Anda di halaman 1dari 6

Point processes, spatial–temporal

Frederic Paik Schoenberg, David R. Brillinger & Peter Guttorp

Volume 3, pp 1573–1577


Encyclopedia of Environmetrics
(ISBN 0471 899976)

Edited by

Abdel H. El-Shaarawi and Walter W. Piegorsch

 John Wiley & Sons, Ltd, Chichester, 2002

Point processes, 3 of space–time, taking values in the non-negative
integers C (or infinity). In this framework the mea-
spatial–temporal sure NA represents the number of points falling in
the subset A of S. For the set A in Figure 1, for exam-
ple, the value of NA is 2. Attention is typically
A spatial–temporal point process (also called space–
restricted to points in some time interval [T0 , T1 ],
time or spatio-temporal point process) is a random
and to processes with only a finite number of points
collection of points, where each point represents the
in any compact subset of S.
time and location of an event. Examples of events
Traditionally the points of a point process are
include incidence of disease, sightings or births of
thought to be indistinguishable, other than by their
a species, or the occurrences of fires, earthquakes,
times and locations. Often, however, there is other
lightning strikes, tsunamis, or volcanic eruptions.
important information to be stored along with each
Typically the spatial locations are recorded in three
point. For example, one may wish to analyze a list
spatial coordinates, e.g. longitude, latitude, and height
of points in time and space where a member of a
or depth, though sometimes only one or two spatial
certain species was observed, along with the size
coordinates are available or of interest. Figure 1 is
or age of the organism, or alternatively a catalog
an illustration of a realization of a spatial–temporal
of arrival times and locations of hurricanes along
point process with one spatial coordinate depicted.
with the amounts of damage attributed to each. Such
Figure 2 displays some point process data consisting
processes may be viewed as marked spatial–temporal
of microearthquake origin times and epicenters in
point processes, i.e. random collections of points,
Parkfield, CA, between 1988 and 1995, recorded
by the US High-Resolution Seismographic Station
Network [16]. Figure 3 displays the centroids of
wildfires occurring between 1876 and 1996 in Los
Angeles County, CA, recorded by the Los Angeles

County Department of Public Works (times of the

events not shown). A

A spatial–temporal point process N is mathematically
defined as a random measure on a region S   ð Figure 1 Spatial–temporal point process

Distance along fault (km)


1988 1989 1990 1991 1992 1993 1994 1995

Figure 2 Epicenters and times of Parkfield microearthquakes, 1988–1995

2 Point processes, spatial–temporal

rate process [6]. t, x, y, z may be thought of

as the frequency with which events are expected
to occur around a particular location (t, x, y, z) in
space–time, conditional on the prior history, Ht , of
the point process up to time t. Note that in the statisti-
cal literature (e.g. [4] and [12]), is more commonly
referred to as the conditional intensity rather than
the conditional rate. However, the term intensity is
also used in various environmental sciences, e.g. in
describing the size or destructiveness of an earth-
quake, so to avoid confusion, the term rate may be
Formally, the conditional rate t, x, y, z associ-
ated with a spatial–temporal point process N may be
defined as a limiting conditional expectation, as fol-
lows. Fix any point p D t, x, y, z in space–time.
Figure 3 Centroids of recorded Los Angeles County wild- Let B denote the set t, t C t ð x, x C x ð
fires, 1878–1996
y, y C y ð z, z C z, where  is the vector
t, x, y, z. Then
where each point has associated with it a further
random variable called a mark. p D lim E[NB jHt]/jj 1
Much of the theory of spatial–temporal point
processes carries over from that of spatial point provided the limit exists. Some authors instead define
processes (see Point processes, spatial). However, p as
the temporal aspect enables a natural ordering of lim P[NB  > 0jHt]/jj 2
the points that does not generally exist for spatial
processes. Indeed, it may often be convenient to view For orderly point processes (processes where
a spatial–temporal point process as a purely temporal limjAj#; PrfNA > 1g/jAj D 0 for interval A), the
point process (see Point processes, temporal), with two definitions are equivalent. is a predictable pro-
spatial marks associated with each point. Sometimes cess whose integral C (called the compensator) is
investigating the purely temporal (or purely spatial) such that N C is a martingale. There are different
behavior of the resulting marginalized point process forms of conditioning corresponding to different
is of interest. types of martingales; see [11], [14], or [21].
The spatial region of interest is often a rectan-
gular portion of 2 or 3 , but not always. For the Models
data in Figure 2, for example, the focus is on just
one spatial coordinate, and in Figure 3 the region of The behavior of a spatial–temporal point process N
interest is Los Angeles County, which has an irreg- is typically modeled by specifying a functional form
ular boundary. Cases where the points are spatially for t, x, y, z, which represents the infinitesimal
distributed in a sphere or an ellipse are investigated expected rate of events at time t and location (x, y, z),
by Brillinger [2, 3]. When the domain of possible given all the observations up to time t. Although
spatial coordinates is discrete (e.g. a lattice) rather may be estimated nonparametrically [5, 7, 24],
than continuous, it may be convenient to view the it is more common to estimate via a parametric
spatial–temporal point process as a sequence fNi g of model.
temporal point processes that may interact with one In general, t, x, y, z depends not only on t, x, y
another. For example, one may view the occurrences and z but also on the times and locations of preced-
of cars on a highway as such a collection, where Ni ing events. When N is a Poisson process, however,
represents observations of cars in lane i. is deterministic, i.e. t, x, y, z depends only on
Any analytical spatial–temporal point process is t, x, y and z. The simplest model is the station-
characterized uniquely by its associated conditional ary Poisson, where the conditional rate is constant:
Point processes, spatial–temporal 3

t, x, y, z D ˛ for all t, x, y, z. In the case of mod- rate plus

eling environmental disturbances, this model incor- 
porates the idea that the risk of an event is the t ti , x xi , y yi , z zi , m mi  4
same at all times and locations, regardless of where i
and how frequently such disturbances have occurred A variety of forms has been given for the clustering
previously. Processes that display substantial spa- density . For instance, in modeling seismological
tial heterogeneity, such as earthquake epicenters, are data with two spatial parameters (x and y) and a
sometimes modeled as stationary in time but not mark (m) indicating magnitude, Musmeci and Vere-
space. Jones [15] introduced explicit forms for , includ-
Stationary spatial–temporal point processes are ing the diffusion-type model where t, x, y, m is
sometimes described by the second-order parameter given by
measure t0 , x 0 , y 0 , z0 , which measures the covari-  

ance between the numbers of points in spatial–temp- x2 y2
oral regions A and B, where region B is A shifted  C 2 
C  x2 y 
by (t0 , x 0 , y 0 , z0 ) (see Space–time covariance mod- exp 
˛m ˇt 
 5
els). For example, Kagan and Vere-Jones [10] explore 2x y t  2t 
models for  in describing spatial–temporal patterns
of earthquake hypocenters and times. For a self-
exciting (equivalently, clustered) point process, the Ogata [17] investigated the case where
function  is positive for small values of t0 , x 0 , y 0 K0 exp[˛m m0 ]
and z0 ; N is self-correcting (equivalently, inhibitory) t, x, y, m D 6
t C cp x 2 C y 2 C dq
if instead the covariance is negative. Thus the occur-
rence of points in a self-exciting point process is as well as a variety of other models. Several other
associated with other points occurring nearby in forms for  were suggested by Rathbun [18] and
space–time, whereas in a self-correcting process the Kagan [9]; see [17] for a review.
points have an inhibitory effect. Sometimes is modeled as a product of marginal
Self-exciting point process models are often used conditional intensities
in epidemiology (see Spatial statistics in environ-
mental epidemiology) and seismology (see Seismo- t, x, y, z D 1 t 2 x, y, z 7
logical modeling) to model events that are clustered
or even
together in time and space. A commonly used form
for such models is a spatial–temporal generaliza- t, x, y, z D 1 t 2 x 2 y 4 z 8
tion of the Hawkes model, where t, x, y, z may
be written as These forms embody the notion that the temporal
behavior of the process is independent of the spatial
t, x, y, z behavior, and in the latter case that furthermore the
 behavior along each of the spatial coordinates can
C t ti , x xi , y yi , z zi  3
be seen as independent. In such cases each of the
functions i may be estimated individually; see, for
where the sum is over all points ti , xi , yi , zi  with example, [18] or [21]. Occasionally one subdivides
ti < t. The functions  and  represent the determin- the spatial region into a finite number of subregions
istic background rate and clustering density, respec- and fits temporal point process models to the data
tively. Often  is modeled as merely a function of within each subregion. In such a case the conditional
the spatial coordinates (x, y, z), and may be estimated intensity may be written
nonparametrically as in [17]. When observed marks 
t, x, y, z D 1 t1i x, y, z 9
m associated with each point are posited to affect the
rate at which future points accumulate, this informa-
tion is typically incorporated into the function , i.e. where the 1i are indicator functions denoting the
the conditional rate is modeled as a background relevant region. An example is given in [26]. The
4 Point processes, spatial–temporal

introduction of interactions between different subre- [3] Brillinger, D.R. (2000). Some examples of random
gions is incorporated into this model by Lu et al. [13]. process environmental data analysis, in Handbook of
For further remarks on modeling and examples Statistics, Vol. 18, C.R. Rao & P.K. Sen, eds, North-
Holland, Amsterdam, pp. 33–56.
see [23] and [25].
[4] Daley, D. & Vere-Jones, D. (1988). An Introduction
to the Theory of Point Processes, Springer-Verlag,
Estimation and Inference [5] Diggle, P. (1985). A kernel method for smoothing point
process data, Applied Statistics 34, 138–147.
The parameter vector $ for a model with conditional [6] Fishman, P.M. & Snyder, D.L. (1976). The statistical
rate t, x, y, z; $ is usually estimated by maximizing analysis of space–time point processes, IEEE Transac-
the log-likelihood function tions on Information Theory IT-22, 257–274.


[7] Guttorp, P. & Thompson, M. (1990). Nonparametric
estimation of intensities for sampled counting processes,
L$ D log[ t, x, y, z; $] dNt, x, y, z Journal of the Royal Statistical Society, Series B 52,
T0 x y z


[8] Heinrich, L. (1991). Goodness-of-fit tests for the sec-
t, x, y, z; $ dz dy dx dt 10 ond moment function of a stationary multidimensional
T0 x y z
Poisson process, Statistics 22, 245–278.
Asymptotic properties of the maximum likelihood [9] Kagan, Y.Y. (1991). Likelihood analysis of earth-
estimator $O have been derived under various con- quake catalogs, Journal of Geophysical Research 106,
ditions, along with formulas for standard errors;
[10] Kagan, Y. & Vere-Jones, D. (1996). Problems in
see, e.g., [19]. Alternatively, simulations may be use- the modelling and statistical analysis of earthquakes,
ful for obtaining approximate standard errors and for in Lecture Notes in Statistics (Athens Conference on
other types of inference (see Resampling methods). Applied Probability and Time Series Analysis), Vol. 114,
The estimated conditional rate t, x, y, z; $ O can C.C. Heyde, Yu.V. Prorohov, R. Pyke & S.T. Rachev,
be used directly for prediction and risk assess- eds, Springer-Verlag, New York, pp. 398–425.
ment (see Risk assessment, seismological). See [1] [11] Kallenberg, O. (1983). Random Measures, 3rd Edition,
Akademie-Verlag, Berlin.
and [6], for example.
[12] Karr, A. (1991). Point Processes and Their Statistical
Spatial–temporal point processes may be evalu- Inference, 2nd Edition, Marcel Dekker, New York.
ated via residual analysis, as described in [21]. One [13] Lu, C., Harte, D. & Bebbington, M. (1999). A linked
typically selects a spatial coordinate and rescales the stress release model for historical Japanese earthquakes:
point process in that direction. If the z coordinate coupling among major seismic regions, Earth, Planets,
is chosen, for example, then each point (ti , xi , yi , zi ) Space 51, 907–916.
of the observed point process is moved to a new [14] Merzbach, E. & Nualart, D. (1986). A characterization
of the spatial Poisson process and changing time, The
point (ti , xi , yi , zz0i ti , xi , yi , z; $
O dz), where z0 is
Annals of Probability 14, 1380–1390.
the lower boundary in the z direction of the spatial [15] Musmeci, F. & Vere-Jones, D. (1992). A space–time
region being considered. The resulting rescaled pro- clustering model for historical earthquakes, The Annals
cess is stationary Poisson if and only if the model is of the Institute of Statistical Mathematics 44, 1–11.
correctly specified [22]. Hence a useful method for [16] Nadeau, R., Antolik, M., Johnson, P.A., Foxall, W.
assessing the fit of a point process model is to exam- & McEvilly, T.V. (1994). Seismological studies at
ine whether the rescaled point process looks like a Parkfield III: microearthquake clusters in the study of
fault-zone dynamics, Bulletin of the Seismic Society of
Poisson process with unit rate. Several tests exist for
America 84, 247–263.
this purpose; see, for example, [8] or [20]. [17] Ogata, Y. (1998). Space–time point process models for
earthquake occurrences, The Annals of the Institute of
References Statistical Mathematics 50, 379–402.
[18] Rathbun, S.L. (1993). Modeling marked spatio-tempo-
[1] Brillinger, D.R. (1982). Seismic risk assessment: some ral point patterns, Bulletin of the International Statistical
statistical aspects, Earthquake Prediction Research 1, Institute 55, 379–396.
183–195. [19] Rathbun, S. & Cressie, N. (1994). Asymptotic properties
[2] Brillinger, D.R. (1997). A particle migrating randomly of estimators for the parameters of spatial inhomoge-
on a sphere, Journal of Theoretical Probability 10, neous Poisson point processes, Advances in Applied
429–443. Probability 26, 122–154.
Point processes, spatial–temporal 5

[20] Ripley, B. (1979). Tests of ‘randomness’ for spatial [25] Vere-Jones, D. & Thomson, P.J. (1984). Some aspects
point patterns, Journal of the Royal Statistical Society, of space–time modelling, in Proceedings of the
Series B 41, 368–374. Twelfth International Biometrics Conference, Tokyo,
[21] Schoenberg, F. (1997). Assessment of multi-dimensio- pp. 265–275.
nal point processes, Ph.D. Thesis, University of Cali- [26] Zheng, X. & Vere-Jones, D. (1994). Further applications
fornia, Berkeley. of the stochastic stress release model to historical
[22] Schoenberg, F. (1999). Transforming spatial point pro- earthquake data, Tectonophysics 229, 101–121.
cesses into Poisson processes, Stochastic Process Appli-
cations 81, 155–164.
[23] Snyder, D.L. & Miller, M.I. (1991). Random Point (See also Point processes, dynamic; Stochastic
Processes in Time and Space, Wiley, New York.
model; Stochastic process)
[24] Vere-Jones, D. (1992). Statistical methods for the des-
cription and display of earthquake catalogs, in Statistics
in the Environmental and Earth Sciences, A. Walden & FREDERIC PAIK SCHOENBERG,
P. Guttorp, eds, Edward Arnold, London, pp. 220–246. DAVID R. BRILLINGER & PETER GUTTORP