[
    {
        "id": "authors:961pk-g4n17",
        "collection": "authors",
        "collection_id": "961pk-g4n17",
        "cite_using_url": "https://authors.library.caltech.edu/records/961pk-g4n17",
        "type": "article",
        "title": "Improvements from incorporating machine learning algorithms into near real-time operational post-processing",
        "author": [
            {
                "family_name": "Tepp",
                "given_name": "Gabrielle",
                "orcid": "0000-0001-5388-5138",
                "clpid": "Tepp-Gabrielle-M"
            },
            {
                "family_name": "Yu",
                "given_name": "Ellen",
                "orcid": "0000-0002-2480-8384",
                "clpid": "Yu-Ellen-C"
            },
            {
                "family_name": "Bhaskaran",
                "given_name": "Aparna",
                "clpid": "Bhaskaran-Aparna"
            },
            {
                "family_name": "Tam",
                "given_name": "Ryan",
                "clpid": "Tam-Ryan"
            },
            {
                "family_name": "Zhu",
                "given_name": "Weiqiang"
            },
            {
                "family_name": "Newman",
                "given_name": "Zackary",
                "clpid": "Newman-Zackary"
            },
            {
                "family_name": "Jaski",
                "given_name": "Erika",
                "clpid": "Jaski-Erika"
            },
            {
                "family_name": "Scheckel",
                "given_name": "Nick",
                "clpid": "Scheckel-Dominic-J"
            }
        ],
        "abstract": "<p>During regional seismic monitoring, data is automatically analyzed in real-time to identify events and provide initial locations and magnitudes. Monitoring networks may apply automatic post-processing to small events (M&thinsp;&lt;&thinsp;3) to add and refine picks and improve the event before analyst review. Recently, machine learning algorithms, particularly for phase picking, have matured enough for use in regional monitoring systems. The Southern California Seismic Network has implemented the deep-learning picker PhaseNet in our event post-processing, resulting in about 2&ndash;3 times as many picks, particularly S phases, with slightly better pick accuracy than the previous STA/LTA picker (relative to analyst picks). These improvements have led to better epicenter accuracy. We have also developed an automatic post-processing pipeline (ST-Proc) for sub-network triggers, which are collections of nearby phase picks that the real-time system could not associate into an event. ST-Proc uses PhaseNet to find phase picks and the machine learning algorithm GaMMA to associate events. This pipeline is capable of correctly detecting events in 65&ndash;70% of triggers containing events with a low false event rate around 5%. Additionally, the GaMMA-determined epicenters are generally accurate (within a few kilometers of the final). Both pipelines have helped to reduce analyst workload and streamline event processing.</p>",
        "doi": "10.1038/s41598-025-14491-1",
        "pmcid": "PMC12332030",
        "issn": "2045-2322",
        "publisher": "Nature Publishing Group",
        "publication": "Scientific Reports",
        "publication_date": "2025-08-07",
        "series_number": "1",
        "volume": "15",
        "issue": "1",
        "pages": "28938"
    },
    {
        "id": "authors:nd65w-9xa85",
        "collection": "authors",
        "collection_id": "nd65w-9xa85",
        "cite_using_url": "https://resolver.caltech.edu/CaltechAUTHORS:20130222-081636833",
        "type": "article",
        "title": "Southern California Seismic Network Update",
        "author": [
            {
                "family_name": "Hutton",
                "given_name": "Kate",
                "clpid": "Hutton-K"
            },
            {
                "family_name": "Hauksson",
                "given_name": "Egill",
                "orcid": "0000-0002-6834-5051",
                "clpid": "Hauksson-E"
            },
            {
                "family_name": "Clinton",
                "given_name": "John",
                "orcid": "0000-0001-8626-2703",
                "clpid": "Clinton-J-F"
            },
            {
                "family_name": "Franck",
                "given_name": "Joseph",
                "clpid": "Franck-J"
            },
            {
                "family_name": "Guarino",
                "given_name": "Anthony",
                "clpid": "Guarino-A"
            },
            {
                "family_name": "Scheckel",
                "given_name": "Nick",
                "clpid": "Scheckel-Dominic-J"
            },
            {
                "family_name": "Given",
                "given_name": "Doug",
                "clpid": "Given-D-D"
            },
            {
                "family_name": "Yong",
                "given_name": "Alan",
                "clpid": "Yong-Alan"
            }
        ],
        "abstract": "The authoritative region of the Southern California Seismic Network (SCSN) extends across southern California, from the U.S./Mexico international border to Coalinga and Owens Valley in central California (Figure 1). This area contains almost 20 million inhabitants, including two of the ten largest cities in the United States (Los Angeles and San Diego) and the two largest harbors (Los Angeles and Long Beach) in the nation. SCSN also reports on earthquakes in Baja California, which could potentially cause damage in the U.S. More than fifty earthquakes (not including aftershocks) are felt each year, and an average of 1.5 events per year are potentially damaging (magnitude greater than 5.0). Immediately after a moderate or large earthquake, SCSN provides information about the size, location, and distribution of ground shaking. Emergency managers use this information to coordinate rescue operations, guide inspectors in the search for damage, and satisfy the public's need for information. The historical record of earthquake occurrences in California is important to insurers, geotechnical engineers, and city planners.",
        "issn": "0895-0695",
        "publisher": "Seismological Society of America",
        "publication": "Seismological Research Letters",
        "publication_date": "2006-05",
        "series_number": "3",
        "volume": "77",
        "issue": "3",
        "pages": "389-395"
    }
]