Thermal Earth Model for the Conterminous United States Using an Interpolative Physics-Informed Graph Neural Network (InterPIGNN)

arXiv:2403.09961v1 Announce Type: cross
Abstract: This study presents a data-driven spatial interpolation algorithm based on physics-informed graph neural networks used to develop national temperature-at-depth maps for the conterminous United States. The model was trained to approximately satisfy the three-dimensional heat conduction law by simultaneously predicting subsurface temperature, surface heat flow, and rock thermal conductivity. In addition to bottomhole temperature measurements, we incorporated other physical quantities as model inputs, such as depth, geographic coordinates, elevation, sediment thickness, magnetic anomaly, gravity anomaly, …

abstract algorithm arxiv cs.lg data data-driven earth graph graph neural network graph neural networks heat law maps network networks neural network neural networks physics physics.geo-ph physics-informed spatial study three-dimensional type united united states