Applying Artificial Neural Network and

sciencediscussionAI and Robotics

Oct 20, 2013 (4 years and 24 days ago)

76 views

Abstract

Appl
icability of

Artificial Neural Network
(ANN)
and Decision Tree

(DT)

to Digital (p
redictive
)

Soil
Mapping


MSc thesis of
Ms.
Ruamporn
Moonjun
*

(
moonjun13562@alumni.itc.nl
),
International Instit
ute for Geo
-
information Science and Earth Observation (ITC), Enschede, The Netherlands
.

(
www.itc.nl
), u
nder the
direction of

Dr. A. Farshad and Dr. D.P. Shrestha
, ITC.


Considering th
at
the
land degradation
caused by defo
restation and mismanagement in sloping areas

is steadily increasing
,
conservation
-
oriented
studies in these

are
as

become
vita
l
.
Fortunately,
ample
attention is paid to
landslide and erosion

as the two most

common
degradation types
. The demand
for high reso
lution soil mapping is more and more growing, in particular
in
land

use planning
p
rojects
.

The objective of this study
is
focuse
d

on applying
a few
methods
o
f digital soil mapping in
inaccessible
sloping
areas,
susceptible to landslide and erosion.

The i
n
tention

is to
apply some
of
t
he available methods

of digital soil mapping

in order to select the most effective one
to map the
soils

in a quick, accurate and inexpensive way
. Artificial Neural Network (ANN) and Decision Tree
(DT) were employed to comply wi
th the objectives. Geopedologic approach was applied as from
the first stage
;

that is the
visual
image interpretation, through the fieldwork (during the phase of
data collection). After the geoform map was produced, training areas could be selected, wherei
n the
application of
the
Jenny equation and SCORPAN model
(recently derived from the Jenny equation)
co
uld be executed.


The major task, forming the scientific framework of
this exercise
,

is

parameterization of the
soil forming factors and their integrati
on. A digital soil mapping was done in the study area, Hoi
Num Rin sub
-
watershed, covering an area of about 20 km
2
. The ANN is based on feedforward
-
backpropagation learning algorithm determined with one hidden layer. The decision tree is based on
the exper
t system concept. Both methods were applied to integrate the parameterized soil forming
factors. The description of soil predictors to train the ANN and to formulate the decision trees: 4
organism types, 7 relief
-
type units, 9 lithological units, 3 time se
ries, 4 landscape units and 8
landform units were extracted from the map
s

and databases. The results: soil mapping derived from
ANN, 10 soil classes names showed training error (MSE)
under

0.003, 98% training accuracy and
39 min
ute
s learning time.

The soi
l map resulted from using decision tree took much more time; more than 2 days to
learn soil and its envir
onment

over the landscape and landform variable and to
formalize

and
generalize

10 statements (formulas). Soil physical property maps w
ere

used in
the
ANN topology to
predict 32 soil data from sample areas to unsampled areas. For the validation of soil classes with
observed data, the results show very high accuracy
at

Order and Suborder levels, high accuracy in
Great

group and Subgroup levels and more th
an 90% matching when compared with decision
-
tree
-
derived map. For the validation of soil properties map, there
is

good accuracy of soil bulk density,
shear strength and plasticity index maps
, being

69
%
, 60
%

and 70%, respectively.
In summary, the
geopedolog
ical approach is quite valuable to obtain special soil information in inaccessible areas.
ANN as well as DT can help produce a high resolution map. The difference, however, is that ANN
is faster, thus more recommendable in term
s

of time and cost saving
.

Keyword
: geopedologic approach

to soil survey
, predictive soil map, digital soil map, artificial neural
network, decision tree, ANN, DT, landslide
, erosion
.

*
Ru
a
mporn Moonjun
: Master of Sc
i
ence in Geo
-
information Science and Earth Observation, Specializati
on:
Geohazards (Dep
artment

of Earth Surface System Analysis).

Moonjun, R.

2007
.

Application of artificial neural network and decision tree in a GIS
-
based predictive soil
mapping for landslide vulnerability study: a case study of Hoi Num Rin sub
-
watershed,

Thailand. Enschede,
ITC, 2007.

104 pp.

URL:
http://www.itc.nl/library/papers_2007/msc/aes/ruamporn.pdf

(full thesis)

Present address: Land Development Department, Phaholyothin Rd.
, Bangkok 10900, Thailand