), determination coefficient (R 2 ), Nash–Sutcliffe efficiency (E NS ). outcomes SVM-SSA compared three hybrid models, namely SVM-BOA (Butterfly optimization algorithm), SVM-GOA (Grasshopper SVM-BA (Bat benchmark SVM model. findings revealed that successfully estimates high accuracy scenario V (3-month lag) discharge (current time-step 3-month as input than other alternatives RMSE = 15.5287, MAE 15.3926, E 0.96481. conventional performed the worst prediction. Findings this investigation tend claim suitability employed approach rivers precisely reliably. guarantees precision forecasted while significantly decreasing computing time expenditure, satisfies demands realistic applications.

Language: Английский

---

Applications of deep learning in water quality management: A state-of-the-art review

Journal of Hydrology, Journal Year: 2022, Volume and Issue: 613, P. 128332 - 128332

Published: Aug. 23, 2022

Language: Английский

---

An Efficient Data Driven-Based Model for Prediction of the Total Sediment Load in Rivers

Hydrology, Journal Year: 2022, Volume and Issue: 9(2), P. 36 - 36

Published: Feb. 17, 2022

Sediment load in fluvial systems is one of the critical factors shaping river geomorphological and hydraulic characteristics. A detailed understanding total sediment (TSL) required for protection physical, environmental, ecological functions rivers. This study develops a robust methodological approach based on multiple linear regression (MLR) support vector (SVR) models modified by principal component analysis (PCA) to predict TSL database measurement from large-scale physical modelling tests with 4759 datapoints were used develop predictive model. dimensional was performed literature, ten dimensionless parameters identified as key drivers These converted uncorrelated components feed MLR SVR (PCA-based PCA-based models) developed within this study. stepwise 10-fold model different kernel-type tuned derive an accurate Our findings suggest that radial basis function has best performance terms statistical error measures including root-mean-square normalized standard deviation (RMSE/StD) Nash–Sutcliffe coefficient efficiency (NSE), estimation The models, overall RMSE/StD 0.45 0.35, respectively, outperform existing well-established empirical formulae estimation. results confirms robustness proposed prediction cases high concentration sediments (NSE = 0.68), where usually have poor performance.

Language: Английский

---

Artificial neural network model with different backpropagation algorithms and meteorological data for solar radiation prediction

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: June 21, 2022

Abstract Solar energy serves as a great alternative to fossil fuels they are clean and renewable energy. Accurate solar radiation (SR) prediction can substantially lower down the impact cost pertaining development of Lately, many SR forecasting system has been developed such support vector machine, autoregressive moving average artificial neural network (ANN). This paper presents comprehensive study on meteorological data types backpropagation (BP) algorithms used train develop best predicting ANN model. The data, which includes temperature, relative humidity wind speed collected from station Kuala Terrenganu, Malaysia. Three different BP employed into training model i.e., Levenberg–Marquardt, Scaled Conjugate Gradient Bayesian Regularization (BR). comparison select combination algorithm with predictive ability. findings this shows that temperature both have high correlation whereas little influence over SR. results also showed BR trained models maximum R 0.8113 minimum RMSE 0.2581, outperform other models, indicated by performance score respective models.

Language: Английский

---

Predicting suspended sediment load in Peninsular Malaysia using support vector machine and deep learning algorithms

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Jan. 7, 2022

Abstract High loads of suspended sediments in rivers are known to cause detrimental effects potable water sources, river quality, irrigation activities, and dam or reservoir operations. For this reason, the study sediment load (SSL) prediction is important for monitoring damage mitigation purposes. The present tests develops machine learning (ML) models, based on support vector (SVM), artificial neural network (ANN) long short-term memory (LSTM) algorithms, predict SSL 11 different data sets comprising streamflow (SF) obtained from Malaysian Department Irrigation Drainage. main objective propose a single model that capable accurately predicting SSLs any set within Peninsular Malaysia. ANN3 model, ANN algorithm input scenario 3 (inputs consisting current-day SF, previous-day SSL), determined as best it produced predictive performance 5 out tested highest average RM with score 2.64 when compared other indicating has reliability produce relatively high-accuracy predictions sets. Therefore, proposed universal

Language: Английский

---

Prediction of compaction parameters of compacted soil using LSSVM, LSTM, LSBoostRF, and ANN

Innovative Infrastructure Solutions, Journal Year: 2023, Volume and Issue: 8(2)

Published: Jan. 18, 2023

Language: Английский

---

Long short-term memory models of water quality in inland water environments

Water Research X, Journal Year: 2023, Volume and Issue: 21, P. 100207 - 100207

Published: Nov. 16, 2023

Water quality is substantially influenced by a multitude of dynamic and interrelated variables, including climate conditions, landuse seasonal changes. Deep learning models have demonstrated predictive power water due to the superior ability automatically learn complex patterns relationships from variables. Long short-term memory (LSTM), one deep for prediction, type recurrent neural network that can account longer-term traits time-dependent data. It most widely applied used predict time series First, we reviewed applications standalone LSTM discussed its calculation time, prediction accuracy, good robustness with process-driven numerical other machine learning. This review was expanded into model data pre-processing techniques, Complete Ensemble Empirical Mode Decomposition Adaptive Noise method Synchrosqueezed Wavelet Transform. The then focused on coupling convolutional network, attention transfer coupled networks their performance over model. We also emphasized influence static variables in transformation dataset. Outlook further challenges were addressed. outlook research application hydrology concludes review.

Language: Английский

---

A Novel Smoothing-Based Deep Learning Time-Series Approach for Daily Suspended Sediment Load Prediction

Water Resources Management, Journal Year: 2023, Volume and Issue: 37(11), P. 4271 - 4292

Published: July 22, 2023

Language: Английский

---

A review of the current status of the water quality in the Nile water basin

Bulletin of the National Research Centre/Bulletin of the National Research Center, Journal Year: 2024, Volume and Issue: 48(1)

Published: March 18, 2024

Abstract Background Water contamination has become one of the most challenging problems to clean water supply and infrastructure in twenty-first century. Accordingly, access is limited by negative impacts climate change pollutants varying health risks. Overtime, global population experienced an exponential growth, which put pressure on resources. At least 3 billion people globally rely whose quality largely unknown. Main body abstract The Nile basin, found East Central Africa, covers 11 countries including DRC, Tanzania, South Sudan, Kenya, Uganda, Burundi, Egypt, Ethiopia, Eritrea, Rwanda. River flows through it before draining its into Mediterranean Sea Egypt. was pivotal for ancient civilization Sudan Egypt provision fertile soil irrigation, drinking, fishing, animal husbandry, channel transport modern times, top historical utilization, generation hydroelectric power leading conflict cooperation over shared Literature basin summarized, using traditional review method point out gaps, compare with other areas suggest recommendations based findings this study. been contaminated numerous such as toxic heavy metals organic contaminants, therefore pushing resident above World organization (WHO) acceptable guidelines drinking water, agricultural aquatic life support. Cases outside recommended limits cadmium little Akaki aldrin dieldrin Tanzanian side L. Victoria clearly show WHO basin. Short conclusion effect fish cages, micro-plastics, metals, contaminants suspended sediment load primarily from human activities like agriculture, industries municipal wastes continuously contaminating toward poor status. Consequently, interventions transboundary laws regulations mitigate risks must be enforced.

Language: Английский

---