GEOBIA 2012, Rio de Janeiro
Describing change using
geographical objects
Gilberto Camara
INPE – National Institute for Space Research
The fundamental question of our time
source: IGBP
How is the Earth’s
environment changing, and
what are the consequences for
human civilization?
Global Change
Where are changes taking place?
How much change is happening?
Who is being impacted by the change?
Geoinformatics enables crucial links between nature
and society
Nature: Physical equations
Describe processes
Society: Decisions on how to
Use Earth´s resources
Earth observation satellites and geosensor
webs provide key information about global
change…
…but that information needs to be modelled
and extracted
Communicating change is hard
When did the Aral Sea reach the tipping point?
Describing events and processes is very hard
When did the flood occur?
What types of change can be described
using geo-objects?
What is the role of GEOBIA in describing
change?
Geo-objects in an image
Landsat Image
13/Ago/2003
Geo-objects in an image
Deforestation
13/Ago/2003 until
07/Mai/2004
Deforestation in
13/Aug/2003 (yellow) +
deforestation from
13/Aug/2003 until
07/mai/2004 (red)
Geo-objects in an image
Deforestation on
21/May/2004
Deforestation in
13/Aug/2003
(yellow) +
deforestation from
13/Aug/2003 until
07/May/2004 (red)
+ deforestation on
21/May/2004
(orange)
Land change objects
LAND CHANGE OBJECTS
Boundaries determined by agreement about land
categories (geometry, topology and properties change)
Images as a source for geo-objects
G Câmara, M Egenhofer, F Fonseca, A Monteiro. "What´s in An
Image?“ COSIT 2001.
“Images have an observer-independent ontological
status”
What’s in an image?
Images = acts of
measurement
Segments =
mathematical constructs
Ontology-Based Image Analysis
Structur.
Ontology
Method
Ontology
Physical
Ontology
Segments
(mathematical
constructs)
Semantic
Mediator
Applicat.
Ontology
Task
Ontology
Objects
(conceptual
constructs)
Extracting patterns from sequences of images
M. Silva, G.Câmara, M.I. Escada, R.C.M. Souza, “Remote Sensing Image Mining:
Detecting Agents of Land Use Change in Tropical Forest Areas”. International Journal of
Remote Sensing, vol 29 (16): 4803 – 4822, 2008.
Linking human actions to land change
Remote sensing image mining
M. Silva, G.Câmara, M.I. Escada, R.C.M. Souza, “Remote Sensing Image Mining:
Detecting Agents of Land Use Change in Tropical Forest Areas”. International Journal of
Remote Sensing, vol 29 (16): 4803 – 4822, 2008.
Patterns of tropical deforestation
Spatial patterns in the Vale do Anari
irregular, linear, regular
Decision tree for Vale do Anari
Vale do Anari – 1982 -1985
REG
Patterns/Typology
IRR: Irregular – Colonist parcels
LIN: Linear – roadside parcels
REG: Regular agregation parcels
Pereira et al, 2005
Escada, 2003
Vale do Anari – 1985 - 1988
REG
Pereira et al, 2005
Escada, 2003
Vale do Anari – 1988 - 1991
REG
Pereira et al, 2005
Escada, 2003
Vale do Anari – 1991 - 1994
REG
Pereira et al, 2005
Escada, 2003
Vale do Anari – 1994 - 1997
REG
Pereira et al, 2005
Escada, 2003
Vale do Anari – 1997 - 2000
REG
Pereira et al, 2005
Escada, 2003
Vale do Anari – 1985 - 2000
REG
Confirmed by
field work
Pereira et al, 2005
Escada, 2003
Land change patterns: Anari (1985-2000)
Marked land concentration
Government plan for settling many colonists in the area has failed.
Large farmers have bought the parcels in an illicit way
Discovering the history of land change objects
"Case-Based Reasoning for Eliciting the Evolution of Geospatial
Objects". Joice Mota, Gilberto Câmara et al, COSIT 2009.
Reconstructing the history of a landscape using topological
information of geo-objects
When was this area converted from food to biofuel
production?
Coverage set
(remote sensing
images)

Time Series
(vegetation
index)
Geographic Data Mining Analyst (GeoDMA)
Visualizing time series in polar coordinates
Objects and events
The coast of Japan is an object
The 2011 Tohoku tsunami was an event
Processes and events
Flying is a process - Virgin flight VX 112 (LAX-IAD) on
26 Apr 2012 is an event
Aral Sea (an object) – disaster (an event)
When did the Aral Sea shrank to 10% of its
original size?
objects exist, events occur
Mount Etna is an object
Etna’s 2002 eruption was an event
A view on processes and events
Space
Count
Mass
Objects
Matter
water or lake?
Time
(Worboys & Galton)
Events
Processes
football or game?
A pragmatic view on objects and events
Space
Observable
Objects
Matter
Abstract
water or lake?
Time
Events
Processes
football or game?
Object (GPS buoy) + event (tsunami)
source: USGS
Events are categories (Frank, Galton)
identity : id · a = a
composition : ∀a, ∀b, ∃c, c = a.b
associativity : a · (b · c) = (a · b) · c
Building blocks: Basic Types
type BASE = {Int, Real, String, Boolean}
operations: // lots of them…
Building blocks: Geometry (OGC)
type GEOM = {Point, LineString, Polygon,
MultiPoint, MultiLineString, MultiPolygon}
operations:
equals, touches, disjoint, crosses, within,
overlaps, contains, intersects: GEOM x GEOM → Bool
Building blocks: Time (ISO 19108)
type TIME = {Instant, Period}
operations:
equals, before, after, begins, ends, during,
contains, overlaps, meets, overlappedBy, metBy,
begunBy, endedBy: TIME x TIME → Boolean
What do ST objects have in common?
type STobj [T: TIME, G: GEOM, B: BASE]
operations:
getObs:
ST → {Obs}
begins, ends:
ST → T
where:
ST x T → G
after, before:
ST x T → ST
during:
ST x Period → ST
value:
ST x T → B
Moving objects
MOVING OBJECTS
Objects whose position and extent change continuously
Land change objects
LAND CHANGE OBJECTS
Boundaries determined by agreement about land
categories (geometry, topology and properties change)
How many walruses
reached Baffin island?
When did the Aral Sea shrank to 10% of its
original size?
areaAral: STObject → Time
areaAral obj:
{
area0 = area (obj1.begin());
for t = obj.begin(); t <= obj.end(); t.next()
if area (obj1.begin()) < 0.10*area0) return t;
}
The event data type
An event is an individual episode with a beginning
and end, which define its character as a whole.
An event does not exist by itself. Its occurrence is
defined as a particular condition of one
spatiotemporal type.
The event data type
Type Event [T1: TIME, T2: TIME] uses ST
operations:
new:
{ST x (T1, T2)
→ Event
compose:
Event x Event → Event
intersect:
Event x Event → Event
Event composition
time
Exploração
intensiva
Forest
loss
> 20%
Event 1
Perda
do dossel
Loss >50%
> 50%
Event 2
Event 3
Event 4
Perda
do dossel
Loss >90%
> 90%
Corte
Clearraso
cut
Floresta
Discovering the history of land
change objects
Reconstructing the history of a landscape
TerraLib: spatio-temporal database as a
basis for innovation
Visualization (TerraView)
Modelling (TerraME)
Spatio-temporal
Database (TerraLib)
Statistics (aRT)
Data Mining(GeoDMA)
Algebras for spatio-temporal data
are a powerful way of representing
change