Research on Optimal Selection of Runoff Prediction Models Based on Coupled Machine Learning Methods DOI Creative Commons
Wei Xing,

M.M. Chen,

Yulin Zhou

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Авг. 13, 2024

Abstract Runoff fluctuations under the influence of climate change and human activities present a significant challenge valuable application in constructing high-accuracy runoff prediction models. This study aims to address this by taking Wanzhou station Three Gorges Reservoir area as case optimize various The first selects artificial neural network (ANN) support vector machine (SVM) base Then, it evaluates from three time-series decomposition methods: Time-Varying Filter-based Empirical Mode Decomposition (TVF-EMD), Complete Ensemble with Adaptive Noise (CEEMDAN), Variational (VMD). Subsequently, these methods are coupled optimization algorithms, including Whale Optimization Algorithm (WOA), Grasshopper (GOA), Sparrow Search (SSA), construct hybrid results indicate that: (1) Among single models, Long Short-Term Memory (LSTM) model outperforms Backpropagation Neural Network (BP) SVM terms accuracy; (2) models show superior accuracy compared individual VMD-LSTM outperforming CEEMDAN-LSTM TVF-EMD-LSTM models; (3) learning VMD-SSA-LSTM achieves highest accuracy. Employing "decomposition-reconstruction" strategy combined robust algorithms enhances performance thereby significantly improving capabilities watershed hydrological

Язык: Английский

A Comprehensive Survey of Machine Learning Methodologies with Emphasis in Water Resources Management DOI Creative Commons

Maria Drogkoula,

Konstantinos Kokkinos, Nicholas Samaras

и другие.

Applied Sciences, Год журнала: 2023, Номер 13(22), С. 12147 - 12147

Опубликована: Ноя. 8, 2023

This paper offers a comprehensive overview of machine learning (ML) methodologies and algorithms, highlighting their practical applications in the critical domain water resource management. Environmental issues, such as climate change ecosystem destruction, pose significant threats to humanity planet. Addressing these challenges necessitates sustainable management increased efficiency. Artificial intelligence (AI) ML technologies present promising solutions this regard. By harnessing AI ML, we can collect analyze vast amounts data from diverse sources, remote sensing, smart sensors, social media. enables real-time monitoring decision making applications, including irrigation optimization, quality monitoring, flood forecasting, demand enhance agricultural practices, distribution models, desalination plants. Furthermore, facilitates integration, supports decision-making processes, enhances overall sustainability. However, wider adoption faces challenges, heterogeneity, stakeholder education, high costs. To provide an management, research focuses on core fundamentals, major (prediction, clustering, reinforcement learning), ongoing issues offer new insights. More specifically, after in-depth illustration algorithmic taxonomy, comparative mapping all specific tasks. At same time, include tabulation works along with some concrete, yet compact, descriptions objectives at hand. leveraging tools, develop plans address world’s supply concerns effectively.

Язык: Английский

Процитировано

53
Enhancing Water Level Prediction Using Ensemble Machine Learning Models: A Comparative Analysis DOI
Saleh Alsulamy, Vijendra Kumar, Özgür Kişi

и другие.

Water Resources Management, Год журнала: 2025, Номер unknown

Опубликована: Фев. 11, 2025

Язык: Английский

Процитировано

5
Development of wavelet-based Kalman Online Sequential Extreme Learning Machine optimized with Boruta-Random Forest for drought index forecasting DOI
Mehdi Jamei, Iman Ahmadianfar, Masoud Karbasi

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2022, Номер 117, С. 105545 - 105545

Опубликована: Ноя. 10, 2022

Язык: Английский

Процитировано

42
Flood discharge prediction using improved ANFIS model combined with hybrid particle swarm optimisation and slime mould algorithm DOI
Sandeep Samantaray,

Pratik Sahoo,

Abinash Sahoo

и другие.

Environmental Science and Pollution Research, Год журнала: 2023, Номер 30(35), С. 83845 - 83872

Опубликована: Июнь 23, 2023

Язык: Английский

Процитировано

32
Runoff prediction of lower Yellow River based on CEEMDAN–LSSVM–GM(1,1) model DOI Creative Commons

Shaolei Guo,

Yihao Wen,

Xianqi Zhang

и другие.

Scientific Reports, Год журнала: 2023, Номер 13(1)

Опубликована: Янв. 27, 2023

Abstract Accurate medium and long-term runoff forecasts play a vital role in guiding the rational exploitation of water resources improving overall efficiency use. Machine learning is becoming common trend time series forecasting research. Least squares support vector machine (LSSVM) grey model (GM(1,1)) have received much attention predicting rainfall last two years. “Decomposition-forecasting” has become one most important methods for data. Complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method powerful advantages dealing nonlinear strong fitting ability good robustness. Gray can solve problems little historical data low serial integrity reliability. Based on their respective advantages, combined CEEMDAN–LSSVM–GM(1,1) was developed applied to prediction lower Yellow River. To verify reliability model, results were compared single LSSVM CEEMDAN–LSSVM CEEMDAN–support machines (SVM)–GM(1,1). The show that high accuracy are better than other models, which provides an effective regional application prospects.

