ConfEviSurrogate: A Conformalized Evidential Surrogate Model for Uncertainty Quantification
This addresses the need for reliable uncertainty quantification in surrogate models for scientific simulations, offering a novel method that improves coverage and efficiency, though it appears incremental as it builds on existing conformal prediction and evidential approaches.
The paper tackled the problem of unreliable uncertainty quantification in surrogate models for complex simulations by introducing ConfEviSurrogate, which efficiently learns evidential distributions, separates uncertainty sources, and provides calibrated prediction intervals, demonstrating accurate predictions and robust estimates across cosmology, ocean dynamics, and fluid dynamics simulations.
Surrogate models, crucial for approximating complex simulation data across sciences, inherently carry uncertainties that range from simulation noise to model prediction errors. Without rigorous uncertainty quantification, predictions become unreliable and hence hinder analysis. While methods like Monte Carlo dropout and ensemble models exist, they are often costly, fail to isolate uncertainty types, and lack guaranteed coverage in prediction intervals. To address this, we introduce ConfEviSurrogate, a novel Conformalized Evidential Surrogate Model that can efficiently learn high-order evidential distributions, directly predict simulation outcomes, separate uncertainty sources, and provide prediction intervals. A conformal prediction-based calibration step further enhances interval reliability to ensure coverage and improve efficiency. Our ConfEviSurrogate demonstrates accurate predictions and robust uncertainty estimates in diverse simulations, including cosmology, ocean dynamics, and fluid dynamics.