A research paper titled "Multi-Fidelity Physics-Informed Neural Networks with Bayesian Uncertainty Quantification and Adaptive Residual Learning for Efficient Solution of Parametric Partial Differential Equations" has been withdrawn by its author, Gustav Olaf Yunus Laitinen-Fredriksson Lundstrom-Imanov. The paper, originally submitted on February 1, 2026, and revised on September 6, 2026, proposed a novel multi-fidelity framework combining physics-informed neural networks with Bayesian uncertainty quantification and adaptive residual learning. This approach aimed to address the computational challenges of solving high-fidelity parametric partial differential equations by leveraging low-fidelity simulations alongside sparse high-fidelity data. AI
IMPACT This withdrawn research paper explored advanced techniques for solving complex physics problems using neural networks, but its withdrawal means its potential impact on AI applications in scientific computing is nullified.
RANK_REASON The cluster contains a withdrawn academic paper. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
