Thermodynamic properties of chemically disordered compounds via AI-driven estimation of partition function with the PULSE method
For materials scientists studying chemically disordered compounds, this method offers a more efficient alternative to computationally expensive Monte Carlo simulations.
The paper presents an improved PULSE method to estimate thermodynamic properties of chemically disordered compounds, reducing computational cost compared to Monte Carlo methods. Using the 2D Ising model, it accurately reproduces average properties with high precision and efficiency.
In this article, we present an improved version of the PULSE method (Partition function Unsupervised Learning Sampling and Evaluation) for estimating the thermodynamic properties of chemically disordered compounds. The aim is to reduce the computational cost of Monte Carlo approaches for this type of material and to demonstrate that this generative tool can estimate thermodynamic properties by sampling and estimating the partition function of the system. To validate this innovative approach, we use the 2D Ising model as a benchmark. We demonstrate that our method accurately reproduces average properties with high precision and efficiency compared to traditional Monte Carlo sampling methods. Our results highlight the efficiency and adaptability of the PULSE method, making it a valuable tool for studying materials for which conventional methods are too inefficient to compute properties affected by chemical disorder at low cost.