Information-distilled physics informed deep learning for high order differential inverse problems with extreme discontinuities. [PDF]
Peng M, Tang H.
europepmc +1 more source
Equivariant neural networks for inverse problems. [PDF]
Celledoni E +5 more
europepmc +1 more source
Laser‐induced graphene (LIG) provides a scalable, laser‐direct‐written route to porous graphene architecture with tunable chemistry and defect density. Through heterojunction engineering, catalytic functionalization, and intrinsic self‐heating, LIG achieves highly sensitive and selective detection of NOX, NH3, H2, and humidity, supporting next ...
Md Abu Sayeed Biswas +6 more
wiley +1 more source
On Learned Operator Correction in Inverse Problems. [PDF]
Lunz S +4 more
europepmc +1 more source
BioSenSRRF is an open‐source workflow that combines conventional FRET biosensors with SRRF reconstruction to generate sub‐diffraction FRET index maps on standard microscopes. The pipeline integrates automated image registration, SRRF reconstruction, quantitative FRET index calculation, and random line‐based hotspot analysis to uncover AURKA‐dependent ...
Nicolas Y. Jolivet +5 more
wiley +1 more source
WF-PINNs: solving forward and inverse problems of burgers equation with steep gradients using weak-form physics-informed neural networks. [PDF]
Wang X, Yi S, Gu H, Xu J, Xu W.
europepmc +1 more source
Traction Force Microscopy for Viscoelastic Substrates: A Semi‐Analytical Method
A semi‐analytical viscoelastic traction force microscopy framework is introduced for quantifying time‐resolved cell tractions on flat finite‐thickness substrates. The method generalizes elastic traction force microscopy to Generalized Maxwell materials, identifies when elastic approximations remain valid and, when they do not, shows that inferred ...
Adrià Villacrosa‐Ribas +10 more
wiley +1 more source
Optimization of Sparse Sensor Layouts and Data-Driven Reconstruction Methods for Steady-State and Transient Thermal Field Inverse Problems. [PDF]
Yuan Q, Yao P, Zhao W, Zhang B.
europepmc +1 more source
Physics‐Embedded Neural Network: A Novel Approach to Design Polymeric Materials
Traditional black‐box models for polymer mechanics rely solely on data and lack physical interpretability. This work presents a physics‐embedded neural network (PENN) that integrates constitutive equations into machine learning. The approach ensures reliable stress predictions, provides interpretable parameters, and enables performance‐driven, inverse ...
Siqi Zhan +8 more
wiley +1 more source
Semantic regularization of electromagnetic inverse problems. [PDF]
Zhang H +5 more
europepmc +1 more source

