Hybrid ML Model Predicts Electrolyte Activities

Researchers have developed a novel hybrid machine learning model, Bromley-MCM, to predict activities in aqueous electrolyte solutions. This model integrates the physics-based Bromley model with a matrix completion method, enabling the prediction of electrolyte-specific parameters for the Bromley model. Trained on data from the Dortmund Data Bank for 478 electrolytes, the Bromley-MCM model can now predict activities for a significantly larger set of 9,296 electrolytes, extending the applicability of the Bromley model while maintaining high accuracy. AI

IMPACT This hybrid model could accelerate research and development in chemical engineering and materials science by enabling predictions for previously unstudied electrolyte systems.

RANK_REASON The cluster contains an academic paper detailing a new hybrid machine learning model for predicting chemical properties. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Bromley
• Bromley-MCM
• Dortmund Data Bank
• matrix completion
• Pitzer

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →