lecture 1: introduction to spatial point processes · 1.longleaf dataset (r package spatstat)....
TRANSCRIPT
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Lecture 1: Introduction to spatial pointprocesses
Jean-François Coeurjollyhttp://www-ljk.imag.fr/membres/Jean-Francois.Coeurjolly/
1 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Description of the course
• This introduction is divided into 4 lectures :1. Introduction : examples, general definitions.2. Poisson point process.3. Summary statistics.4. Models for spatial point processes.
• Material : slides, datasets, R instructions used for thelectures can be found athttp://www-ljk.imag.fr/membres/Jean-
Francois.Coeurjolly/
• You are asked to prepare some of the theoretical exercisesand practical exercises (using the R software) at home.
• You are also asked to read a research paper (to be givennext week) and prepare a one-page summary of the paper(either in French or English).
2 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Special thanks to . . .
the Danish team : Jesper Mølle, Ege Rubak and RasmusWaagepetersen
and Adrian Baddeley (Australia), Rémy Drouilhet (Grenoble) andYongtao Guan (USA)
3 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Examples of spatial point pattern data
General definitions and characterization
Moment measures and intensity functions
4 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Spatial data . . .
. . . can be roughly and mainly classified into three categories :
1. Geostatistical data : modelling of a discrete/continuous(vector) real-valued random variable observed at fixedlocations of a continuous space.
2. Lattice data : modelling of a discrete/continuous (vector)real-valued random variable observed at fixed locations of adiscrete space.
3. Spatial point pattern : modelling of random locations ofpoints (or objects) observed on a continuous space.
5 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Geostatistical data• sic.100 dataset (R package geoR) : cumulative rainfall in
Switzerland the 8th May.
• The observation consists in a discretized sample path of arandom field, X = (Xu , u ∈ R2),Xu ∈ R.
• Scientific questions : spatial correlation modelling (covariance,variogram), trend and variogram estimation, spatial prediction =kriging.
0 50 100 150 200 250 300 350
−50
050
100
150
200
250
●
●●
●
●
●
●
●
●●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
● ●
●
●
●
●
●●
●
●
●
6 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Lattice data
• Lightning density =number of lightning strikesper square kilometer peryear in 2013.
• The data are aggregated bydepartment ⇒ randomfield on a network,X = (Xu , u ∈ G),Xu ∈ Rwhere G is a graph.
• Scientific questions : spatial neighborhood correlation, spatialhomogeneity or inhomogeneity, discrete spatial modelling,. . .
7 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Spatial point pattern : forestry datasets• Observation of 65, 71 and 126 japanese, swedish and finnish pines
on W = [5.7, 5.7]2, [−5, 5] × [−8, 2] and [0, 9.6] × [0, 10] (in m).• The locations and the number of points are random !• The state space is denoted by S = R2 and is equipped with ‖ · ‖.
japanese pines
●
● ●
●
● ●
●
● ●
●
●
●
●
●
●
●
●
●● ●
●
●● ● ●
●
● ●
●
●
●●
●
● ●
●
● ● ● ● ● ● ●
● ●
● ●
●●
● ●
●
● ●
●
●
●
●
● ●
●● ● ● ●
swedish pines●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
finnish pines
●
●
●
●
● ● ● ●●
●●
●●●
●●●●
●
●
●
●
● ●
●
●●
●
●
●
●
●
●
●●●
●●
●
●
●
●●●
●
●
●
●
●
●
●
●●
●
●
●
● ●●●
●●
●●
●●●●
●
●
●
● ●
●●●●
●●●●
●
●●
●●
●
●
●
●
●
●
●●
●
●●●●●● ●● ● ● ●
●●●
● ●●●●
●
●●
●
●
●
●●
●
●●
●
Scientific questions :
• Understanding of the arrangement of the points : is thearrangement spatially homogeneous or inhomogeneous.
• Are the points independent one from each other (CSR) or dothey exhibit a particular structure (clustered or repulsion) ?
• Among the three species, which one has the highest intensity ? Isthis difference significant ? 8 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Spatial point pattern : earth quakes dataset
• R package dataset.• The data set give the locations of 1000 seismic events of
MB > 4.0. The events occurred in a cube near Fiji since 1964.
Scientific questions :
• Can we estimate the spatialinhomogeneity of seismicevents ?
• Can we prove statistically thepresence of two main clusters ?
• Can we highlight theanisotropy ?
165 175 185
−35
−25
−15
●●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
● ●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●●● ●●●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
● ●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
● ●
●
●
●
●●
●
●
●
●
●
●
●●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●●
●
●
●
●
●
●
●●
●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●●
●
●
●●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●● ● ●
●
●
●
●●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●●
●●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●●
●
●
●
●●●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●
●●
●
●
●
●
●
New Zealand
New Caledonia
VanuatuFiji
Samoa
165 175 185
−35
−25
−15
9 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Spatial point pattern : earth quakes dataset
• R package dataset.• The data set give the locations of 1000 seismic events of
MB > 4.0. The events occurred in a cube near Fiji since 1964.
