The paper introduces a workflow that ranks competing geological interpretations by converting them into spatial priors and assessing their consistency with hydraulic‑head observations. Using a text‑to‑image model to generate 1600 geologic images per interpretation, a variational autoencoder encodes them, and a supervised inverse network maps head data into this latent space, producing log‑conductivity fields for flow simulation. The method is validated on a synthetic Johansen Formation benchmark and applied to two conceptual models of the Culebra Dolomite, yielding compatibility scores that align with independent evidence.
By Harun Ur Rashid, Daniel O'Malley
arXiv:2609.20978v2 Announce Type: replace
Abstract: High-consequence subsurface decisions often rely on sparse data that permit competing geological interpretations. Determining consistency of these...
By Harun Ur Rashid, Daniel O'Malley
arXiv:2606. 25000v1 Announce Type: new Abstract: To evaluate whether vision-language models can reason about geological histories, it is necessary to construct observations for which the underlying process history is known.
By Lukas Mosser
arXiv:2607. 29378v1 Announce Type: cross Abstract: Large language models (LLMs) generate text by auto-regressively sampling the next token.
By Pirzada Suhail, Nagasai Saketh Naidu, Atanu R Sinha, Amit Sethi
arXiv:2609.37066v1 Announce Type: cross
Abstract: Post-training is central to mathematical reasoning in modern large language models (LLMs), but endpoint pass@1 alone underidentifies what has changed...
By Hongyang Li, Yiming Zhu, Xiao Li, Caesar Wu, Said Mammar, Pascal Bouvry
Autoregressive modelling, successful in language tasks, is applied to mineral‑exploration drillholes where lithology is revealed sequentially from shallow to deep. The authors introduce DrillBench, a benchmark of 49,671 Western Australian drillholes for next‑layer prediction and autoregressive stratigraphic generation across a graded transfer spectrum. Experiments show that spatial conditioning helps locally but fails under strong shift, while autoregressive models transfer more robustly; a backbone‑agnostic recipe combining large‑scale pretraining and spatial retrieval improves generalisation, especially in distant geological splits.
By Yihao Ding, Daniel Yitian Su, Yiran Zhang, Christopher M. Gonzalez, Wei Liu