Tag: physics-informed deep learning

A hybrid physics-informed neural network extracts concrete fracture parameters from stress images with an error margin of about 3.9 percent.

A physics-informed GRU–GNN study estimated marine oil-spill growth and spatial spread over 48 hours, but held-out tests showed limited case-specific ...

A dual-graph deep learning network that hard-codes petroleum physics alongside learned statistics cuts oil production prediction error to about 20 ...

Researchers have developed a hybrid U-Net Transformer neural operator and an open-source simulation framework that significantly improves the speed and ...

A new study published in Communications Earth & Environment reports a physics-guided deep learning system designed to forecast wind speed ...

In an era where urban landscapes evolve at a breakneck pace, understanding human mobility has emerged as a cornerstone for ...

In the rapidly evolving field of renewable energy, agrivoltaics—the simultaneous use of land for both agriculture and solar photovoltaic power ...

In the rapidly evolving intersection of artificial intelligence and applied mathematics, a transformative breakthrough has emerged poised to reshape how ...