Advanced Generalized Machine Learning Models for Predicting Hydrogen–Brine Interfacial Tension in Underground Hydrogen Storage Systems

Advanced generalized machine learning models for predicting hydrogen–brine interfacial tension in underground hydrogen storage systems

The global transition to clean energy has highlighted hydrogen (H2) as a sustainable fuel, with underground hydrogen storage (UHS) in geological formations emerging as a key solution. Accurately predicting fluid interactions, particularly interfacial tension (IFT), is critical for ensuring reservoir integrity and storage security in UHS. IFT is key in fluid behavior, influencing structural and residual trapping capacities. However, measuring IFT…

Machine Learning Optimisation: Performance, Cost And Large Language Model Tuning.

Optimisation techniques including distributed data parallelism, LoRA, and QAT demonstrably enhance the efficiency of machine learning models – particularly large language models – across diverse hardware configurations such as the H100 GPU, reducing iteration times and VRAM utilisation while acknowledging task-specific performance variations.