Imagen de Portada

Uncertainties in Physics-informed Inverse Problems: The Hidden Risk in Scientific AI

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Mototake, Yoh-ichi, Sasaki, Makoto
Formato:	Preprint
Publicado:	2025
Materias:	Computational Physics Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Algebraic Geometrical Analysis of Metropolis Algorithm When Parameters Are Non-identifiable
por: Nagata, Kenji, et al.
Publicado: (2024)

Unsupervised feature selection using Bayesian Tucker decomposition
por: Taguchi, Y-h., et al.
Publicado: (2026)

Intrinsic Signal Models Defined by the High-Dimensional, Small-Sample Limit
por: Mototake, Yoh-ichi, et al.
Publicado: (2023)

Autoregressive with Slack Time Series Model for Forecasting a Partially-Observed Dynamical Time Series
por: Okuno, Akifumi, et al.
Publicado: (2023)

Integrating Bayesian Spectral Deconvolution and Expert Scientific Reasoning for Robust Peak Estimation
por: Okubo, Hayato, et al.
Publicado: (2026)

Contrast-Source-Based Physics-Driven Neural Network for Inverse Scattering Problems
por: Du, Yutong, et al.
Publicado: (2026)

Fast Physics-Driven Untrained Network for Highly Nonlinear Inverse Scattering Problems
por: Du, Yutong, et al.
Publicado: (2026)

Efficient Deconvolution in Populational Inverse Problems
por: Vadeboncoeur, Arnaud, et al.
Publicado: (2025)

Adaptive Uncertainty-Guided Model Selection for Data-Driven PDE Discovery
por: Thanasutives, Pongpisit, et al.
Publicado: (2023)

Physics-Informed Uncertainty Enables Reliable AI-driven Design
por: Xue, Tingkai, et al.
Publicado: (2026)

Examining the robustness of Physics-Informed Neural Networks to noise for Inverse Problems
por: Jekic, Aleksandra, et al.
Publicado: (2025)

Is AI Robust Enough for Scientific Research?
por: Zhang, Jun-Jie, et al.
Publicado: (2024)

A Model-Guided Neural Network Method for the Inverse Scattering Problem
por: Tsang, Olivia, et al.
Publicado: (2025)

Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problems
por: Du, Yutong, et al.
Publicado: (2025)

TAEN: A Model-Constrained Tikhonov Autoencoder Network for Forward and Inverse Problems
por: Nguyen, Hai V., et al.
Publicado: (2024)

Evidential Physics-Informed Neural Networks for Scientific Discovery
por: Tan, Hai Siong, et al.
Publicado: (2025)

Physics-Informed Deep Contrast Source Inversion: A Unified Framework for Inverse Scattering Problems
por: Sun, Haoran, et al.
Publicado: (2025)

PIED: Physics-Informed Experimental Design for Inverse Problems
por: Hemachandra, Apivich, et al.
Publicado: (2025)

PHASE: Physics-Integrated, Heterogeneity-Aware Surrogates for Scientific Simulations
por: Gao, Dawei, et al.
Publicado: (2025)

Physics-Informed Weakly Supervised Learning for Interatomic Potentials
por: Takamoto, Makoto, et al.
Publicado: (2024)

AI for Scientific Discovery is a Social Problem
por: Channing, Georgia, et al.
Publicado: (2025)

Physics-informed AI and ML-based sparse system identification algorithm for discovery of PDE's representing nonlinear dynamic systems
por: Pal, Ashish, et al.
Publicado: (2024)

Bayesian Inference for PDE-based Inverse Problems using the Optimization of a Discrete Loss
por: Amoudruz, Lucas, et al.
Publicado: (2025)

Differentiation Strategies for Acoustic Inverse Problems: Admittance Estimation and Shape Optimization
por: Borrel-Jensen, Nikolas, et al.
Publicado: (2025)

Instance-Wise Adaptive Sampling for Dataset Construction in Approximating Inverse Problem Solutions
por: Han, Jiequn, et al.
Publicado: (2025)

Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
por: Zaverkin, Viktor, et al.
Publicado: (2023)

Calibrated Physics-Informed Uncertainty Quantification
por: Gopakumar, Vignesh, et al.
Publicado: (2025)

PIP$^2$ Net: Physics-informed Partition Penalty Deep Operator Network
por: Mi, Hongjin, et al.
Publicado: (2025)

SPINONet: Scalable Spiking Physics-informed Neural Operator for Computational Mechanics Applications
por: Garg, Shailesh, et al.
Publicado: (2026)

Physics-informed Deep Learning to Solve Three-dimensional Terzaghi Consolidation Equation: Forward and Inverse Problems
por: Yuan, Biao, et al.
Publicado: (2024)

Neural Operators for Accelerating Scientific Simulations and Design
por: Azizzadenesheli, Kamyar, et al.
Publicado: (2023)

PI-MFM: Physics-informed multimodal foundation model for solving partial differential equations
por: Zhu, Min, et al.
Publicado: (2025)

Distributional Consistency Loss: Beyond Pointwise Data Terms in Inverse Problems
por: Webber, George, et al.
Publicado: (2025)

Physics-Informed Machine Learning for Two-Phase Moving-Interface and Stefan Problems
por: Chang, Che-Chia, et al.
Publicado: (2025)

PDEInvBench: A Comprehensive Dataset and Design Space Exploration of Neural Networks for PDE Inverse Problems
por: Goel, Divyam, et al.
Publicado: (2026)

Scientific Machine Learning Seismology
por: Okazaki, Tomohisa
Publicado: (2024)

LT-PINN: Lagrangian Topology-conscious Physics-informed Neural Network for Boundary-focused Engineering Optimization
por: Zhou, Yuanye, et al.
Publicado: (2025)

Error Analysis and Numerical Algorithm for PDE Approximation with Hidden-Layer Concatenated Physics Informed Neural Networks
por: Qian, Yianxia, et al.
Publicado: (2024)

Inverse Modeling of Dielectric Response in Time Domain using Physics-Informed Neural Networks
por: Esenov, Emir, et al.
Publicado: (2025)

Physics-informed AI Accelerated Retention Analysis of Ferroelectric Vertical NAND: From Day-Scale TCAD to Second-Scale Surrogate Model
por: Jeong, Gyujun, et al.
Publicado: (2026)