3 papers
cs.LG2025
BuildSTG: A Multi-building Energy Load Forecasting Method using Spatio-Temporal Graph Neural Network
Yongzheng Liu, Yiming Wang, Po Xu +3
Due to the extensive availability of operation data, data-driven methods show strong capabilities in predicting building energy loads. Buildings with similar features often share e…
cs.LG2025
Capturing Unseen Spatial Heat Extremes Through Dependence-Aware Generative Modeling
Xinyue Liu, Xiao Peng, Shuyue Yan +5
Observed records of climate extremes provide an incomplete view of risk, missing "unseen" events beyond historical experience. Ignoring spatial dependence further underestimates ha…
physics.geo-ph2024
Physics-Informed Convolutional Decoder (PICD): A novel approach for direct inversion of heterogeneous subsurface flow
Nanzhe Wang, Xiang-Zhao Kong, Dongxiao Zhang
In this study, we present the development and application of the physics-informed convolutional decoder (PICD) framework for inverse modeling of heterogenous groundwater flow. PICD…