|
|
Garcia Navarro, J. E., Fernandez-Prieto, L. M., Villaseñor, A., Sanz, V., Ammirati, J. B., Diaz Suarez, E. A., et al. (2022). Performance of Deep Learning Pickers in Routine Network Processing Applications. Seismol. Res. Lett., 93, 2529–2542.
Abstract: Picking arrival times of P and S phases is a fundamental and time‐consuming task for the routine processing of seismic data acquired by permanent and temporary networks. A large number of automatic pickers have been developed, but to perform well they often require the tuning of multiple parameters to adapt them to each dataset. Despite the great advance in techniques, some problems remain, such as the difficulty to accurately pick S waves and earthquake recordings with a low signal‐to‐noise ratio. Recently, phase pickers based on deep learning (DL) have shown great potential for event identification and arrival‐time picking. However, the general adoption of these methods for the routine processing of monitoring networks has been held back by factors such as the availability of well‐documented software, computational resources, and a gap in knowledge of these methods. In this study, we evaluate recent available DL pickers for earthquake data, comparing the performance of several neural network architectures. We test the selected pickers using three datasets with different characteristics. We found that the analyzed DL pickers (generalized phase detection, PhaseNet, and EQTransformer) perform well in the three tested cases. They are very efficient at ignoring large‐amplitude transient noise and at picking S waves, a task that is often difficult even for experienced analysts. Nevertheless, the performance of the analyzed DL pickers varies widely in terms of sensitivity and false discovery rate, with some pickers missing a significant percentage of true picks and others producing a large number of false positives. There are also variations in run time between DL pickers, with some of them requiring significant resources to process large datasets. In spite of these drawbacks, we show that DL pickers can be used efficiently to process large seismic datasets and obtain results comparable or better than current standard procedures.
|
|
|
|
Conde, D., Castillo, F. L., Escobar, C., García, C., Garcia Navarro, J. E., Sanz, V., et al. (2023). Forecasting Geomagnetic Storm Disturbances and Their Uncertainties Using Deep Learning. Space Weather, 21(11), e2023SW003474–27pp.
Abstract: Severe space weather produced by disturbed conditions on the Sun results in harmful effects both for humans in space and in high-latitude flights, and for technological systems such as spacecraft or communications. Also, geomagnetically induced currents (GICs) flowing on long ground-based conductors, such as power networks, potentially threaten critical infrastructures on Earth. The first step in developing an alarm system against GICs is to forecast them. This is a challenging task given the highly non-linear dependencies of the response of the magnetosphere to these perturbations. In the last few years, modern machine-learning models have shown to be very good at predicting magnetic activity indices. However, such complex models are on the one hand difficult to tune, and on the other hand they are known to bring along potentially large prediction uncertainties which are generally difficult to estimate. In this work we aim at predicting the SYM-H index characterizing geomagnetic storms multiple-hour ahead, using public interplanetary magnetic field (IMF) data from the Sun-Earth L1 Lagrange point and SYM-H data. We implement a type of machine-learning model called long short-term memory (LSTM) network. Our scope is to estimate the prediction uncertainties coming from a deep-learning model in the context of forecasting the SYM-H index. These uncertainties will be essential to set reliable alarm thresholds. The resulting uncertainties turn out to be sizable at the critical stages of the geomagnetic storms. Our methodology includes as well an efficient optimization of important hyper-parameters of the LSTM network and robustness tests.
|
|
|
|
ATLAS Collaboration(Aad, G. et al), Cabrera Urban, S., Castillo Gimenez, V., Costa, M. J., Ferrer, A., Fiorini, L., et al. (2015). Measurement of the inclusive jet cross-section in proton-proton collisions at root s=7 TeV using 4.5 fb(-1) of data with the ATLAS detector. J. High Energy Phys., 02(2), 153–54pp.
Abstract: The inclusive jet cross-section is measured in proton-proton collisions at a centre-of-mass energy of 7 TeV using a data set corresponding to an integrated luminosity of 4.5 fb(-1) collected with the ATLAS detector at the Large Hadron Collider in 2011. Jets are identified using the anti-k(t) algorithm with radius parameter values of 0.4 and 0.6. The double-differential cross-sections are presented as a function of the jet transverse momentum and the jet rapidity, covering jet transverse momenta from 100 GeV to 2 TeV. Next-to-leading-order QCD calculations corrected for non-perturbative effects and electroweak effects, as well as Monte Carlo simulations with next-to-leading-order matrix elements interfaced to parton showering, are compared to the measured cross-sections. A quantitative comparison of the measured cross-sections to the QCD calculations using several sets of parton distribution functions is performed.
|
|
|
|
ATLAS Collaboration(Aad, G. et al), Cabrera Urban, S., Castillo Gimenez, V., Costa, M. J., Ferrer, A., Fiorini, L., et al. (2012). Underlying event characteristics and their dependence on jet size of charged-particle jet events in pp collisions at root(s)=7 TeV with the ATLAS detector. Phys. Rev. D, 86(7), 072004–34pp.
Abstract: Distributions sensitive to the underlying event are studied in events containing one or more chargedparticle jets produced in pp collisions at root s = 7 TeV with the ATLAS detector at the Large Hadron Collider (LHC). These measurements reflect 800 μb(-1) of data taken during 2010. Jets are reconstructed using the anti-k(t) algorithm with radius parameter R varying between 0.2 and 1.0. Distributions of the charged-particle multiplicity, the scalar sum of the transverse momentum of charged particles, and the average charged-particle p(T) are measured as functions of p(T)(jet) in regions transverse to and opposite the leading jet for 4 GeV < p(T)(jet) < 100 GeV. In addition, the R dependence of the mean values of these observables is studied. In the transverse region, both the multiplicity and the scalar sum of the transverse momentum at fixed p(T)(jet) vary significantly with R, while the average charged- particle transverse momentum has a minimal dependence on R. Predictions from several Monte Carlo tunes have been compared to the data; the predictions from Pythia 6, based on tunes that have been determined using LHC data, show reasonable agreement with the data, including the dependence on R. Comparisons with other generators indicate that additional tuning of soft-QCD parameters is necessary for these generators. The measurements presented here provide a testing ground for further development of the Monte Carlo models.
|
|
|
|
ATLAS Collaboration(Aad, G. et al), Cabrera Urban, S., Castillo Gimenez, V., Costa, M. J., Ferrer, A., Fiorini, L., et al. (2012). Search for the decay B-s(0) -> mu(+)mu(-) with the ATLAS detector. Phys. Lett. B, 713(4-5), 387–407.
Abstract: A blind analysis searching for the decay B-s(0) -> mu(+)mu(-) has been performed using proton-proton collisions at a centre-of-mass energy of 7 TeV recorded with the ATLAS detector at the LHC. With an integrated luminosity of 2.4 fb(-1) no excess of events over the background expectation is found and an upper limit is set on the branching fraction BR(B-s(0) -> mu(+)mu(-)) <2.2(1.9) x 10(-8) at 95% (90%) confidence level.
|
|
