Modeling thermo-physical properties of hydrogen utilizing machine learning schemes: Viscosity, density, diffusivity, and thermal conductivity

International Journal of Hydrogen Energy, Journal Year: 2024, Volume and Issue: 72, P. 1127 - 1142

Published: June 1, 2024

Language: Английский

---

Exploring advanced artificial intelligence techniques for efficient hydrogen storage in metal organic frameworks

Adsorption, Journal Year: 2025, Volume and Issue: 31(2)

Published: Jan. 31, 2025

Language: Английский

---

White-box methodologies for achieving robust correlations in hydrogen storage with metal-organic frameworks

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

Published: Feb. 10, 2025

Hydrogen is recognized as a clean energy replacement for non-renewable fossil fuels, and the utilization of metal-organic frameworks (MOFs) hydrogen storage has gained considerable interest in recent years. In this study, MOFs was estimated using white-box methods, namely group method data handling (GMDH), genetic programming (GP), gene expression (GEP), which are robust soft-computing methods known generating innovative correlations. To end, temperature, pressure, pore volume, surface area were implemented input parameters constructing these After that, superiority established correlations demonstrated through multiple statistical graphical error assessment. The results indicated, GMDH model demonstrates highest accuracy with root mean square (RMSE), absolute (MAE) values 0.410 0.307, respectively. However, GEP model's comparable to that model. addition, sensitivity assessment showed volume pressure exhibit strongest linear non-linear relationships, respectively, H2 MOFs. This by Pearson correlation coefficient 0.5 Spearman 0.56, Furthermore, temperature had minimal negative impact on according Pearson, Spearman, Kendall coefficients. Finally, confirm findings model, leverage approach applied, demonstrating 96% falls within acceptable region, confirming reliability developed models.

Language: Английский

---

Applying artificial intelligence for forecasting behavior in a liquefied hydrogen unit

International Journal of Hydrogen Energy, Journal Year: 2025, Volume and Issue: 114, P. 31 - 51

Published: March 1, 2025

Language: Английский

---

EFFECT OF SEASONAL-TREND DECOMPOSITION ON MACHINE LEARNING-BASED SUSPENDED SEDIMENT LOAD PREDICTION PERFORMANCE

Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, Journal Year: 2025, Volume and Issue: 28(1), P. 1 - 18

Published: March 3, 2025

Forecasting of sediment is vital for water resources management. In this study, the machine learning-based prediction performance suspended load (SSL) at Bulakbaşı station Kızılırmak River was investigated. Also, effect seasonal decomposition on searched. Accordingly, Support Vector Machine (SVM), Adaptive Boosting (AdaBoost), and Generalized Regression Neural Network (GRNN) methods were used SSL prediction. Grid Search (GS) algorithm preferred hyperparameter optimization. The component obtained by Seasonal-Trend using LOESS (STL) method. Six input combinations generated flow (Qt), lag (Qt-1), (S-SSLt). According to findings, AdaBoost (M6-NSETrain=0.914, M4-NSETest=0.765), SVM (M6-NSETrain=0.912, M6-NSETest=0.863), GRNN M4-NSETest=0.834) models produced quite consistent results. test phase, SVM-M6 (R2=0.893, NSE=0.863) most successful model according various evaluation metrics. It also observed that last three combinations, where added, generally improved performance. For in which model, R2=0.873, NSE=0.820 values combination without (M3), R2=0.893, NSE=0.863 with (M6)

Language: Английский

---

Research on quantitative analysis method of shale oil reservoir sensitivity based on mineral analysis

Geoenergy Science and Engineering, Journal Year: 2024, Volume and Issue: 239, P. 212952 - 212952

Published: May 22, 2024

Language: Английский

---

A comparative study of machine learning frameworks for predicting CO2 conversion into light olefins

Fuel, Journal Year: 2024, Volume and Issue: 379, P. 133017 - 133017

Published: Sept. 9, 2024

Language: Английский

---