Preface to the Focus Section on Machine Learning in Seismology

Journal Article · Wed Feb 13 00:00:00 EST 2019 · Seismological Research Letters

DOI:https://doi.org/10.1785/0220190018· OSTI ID:1511263

Bergen, Karianne J. ^[1]; Chen, Ting  ^[2]; Li, Zefeng ^[3]

---

1. Harvard Univ., Cambridge, MA (United States)
2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
3. California Inst. of Technology (CalTech), Pasadena, CA (United States)

Machine learning (ML) is a collection of algorithms and statistical models that enable computers to extract relevant patterns and information from large data sets. Unlike physical modeling approaches, in which scientists develop theories based on physical laws to compare with real–world observations, ML approaches learn directly from data without explicitly reasoning about the underlying physical mechanisms. ML algorithms are often categorized into supervised and unsupervised learning (see fig. 2 in Kong et al., 2018). Supervised learning algorithms build a model from existing labeled input data with the goal of predicting the labels of new data.

• Research Organization: Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE
• Grant/Contract Number: 89233218CNA000001
• OSTI ID: 1511263
• Report Number(s): LA-UR-19-20450
• Journal Information: Seismological Research Letters, Vol. 90, Issue 2A; ISSN 0895-0695
• Publisher: Seismological Society of America
• Country of Publication: United States
• Language: English

Related Subjects

58 GEOSCIENCES
Earth Sciences