Estimation of Space–Time Branching Process Models in Seismology Using an EM–Type Algorithm

By Alejandro Veen, Frederic Paik Schoenberg. 2006

322 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Environmental Engineering, Geophysics

View Paper: https://www.semanticscholar.org/paper/9589500acbc1107c16dc7ff3da5794e7bc8ee7ad

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Environmental Engineering

In Geophysics

Citations in the corpus

Hawkes Processes in Finance (2015, methodology): “In [67], the authors use an Expectation Maximization (EM) based technique, an iterative procedure comprising the alternation of two steps of expectation (E) and maximization (M), in order to exploit the cluster representation of the Hawkes process described in Sec.”
COLLABORATIVE PROBLEM SOLVING AND THE ASSESSMENT OF COGNITIVE SKILLS: PSYCHOMETRIC CONSIDERATIONS (2013, background): “Recent literature (Halpin, in press; Halpin & De Boeck, in press; Rasmussen, 2013; Veen & Schoenberg, 2008) has addressed the computational aspects of estimation for Hawkes processes (Hawkes, 1971; Hawkes & Oakes, 1974) using Equation 11.”
Earthquake clusters in southern California I: Identification and stability (2013, methodology): “[34] In this study, we consider a version of the ETAS model with isotropic spatial kernel and homogeneous spatial background distribution, which is commonly used in analysis of observed seismicity [e.g., Veen and Schoenberg, 2008; Wang et al., 2010; Chu et al., 2011].”
Doctor AI: Predicting Clinical Events via Recurrent Neural Networks (2015, background): “Finally, Hawkes processes are known to have a flat loss function near optimal value of the parameters which renders the gradient-based learning algorithms inefficient (Veen and Schoenberg, 2008).”
Evaluation of space–time point process models using super‐thinning (2011, methodology): “…Aftershock Sequence (ETAS) model of Ogata (1998), which is widely used for modeling catalogs of earthquake occurrences (Schoenberg, 2003; Veen and Schoenberg, 2008), is defined as .x; t /D .x; y/C X i Wti<t g.jjx xi jj; t ti ; mi / (1) 610 wileyonlinelibrary.com/journal/environmetrics…”
Randomized Controlled Field Trials of Predictive Policing (2015, unknown): “For a detailed treatment of the EM algorithm in the context of ETAS see Veen and Schoenberg (2008) or Lewis and Mohler (2011) where the EM algorithm is shown to be equivalent to projected gradient ascent optimization on the log-likelihood.”