地質学的CO2貯留のための不確実性定量化を伴うデジタルロックセグメンテーション：画像精度から炭素貯留信頼性へ
Digital Rock Segmentation with Uncertainty Quantification for Geological CO2 Storage: From Image Accuracy to Carbon Storage Reliability (原題)
William Marfo, William Ampomah, H. Rahnema, Carlos Ronaldo Oliva, G. Akpabli, Kwamena Opoku Duartey, Elizabeth Akonobea Appiah, Sylvester Agyei, Jacqueline Margaret Adjimah
🤖 gxceed AI 要約
日本語
本レビューは、地質学的CO2貯留の信頼性評価に用いるデジタルロック物理の画像セグメンテーションを、単なる画像精度ではなく貯留意思決定への寄与で評価する。古典的手法から深層学習・基盤モデルまでを、クラス精度・境界忠実度・トポロジー・形態・不確実性・物性感度・工学的帰結の7次元で整理。類似画像でも透水性や漏洩経路の予測が大きく異なることを示し、不確実性を定量化したセグメンテーションをリスク管理として扱うことを推奨する。
English
This review evaluates digital rock image segmentation for geological CO2 storage not by image overlap but by its contribution to reliable storage decisions. It synthesizes classical, machine learning, deep learning, transformer, and foundation model methods across seven dimensions: class accuracy, boundary fidelity, topology, morphology, calibrated uncertainty, physical property sensitivity, and engineering consequences. Visually similar segmentations can yield divergent predictions of permeability, trapping, and leakage paths, so the authors recommend task- and lithology-specific method selection, uncertainty propagation, and validation against laboratory measurements.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本はCCS事業化を加速しており、貯留サイト選定・モニタリングの信頼性評価は政策的に重要。本レビューは、画像解析の不確実性管理が事業リスク低減に直結することを示し、国内CCSプロジェクトの技術基準策定に示唆を与える。
In the global GX context
Globally, CCUS is central to net-zero pathways and transition finance, but storage reliability must be auditable. This review bridges pore-scale imaging and formation-scale performance, offering a framework for uncertainty-aware segmentation that can strengthen site screening, injection design, and monitoring—key for de-risking CCUS investments under emerging disclosure and verification regimes.
👥 読者別の含意
🔬研究者:デジタルロック物理と不確実性定量化を統合する研究課題を明確化し、物性予測の信頼性評価手法を提供する。
🏢実務担当者:CCSプロジェクトのサイト選定やモニタリングにおいて、画像解析の不確実性をリスク管理に組み込む実務的指針となる。
🏛政策担当者:CCSの貯留性能評価やモニタリング基準に、不確実性を考慮した画像解析の検証要件を組み込む必要性を示唆する。
📄 Abstract（原文）
Geological CO2 storage is essential to pathways to carbon neutrality, but its deployment depends on trustworthy estimates of storage capacity, injectivity, trapping, reactive evolution, and containment. Digital rock physics can provide pore-scale inputs to these estimates from X-ray and electron microscopy images, but translation to formation-scale performance requires additional geological, fluid, and operational information. Each image-derived result depends on image segmentation, which converts grayscale data into pore, mineral, fracture, and fluid phases. This review evaluates classical methods, machine learning, deep learning, transformers, and foundation models according to whether they support reliable storage decisions rather than image overlap scores alone. Evidence is synthesized from imaging of dry rocks, CO2–brine experiments, multiscale studies of carbonates and shales, and analyses of fractured rocks. We introduce a framework with seven dimensions: class accuracy, boundary fidelity, topology, morphology, calibrated uncertainty, sensitivity of physical properties, and consequences for engineering decisions. The evidence shows that visually similar segmentations can yield substantially different predictions of permeability, connected porosity, residual trapping, reactive surface area, and leakage paths when errors occur at critical pore throats, fluid interfaces, or fractures. We therefore recommend selecting methods according to storage task and lithology, validating them on independent samples, propagating ensembles of plausible segmentations, using metrics that account for topology, and comparing predictions with laboratory measurements. The central message is simple: segmentation should be treated as both a measurement process and a form of risk control. Segmentation with auditable and quantified uncertainty has the potential to improve the inputs to site screening, injection design, and monitoring. These project-level benefits are proposed consequences requiring upscaling and project-specific validation, not outcomes demonstrated by this review.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.3390/acn1020006first seen 2026-10-06 05:44:18
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。