Evaluation and Improvement of the Method for Selecting the Ridge Parameter in System Differential Response Curves DOI Open Access
Hao Xiao, Simin Qu, Xumin Zhang

et al.

Water, Journal Year: 2023, Volume and Issue: 15(24), P. 4205 - 4205

Published: Dec. 5, 2023

The selection of an appropriate ridge parameter plays a crucial role in estimation. A smaller leads to larger residuals, while reduces the unbiasedness This paper proposes constrained L-curve method accurately select optimal parameter. Additionally, method, traditional and trace are individually coupled with system differential response curve update streamflow Jianyang Basin using SWAT model. Multiple evaluation criteria employed analyze efficacy three methods for correction. results demonstrate that identifies actual Furthermore, coupling exhibits markedly superior accuracy simulated compared methods, mean Nash–Sutcliffe efficiency (NSE) improving from 0.71 0.88 after which incorporates physical interpretation estimated parameters, effectively practical scenarios. As result, it demonstrates usability applicability when method.

Language: Английский

Comparison and integration of physical and interpretable AI-driven models for rainfall-runoff simulation DOI Creative Commons
Sara Asadi, Patricia Jimeno‐Sáez, Adrián López-Ballesteros

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 24, P. 103048 - 103048

Published: Oct. 5, 2024

Language: Английский

Citations

9
Monthly runoff prediction using gated recurrent unit neural network based on variational modal decomposition and optimized by whale optimization algorithm DOI
Wenchuan Wang, Bo Wang, Kwok‐wing Chau

et al.

Environmental Earth Sciences, Journal Year: 2024, Volume and Issue: 83(2)

Published: Jan. 1, 2024

Language: Английский

Citations

7
Assessing long-term water storage dynamics in Afghanistan: An integrated approach using machine learning, hydrological models, and remote sensing DOI Creative Commons
Abdul Haseeb Azizi, Fazlullah Akhtar, Bernhard Tischbein

et al.

Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 370, P. 122901 - 122901

Published: Oct. 21, 2024

Language: Английский

Citations

4
Integration of Gaussian process regression and K means clustering for enhanced short term rainfall runoff modeling DOI Creative Commons
Özgür Kişi, Salim Heddam, Kulwinder Singh Parmar

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 3, 2025

Abstract Accurate rainfall-runoff modeling is crucial for effective watershed management, hydraulic infrastructure safety, and flood mitigation. However, predicting remains challenging due to the nonlinear interplay between hydro-meteorological topographical variables. This study introduces a hybrid Gaussian process regression (GPR) model integrated with K-means clustering (GPR-K-means) short-term forecasting. The Orgeval in France serves as area, providing hourly precipitation streamflow data spanning 1970–2012. performance of GPR-K-means compared standalone GPR principal component (PCR) models across four forecasting horizons: 1-hour, 6-hour, 12-hour, 24-hour ahead. results reveal that significantly improves accuracy all lead times, Nash-Sutcliffe Efficiency (NSE) approximately 0.999, 0.942, 0.891, 0.859 forecasts, respectively. These outperform other ML models, such Long Short-Term Memory, Support Vector Machines, Random Forest, reported literature. demonstrates enhanced reliability robustness forecasting, emphasizing its potential broader application hydrological modeling. Furthermore, this provides novel methodology combining Bayesian techniques surface hydrology, contributing more accurate timely prediction.

Language: Английский

Citations

0
Intercomparison of sediment transport curve and novel deep learning techniques in simulating sediment transport in the Wadi Mina Basin, Algeria DOI
Mohammed Achite, Okan Mert Katipoğlu, Nehal Elshaboury

et al.

Environmental Earth Sciences, Journal Year: 2025, Volume and Issue: 84(2)

Published: Jan. 1, 2025

Language: Английский

Citations

0
Comparison of Machine Learning Models for Real-Time Flow Forecasting in the Semi-Arid Bouregreg Basin DOI Creative Commons
Fatima Zehrae Elhallaoui Oueldkaddour, Fatima Wariaghli,

Hassane Brırhet

et al.

Limnological Review, Journal Year: 2025, Volume and Issue: 25(1), P. 6 - 6

Published: March 5, 2025

Morocco is geographically located between two distinct climatic zones: temperate in the north and tropical south. This situation reason for temporal spatial variability of Moroccan climate. In recent years, increasing scarcity water resources, exacerbated by climate change, has underscored critical role dams as essential reservoirs. These serve multiple purposes, including flood management, hydropower generation, irrigation, drinking supply. Accurate estimation reservoir flow rates vital effective resource particularly context variability. The prediction monthly runoff time series a key component resources planning development projects. this study, we employ Machine Learning (ML) techniques—specifically, Random Forest (RF), Support Vector Regression (SVR), XGBoost—to predict river flows Bouregreg basin, using data collected from Sidi Mohamed Ben Abdellah (SMBA) Dam 2010 2020. primary objective paper to comparatively evaluate applicability these three ML models forecasting River. models’ performance was assessed criteria: correlation coefficient (R2), Akaike Information Criterion (AIC), Bayesian (BIC). results demonstrate that SVR model outperformed RF XGBoost models, achieving high accuracy prediction. findings are highly encouraging highlight potential machine learning approaches hydrological semi-arid regions. Notably, used study less data-intensive compared traditional methods, addressing significant challenge modeling. research opens new avenues application techniques management suggests methods could be generalized other basins Morocco, promoting efficient, effective, integrated strategies.

