Property prediction for ionic liquids without prior structural knowledge using limited experimental data: A data-driven neural recommender system leveraging transfer learning
This work addresses the problem of efficient ionic liquid screening for process design, offering a scalable solution that is incremental by building on existing transfer learning and simulation methods.
The study tackled the challenge of predicting key thermophysical properties for ionic liquids with limited experimental data by developing a data-driven transfer learning framework using a neural recommender system, achieving improved performance for four out of five properties and enabling scalable prediction for over 700,000 IL combinations.
Ionic liquids (ILs) have emerged as versatile replacements for traditional solvents because their physicochemical properties can be precisely tailored to various applications. However, accurately predicting key thermophysical properties remains challenging due to the vast chemical design space and the limited availability of experimental data. In this study, we present a data-driven transfer learning framework that leverages a neural recommender system (NRS) to enable reliable property prediction for ILs using sparse experimental datasets. The approach involves a two-stage process: first, pre-training NRS models on COSMO-RS-based simulated data at fixed temperature and pressure to learn property-specific structural embeddings for cations and anions; and second, fine-tuning simple feedforward neural networks using these embeddings with experimental data at varying temperatures and pressures. In this work, five essential IL properties are considered: density, viscosity, surface tension, heat capacity, and melting point. The framework supports both within-property and cross-property knowledge transfer. Notably, pre-trained models for density, viscosity, and heat capacity are used to fine-tune models for all five target properties, achieving improved performance by a substantial margin for four of them. The model exhibits robust extrapolation to previously unseen ILs. Moreover, the final trained models enable property prediction for over 700,000 IL combinations, offering a scalable solution for IL screening in process design. This work highlights the effectiveness of combining simulated data and transfer learning to overcome sparsity in the experimental data.