Scientific questions :
• Can we estimate the spatialinhomogeneity of seismicevents ?
• Can we prove statistically thepresence of two main clusters ?
• Can we highlight theanisotropy ?
165 175 185
−35
−25
−15
0.5
0.5
1
1
1.5
1.5
2
2
2.5
2.5
3 3
3.5
3.5
4
4.5
5
5.5
6
6.5
7
7.5
8
9 ●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
● ●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●●● ●●●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
● ●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
● ●
●
●
●
●●
●
●
●
●
●
●
●●
●
●●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●●
●
●
●
●
●
●
●●
●
●
●
●
●●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●●
●
●
●●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●● ● ●
●
●
●
●●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●●
●●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●●
●
●
●
●●●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●●
●
●
●●
●
●
●
●
●
●●
●
●
●
●
●
New Zealand
New Caledonia
VanuatuFiji
Samoa
165 175 185
−35
−25
−15
9 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Spatial point pattern : marked point process1. Longleaf dataset (R package spatstat). Locations of 584 trees
observed with their diameter at breast height. S = R2 × R+(equipped with max(‖ · ‖, | · |)).
2. Ants dataset (R package spatstat). Locations of 97 antscategorised into two species. S = R2 × {0, 1} (equipped with themetric max(‖ · ‖, dM ) for any distance dM on the mark space).
longleaf
●●●
●
●●●●●●●
●●
●
●
●●●
●
●●●●●●●●●
●●
●● ●●●● ●● ●●
●
●
●
●●●●● ●●●●●
●●●●●●
●
●
●
●●
●●
●●●
●●●●●
●●●●●
●●●●●
● ● ●● ●●
●
●
●●
●●
●
●●●●
●
●●●
●
●●●
●●●
●●
●●●
●●●
●●
●●
●
●●
●●
●●
●
●●●●●●
●
●
●●
●●●●●
●●
●
●
●●
●
●●
●
●●●
●●
●
●
●
●●●
●
●
●
●
●
●●
●●
●
●
●
●●●●
●●●●●
●●●●●
●● ● ●
●●●
●
●●●
●●●●●
●●●●
●●●●
●●
●
●
●
●●
●●●
●●●●
●●●
●● ●●●
●●●
●●●
●
●●
●●
●●
●●
●●
●
●
●●
●●●●●
●●
●
●●
●●
●●●●●
●
●●
●
●
●●
●●
●●
●
●●●●●●●●●●
●
●
●●
●
●
●●●
●
●●
●
●●
●●
●●●
●
●
●
●
●●●
●
●
●●
●
●
●●●
●●
●
●
●
● ●● ●●
●●●
●●●●●●●
●
●
●
●●●●
●
●●●●
●
●
●●
●●●
●●
●●●
●●
●
●●●
●●●●
●●●
●●
●
●
●
●●●
●●●●●
●●
●●
●●● ●●●
●●●●
●
●●
●
●●●●●
●
●
●●
●●●●
●
●●
●
●
●
●●●
●●
●●
●
●
●●
●●●●
●
●●
●●●●●
●●
●
●●●
●●●
●
●
●
●
●●●●●●
●●
●
●●●●●
●●●●●
● ●●●
●●
● ●●●●
●●●●●●●
●
●●
●●●●●● ●
● ● ●●●●
●●●
●
●
●
●
●●
● ● ●●●
●
●●●●●
●
●●
●●●●
●
●●●●
●●●
●● ●●●●
●●●●●●●
●●
●
ants
● ●
●
●
●●
●
●●
●
●
●●
●
●●
●
●●
●
●
●
●
●●
●
● ●●
Scientific questions :
1. Are large trees independent ? Do large trees influence thepositions of smaller ones ?
2. Is there any competition inside each specie ? Are the two speciesindependent ?
10 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Spatial point pattern with extra information
• chorley dataset (R packagespatstat)
• Cases of larynx and lungcancers and position of anindustrial incinerator.
• S = R2 × {0, 1} (equipped withthe metric max(‖ · ‖, dM ) forany distance dM on the markspace).
Chorley−Ribble Data
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●●
●
●
●●
●
●
●
●
●
●●
●
●
●●●●●●
Scientific questions :
• Can we input the spatial positions of cancer cases to thepresence of the industriel incinerator ? to any other extrainformation (population density,. . .) ?
11 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Spatial point pattern with spatial covariates• Beischmedia dataset (R package spatstat, large tropical forest
dataset).
• 3604 locations of trees observed with two spatial covariates (herethe elevation field, gradient of the elevation).
