🤖 AI Summary
Accurate reconstruction of continental-scale subsurface temperature fields is hindered by sparse borehole observations, limiting geothermal resource assessment and shallow heat transport studies. This work proposes the In-Context Earth model, which introduces in-context learning to cross-regional subsurface temperature modeling for the first time. By treating sparse borehole measurements as geological context and integrating a Transformer architecture with multi-source geological embeddings and uncertainty calibration, the model generalizes to geologically distinct regions without fine-tuning and implicitly captures unobserved geophysical properties. Experiments demonstrate a mean absolute error of 4.7 °C across the conterminous United States, substantially outperforming baseline methods. Furthermore, using only 20 observation points, the model achieves errors of 2.2–6.2 °C in Alberta, Australia, and the UK, with highly reliable uncertainty estimates.
📝 Abstract
Continental-scale knowledge of subsurface temperature is limited by the cost and sparsity of borehole measurements, but such information is essential for geothermal resource assessment and for understanding heat transport in the shallow crust. The thermal field reflects the interaction between lithology, crustal structure, radiogenic heat production, and advective fluid flow, sometimes producing sharp anomalies that are smoothed by conventional interpolation or difficult to capture with physical models. Here we introduce In-Context Earth, a transformer-based model that uses sparse local borehole observations as geological context to predict continuous temperature-at-depth fields with calibrated uncertainty. In the contiguous United States, the model achieves a mean absolute error of 4.7 °C, outperforming the physics-informed Stanford Thermal Model, a model based on AlphaEarth embeddings, the multimodal Transparent Earth model, and universal kriging, while resolving sharper thermal gradients in geothermal provinces. Its uncertainty estimates are well calibrated, with a Kolmogorov-Smirnov statistic of 2.5%. Without finetuning, the model adapts to Alberta, Australia, and the United Kingdom (UK) using only 20 local observations at inference time, maintaining high accuracy in geologically distinct test regions with a mean absolute error of 2.2 °C in Alberta, 6.2 °C in Australia, and 5.4 °C in the UK. Interpretability analyses show that the model learns internal representations of subsurface properties it never observes during training, including seismic velocities, geochemistry, and crustal structure, and uses these representations in physically consistent ways. More broadly, this work shows that in-context learning can use sparse borehole observations for continental-scale subsurface characterization, without requiring dense measurements or region-specific retraining.