Hybrid Atomistic Simulation With Dynamic Switching for Reaction Accuracy
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 inefficiencies in simulating complex chemical systems.
Innovation Solution
Implementing a hybrid simulation method that combines high-fidelity MLIPs with fixed shell simulations and electrostatic embedding, allowing for geometrically complex boundary conditions and reduced computational costs by using MLIPs with finite interaction ranges and dynamic boundary conditions.
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 costs
Solution Approach 1:
The patent creates a machine learning model that copies the behavior and accuracy of ab-initio calculations. The model is trained on ab-initio data and then used to predict interaction energies with similar accuracy but at much lower computational cost, effectively creating a fast replica of the expensive quantum mechanical calculations
Solution Approach 2:
The patent employs cheaper computational models (machine learning potentials and classical force fields) that can be used extensively without the high computational burden of ab-initio methods. These lower-fidelity models serve as disposable alternatives for routine simulations where full ab-initio accuracy is not required
2Productivity
If machine learning interatomic potentials are used to reduce computational costs, then productivity is improved, but measurement precision deteriorates due to inaccuracies in capturing discontinuities and physical charges
Solution Approach 1:
The patent creates a composite simulation approach that combines multiple models with different strengths. The hybrid system integrates machine learning potentials with classical force fields and incorporates electrostatic embedding to capture long-range effects, creating a composite model that achieves both computational efficiency and improved accuracy
Solution Approach 2:
The patent introduces an intermediary electrostatic embedding approach that mediates between the machine learning model and the surrounding environment. This intermediary layer captures long-range electrostatic effects and discontinuities that pure MLIPs miss, while maintaining the computational efficiency of the machine learning approach
3Device complexity
If fixed boundary conditions are used in simulations, then device complexity is reduced, but adaptability deteriorates due to inability to capture long-range effects
Solution Approach 1:
The patent transitions from static fixed boundaries to dynamic boundary conditions. The simulation box can expand and contract, and the boundary conditions adapt dynamically during the simulation to capture long-range effects. This dynamic approach maintains reasonable complexity while significantly improving the ability to model long-range interactions
Data Source
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.