arXiv：cs.LG· Taiga Saito, Yu Otake, Daijiro Mizutani, Sopheakpolin Mom·· 4 小时前AI 评分31
地质文本描述如何辅助不适定水力传导率反演：基于学习式反演的研究
Geological text descriptions in ill-posed inverse problems: insights from learned hydraulic-conductivity inversion
AI 导读
研究用合成 Darcy 流基准检验地质文本描述能否约束不适定水力传导率反演，发现稀疏观测下描述可改善重建，但增益随条件与运行波动，且实例专属内容优于场类型信息。编辑描述内容可使重建向所述几何偏移，观测越充分偏移越弱；研究未证实文本相较编码同等地质信息的数值输入有重建优势。
正文
Abstract:Hydraulic-conductivity inversion is ill posed: even complete head observations can leave structural ambiguity. Geological text descriptions can supply additional information about subsurface structure to constrain reconstruction. However, it remains unclear when descriptions improve reconstruction and how solvers use their stated content. We examine these questions in learned inversion using a synthetic Darcy-flow benchmark with idealised descriptions, varying observation density and flow direction. After sparse-observation training, descriptions can improve reconstruction over models trained without them when observations leave structural ambiguity, though gains vary across conditions and runs. Instance-specific content can improve reconstruction beyond field-type information. Editing this content shifts reconstructions toward the stated geometry of selected features, less strongly as observations become more informative about those features. We do not establish a reconstruction advantage of text over numerical inputs encoding the same geological information. Finally, we discuss how this complementarity could guide the joint design of measurements and geological knowledge acquisition.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.24967 [cs.LG] |
| (or arXiv:2606.24967v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.24967 arXiv-issued DOI via DataCite |
Submission history
From: Taiga Saito [view email]
[v1]
Tue, 23 Jun 2026 10:07:34 UTC (1,990 KB)
[v2]
Tue, 6 Oct 2026 19:28:47 UTC (1,599 KB)
来源：arXiv：cs.LG · arxiv.org