New GNN methods target environmental and structural prediction

Arxiv CS.LG (machine learning)

Multiple arXiv preprints propose GNNs for PM2.5 forecasting, water storage reconstruction, traffic demand, and structural response. Architectures include auto-configured explainable GNNs, physics-guided dual-stream heterogeneous GNNs, and multi-view wind-guided KANs.

GNN

See 6 more sources

Low-Cost High-Order Singular Value Decomposition for Tensor-Based Reconstruction from Sparse Sensor Measurements: Urban Flow and Air-Quality Applications4 days agoArindam Sengupta, Paul Jeanney, Ricardo Vinuesa, Jose Miguel Perez, Soledad Le Clainche

MVG-KAN: Multi-View Geo-Wind Guided KAN for PM$_{2.5}$ Forecasting5 days agoCheng Huang, Muyao Guan, Jairus Yougui Railey, Ning Xu, Honghui Xu, Changjiang Zhang, Zhen Zhang, Shiqing Zhang, Cong Bai

GRACE: Gated Refinement for Accurate Causal Edge Discovery in High-Dimensional Time Series5 days agoMohammad Fesanghary, Abhinav Havaldar

Reconstructing GRACE Terrestrial Water Storage with Spatio-Temporal Graph Neural Networks: An Application to South America5 days agoLukas Arzoumanidis, Lara Johannsen, Klara Middendorf, Annette Eicker, Youness Dehbi

Structure-Aware Graph Multi-Task Learning for Dynamic Sparse OD Demand Prediction6 days agoMing Xu, Jiawei Cao

Physics-Guided Dual-Stream Heterogeneous Graph Neural Network for Predicting Full-Field Structural Response of Stiffened Panels6 days agoYuecheng Cai, Jasmin Jelovica

Arxiv CS.LG (machine learning)·Abdelkader DairiFouzi HarrouYing Sun

Jun 25, 4:00 AM