机器学习用于可持续地热能:不确定性、物理和可决策推断
Machine learning cannot decarbonise the subsurface until it can be audited
AI总结:
本文探讨了机器学习在可持续地热能项目中的应用,针对不确定性、物理约束和决策推断等关键问题,提出混合物理-机器学习、概率不确定性量化等方法,以提升项目风险控制和决策可靠性。
摘要:
地热能项目(如二氧化碳储存、地热能、地下氢气生成/储存、关键矿物提取、核废料处置)正逐步采用石油行业的 funnel 模式,从筛选和评估到运营、监控和管理。在整个 funnel 中,有限且异质的观测数据必须在强物理和地质约束下转化为风险有限的运营决策,这些决策影响部署速度、资本成本和气候缓解声明的可信度。这些决策本质上是多目标的,需在性能、 containment、压力足迹、诱发地震、能量/水强度和长期管理之间平衡。本文认为进展受限于四个反复出现的瓶颈:(i)稀缺、有偏标签和少量现场性能结果;(ii)不确定性被视为次要而非交付成果;(iii)从孔隙到盆地的弱尺度桥梁(包括耦合的化学-流体-地质力学);(iv)监管面向部署的 QA、可审计性和治理不足。本文概述了匹配这些现实的机器学习(ML)方法(混合物理-ML、概率不确定性量化(UQ)、结构感知表示、多保真度/持续学习)并将其连接到四个锚定应用:成像到过程数字孪生、多相流和近井符合、监控和反问题(监控、测量和验证(MMV),包括变形和微地震性)、盆地尺度投资组合管理。最后,本文提出一个务实议程,包括基准测试、验证、报告标准和政策支持,以确保可持续地热能中可重复和可辩护的 ML 应用。
英文摘要:
Geological CO2 storage, geothermal energy and underground hydrogen storage depend on irreversible or high-cost decisions made with sparse data and incomplete physical understanding. Machine learning (ML) increasingly informs these decisions, yet methods are usually judged on predictive accuracy rather than on whether their outputs can be trusted, traced and acted upon. We argue that subsurface ML should be designed as decision infrastructure with shared systems that carry calibrated uncertainty and provenance from observation to operating decision. We propose a decision-readiness checklist, an audit-trail workflow for monitoring updates, and benchmark designs that score models by the decisions they support. We identify validation needs shared across the three technologies, and the data-access and governance steps needed for ML to support regulatory and investment decisions.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。