Assessing the Performance of Machine Learning Algorithms for Water Level Prediction in the Chao Phraya River and its Tributaries: A Focus on Low and High Water Levels DOI

Wilmat D.S.M. Priyasiri,

Areeya Rittima,

Jidapa Kraisangka

et al.

Published: Jan. 1, 2024

Language: Английский

River stream flow prediction through advanced machine learning models for enhanced accuracy DOI Creative Commons
Naresh Kedam, Deepak Kumar Tiwari, Vijendra Kumar

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 22, P. 102215 - 102215

Published: May 4, 2024

The Narmada River basin, a significant water resource in central India, plays crucial role supporting agricultural, industrial, and domestic supply. Effective management of this basin requires accurate streamflow forecasting, which has become increasingly important. This study delves into forecasting using historical data from five major river stations, covering the upper reaches East middle sections. dataset spans 1978 to 2020 undergoes rigorous screening preparation, including normalization StandardScaler. research adopts comprehensive approach, developing models for training on 70% data, validation most current 15%, testing against future targets with another 15% data. To achieve precise predictions, suite machine learning is employed, CatBoost, LGBM (Light Gradient Boosting Machine), Random Forest, XGBoost. Performance evaluation these relies key indices such as mean squared error (MSE), absolute (MAE), root square (RMSE), percent (RMSPE), normalized (NRMSE), R-squared (R2). Notably, among models, Forest emerges robust prediction, showcasing its effectiveness handling complexities hydrological forecasting. contributes significantly field by providing insights performance various models. findings not only enhance our understanding watershed dynamics but also highlight pivotal that can play improving sustainable management.

Language: Английский

Citations

24
Hybridization of Stochastic Hydrological Models and Machine Learning Methods for Improving Rainfall-Runoff Modelling DOI Creative Commons

Sianou Ezéckiel Houénafa,

Olatunji Johnson,

Erick Kiplangat Ronoh

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104079 - 104079

Published: Jan. 1, 2025

Language: Английский

Citations

3
A residual learning-based grey system model and its applications in Electricity Transformer’s Seasonal oil temperature forecasting DOI
Yiwu Hao, Xin Ma, Lili Song

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 147, P. 110260 - 110260

Published: Feb. 25, 2025

Language: Английский

Citations

3
Comparative analysis of data driven rainfall-runoff models in the Kolar river basin DOI Creative Commons
Deepak Kumar Tiwari, Vijendra Kumar,

Anuj Goyal

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102682 - 102682

Published: Aug. 8, 2024

To effectively tackle the challenges posed by climate change, it is crucial to enhance accuracy of rainfall-runoff models ensure reliability amidst changing climatic conditions. Neural networks, renowned for their ability capture complex patterns and relationships within uncertain input output data, offer valuable tools in this pursuit. This study aims evaluate efficacy two neural network (NN) models: Radial Basis Function Network (RBFNN) Model Tree M5 (MTM5NN). These are assessed both individually combination with Wavelet (WT) data processing technique modeling Kolar River watershed located Madhya Pradesh, India. Fifteen were developed employing four algorithms: RBFNN models, WRBFNN (RBF model integrating wavelet components rainfall as inputs), MTM5NN, WMTM5NN (MT incorporating inputs). Initially, runoff underwent normalization applied MTM5NN networks. Subsequently, time series decomposed using transforms, resulting various sub-time signals such approximations decompositions. derived then utilized specifically designated WMTM5NN. The most effective identified was 8 WMTM5NN, which demonstrated R2 values close 0.97, outperforming other models. results underscore superior performance model, highlighting its effectiveness achieving heightened predicting specific watershed.

