Learning operators from data is central to scientific machine learning. While DeepONets are widely used for their ability to handle complex domains, they require fixed sensor numbers and locations, lack mechanisms for uncertainty quantification, and are thus limited in practical applicability. Recent permutation-invariant extensions, such as the Variable-Input Deep Operator Network, relax these sensor constraints but still rely on sufficiently dense observations and cannot capture uncertainties arising from incomplete measurements or from operators with inherent randomness. To address these challenges, we propose UQ-SONet, a permutation-invariant operator learning framework with built-in uncertainty quantification. Our model integrates a set transformer embedding to handle sparse and variable sensor locations, and employs a conditional variational autoencoder to approximate the conditional distribution of the solution operator. By minimizing the negative ELBO, UQ-SONet provides principled uncertainty estimation while maintaining predictive accuracy. Numerical experiments on deterministic and stochastic PDEs, including the Navier-Stokes equation, demonstrate the robustness and effectiveness of the proposed framework.

Publication:

JOURNAL OF COMPUTATIONAL PHYSICS

http://dx.doi.org/10.1016/j.jcp.2026.115011

Author:

Ma, Lei

Shanghai Normal Univ, Dept Math, Shanghai, Peoples R China

Guo, Ling

Shanghai Normal Univ, Dept Math, Shanghai, Peoples R China

Wu, Hao (corresponding author)

Shanghai Jiao Tong Univ, Inst Nat Sci, Sch Math Sci, Shanghai, Peoples R China

Shanghai Jiao Tong Univ, MOE LSC, Shanghai, Peoples R China

Email address:hwu81@sjtu.edu.cn

Zhou, Tao

Chinese Acad Sci, AMSS, Inst Computat Math & Sci Engn Comp, Beijing, Peoples R China