Analytical Prediction of Critical Transitions in Oscillator Networks With Non‐Local Links
Advanced Science, EarlyView.An analytical framework reveals how global coupling, second‐harmonic strength, noise, and network structure govern oscillator‐based Ising dynamics. Spectral reduction predicts stability boundaries, while Fokker–Planck analysis captures one‐ to two‐cluster transitions and identifies conditions favoring low‐energy configurations.
Qiang Li +5 more
wiley +1 more source
Parameter calibration of finite element model of reinforced concrete arch bridge based on ISOA-RBF neural network. [PDF]
Sci RepPeng W +4 more
europepmc +1 more source
Enhancing Specific Stiffness of Nano‐Architected Materials Through Generative AI and Active Learning
Advanced Science, EarlyView.A structure‐centric generative framework searches voxelated design space directly, coupling a variational autoencoder with multi‐objective optimization and active learning to progressively expand the validated design domain. The discovered nano‐architectures, realized as pyrolytic carbon by two‐photon lithography, deliver 18–23% higher stiffness and 26–
Jinwook Yeo +4 more
wiley +1 more source
A Mesh Updating Framework for Shell-Element Finite Element Models Based on Projection of Anomaly Regions Extracted from Point-Cloud Data. [PDF]
Sensors (Basel)Wang J, Nishio M.
europepmc +1 more source
LLM‐Assisted Design of Ultralow‐κ$\kappa$ Chalcogenides
Advanced Science, EarlyView.An AI assisted, physics guided workflow accelerates the discovery of ultralow thermal conductivity materials by combining Bayesian optimization, evidence conditioned LLM reasoning, and automated physics‐based validation. The framework uncovers dynamically stable Ag based chalcogenides with ultralow thermal conductivity and promising thermoelectric ...
Yujie Liu +9 more
wiley +1 more source
Advanced Science, EarlyView.Probabilistic Ising machines are introduced as hardware‐native Gaussian samplers for edge communication workloads. Tunable variance and sampling density enable accurate distributions for Falcon‐class post‐quantum signatures and diffusion‐based semantic communication.
Davi Rodrigues +10 more
wiley +1 more source
Training-Free Structural Damage Localization Using Spatial-Correlation Sensor Networks: Full-Scale Validation on a Seven-Story Reinforced-Concrete Building. [PDF]
Sensors (Basel)Ghorbani E, Hackl J.
europepmc +1 more source
AI‐EXAFS: Physics‐Informed Prediction of EXAFS from Atomic Structure
Advanced Science, EarlyView.AI‐EXAFS presents a neural network to reproduce EXAFS. Trained on synthetic data and with a careful selection of the settings both for the physical representation of the system and following the experimental heuristic loss functions, the model is capable of reproducing EXAFS spectra for molecules from the tridimensional structure.
Javier Heras‐Domingo +6 more
wiley +1 more source
Research progress on digital-twin-driven full life-cycle design and manufacturing of rehabilitation assistive devices. [PDF]
Front Bioeng BiotechnolTian H, Song X, Li D.
europepmc +1 more source
Improved Skills for Predicting Sub‐Seasonal to Seasonal Global Sea Surface Temperature
Advanced Science, EarlyView.Addressing the critical Sub‐seasonal to Seasonal predictability gap, this study presents CAS‐Canglong, a novel deep learning framework. By leveraging 3D Swin‐Transformers to capture long‐range ocean interactions, the model demonstrates superior skill over traditional GCMs.
Longhao Wang +6 more
wiley +1 more source