Language: Английский

Citations

0
Response of climate change and land use land cover change on catchment-scale water balance components: a multi-site calibration approach DOI Creative Commons
Shashi Bhushan Kumar, Ashok Mishra, Sonam Sandeep Dash

et al.

Journal of Water and Climate Change, Journal Year: 2024, Volume and Issue: 15(4), P. 1750 - 1771

Published: March 7, 2024

ABSTRACT The present study focused on evaluating the separate and combined response of land use cover climate change (CC) future water balance components a Subarnarekha River basin, spanning between latitudes 21°33′N–23°18′N longitudes 85°11′E–87°23′E, situated in eastern India. Soil Water Assessment Tool is used for single-site calibration multi-site (MSC) model to characterize basin using Cellular Automata-Markov projections under two representative concentration pathway (RCP) scenarios (4.5 8.5). findings indicate that parameters obtained through MSC better represent spatial heterogeneity, making it preferred approach simulations. In middle region annual yield, groundwater recharge (GWR), streamflow showed reduction, respectively, by 46–47%, 29–30%, 13–15%, while evapotranspiration an increase 5–7% following projected CC both RCP scenarios. are relevant policy-makers mitigate adverse effects reduced GWR sustainable resources management. Future research may integrate reservoir operation frameworks effectively address management issues basin.

Language: Английский

Citations

3
Analysis of recent decade rainfall data with new exponential-exponential distribution: Inference and applications DOI Creative Commons
Hleil Alrweili

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 95, P. 306 - 320

Published: April 4, 2024

This study introduces the New Exponential-Exponential Distribution (NEED) within broader Exponential-Generating (NE-G) family of distributions, targeting enhancements in rainfall data analysis. The significance this research lies addressing need for sophisticated statistical models to accurately capture complex variability patterns, which are critical effective environmental planning and disaster management. Aiming refine modeling, we employ NEED model, emphasizing its application across diverse climatic conditions. Our methodology encompasses a comprehensive evaluation seven distinct parameter estimation techniques, with particular focus on Anderson-Darling maximum product spacing methods. These were selected based their performance minimizing bias mean square error, assessed through rigorous Monte-Carlo simulation study. Additionally, utilizes from various geographical regions validate model's efficacy. major conclusion our investigation is demonstrable superiority over traditional fitting data, as evidenced by enhanced predictive accuracy. outcome not only contributes theoretical advancements meteorology but also offers practical methodologies improved weather forecasting. integration contemporary machine learning algorithms further suggests potential groundbreaking applications climate science water resource

Language: Английский

Citations

2
Simulating the climate change effects on the Karaj Dam basin: hydrological behavior and runoff DOI Creative Commons
Mohammad Sadeghi Nasirabadi, Amir Khosrojerdi, Seyed Habib Musavi-Jahromi

et al.

Journal of Water and Climate Change, Journal Year: 2024, Volume and Issue: 15(7), P. 3094 - 3114

Published: June 15, 2024

ABSTRACT This study has used Coupled Model Intercomparison Project Phase 5 (CMIP5) and 6 (CMIP6). Hence, the runoff simulation was done in near-future period (2030–2050) scenarios by applying climate change conditions for HadGEM2-ES model under three representative concentration pathways RCP2.6, 4.5 8.5 HadGEM3-GC31-LL SSP1-2.6, SSP2-4.5 SSP5-8.5 scenarios. Examining climatic precipitation variables minimum maximum temperature showed a increase of 1.51–2.91 °C all models decrease 0.05–11.15% most them, SWAT four stations SSP RCP Since data have become available only recently, results this predict that overall future flow will vary −5 to 28% range, resulting 5–35% and, hence, inflow dam reservoir. Based on results, there is possibility 5–30% reduction entering

Language: Английский

Citations

2
Suspended sediment load prediction in river systems via shuffled frog-leaping algorithm and neural network DOI
Okan Mert Katipoğlu, Gaye Aktürk, Hüseyin Çağan Kılınç

et al.

Earth Science Informatics, Journal Year: 2024, Volume and Issue: 17(4), P. 3623 - 3649

Published: June 18, 2024

Language: Английский

Citations

2