Property prediction for ionic liquids without prior structural knowledge using limited experimental data: A data-driven neural recommender system leveraging transfer learning

2025-09-12

AI Summary

Predicting thermophysical properties (density, viscosity, surface tension, heat capacity, melting point) of ionic liquids faces dual challenges: lack of structural prior knowledge and scarcity of experimental data. Method: This study proposes a two-stage transfer learning neural recommendation system (NRS) framework. First, the model is pre-trained on large-scale simulated data generated by COSMO-RS; then, multi-task fine-tuning enables both intra-property and cross-property knowledge transfer. Contribution/Results: The approach significantly improves prediction accuracy under small-data regimes, outperforming state-of-the-art methods on four of the five target properties. It exhibits strong generalization capability, enabling efficient screening of over 700,000 previously uncharacterized ionic liquid combinations. By bridging computational simulation and experimental scarcity, this framework establishes a new paradigm for high-throughput ionic liquid design and property prediction.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Natural Language Processing: Learning & Optimization for NLP
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

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.

Problem

• Predicting ionic liquid properties without structural data
• Overcoming limited experimental data via transfer learning
• Enabling scalable screening for diverse ionic liquids

Innovation

• Neural recommender system with transfer learning
• Pre-training on simulated data with embeddings
• Fine-tuning with experimental data for prediction