Scientific questions :
• Can we explain the spatialinhomogeneity by the elevation,the slope ?
• Can we statistically prove thepositive influence of these twocovariates ?
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●●●
●●
●●
● ●
●●●●●●
●
● ●
●●
● ●
●●
●
●
●
● ●
●
●
●
● ●
●
●
●
●
●
●●●
●
●
●●●
●
●
●
●
●
●
●
●
●●●
●
●
●●
●
●
●
●●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●●●
●●●●
●
●●
●●●
●
●
●
●●
●
●
●●
●
●
●
●
●
●● ●
●
●
●●
●●
●
●●●
●●
●
●
●●●
●●●
●
●
●
●
●●●●
●●
●●●●●●●●●●
●●
●●●
●●
●●
●●●●
●
●
●●●●●●●●
●● ●●
●●●●●●●●
●●●
●●
●●
●
●●●
●
● ●
●
●●●●
●●
●●●●●
●
●●●
●●●●
●●●
●●●●●
●
●●
●
●
●●●●●
●
●
●●
●●
●
●
●
●●●
●●●
●●●
●●●●
●
●
●
●
●●●●●
●
●●●
●●●●●●●●
●●●●●●●●●●
●●●●●●
●●
●●●
●●
●●●●●
●●
●
●
●●
●●●●●
●●
●●●●●
●●●●●●●●●●●●
●●●
●●●●
●●●
●
●
●
●
●●●●
● ●
●●●
●
●●
●●●●
●●
●●
●●●●
●●
●
●●
●●
●●
●
●●
●
●●
●
●
●●●●
●●● ●●●
●●
●
●●●●
●●
●
●●●●
●●
●
●
●
●●
●
●●●●
●
●
●●●●●●
●●
●●
●●
●●●
●
●
●
●●
●●
●●
●●●●●●
●●
●
●●●
●●
●●●
●●●●
●
●
●
●●●
●
●●●
●●●
●● ●
●
●●
●●
●
●
●●
●
●
●
●
●●
●●
●●
●
●
●
●
●
●
●●
●●●
●●
●● ●
●●
●●●
●●●●●●
●
● ●
●● ●●
●
●
●●
●
●
●●
●●●●●●
●●●
●●●●
●●●
●
●●
●●
●
●
●●●●●●
●●●●
●●●
● ●●●●●●
●●●●
●
●●●
●●●
●
●
●
●●
●●●●
●●
●●● ●
●●●
●●●
●●●●●●●
●
●
●
●●●
●●●
●●
●
●●●
●●●●
● ●
●
●
●●
●
●
●●
●
●●●
●
●
●
●● ●●
●●
●
●
●
●
●
●●
●●
●
●
●
●●●
●● ●
●●● ●
●
●●●●
●●●
●●● ●● ●
●
●
●●
● ●●●
●
● ●●●
●
●●●
●
●
●●●
●●●
●●
●●●●●●●●●●
●●●●
●●●●●●●●●●●●●●●●●
●●●●●●●●●●
●●●
●●●●●●●●
●●●
●●●
●●●●●●●●●●
●●●●●●●●●●●●●●●● ●●●
●●●●
●
●
● ●
●●●
●●
●
●
●●●
●● ●
●
●●●●●●
●●●●●●
●
●●●●●●●●●●
●
●●●●● ●●
●●● ●●
●●●●●●●●●●●●●●●●●●● ●●●●●●●
●●●●●●●●●●●●●●●●●●●●●
●●●●●
●●●●●●●
●●●
●●●●●●●●
●●●●●●●●●●●●●●●●●●
●● ●●●●●●●
●●●●●●●●●●●●●●●
●●●
●
●
●
●●
●●
●●●
●●●
●
●●●●●
●
●●●●●
●
●●
●
●●
●●●
●●●
●●●
●● ●●●●
●●●●
●
●●
●●
●
●
●●
●●●●
● ●●●
●●●●
●●●
●●●●
●
●●
●
●
● ●●
●
●●●●●
●
●●●
●●
●●● ●●
●● ●
●●
●● ●●
●●●
●
●
●●
●●●
●●●●
●●●●●●
●●●
●●●●●● ●
●●
● ●●●
● ●●
●
●
● ●
● ●●
●●
●●
●●●
●
●●●
●●●
●
●
● ●
●● ●●●
●●●
●
●
●●●
●●●
●●●
●●●
●●●
●●
●
● ●●●●●●
●●●
●●●●
●●●
●●●●● ●●
●
●●● ●
●
●
●●
●●
●●●
●●●
●
●
●●
●● ●
●●●
●
●
●●●
●
●●●● ●
●●
●
●●
●●●●
●
●●
●●●●●●●
●
●●
●●●
●●
●● ●●●●
● ●●● ●
●●● ●
● ●●
●●
●
●●
●●●●● ●
●●●●
●●●●●
●●●●●
●●
●
●●●●●●
●
●●
●●
●
●
●
●●●●●● ●
●●●
●●
●
●● ● ●●
●●
●●
●●●
● ●
● ●
●●●●
●●●● ●●
●●●●●
●
●●
●
●●
●
●
●
●●
●●
●
● ●●
●
●
●● ●●
●●
●●●
●
●●●
●●●●●●●
●●●
●●●
●
●● ●
●●● ●●●
●●● ●● ●●●●●●
●●●
●●
●
●
●
●
●
●
●
●●●
●
●●●
● ●
●●●●
●●
●●
●●●●●●●●●●
●●● ●●●●
●●● ●●●● ●
●●●●
●
●●
●●
●●●
●●●
●●
●● ●
●●●●
●●●●●●●
●
●
●●
●
●
● ●●
●●●
●●
●
●
●
●●
●●
●
●
●
●
●
●
●
●●
●
●●
●●
●●●●
●●●●
●●●
●●
● ●
●●●●●●●●
●● ●●●●
●●●●●●
●●●
●●●
●●
●●●●●
●
●●●
●●
●
●
●● ●
●
●
●●●
●
●
●
●
●●●●●
●●
●●
●
●
●
●
●
●
●
●
●
●
●
●●●
●
●●
●●
●
●
●
●
●
●
●
●
●
●●
● ●●
●
● ●
●
●
●
●●
●●
●●●
●
●
●●●
●●
●
●●●
●
●●
●
●
●●●
●●
●
●
●
●●
●
●●
●
●
●
●
●
●●●●●
●
●●●
●●●●
●
●
●●●●
●
●
●
● ●
●●
●
●●
●●
●
●
●
●
● ●●●●●●●●
● ●
●●● ●●●●
●●
●
●
●
●
●●●●
●●
●●
●●●
●●●●●
●●●●
●
●●●●●●●●●●●●●●●●●
●●●●●●●●●
●
●●
●●●●● ●● ●●●●●●●
●●●●●●●●
●●●●●●●●●●●●●●●●●●
●●●
●●
●
●
●
●
● ●
●
●●
●
●●●
●
●
●●
●
●
●●●
●
●
●
●
●●●
●
●●
●
●
●
●
●
●●
●●●●●●
●
●●
●●
●●
●
●●●●
●
●●
●●
●
●●
●●●
●●
●
●●
●
●●●
●●●
●●●
●
●
●●●●●●●●
●
●
●●
●
●●
●
●
●●
●●●●
●● ●
●
●
●
●
●
●
●
●●●
●
●●
●
●
●
●●●●
●
●●
●●●●●
●●
●
●
●●
●
●●●●●
●
●
●●●
●●
●●
●
●
●
●
●
●●●●
●
●●
●
●
●●●●
●
●
● ●
●
●
●●
●
●
●●
●●
●
●
●
●●● ●
●
●
●
●
●
●●
●
●●●
●
●●
● ●
●●●
●
●●
● ●
●
●●●
●●
●
●
●
●
●●
●●
●●
●●
●
●
●
●
●●
●●
●
●
●
●●
●●
●
●●●●●
●
●
●
●
●●
●
●
●
●●●●●●
●●
●●
●
●
●
●
●●●
●
●
●
●●
●●
●●●
●●●●●
●●
●●
●●●●●
●●●
●
●
●●●
●●●●
●
●
●
●
●
●●
●●
●
●
●
●●●
●
●
●
●
●
●
●
●●
●
●
●
●●●
●●●●
●
●
●
●●
●●
●
●
●●●
●●
●
●
●
●
●
●
●
●●●●●●●●
●●
●
●●
●
●●
●●
●●
●●
●
●●●
●
●●●●
●
●
●
●●●●●
●
●
●
●
●●
●
●
●
●●
●●
●
●●
●●
●
●
●
●●
●●●
●
●●
●
●
●
●●
●●●●●
●●●●
●●●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●●
●●
●
●
●●
●
●●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●●●
● ●
●
●●
●
●
●
●
●
●
●●●
●
●
●
●
●
●
●●●
●
●●
●●●
●
●
●●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●●
●
●●
●
● ●
●
●
●
●
●
●●
●
●
●
●●●●
●
●●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●●●
●
●●
●●
●
●
●●
●
●
●
●
●
12 / 19
-
Spatial datasets Definition and theoretical characterization Moment measures and intensity functions
Spatio-temporal point process• Lightning strikes observed on the domain [−5, 9] × [42, 53]
(long,lat) observed temporally since the period 2010-2013.
• Both time and position are point processes ; S = R2 × R. Summer 2010
5000
1000
015
000
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
● ●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●
●