Язык: Английский

Процитировано

24
Digital elevation model for flood hazards analysis in complex terrain: Case study from Jeddah, Saudi Arabia DOI Creative Commons
Ahmed M. Al‐Areeq, Hatim O. Sharif, Sani I. Abba

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2023, Номер 119, С. 103330 - 103330

Опубликована: Апрель 29, 2023

Global Digital Elevation Models (GDEMs) have been increasingly used to assess the risk of flooding worldwide. However, their effectiveness and performance flood models in areas with complex terrain, such as Jeddah, Saudi Arabia, not comprehensively studied. This study aims compare five distinct − 30-m SRTM, ASTER, 90-m MERIT, 10 m Sentinel-1 DEM, 12.5 ALOSPALSAR - estimating inundation extent depth Jeddah watershed, including three dams. Both hydrological hydraulic modeling approaches were utilized achieve this objective. The findings revealed that all produced similar watershed boundaries mountain area (Wadi Qaws), except for ALOS-PALSAR, which generated a different boundary from previous reports studies. GDEMs failed accurately delineate drainage one dams, SRTM ALOS-PALSAR. Moreover, ASTER products provided closest estimates ground observations, producing peak discharges 114.1 m3/s 110 m3/s, respectively. For entire encompassing mountain, urban, coastal areas, demonstrated significant differences boundary, streams, outlet location, discharge at outlet. In addition, each GDEM's map was significantly distinct. Overall, results suggest outperformed other area.

Язык: Английский

Процитировано

21
A Hybrid Data-Driven Deep Learning Prediction Framework for Lake Water Level Based on Fusion of Meteorological and Hydrological Multi-source Data DOI
Zhiyuan Yao, Zhaocai Wang, Tunhua Wu

и другие.

Natural Resources Research, Год журнала: 2023, Номер 33(1), С. 163 - 190

Опубликована: Дек. 10, 2023

Язык: Английский

Процитировано

20
Geographic heterogeneity of activation functions in urban real-time flood forecasting: Based on seasonal trend decomposition using Loess-Temporal Convolutional Network-Gated Recurrent Unit model DOI

Songhua Huan

Journal of Hydrology, Год журнала: 2024, Номер 636, С. 131279 - 131279

Опубликована: Май 7, 2024

Язык: Английский

Процитировано

7
Modeling of Monthly Rainfall–Runoff Using Various Machine Learning Techniques in Wadi Ouahrane Basin, Algeria DOI Open Access
Mahdi Valikhan Anaraki, Mohammed Achite, Saeed Farzin

и другие.

Water, Год журнала: 2023, Номер 15(20), С. 3576 - 3576

Опубликована: Окт. 12, 2023

Rainfall–runoff modeling has been the core of hydrological research studies for decades. To comprehend this phenomenon, many machine learning algorithms have widely used. Nevertheless, a thorough comparison and effect pre-processing on their performance is still lacking in literature. Therefore, major objective to simulate rainfall runoff using nine standalone hybrid models. The conventional models include artificial neural networks, least squares support vector machines (LSSVMs), K-nearest neighbor (KNN), M5 model trees, random forests, multiple adaptive regression splines, multivariate nonlinear regression. In contrast, comprise LSSVM KNN coupled with gorilla troop optimizer (GTO). Moreover, present study introduces new combination feature selection method, principal component analysis (PCA), empirical mode decomposition (EMD). Mean absolute error (MAE), root mean squared (RMSE), relative RMSE (RRMSE), person correlation coefficient (R), Nash–Sutcliffe efficiency (NSE), Kling Gupta (KGE) metrics are used assessing developed proposed applied data collected Wadi Ouahrane basin, Algeria. According results, KNN–GTO exhibits best (MAE = 0.1640, 0.4741, RRMSE 0.2979, R 0.9607, NSE 0.9088, KGE 0.7141). These statistical criteria outperform other by 80%, 70%, 72%, 77%, 112%, 136%, respectively. provides worst results without data. findings indicate that selection, PCA, EMD significantly improves accuracy rainfall–runoff modeling.

Язык: Английский

Процитировано

17
Monthly Runoff Prediction Via Mode Decomposition-Recombination Technique DOI
Xi Yang, Zhihe Chen, Min Qin

и другие.

Water Resources Management, Год журнала: 2023, Номер 38(1), С. 269 - 286

Опубликована: Дек. 1, 2023

Язык: Английский

Процитировано

17