Hybrid Atomistic Simulation for Accurate Long-Range Chemical Reactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning interatomic potential (MLIP) methods face challenges such as scalability issues, inability to capture long-range effects, and inaccuracies in capturing discontinuities and physical charges, leading to high computational costs and limited applicability in complex chemical systems.
Innovation Solution
Implementing a hybrid simulation method that combines high-fidelity MLIPs with fixed shell simulations and electrostatic embedding, allowing for accurate and efficient simulation of chemical systems with complex boundary conditions, using ML/MM and ML/ML hybrid models to address scalability and long-range interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ab-initio calculations are used to obtain accurate estimations of interaction energies, then measurement precision is improved, but productivity deteriorates due to high computational cost
Solution Approach 1:
The patent creates a machine learning model that copies the accurate predictions of ab-initio calculations. The model is trained on ab-initio data and then used to replicate those accurate interaction energy estimations without incurring the high computational cost of running ab-initio calculations again, thus achieving both accuracy and efficiency
Solution Approach 2:
The patent replaces expensive ab-initio calculations with a cheaper machine learning model. The ML model, once trained, provides rapid predictions at a fraction of the computational cost, making it feasible to perform numerous simulations that would be prohibitively expensive using ab-initio methods
2Productivity
If machine learned interatomic potentials are used to reduce computational costs, then productivity is improved, but measurement precision deteriorates due to reduced accuracy
Solution Approach 1:
The patent changes the parameters and architecture of the machine learning model to improve its accuracy. By adjusting model parameters, using more sophisticated neural network architectures, and incorporating additional physical constraints, the model achieves accuracy closer to ab-initio calculations while maintaining computational efficiency
Solution Approach 2:
The patent creates a composite modeling approach that combines machine learning interatomic potentials with classical force fields. This hybrid model leverages the strengths of both approaches: the accuracy of MLIPs for chemical reactions and the computational efficiency of classical force fields for bulk material behavior
3Measurement precision
If hybrid simulation methods are used to capture long-range effects, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent divides the simulation system into different regions with different levels of accuracy. High-accuracy MLIP models are applied only to regions where chemical reactions occur, while lower-accuracy classical force fields are used for bulk regions. This segmentation reduces overall computational cost while maintaining accuracy where needed
Solution Approach 2:
The patent introduces an intermediary layer that bridges the MLIP and classical force field regions. This intermediary handles the interface between the two models, ensuring smooth transitions and proper coupling of long-range effects without requiring the entire system to use the computationally expensive MLIP
Data Source
Figure 1~2
Figure 3
Figure 4A~5
AI summary
A machine learning simulation method of determining a physical state of interaction between atoms from one or more physical properties of the atoms is disclosed. The method includes dynamically evolving the atoms via a classical force field or a first model having a first accuracy during a first period of the machine learning simulation, dynamically evolving chemical reactions of the atoms via a second model having a second accuracy higher than the first accuracy during a second period of the machine learning simulation, and identifying a flagging event to start and/or stop the second period of the machine learning simulation. The evolving simulation may be used to determine the physical state of interaction between the atoms. The physical state of interaction between the atoms may be used to control the chemical system.