这篇论文用三个真实数据把故障容错和抗噪鲁棒性分清楚了，发现训练方式比架构更关键，做事件检测的可以看看。
研究人员针对碳捕获与封存（CCS）、地热等场景中事件检测的鲁棒性展开研究，将传感器故障容错与低信噪比鲁棒性区分开。他们基于Hi-net地震波形、Utah FORGE 2024钻孔DAS和MAFAULDA工业振动三个真实数据集构建了统一二进制事件检测基准，使用8通道256样本表示。在干净数据上所有模型AUC约0.99。在渐进式传感器丢失下，简单模型已具备鲁棒性，CEPHALON无优势。但在加性噪声-2.5 dB时，CEPHALON的AUC为0.939，而卷积基线在0.532-0.572之间。消融实验表明训练策略（每样本传感器丢弃）是低SNR鲁棒性的主导因素，而非平行冗余架构。
Two kinds of robustness are not the same: disentangling fault tolerance and low-SNR robustness in multi-domain event detection on real data
Reliable event detection underpins induced-seismicity monitoring for Carbon dioxide Capture and Storage (CCS) and geothermal operations, distributed acoustic sensing (DAS), and industrial condition monitoring. In each setting a detector must stay reliable both when sensors fail and when the signal is buried in noise. These two failure modes are routinely conflated, and architectural complexity is often credited with robustness it may not deserve. We assemble a unified binary event-detection benchmark from three physically distinct real sources -- Hi-net seismic waveforms, Utah FORGE 2024 borehole DAS, and MAFAULDA industrial vibration -- each mapped to a common 8-channel, 256-sample representation, and evaluate a fault-tolerant detector (CEPHALON) trained with per-sample sensor-dropout against standard detectors (a 1D convolutional network, a temporal convolutional network, and a compact Transformer) trained with an identical recipe. On clean data every model is near-perfect (AUC ~ 0.99). Under progressive sensor loss, simple models with sensor-dropout are already robust and CEPHALON holds no advantage. Under additive noise, however, CEPHALON degrades far more gracefully: at -2.5 dB its overall AUC is 0.939 versus 0.532-0.572 for the convolutional baselines. Same-architecture ablations isolate the cause: disabling internal redundancy at inference reduces the low-SNR advantage only modestly, whereas removing sensor-dropout training collapses it (0.899 to 0.603 at -5 dB). The training recipe is therefore the dominant cause and parallel redundancy only secondary. We release a complete, numbered, reproducible pipeline so that every figure can be regenerated.