Language: Английский

Citations

10
Modeling sediment accumulation in Pare Reservoir using HEC-RAS 2D: Assessing storage capacity over a 10-year period DOI Creative Commons
Filli Pratama, Siska Wulandari, Faizal Immaddudin Wira Rohmat

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 104333 - 104333

Published: Feb. 1, 2025

Language: Английский

Citations

2
Residual energy evaluation in vortex structures: On the application of machine learning models DOI Creative Commons
Mohammad Najafzadeh, Mohammad Mahmoudi-Rad

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102792 - 102792

Published: Aug. 30, 2024

Vortex structures are widely employed for energy dissipation in urban surface water conveyance systems. When transporting wastewater through these networks, a substantial amount of is dissipated. The effectiveness usually evaluated by their efficiency dissipating energy. Recent literature reviews on vortex have emphasized that, despite numerous experimental studies aimed at assessing hydraulic performance, reliable mathematical model to predict the residual head ratio remains elusive. In this study, resilient numerical models employing Artificial Intelligence (AI) methodologies (such as non-parametric regression, decision trees, and ensemble learning) been structured tests. By analyzing experiments, three primary factors, referred flow Froude number (Fr), sump height (Hs) shaft diameter (D), drop total (L) (D) were determined estimate ratio. Through computed downstream (E2) upstream (E1) structure. During training testing phases AI models, results statistical tests, serving quantitative evaluations, shown that learning namely Adaptive Boosting (AdaBoost) Categorical (CatBoost) had higher level E2/E1 predictions followed Model Tree (MT), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Extreme Gradient (XGBoost) Multivariate Regression Spline (MARS). Additionally, second-order regression-based equation was obtained from Fully Factorial Method (FFM) which lower precision (R = 0.8275, RMSE 0.1156, MAE 0.0846) when compared with all predictive models. Variations effective factors (i.e., Fr, L/D, Hs/D) versus predicted ratios well agreement observational Moreover, Sobol's index indicated Fr most parameter evaluation

Language: Английский

Citations

9
Streamlining the monitoring and assessment of irrigation groundwater quality using machine learning techniques DOI Creative Commons
Ahmed Makhlouf, Mustafa El-Rawy, Shinjiro Kanae

et al.

Environmental Earth Sciences, Journal Year: 2025, Volume and Issue: 84(5)

Published: March 1, 2025

Language: Английский

Citations

1
Hydrological responses projection to the potential impact of climate change under CMIP6 models scenarios in Omo River Basin, Ethiopia DOI Creative Commons
Tolera Abdissa Feyissa, Tamene Adugna Demissie, Fokke Saathoff

et al.

Results in Engineering, Journal Year: 2024, Volume and Issue: 23, P. 102708 - 102708

Published: Aug. 9, 2024

Climate change has a negative impact on the basin's hydrological processes and water resources. In this study, projected impacts of climate in Omo River Basin was evaluated under two Shared Socioeconomic Pathways (SSP245 SSP585) scenarios. The latest Coupled Model Inter-comparison Project (CMIP6) model dataset precipitation temperature were used to assess anticipated basin. SWAT simulate effects throughout baseline (1990–2019), near (2031–2060), far future (2071–2100) periods. predicted stream flow will increase annually monthly June, July, August, September (JJAS) both scenarios except decrease months March, April, May (MAM) SSP245 scenario. basin mean annual seasonal (JJAS MAM) surface runoff SSP585 scenarios; however, it decreases groundwater decline MAM Likewise, yield scenario, nevertheless, increases potential evapotranspiration with over all circumstances. There be significant spatial variations balance components future. results study essential for managing resources future, creating plans coping change, reducing risk flooding scarcity.

Language: Английский

Citations

3
AI-driven forecasting of river discharge: the case study of the Himalayan mountainous river DOI
Shakeel Ahmad Rather, Mahesh Patel, Kanish Kapoor

et al.

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(2)

Published: Feb. 1, 2025

Language: Английский

Citations

0
Multi-approaches Evaluation for Prediction of Discharge Coefficient of Porous Broad-Crested Weirs Under Upstream Partial Blockage DOI

Sanaz Hasanian Shirvan,

Bahareh Pirzadeh,

Seyed Hosein Rajaei

et al.

Iranian Journal of Science and Technology Transactions of Civil Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 7, 2025

Language: Английский

Citations

0