Log-Gaussian Cox process modeling of large spatial lightning data using spectral and Laplace approximations

Lightning is a destructive and highly visible product of severe storms, yet there is still much to be learned about the conditions under which lightning is most likely to occur. The GOES-16 and GOES-17 satellites, launched in 2016 and 2018 by NOAA and NASA, collect a wealth of data regarding individual lightning strike occurrence and potentially related atmospheric variables. The acute nature and inherent spatial correlation in lightning data renders standard regression analyses inappropriate. Further, computational considerations are foregrounded by the desire to analyze the immense and rapidly increasing volume of lightning data. We present a new computationally feasible method that combines spectral and Laplace approximations in an EM algorithm, denoted SLEM, to fit the widely popular log-Gaussian Cox process model to large spatial point pattern datasets. In simulations, we find SLEM is competitive with contemporary techniques in terms of speed and accuracy. When applied to two lightning datasets, SLEM provides better out-of-sample prediction scores and quicker runtimes, suggesting its particular usefulness for analyzing lightning data, which tend to have sparse signals.

[1]  David S. Henderson,et al.  Evaluating Convective Initiation in High-Resolution Numerical Weather Prediction Models Using GOES-16 Infrared Brightness Temperatures , 2021, Monthly Weather Review.

[2]  Jaewoo Park,et al.  Reduced-dimensional Monte Carlo Maximum Likelihood for Latent Gaussian Random Field Models , 2019 .

[3]  Matthias Katzfuss,et al.  Vecchia-Laplace approximations of generalized Gaussian processes for big non-Gaussian spatial data , 2019, Comput. Stat. Data Anal..

[4]  C. Kummerow,et al.  A simplified method for the detection of convection using high-resolution imagery from GOES-16 , 2020, Atmospheric Measurement Techniques.

[5]  M. Haran,et al.  Fast expectation-maximization algorithms for spatial generalized linear mixed models , 2019, 1909.05440.

[6]  Finn Lindgren,et al.  inlabru: an R package for Bayesian spatial modelling from ecological survey data , 2019, Methods in Ecology and Evolution.

[7]  Robert H. Holzworth,et al.  Lightning: A New Essential Climate Variable , 2018, Eos.

[8]  A. Blyth,et al.  A projected decrease in lightning under climate change , 2018, Nature Climate Change.

[9]  Murali Haran,et al.  A Computationally Efficient Projection-Based Approach for Spatial Generalized Linear Mixed Models , 2016, Journal of Computational and Graphical Statistics.

[10]  Spencer K. Clark,et al.  Parameterization‐based uncertainty in future lightning flash density , 2017 .

[11]  M. Fuentes,et al.  Circulant Embedding of Approximate Covariances for Inference From Gaussian Data on Large Lattices , 2017 .

[12]  Alan E. Gelfand,et al.  Inference for log Gaussian Cox processes using an approximate marginal posterior , 2016, 1611.10359.

[13]  Peter J. Diggle,et al.  Bayesian Inference and Data Augmentation Schemes for Spatial, Spatiotemporal and Multivariate Log-Gaussian Cox Processes in R , 2015 .

[14]  Peter J. Diggle,et al.  lgcp: An R Package for Inference with Spatial and Spatio-Temporal Log-Gaussian Cox Processes , 2013 .

[15]  Finn Lindgren,et al.  Bayesian computing with INLA: New features , 2012, Comput. Stat. Data Anal..

[16]  William J. Koshak,et al.  The GOES-R GeoStationary Lightning Mapper (GLM) , 2012 .

[17]  Haavard Rue,et al.  A toolbox for fitting complex spatial point process models using integrated nested Laplace approximation (INLA) , 2012, 1301.1817.

[18]  Peter J. Diggle,et al.  INLA or MCMC? A tutorial and comparative evaluation for spatial prediction in log-Gaussian Cox processes , 2012, 1202.1738.

[19]  H. Rue,et al.  An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach , 2011 .

[20]  H. Rue,et al.  Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations , 2009 .

[21]  V. Kotroni,et al.  Lightning occurrence in relation with elevation, terrain slope, and vegetation cover in the Mediterranean , 2008 .

[22]  J. Beringer,et al.  The Spatial and Temporal Distribution of Lightning Strikes and Their Relationship with Vegetation Type, Elevation, and Fire Scars in the Northern Territory , 2007 .

[23]  Peter J. Diggle,et al.  Point process methodology for on‐line spatio‐temporal disease surveillance , 2005 .

[24]  J. Mecikalski,et al.  Forecasting Convective Initiation by Monitoring the Evolution of Moving Cumulus in Daytime GOES Imagery , 2004 .

[25]  P. Diggle,et al.  Spatiotemporal prediction for log‐Gaussian Cox processes , 2001 .

[26]  J. Møller,et al.  Log Gaussian Cox Processes , 1998 .

[27]  A. Wood,et al.  Simulation of Stationary Gaussian Processes in [0, 1] d , 1994 .

[28]  M. Hutchinson.  A stochastic estimator of the trace of the influence matrix for laplacian smoothing splines , 1989 .

[29]  M. Hestenes,et al.  Methods of conjugate gradients for solving linear systems , 1952 .