August 14, 2025The Canadian Journal of Chemical Engineering

Application of machine learning in modelling gas dispersion coefficients for hydrogen storage in porous media

View Full Paper

Ask AI

Bookmark

Authors

AAAli AkbariLakehead University

Discussion

Member takes

Implication

Integration of machine learning and core flooding experiments improves gas dispersion prediction for hydrogen storage, optimizing efficiency and gas purity.

Key Points

Support vector regression demonstrated superior predictive performance for gas dispersion coefficients, leading to more reliable hydrogen storage.
The machine learning model achieved R² values above 0.996 for methane, nitrogen, and carbon dioxide, indicating high accuracy in gas dispersion prediction.
Core flooding experiments combined with advanced modeling captured complex gas mixing behavior in porous media effectively.
This approach enhances understanding of gas dispersion, improving hydrogen storage systems' efficiency and reliability for energy management.

Cite This Study

Ali Akbari (2025) studied this question.

synapsesocial.com/papers/68af50a7ad7bf08b1ead8ee0 https://doi.org/10.1002/cjce.70064

View Full Paper

Ask AI

Bookmark

Implication

Integration of machine learning and core flooding experiments improves gas dispersion prediction for hydrogen storage, optimizing efficiency and gas purity.

Application of machine learning in modelling gas dispersion coefficients for hydrogen storage in porous media

Discussion

Member takes

Implication

Key Points

Cite This Study

Application of machine learning in modelling gas dispersion coefficients for hydrogen storage in porous media

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider