You are on page 1of 15

LANSAS: a computer system for land suitability

assessment based on fuzzy neural networks

Luis Manuel Callejas Saenz 1


1
Instituto Tecnológico y de Estudios Superiores de Monterrey- Campus Hidalgo, Blvd.
Felipe Ángeles No. 2003 Col. Venta Prieta, Pachuca, Hidalgo, México

luis.manuel.callejas@itesm.mx

ABSTRACT.
This paper shows how an information system based on a fuzzy neural network
carry out a land suitability assessment. The process done by the information
system is base on an fuzzy logic algorithm in order to determine which can be
the most optimum crop or tree to grown in a given plot of land.
The information system is capable to assess around to 1711 different types of
crops or trees, using information about to climate (rainfall intensity,
temperature, sun radiation and humidity regime), Soil characteristics such as
depth, moisture, slope and other important soil characteristics.
The computer system was tested in field situations and it showed to be more
accurate than the current land evaluation methods and systems.

Keywords: Fuzzy Neural Network, Land Evaluation, Expert System, Decision


Support System.

Introduction

Current approaches to land evaluation are based on "crisp" or "hard" classification


systems for the ranges of values of a given land characteristic, and for the suitability
classes to which that land characteristic is allocated. In turn, suitability classes may be
seen as being discrete or "hard" too. This poses a double "crispness" problem whose
end result may be significant misallocation of suitability classes, particularly in the case
of the values of characteristics very near to the threshold of the range of values or class
limits.

The effects of crisp classification systems (whether in terms of threshold values of a


given land characteristic, or whether in terms of limits a suitability class) on land
suitability assessment results have not been thoroughly investigated yet. Moreover, vast
improvements could be made to any system by developing the option of relying on a
built-in, universally applicable knowledge base to allow inexperienced users access to
automated land suitability assessment procedures.
This research aims to determine the effect of the land qualities in land suitability
assessment [1] exercise using the theory of fuzzy logic and artificial neural networks
[2].

The approach proposed in this research differs from the current approaches of land
suitability assessment [3] by (1) translating the evaluation of land characteristics into a
fuzzy suitability class avoiding crisp suitability classes, (2) developing and applying a
fuzzy neural network in order to estimate crop yield productions, and (3) developing
digital knowledge bases with the climatic and soil requirements for 1711 different
types of crops and trees.

Land Suitability Assessment

The FAO Framework for Land Evaluation is based on a matching exercise between
specific land utilization type (LUT) requirements and the natural conditions of the land
(Figure 1).

Fig. 1 :Land Suitability Assessment

This approach uses a step-by-step procedure involving the following 6 major


operations:

1. Selection and definition of the LUT.


2. Identifying LUT requirements.
3. Definition and survey of Land Management Unit (LMU).
4. Selection of land characteristics.
5. Matching of the land characteristics with the LUT requirements (Figure 2).
6. Definition of a suitability classification.
Fig. 2 : Matching Process

Suitability Classes

Depending on the objectives of the evaluation, the suitability of an LMU evaluated for
a given LUT can be described by four levels of detail (Figure):

Suitability orders: All land is divided into two suitability orders, according to whether
the land is suitable or not for a given LUT:
‘S’ = suitable
‘N’ = not suitable.

Suitability classes: These are divisions of suitability orders that indicate the degree of
suitability. These can be thought of as modifiers of suitable vs. not suitable
‘S1’ = suitable
‘S2’ = moderately suitable
‘S3’ = marginally suitable
‘N1’ temporarily unsuitable
‘N2’ = unsuitable

The limits between S1 and S2, S2 and S3/N1 are arbitrary or based on single-factor
yield reductions.
Suitability subclasses: These are divisions of suitability classes that indicate not only
the degree of suitability (as in the suitability class) but also the nature of the limitations
that make the land less than completely suitable. Only suitability class S1 has no
subclasses. E.g. ‘S3e’: marginally suitable (‘S3’) because of erosion hazard (‘e’).
S3e-2
S management unit
order: 'suitable' 2
e
3
subclass
class: 'marginal'
'erosion hazard'

Fig. 3: Suitability classes

Application of fuzzy set theory in land suitability assessment

Huajun et al. (1991) [4] proved that their approach to land suitability assessment based
on fuzzy set theory is a potentially fruitful option for improving land evaluation results.
The authors showed that there is evidence that the fuzzy set approach yields more
accurate results in comparison to parametric and limitation methods.

But, when this research tested the Huajun's algorithm some errors and missed
specifications were found:

• Only one membership function is defined for all kind of land characteristics to
be evaluated.
• Only the suitability class S (suitable) is evaluated, and other three suitability
classes (S1 suitable, S2 moderately suitable, and S3 marginally suitable) are
not used.(see figure 4)
• Huajun’s research only applies to corn production, and his member function is
very generic in order to be applied to a wide number of different types of
crops.

Huanjun's 0; x ∈ ( −∞, α ) (1)



membership 2[( x − α ) /(γ − α )] ; x ∈ [α , β ]
S ( x; α , β , γ ) = 
2

function 1 − 2[( x − γ ) /(γ − α )] ; x ∈ [ β , γ ]


2

1; x = γ

Where: γ= the highest value of the land characteristic, there is the point where
membership is 1; β is an intermediate value and it can be found by β=(α+γ)/2, here
the membership value is 0.5; α is the lowest value of the membership function. x is the
value assessed on a given requirement

Table 1: Land Characteristic (LC) Types according to their effect on crop performance
Land Characteristic (LC) Types Crop performance pattern charts
according to their effect on crop
performance
Type 1: “Positive Effect”
These type of LC have a crop response
pattern, which corresponds to an increase 150
(not necessarily monotonic nor linear) to a 100
ar abi ca cof f ee
maximum of crop performance with banana
50
increases in the values of the LC followed, in bar l ey

most instances, by asymptotic behaviour 0 cashew


0 50 100 150
along the LC axis.
B a se sa t u r a t i o n ( %)

Type 2: “Ambivalent Effect”


This LC type is characterized by a “two-

crop performance
120
cassave
tailed” curve behaviour of crop performance 100
80 cotton

relative to the values of the LC. Typically, 60 groundnuts

an increase of performance with increases in 40


20
maize

the values of the LC followed by a 0


millets

maximum and a subsequent decrease in 0 100 200 300 400

LGP (days)
performance as the values of the LC
continue to increase.
Type 3: “Negative Effect”
These LC have typically a negative effect on
Crop Performance

150
arabica coffee
crop performance, which decreases with an 100 banana
increase in the values of the LC until cassave
50
reaching a minimum. cocoa
0
coconut
0 2 4 6 8
Dry season (months)

Fig. 4: Relationship between crisp suitability classes, Huajun suitability class (S) and Fuzzy suitability
classes

Crisp Suitability Classes

E
N S3 S2 S1
E
R
G 1
E
D
P
I S
H
S
R
E
B 0.5
M
E
M 0 S1

0
S2
0 25 50 75 100

PERFORMANCE (%)
S3

In order to improve on the simplistic model advanced by Huajun, three knowledge


bases with data about LUT requirements were developed and used to attempt to fit
Huajun’s membership function to describe the ranges of values of each of the land
characteristics in the knowledge bases generated.
The results of this exercise showed that the variations or ranges of values of most land
characteristics do not fit the membership function.

In fact, the values variation on most land characteristics, (i.e. requirements) do not
follow the shape of the membership function defined by Huajun. Thus the impact of
using such fuzzy function generically to any land characteristic could lead to large
interpretation errors.

Moreover, it was found that the relationship between each land characteristic and crop
performance is not generic either. Thus it is not the same for each land characteristic.
These relationships only changes on some particular crops.

Land characteristics on crop performance was determined after plotting the data
contained in the knowledge bases on land characteristics and their relationship with
crop performance.

The investigation of the nature of the patterns that were found graphically by plotting
Land Characteristics versus crop performance, lead to interesting results, which are
shown in Table 1.

After adopting some aspects of Huajun’s approach and using the knowledge bases
developed to determine and classify the LC into the three performance pattern types.

Such patterns of crop performance relative to the behaviour of land characteristics


allow for their groupings into different types, depending on their effect on crop
performance: Type 1: “positive effect; Type 2: “ambivalent effect”; and Type 3:
“negative effect”.

Another important contribution of this research is the definition of a number of Fuzzy


Membership Functions (FMF) for more than one suitability class, which overcomes
one of the major shortcomings of the work by Huajun defining only one suitability
class (“S”). So either, the crop or land utilization type could be with degree of
membership to the “suitable” class or completely unsuitable.

In this research the membership function to the class “suitable” is broken into
membership functions for suitability classes (S), and suitability classes S1, S2, and S3,
and a FMF for each of these suitability subclasses. In contrast, Huajun defined the
suitability class S as the whole universe of suitability possibilities of crop performance.

Since, Super class “S” contain the three basic suitability classes (Figure 4), each one of
these suitability classes should have a different LC pattern type and its own FMF.

The suitability classes (S1, S2, and S3) have their corresponding FMF, which are
inferred from the generic membership function defined by Huajun.

Following a set of rules starting from the generic function, the rest of the FMF, one for
each suitability subclass, can be generated. Figure 4 illustrates in graphical form the
nature of the functions generated. The generic suitability function (S) of Huajun is
represented stretching from a point of maximum performance γ (100%) and FMF = 1,
to a point of minimum performance α with a FMF= 0.

Thus the rules are as follows:


Subclass “S1”: γ = maximum performance (100%) where FMF = 1, and α represents
the minimum performance of the subclass (50%), which corresponds to the mean
performance reached in suitability class “S2”.
Subclass“S2”: has two minima (FMF = 0): one of them coincides with γ (maximum
performance) and the other with γ3 (mean performance in “S3”), and γ2 is the point
where FMF= 1.
Subclass “S3”: has two minima (FMF = 0), and they are represented by α (minimum
performance) and γ2 (mean performance in “S2”). The maximum is achieved at γ3
where FMF = 1. In order to calculate γ2 and γ3, the crisp boundaries for “S3” and “S2”
must be determined using the following expression:

Top point function Η = (m + M ) / 2 (2)

Where: H is the γ value calculated from a suitability class, m and M are the minimum and maximum
values in the interval of the crisp class. Crisp classes can be retrieved form the knowledge bases.

• From above premises, three new membership functions can be inferred as


follows:

FMF for Class S1 0; x ∈ (−∞, γ 2)



2[(x −γ 2) /(γ − γ 2)] ; x ∈[γ 2, β )
2

f1 ( x; γ 2, β , γ ) =  (3)
1 − 2[(x − γ ) /(γ − γ 2)]2
; x ∈[β , γ )
1; x ∈[γ , ∞)

FMF for Class S2 0; x ∈ (−∞, γ 3)orx ∈ (γ , ∞)

2[( x − γ 3) /(γ − γ 3)] ; x ∈ [γ 31 , β 1 )
2

2[( x − γ ) /(γ − γ 2)] ; x ∈ ( β 2 , γ ]


2

f 2 ( x; γ 2, γ 3, β 1 , β 2 , γ ) =  (4)
1 − 2[( x − γ 2) /(γ − γ 3)] ; x ∈ [ β 1 , γ 2)
2

1 − 2[( x − γ ) /(γ − γ 3)] 2 ; x ∈ (γ , γ 3]



1; x = γ 2
FMF for Class S3 0; x ∈ (−∞, α )orx ∈ (γ 2, ∞)

2[( x − α ) /(α − γ 3)] ; x ∈ [α , β1 )
2

2[( x − γ 2) /(γ 3 − γ 2)]2 ; x ∈ (β , γ 2]


f 3 ( x; γ 2, γ 3, β1 , β 2 , α ) =  2
(5)
1 − 2[( x − γ 3) /(α − γ 3)] ; x ∈ [ β1 , γ 3)
2

1 − 2[( x − γ 3) /(γ 2 − γ 3)]2 ; x ∈ (β , γ 2]


 2

1; x = γ 3

When the Fuzzy Membership Functions (FMF) for S1, S2 and S3 are combined with the
three different types of land characteristics (Type 1, Type 2 and Type 3) allowed for
deriving nine new membership functions. These membership functions (one for each
type of land characteristics) are resulting from the combinations of membership
functions and LC types.
0; x ∈ (−∞, γ 2 ) (6)

2[(x − γ 2 ) /(γ − γ 2 )] ; x ∈[γ 2 , β )
2

f1 ( x; γ 2 , β , γ ) = 
1− 2[(x − γ ) /(γ − γ 2 )] ; x ∈[β , γ )
2

1; x ∈[γ , ∞)

0; x ∈ (−∞, γ 3 ) ∨ x ∈ (γ , ∞) (7)



2[( x − γ 3 ) /(γ 2 − γ 2 )] ; x ∈ [γ 3 , β 1 )
2

2[( x − γ ) /(γ − γ )] 2 ; x ∈ ( β , γ ]

f 2 ( x; γ , γ 2 , γ 3 β 1 , β 2 ) =  2 2

1 − 2[( x − γ 2 ) /(γ 2 − γ 3 )] ; x ∈ [ β 1 , γ 2 )
2

1 − 2[( x − γ ) /(γ − γ )] 2 ; x ∈ (γ , β ]
 2 2 2 2

1; x = γ 2

0; x ∈ (−∞,0) ∨ x ∈ (γ 2 , ∞) (8)



2[( x − 0) /(γ 2 − 0)] ; x ∈ [0, β 1 )
2

2[( x − γ ) /(γ − γ )]2 ; x ∈ ( β , γ ]



f 3 ( x; γ 2 , γ 3 β 1 , β 2 ) = 
2 3 2 2 2

1 − 2[( x − γ 3 ) /(0 − γ 3 )] ; x ∈ [ β 1 , γ 3 )
2

1 − 2[( x − γ ) /(γ − γ )]2 ; x ∈ (γ , β ]


 3 3 2 3 2

1; x = γ 3

0; x ∈ (−∞, γ ' ) ∨ x ∈ (γ 2' , ∞) (9)



2[(x − γ 2 ) /(γ − γ 2 )] ; x ∈[γ 2 , β1 )
2

2[(x − γ 2' ) /(γ − γ 2' )] ; x ∈ ( β 2 , γ 2' ]


2

f 4 ( x; γ 2 , γ 2' , β1 , β 2 , γ ) = 
1 − 2[(x − γ ) /(γ − γ 2 )] ; x ∈[ β1 , γ )
2

1 − 2[(x − γ ) /(γ − γ )]2 ; x ∈ (γ , β ]


 2' 2

1; x = γ

0; x = γ ∨ x ∈ (−∞, γ 3 ) ∨ x ∈ (γ 3' , ∞) (10)



2[( x − γ 3 ) /(γ 2 − γ 3 )] ; x ∈ [γ 3 , β1 )
2

1 − 2[( x − γ ) /(γ − γ )]2 ; x ∈ [ β , γ )


 3 2 3 1 2

1; x = γ 2 ∨ x = γ 2 '

1 − 2[( x − γ 2 ) /(γ 2 − γ )] ; x ∈ (γ 2 , β 2 ]
2

f5 ( x; γ , γ 3 , γ 3' , β1 , β 2 , β 3 , β 4 , γ 2 , γ 2 ' ) = 2[( x − γ ) /(γ − γ )]2 ; x ∈ ( β , γ ]


 2 2

2[( x − γ 2' ) /(γ 2' − γ )]2 ; x ∈ [γ 2' , β 3 )



1 − 2[( x − γ 2' ) /(γ 2' − γ )] ; x ∈ [ β 3 , γ 2 ' )
2

1 − 2[( x − γ ) /(γ − γ )]2 ; x ∈ (γ , β ]


 2' 2' 3' 2' 4

2[( x − γ 3' ) /(γ 2' − γ 3' )]2 ; x ∈ ( β 4 , γ 3' ]




0; x = α1 (11)

2[(x − α1 ) /(γ 2 − α1 )] ; x ∈(α1 , β 2 )
2


2[(x − α1 ) /(γ 1 − α1 )] ; x ∈(β1 ,α1 )
2

f 6 (x;α1 , β1 , β 2 , γ 1 , γ 2 ) = 
1 − 2[(x − γ 1 ) /(γ 1 − α1 )] ; x ∈(γ 1 , β1 ]
2

1 − 2[(x − γ ) /(γ − α )]2 ; x ∈[β , γ )


 2 2 1 2 2

1; x ∈(−∞, γ 1 ] ∨ x ∈(γ 2 , ∞)


1; x ∈(−∞,γ ) (12)

2[(x − α1) /(γ − α1)] ; x ∈[α1, β1)
2

f7 (x;α1, β1,γ ) = 
1 − 2[(x − γ ) /(γ − α1)] ; x ∈[β1,γ )
2

0; x ∈(α , ∞)
 1

0; x∈(−∞,α1) ∨ x∈(α2 , ∞) (13)



2[(x −α1 ) /(γ −α1 )] ; x∈[α1, β1 )
2

2[(x −α ) /(γ −α )]2 ; x∈(β ,α ]



f8 (x;α1,α2 , β1, β2 ,γ ) =  2 2 2 2

1− 2[(x −γ ) /(γ −α1 )] ; x∈[β1,γ )


2

1− 2[(x −γ ) /(γ −α )]2 ; x∈(γ , β ]


 2 2

1; x =γ

0; x∈(−∞,α1) (14)



2[(x −α1) /(γ −α1)] ; x∈[α1, β1]
2

f9 (x;α1, β1,γ ) =
1−2[(x −γ ) /(γ −α1)] ; x∈[β1,γ )
2

1; x∈[γ,∞)

The definition of the nine membership functions, as introduced above, shows how the
effect of the range of values of land characteristics on crop performance, can be
accounted for through Fuzzy Set Theory. It also shows how land characteristics can be
reclassified and grouped in patterns or types. These two findings are important
contributions from this research to the field of land suitability assessment and
automated land evaluation systems in natural resources management.

It must be noted that for each land characteristic the critical values ( i i i) of the
nine membership functions derived above, are usually difficult to determine by
traditional methods of analysis. An important feature of these functions is that such
critical values ( i i i) are selected here based on expert knowledge and experience
about the ranges and critical values for the different suitability classes. As it has been
shown in these results, the nine (9) different membership functions are directly related
to the type of land characteristic and are the direct result too of investigations into
global knowledge bases. Particularly, on how a most generic membership function
described the behaviour of the three different land characteristics types (types 1, 2 and
3) on the membership functions to three different land suitability classes (S1, S2, S3).

Algorithm for land suitability assessment based on Fuzzy Set Theory

Having explored and analyzed some important membership functions of suitability


classes with the knowledge available, starting from the approach used by Huajun, the
algorithm for the land suitability classification based on fuzzy set theory can be defined
by the following sequence of steps:
• For a given type of land characteristic (type 1, 2, or 3) and for each of the
suitable classes (S1, S2 and S3) the membership functions established (S11,
S21, S31, S12, S22, S32, S13, S23, S33) express the degree of belonging to a
suitability class (S1, S2, S3) for a given value of the land characteristic
assessed. Note that the suitability class N, has been left out, because the
degree of membership for this class is zero in the whole set of possible values
that can be given for each one of the three different suitability classes. If a
value of a land characteristic does entirely belong or absolutely not belong to
the considered class, the membership value is 1 or 0 respectively.
• If the value of land characteristic belongs to some extent to the considered
class, an intermediate membership value is determined, which results from a
membership function whose shape is proportional to the degree of
"belonging" to such class.
• Thus, the evaluation of a land characteristic consists of the determination of
the degree of membership of the characteristic to each of the suitability classes
by using the membership function. The result of this evaluation for all land
characteristics and for a given LUT, is a matrix of membership values of land
characteristics for the considered suitability classes in which the land unit in
turn can be allocated in its suitability for a given LUT. Such matrix (Mij) has
the membership values arranged in the following sequence: the element mij of
Mij denotes the membership values for the ith land characteristic under jth
suitability class (i=1,2,3,n; j=S1, S2, S3).
• The degree of importance of land characteristics on crop performance and land
suitability can be expressed by a weight factor. The weight values for all
considered land characteristics forms a matrix of weights (Wi). The weight
factor for a given land characteristic can be defined by the user, and this factor
must have values between 1 and 0. In this fashion, the approach allows for the
user to enter his/her knowledge about the importance or significance of any
land characteristic related to land performance.
• The final suitability is obtained by multiplying the matrices Mij and Wi and
storing the result in a matrix called “S”. The elements of matrix S express the
degree of membership of the land management unit being evaluated to the any
of the suitability classes S1 to N.

The findings about the Fuzzy Membership Functions, the typification of land
characteristics (LC) and the procedures for the computation of fuzzy suitability classes
described in the sequence of steps above were all incorporated into the architecture of
an automated fuzzy neural network system for land suitability assessment. The
development of such a system is the central contribution of this research.
Land suitability assessment using a fuzzy neural network

Neural network characteristics have been found useful in a variety of applications, but
its application in agriculture has been limited, the few existing applications fall into
five groups:

• Pattern recognition, classification, and grading: Liao et al. [5] developed a


back propagation network as a shape classifier for corn kernels. A back
propagation network has been used also with a colour computer vision system
for segmentation of images to evaluate quality [6].
• Sensory evaluation and quality control: The performance of neural
networks and statistical regression techniques for modelling sensory colour
quality of tomato and peaches, this was compared by Thai and Shewfelt [7].
Two neural network architectures (back propagation and recurrent) are
compared with a Bayesian classifier for classification of cantaloupe based on
different quality parameters by Ozer and Engel [8].
• Prediction and process control: Neural networks with back propagation
architecture also have been implemented for predicting crop yield [9].
• Modelling and optimization: Applications of neural network techniques have
been further extended to optimal control and irrigation management [9].
• Remote sensing and terrain classification: Easson and Barr [10] developed
an integration of GIS and artificial neural network for natural resources.
Decatur [11] investigated the applicability of a back propagation network for
the classification of terrain from radar images.

This project based on the goodness of the neural networks and in order to apply the
algorithm defined, attempted to design of a fuzzy neural network, which can carry out
land suitability assessment using the algorithm described in this work. And applying it
to evaluate land utilization types on rain fed agriculture. The neural fuzzy network
(FNN) proposed is a network with a typical feed-forward multi-layer perceptron (see
figure 5).

Fig. 5: Fuzzy Neural Network for Land Suitability Assessment


The FNN executed a “once-off” procedure in order to calculate the weights
(knowledge) for each land characteristic involved in each of the crops or LUT
evaluated. This process is performed only once because the calculated weights are
stored in the knowledge base and can be retrieved and used in future evaluations.

The weights are calculated by the back propagation algorithm, which is commonly
used among the current types of ANN systems available.

A back propagation ANN learns from a set of input values to a set of output values and
its name comes from the fact that the error of hidden layer or units are derived from
propagating backward the errors associated with the output units since the target values
for the hidden units are not given.
The ANN calculated the weights using the data from Sys (1983), and “trained” it with a
cycle of 10000 epoch or calculations for each crop. Later, the ANN was tested with
some standard values from Sys research in order to determine the range of expected
errors from using the weights.

The accuracy of predictions of the neural network was calculated using a cost function.
The cost function calculates the deviation in predictions, which results from the
difference between the network output and the desired behaviour.

Fig. 6: Active cost graph for 10000 epoch

Land suitability assessment system (lansas)

The development of a system based on the approach proposed in this research was
undertaken.

The computer system developed was named as “LANSAS” from the acronym of
LANd Suitability Assessment System. LANSAS is a computer system based on a
fuzzy artificial neural network approach and based on the framework defined by [13],
and it has the capability to carry out land suitability assessments using a recursive and
parallel method allowing users to access three different knowledge bases.
These knowledge bases provide information regarding to LUT requirements for a wide
variety of crops (mostly for rain fed agriculture). Additionally, LANSAS is designed as
to use geographic information from standard GIS software (raster and vector). The
capability of LANSAS to import-export data from standard relational database
management systems, are also part of the design.

Fig. 7: LANSAS knowledge acquisition procedure

Results

The new paradigm was tested using climatic and soil data from a watershed in centre of
Mexico, the test was based on an evaluation of estimated crop yield production made
by each of the current land suitability assessment methods such as parametric and
limitation method and the current computer approach called ALES [14] and the new
approach (LANSAS).

The results shown new paradigm is more accurate than current methods (see table 2).

Table 2: Observed error percent for corn yield prediction

site ep LANSASep Parametricep Limitation ep ALES


TX3 0.0625 0.30375 0.0234375 0.578125
TX3 0.00990099 0.264686469 0.031353135 0.554455446
IX1 0.1 0.365 1.53125 0.4375
IX1 0.00677201 0.232505643 1.285553047 0.492099323
TN3 0.18857143 0.303428571 0.228571429 0.228571429
TN3 0.1125 0.238125 0.15625 0.15625
TN4 0.35084428 0.639774859 1.532833021 0.155722326
TN4 0.1 0.0925 0.6875 0.4375
Average0.11638609 0.304971318 0.684593516 0.38002794

The weights calculated define an average value estimated for each land characteristic in
order to use those in future evaluations as universal knowledge.
Table 3: Impact weights of land characteristics for rain-fed agriculture

Land Characteristic Average Weight


Precipitation 0.4089
Length Growing Season 0.7401
Temperature 1
Humidity 0.7986
Slope 0.6999
Coarse Fragments 0.3279
Soil Depth 1
CaCO3 0.3243
Gypsum 0.6445
Cation Exchange Capacity (CEC) 0.2278
Base Saturation 0.0356
Organic Matter 0.899
pH 0.09

Agronomically speaking, the calculated weights indicate that soil depth, air
temperature, the soil organic matter, air humidity and the length of the growing season
are the determining factors, in that order, for most crops under rain-fed agriculture in
the Texcoco River watershed.

These findings do not contradict empirical evidence of observations and information


from the field, except perhaps on the role of soil moisture through the Length of
Growing Season, which would be expected to play a more determinant role.

References

[1] [FAO, 1983]. FAO; Guidelines: Land evaluation for rain fed agriculture; FAO Soils
bulletin 52, FAO, Rome, 1983.
[2] [Fu, 1994] Fu, LiMin; neural networks in computer intelligence; McGraw Hill, 1994.
[3] [Sys, 1985] Sys, Ir C.; Land Evaluation; State University of Ghent; Ghent, 1985.
[4] [Huajun, 1991] Huajun, Tang; Debaveye, J.; Da, Ruan; Van Ranst, E.; Land suitability
classification based on fuzzy set theory; Pedologie XLI-3 pp 277 - 290, 1991.
[5] [Liao et al., 1992] Liao, K., M.R. