SHRAV framework improves physical modeling and inverse design accuracy
SHRAV: State-Hypothesis-Reason-Action-Verify Framework for Physical Modeling and Inverse Design
Artificial IntelligenceComputational Engineering, Finance, and Science
Summary
Physical modeling and designing objects based on desired properties is often slow and complex because it needs continuous updates from previous calculations. The authors introduce SHRAV, a general method breaking down the process into clear steps involving state, hypotheses, reasoning, actions, and verification. This approach allows computing solutions more efficiently by reusing parts of the work and improving predictions. They tested SHRAV in electromagnetic simulations and a computer chip manufacturing design task, showing significant improvements in accuracy and speed.
What this means in practice
- •For computational physicists: Use SHRAV to speed up electromagnetic simulations by reusing computational states and improving prediction accuracy.
- •For semiconductor process engineers: Apply SHRAV to optimize photolithography mask designs and achieve more accurate patterning with fewer iterative updates.
Authors
Ziheng Guo, Yang Bu
Abstract
Physical modeling and inverse design require computation that can continue from reusable state. We introduce SHRAV, an architecture-independent computational framework organized around State, Hypothesis, Reason, Action, and Verify. Its central mechanism is a state-continuation core with declared reuse boundaries and explicit roles for learned evolution and numerical quantities. Forward configurations evolve predictive state and read out physical responses; inverse-design configurations additionally generate target-directed modifications and consume evaluator feedback. Electromagnetic world-model studies are mapped to forward configurations, with selected readout and reuse diagnostics reported here. Computational lithography demonstrates an inverse-design configuration: four fixed-weight design updates improve thresholded aerial-image intersection-over-union from 0.5313 to 0.8153 under independent scalar-pupil replay, with maximum absolute prediction-replay difference approximately 0.000824 between predictor estimates and independent replay.