Honors & Awards
Student Presentation Award, Seismological Society of America (SSA) Annual Meeting (2017)
Senior Teaching Fellow, ICME, Stanford University (2016)
ICME Short Course Instructor Award, Stanford University (2015)
Student Presentation Award, Seismological Society of America (SSA) Annual Meeting (2016)
Outstanding Student Paper Award, American Geophysical Union (AGU) Annual Meeting (2015)
Stanford Graduate Fellowship, Stanford University (2011)
Education & Certifications
M.Sc., Stanford University, Computational and Mathematical Engineering (2015)
B.Sc., Brown University, Applied Mathematics (2009)
Gregory Beroza, Ossian O'Reilly, Clara Yoon, Karianne Bergen. "United States Patent 20,150,316,666 Efficient Similarity Search of Seismic Waveforms", Leland Stanford Junior University, Nov 5, 2015
Assistant Staff Researcher, MIT - Lincoln Laboratory (8/1/2009 - 6/1/2011)
As a member of the Biological and Chemical Defense Systems Group I developed algorithms for biodefense applications.
Instructor, CME 250: Introduction to Machine Learning, Stanford University (1/1/2015 - 3/31/2016)
I developed new 4-week short-course, included designing syllabus and creating course materials, with co-instructor Alex Ioannidis. I co-taught the course for four quarters (Winter, Spring, Fall 2015 and Winter 2016), twice as week-long summer workshop (August 2014 and 2015), and twice as half-day workshop (June 2015).
Scalable Similarity Search in Seismology: A New Approach to Large-Scale Earthquake Detection
International Conference on Similarity Search and Applications
View details for DOI 10.1007/978-3-319-46759-7 23
Earthquake detection through computationally efficient similarity search.
2015; 1 (11)
Seismology is experiencing rapid growth in the quantity of data, which has outpaced the development of processing algorithms. Earthquake detection-identification of seismic events in continuous data-is a fundamental operation for observational seismology. We developed an efficient method to detect earthquakes using waveform similarity that overcomes the disadvantages of existing detection methods. Our method, called Fingerprint And Similarity Thresholding (FAST), can analyze a week of continuous seismic waveform data in less than 2 hours, or 140 times faster than autocorrelation. FAST adapts a data mining algorithm, originally designed to identify similar audio clips within large databases; it first creates compact "fingerprints" of waveforms by extracting key discriminative features, then groups similar fingerprints together within a database to facilitate fast, scalable search for similar fingerprint pairs, and finally generates a list of earthquake detections. FAST detected most (21 of 24) cataloged earthquakes and 68 uncataloged earthquakes in 1 week of continuous data from a station located near the Calaveras Fault in central California, achieving detection performance comparable to that of autocorrelation, with some additional false detections. FAST is expected to realize its full potential when applied to extremely long duration data sets over a distributed network of seismic stations. The widespread application of FAST has the potential to aid in the discovery of unexpected seismic signals, improve seismic monitoring, and promote a greater understanding of a variety of earthquake processes.
View details for DOI 10.1126/sciadv.1501057
View details for PubMedID 26665176
Information fusion of standoff and other information for biodefense decision support
SPIE Chemical, Biological, Radiological, Nuclear, and Explosives (CBRNE) Sensing
View details for DOI 10.1117/12.852817
Approaches to information fusion with spatiotemporal aspects for standoff and other biodefense information sources
SPIE Defense, Security and Sensing: Multisensor, Multisource Information Fusion: Architectures, Algorithms, and Applications
View details for DOI 10.1117/12.852862