Theoretical framework can predict how complex networks behave

The University of Hong Kong (HKU) has spearheaded an international research collaboration to develop a pioneering theoretical ...
Hosted on MSN

AI is digging deeper into geoscience research

From mineral exploration to seismic interpretation, AI is reshaping how geoscientists work with complex, multi-source data. Machine learning models, generative AI, and prompt engineering are enabling ...
IEEE

A 2D Physics-Informed Neural Network-Based Inverse-Design Method of Antenna Superstrate for Radiation and Scattering Problems

Abstract: Based on unsupervised physics-informed neural network (PINN) framework, a two-dimensional inverse-design method for antenna superstrate is proposed, which can simultaneously realize the ...
Hosted on MSN

Frontier supercomputer and AI crack plasma turbulence code

Scientists at the Department of Energy’s Oak Ridge National Laboratory have used the Frontier supercomputer, combined with AI, to model magnetic plasma turbulence with unprecedented accuracy. The ...
IEEE

Physics-Informed Koopman Neural Operator for Augmented Dynamics Visual Servoing of Multirotors

Abstract: This paper introduces a Physics-Informed Koopman Neural Operator (PI-KNO) for augmented dynamics visual servoing of multirotors that integrates Koopman operator theory with neural networks.
GitHub

Space Correlation Constrained Physics Informed Neural Network (SC-PINN) for Seismic Tomography

This repository contains the source code for the paper "Space Correlation Constrained Physics Informed Neural Network for Seismic Tomography", accepted by JGR: Machine Learning and Computation on ...
Frontiers

OrientationNN: a physics-informed lightweight neural network for real-time joint kinematics estimation from IMU data

Accurate joint kinematics estimation is essential for understanding human movement and supporting biomechanical applications. Although optical motion capture systems are accurate, their high cost, ...
Frontiers

Bridging computational power and environmental challenges: a perspective on neural network predictive models for environmental engineering

The escalating frequency and severity of extreme environmental events underscores the critical need for a paradigm shift from reactive to proactive management strategies. This perspective article ...
Scientific Research Publishing

Fatigue Life Prediction of Vehicle Rubber Elastic Support Components Based on Physics-Informed Neural Networks ()

Rubber is widely used in automotive vibration isolation systems due to its excellent mechanical properties and durability. However, elastomeric support components tend to experience performance ...
GitHub

Rapid Spatio-temporal MR Fingerprinting Using Physics-Informed Implicit Neural Representation

πMRF (Physics-informed implicit neural MRF) is a physics-informed unsupervised framework for accurate quantitative parameter mapping via global spatio-temporal inversion. piMRF/ ├── main.py # Runnable ...