In-context learning enables continental-scale subsurface temperature prediction from sparse local observations

• URL: http://arxiv.org/abs/2605.16665v1
• Date: Fri, 15 May 2026 22:03:34 GMT
• Title: In-context learning enables continental-scale subsurface temperature prediction from sparse local observations
• Abstract summary: In-context learning can use sparse borehole observations for continental-scale subsurface characterization.<n>Model adapts to Alberta, Australia, and the United Kingdom using only 20 local observations at inference time.<n>Interpretability analyses show that the model learns internal representations of subsurface properties it never observes during training.
• Score: 2.9599087767908423
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Predicting Pseudo-nitzschia harmful algal blooms along the Portuguese Coast using satellite-derived predictors [69.38367341895632]
  Pseudo-nitzschia diatoms pose recurrent risks to coastal ecosystems and harvesting along the Portuguese Atlantic coast.<n>We develop and evaluate a machine-learning framework to predict harmful algal bloom occurrence using exclusively satellite-derived predictors.
  arXiv  Detail & Related papers  (2026-07-08T18:14:24Z)
• Exploring Convolutional Neural Processes for Weather Downscaling [0.0]
  Global reanalysis products such as ERA5-Land provide spatially complete weather fields but at resolutions too coarse for local applications.<n>This project investigates Convolutional Conditional (ConvCNPs) for statistical downscaling of daily maximum temperature from the 11km resolution ERA5-Land grid to 1km resolution over Switzerland.
  arXiv  Detail & Related papers  (2026-07-05T09:24:18Z)
• EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting [50.31500063307306]
  We introduce EO-WM, a video diffusion transformer for multispectral Earth Observation forecasting.<n> EO-WM incorporates a physically informed conditioning framework that represents meteorological forcing through a climatological baseline, weather anomalies, and cumulative physical stress signals.<n>Experiments show that EO-WM reduces the error in predicted Normalized Difference Vegetation Index (NDVI) decline amplitude by a relative 5.63% and improves directional hit rate by a relative 7.80%.
  arXiv  Detail & Related papers  (2026-06-25T16:53:30Z)
• Causal Time Series Modeling of Supraglacial Lake Evolution in Greenland under Distribution Shift [2.5551933647600693]
  Causal modeling offers a principled foundation for uncovering stable, invariant relationships in time-series data.<n>We propose RIC-TSC, a regionally-informed causal time-series classification framework that embeds lag-aware causal discovery directly into sequence modeling.
  arXiv  Detail & Related papers  (2025-10-17T03:06:08Z)
• Climate Knowledge in Large Language Models [0.0]
  This study investigates the capacity of large language models to recall climate normals without external retrieval.<n>We construct a global grid of queries at 1deg resolution land points, providing coordinates and location descriptors, and validate responses against ERA5 reanalysis.<n>Results show that LLMs encode non-trivial climate structure, capturing latitudinal and topographic patterns, with root-mean-square errors of 3-6 degC and biases of $pm$1 degC.<n>We find that including geographic context reduces errors by 27% on average, with larger models being most sensitive to location descriptors.
  arXiv  Detail & Related papers  (2025-10-09T10:25:36Z)
• ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion [48.540756751934836]
  ReconMOST is a data-driven guided diffusion model framework for multi-layer sea temperature reconstruction.<n>Our method extends ML-based SST reconstruction to a global, multi-layer setting, handling over 92.5% missing data.
  arXiv  Detail & Related papers  (2025-06-12T06:27:22Z)
• Causal Representation Learning in Temporal Data via Single-Parent Decoding [66.34294989334728]
  Scientific research often seeks to understand the causal structure underlying high-level variables in a system. Scientists typically collect low-level measurements, such as geographically distributed temperature readings. We propose a differentiable method, Causal Discovery with Single-parent Decoding, that simultaneously learns the underlying latents and a causal graph over them.
  arXiv  Detail & Related papers  (2024-10-09T15:57:50Z)
• MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling [68.69647625472464]
  Downscaling, a crucial task in meteorological forecasting, enables the reconstruction of high-resolution meteorological states for target regions. Previous downscaling methods lacked tailored designs for meteorology and encountered structural limitations. We propose a novel model called MambaDS, which enhances the utilization of multivariable correlations and topography information.
  arXiv  Detail & Related papers  (2024-08-20T13:45:49Z)
• Predicting the Geothermal Gradient in Colombia: a Machine Learning Approach [0.0]
  geothermal gradient determination is critical for assessing the geothermal energy potential of a given region.<n>We present an approach that leverages recent advances in supervised machine learning to predict the geothermal gradient.<n>We show that predictions of our model are within 12% accuracy and that independent measurements performed by other authors agree well with our model.
  arXiv  Detail & Related papers  (2024-04-08T04:18:54Z)
• Thermal Earth Model for the Conterminous United States Using an Interpolative Physics-Informed Graph Neural Network (InterPIGNN) [0.0]
  This study presents a data-driven spatial algorithm based on physics-informed graph neural networks. 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.
  arXiv  Detail & Related papers  (2024-03-15T01:55:07Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Spatiotemporal modeling of European paleoclimate using doubly sparse Gaussian processes [61.31361524229248]
  We build on recent scale sparsetemporal GPs to reduce the computational burden. We successfully employ such a doubly sparse GP to construct a probabilistic model of paleoclimate.
  arXiv  Detail & Related papers  (2022-11-15T14:15:04Z)
• Dynamical Landscape and Multistability of a Climate Model [64.467612647225]
  We find a third intermediate stable state in one of the two climate models we consider. The combination of our approaches allows to identify how the negative feedback of ocean heat transport and entropy production drastically change the topography of Earth's climate.
  arXiv  Detail & Related papers  (2020-10-20T15:31:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.