MLPROP -- an open interactive web interface for thermophysical property prediction with machine learning

2025-04-08

AI Summary

Despite high accuracy and broad coverage of existing machine learning (ML) models for thermophysical property prediction, their complex integration and steep learning curve hinder adoption by non-ML-expert chemical engineers. To address this, we propose MLPROP—a fully open-source, interactive web platform delivering low-code ML services tailored to chemical thermodynamics. MLPROP integrates novel models including the graph neural network GRAPPA, an enhanced UNIFAC 2.0, and HANNA, enabling online prediction of key properties (e.g., vapor pressure, activity coefficients, vapor–liquid equilibrium) and NRTL parameter regression. Lightweight and embeddable, the platform supports over 100 pure components and binary mixtures, achieving prediction accuracy comparable to conventional methods. Publicly available at no cost, MLPROP significantly advances the practical deployment of ML in process engineering by bridging the gap between advanced modeling and domain-specific usability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Machine learning (ML) enables the development of powerful methods for predicting thermophysical properties with unprecedented scope and accuracy. However, technical barriers like cumbersome implementation in established workflows hinder their application in practice. With MLPROP, we provide an interactive web interface for directly applying advanced ML methods to predict thermophysical properties without requiring ML expertise, thereby substantially increasing the accessibility of novel models. MLPROP currently includes models for predicting the vapor pressure of pure components (GRAPPA), activity coefficients and vapor-liquid equilibria in binary mixtures (UNIFAC 2.0, mod. UNIFAC 2.0, and HANNA), and a routine to fit NRTL parameters to the model predictions. MLPROP will be continuously updated and extended and is accessible free of charge via https://ml-prop.mv.rptu.de/. MLPROP removes the barrier to learning and experimenting with new ML-based methods for predicting thermophysical properties. The source code of all models is available as open source, which allows integration into existing workflows.

Problem

• Provides interactive web interface for thermophysical property prediction
• Removes technical barriers to applying ML methods without expertise
• Enables integration of open-source ML models into existing workflows

Innovation

• Interactive web interface for ML property prediction
• No ML expertise required for thermophysical predictions
• Open source models for workflow integration