28 June 2021 to 2 July 2021
Europe/Vienna timezone

Simulation of operational results of NET-VISA on a three-month historical data set

P3.6-651
1 Jul 2021, 09:00
3h
Online

Online

e-Poster T3.6 - Artificial Intelligence and Machine Learning T3.6 e-poster session

Speaker

Mr Ronan Le Bras (CTBTO Preparatory Commission, Vienna, Austria)

Description

NET-VISA has benefitted tremendously from the interaction between its developers and CTBT State Signatories experts. One way that this interaction has taken place is through the delivery of data sets processed with successively enhanced versions of the software, with feedback from the experts. We present the results of a full simulation of operational results conducted offline with a recent version of NET-VISA (December 2020). The processing includes the complete three-pipeline configuration. The data set covers August-October 2016, includes an announced nuclear test, and is intended to be delivered to the State Signatories experts. The analysis will cover the essential comparison criteria of overlap and inconsistency between the automatic results and reviewed results, but will also go deeper into the comparison of the NET-VISA results with the SEL3 automatic bulletin for that period, taking into account location accuracy and completeness of the automatic events.

Promotional text

The physics-based Machine Learning operational software NET-VISA is being continuously improved. We present the most recent offline results on a three-month historical data set to be distributed to State Signatories.

Primary author

Mr Ronan Le Bras (CTBTO Preparatory Commission, Vienna, Austria)

Co-authors

Mr Noriyuki Kushida (CTBTO Preparatory Commission, Vienna, Austria) Mr Pavel Strachota (CTBTO Preparatory Commission, Vienna, Austria) Mr Nimar Arora (Bayesian Logic, Inc., CA, USA) Ms Geeta Arora (Bayesian Logic, Inc., CA, USA)

Presentation materials