Tag: spatiotemporal modeling

A Mount Umyeon case study found that a physics-informed recurrent network achieved an 81.20% validation ROC-AUC for annual landslide peak ...

A Chiba University machine-learning model reconstructed missing regions in global satellite rainfall maps with higher accuracy and image quality than ...

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 new graph neural network framework shows that continuous emotional embeddings from disaster images can predict how far and how ...

A new computational model shows that a small pool of internalized follicle-stimulating hormone receptors can drive outsized endosomal signaling, revealing ...

A new diffusion-model-based tool called Influpaint encodes influenza seasons as spatiotemporal images and generates competitive, probabilistic forecasts of epidemic trajectories ...

Researchers at Linyi University have combined wavelet decomposition with denoising diffusion models to forecast urban traffic flow more accurately across ...

Researchers have developed a cross-temporal attention network that fuses short-term motion and long-term behavioral cues to recognize gun threats, aggression, ...

Researchers have developed a frequency-domain AI network that detects periodic patterns in human check-in data to predict a user's next ...

Researchers have developed STAAT, a transformer-based AI model that improves anomaly detection in IoT sensor networks by jointly modeling spatial ...