Removing noise from a signal without knowing the characteristics of the noise is a challenging task. This paper introduces a signal-noise separation method based on time series prediction. We use Reservoir Computing (RC) to extract the maximum portion of "predictable information" from a given signal. Reproducing the deterministic component of the signal using RC, we estimate the noise distribution from the difference between the original signal and reconstructed one. The method is based on a machine learning approach and requires no prior knowledge of either the deterministic signal or the noise distribution. It provides a way to identify additivity/multiplicativity of noise and to estimate the signal-to-noise ratio (SNR) indirectly. The method works successfully for combinations of various signal and noise, including chaotic signal and highly oscillating sinusoidal signal which are corrupted by non-Gaussian additive/ multiplicative noise. The separation performances are robust and notably outstanding for signals with strong noise, even for those with negative SNR.
Prediction of Unobserved Bifurcation by Unsupervised Extraction of Slowly Time-Varying System Parameter Dynamics from Time Series Using Reservoir Computing
Faculty of Health Data science, Juntendo University(顺天堂大学健康数据科学学部);The School of Systems Information Science, Future University Hakodate(函馆未来大学系统信息科学学院)
Unsupervised learning for anticipating critical transitions
School of Electrical, Computer, and Energy Engineering, Arizona State University(亚利桑那州立大学电气、计算机与能源工程学院);Department of Computational Biology, Cornell University(康奈尔大学计算生物学系);Vehicle Technology Directorate, CCDC Army Research Laboratory(CCDC陆军研究实验室车辆技术局);Department of Physics, Arizona State University(亚利桑那州立大学物理系)
Quantum Reservoir Computing: Recent Advances and Future Directions
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg(安全、可靠性与信任跨学科中心(SnT),卢森堡大学);School of Computing, Engineering and Digital Technologies, Teesside University(计算、工程与数字技术学院,泰赛大学)
4D Seismic History Matching Incorporating Unsupervised Learning
School of Applied Mathematics, the University of Manchester(曼彻斯特大学应用数学学院)
本文讨论和介绍的工作重点是通过使用机器学习技术将4D地震数据集成到反演过程中来进行储层的历史匹配。提出了一种新的综合方案,用于在合成储集层中使用改进的Encyclopsis Smooter和Multiple Data Assimilation(ES-MDA)重建岩石物理性质。储层内部的渗透率场采用无监督学习方法进行参数化,即具有奇异值分解的K均值(K-SVD)。这是结合正交匹配追踪(OMP)技术,这是非常典型的稀疏促进正则化计划。此外,地震属性,特别是声阻抗,参数化与离散余弦变换(DCT)。这种新颖的机器学习、稀疏正则化、地震成像和历史匹配技术的组合旨在使用ES-MDA有效地解决历史生产数据反演的不适定性。在提供的数值实验中,我证明,这些稀疏表示的岩石物理性质和地震属性,使获得更好的生产数据匹配的真实生产数据和量化的传播海滨更好地相比,更传统的方法,不使用可比的参数化技术。
Unearthing InSights into Mars: Unsupervised Source Separation with Limited Data
Rice University(莱斯大学);École Normale Supérieure(巴黎高等师范学院);PSL University(巴黎文理研究大学);Sorbonne Université(索邦大学);Université Paris Cité(巴黎西岱大学);Institut de Physique du Globe de Paris(巴黎地球物理研究所)
ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
Faculty of Mathematics and Computer Science, Jagiellonian University(数学与计算机科学学院,杰团大学);Doctoral School of Exact and Natural Sciences, Jagiellonian University(精确与自然科学博士学院,杰团大学)
Multi-scale clustering and source separation of InSight mission seismic data
Department of Computer Science, University of Central Florida(中央佛罗里达大学计算机科学系);Rice University(里士满大学);Département d’Informatique, École Normale Supérieure(高等师范学院信息学院);Department of Computer Science, Brown University(布朗大学计算机科学系);Laboratoire de Physique de l’Ecole normale supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université Paris-Cité(高等师范学院物理实验室,ENS,大学巴黎-勒阿弗尔,CNRS,索邦大学,巴黎-勒阿弗尔大学);LUX, Observatoire de Paris, Université PSL, Sorbonne Université, CNRS(LUX,巴黎天文台,大学巴黎-勒阿弗尔,索邦大学,CNRS);Université Paris Cité, Institut de Physique du Globe de Paris, CNRS(巴黎-勒阿弗尔大学,巴黎地球物理研究所,CNRS);Department of Computational Applied Mathematics and Operations Research, Rice University(里士满大学计算应用数学与运营管理系)