用Transformer模型预测流体注入引发的微地震时空演化。
Deep learning forecasts the spatiotemporal evolution of fluid-induced microearthquakes
- 基于液压刺激历史和前期微地震数据，预测四类关键指标。
- 1秒预测准确率R²超0.98，15秒仍超0.88，含不确定性估计。
- 适合地质工程、碳封存等场景实时风险评估与决策支持。
由地下流体注入引发的微地震（MEQ）记录了储层应力状态和渗透率的动态变化。预测其完整的时空演化对增强型地热系统（EGS）、CO₂封存及其他地质工程应用至关重要。本文提出一种基于Transformer的深度学习模型，输入液压刺激历史和先前的微地震观测，预测四项关键量：累计微地震数量、累计对数震级、微地震云的第50百分位和第95百分位范围（P₅₀, P₉₅）。在EGS Collab Experiment 1数据集上，该模型在1秒预测时长下所有目标的R²均超过0.98，在15秒预测时长下仍高于0.88，并通过学习到的标准差项提供不确定性估计。这些高精度且带不确定性的预测，可实现实时推断断裂扩展与渗透率演化，展示了深度学习在提升地震风险评估与指导未来流体注入操作减缓策略方面的巨大潜力。
原文摘要 · Abstract (English)
Microearthquakes (MEQs) generated by subsurface fluid injection record the evolving stress state and permeability of reservoirs. Forecasting their full spatiotemporal evolution is therefore critical for applications such as enhanced geothermal systems (EGS), CO$_2$ sequestration and other geo-engineering applications. We present a transformer-based deep learning model that ingests hydraulic stimulation history and prior MEQ observations to forecast four key quantities: cumulative MEQ count, cumulative logarithmic seismic moment, and the 50th- and 95th-percentile extents ($P_{50}, P_{95}$) of the MEQ cloud. Applied to the EGS Collab Experiment 1 dataset, the model achieves $R^2 >0.98$ for the 1-second forecast horizon and $R^2 >0.88$ for the 15-second forecast horizon across all targets, and supplies uncertainty estimates through a learned standard deviation term. These accurate, uncertainty-quantified forecasts enable real-time inference of fracture propagation and permeability evolution, demonstrating the strong potential of deep-learning approaches to improve seismic-risk assessment and guide mitigation strategies in future fluid-injection operations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。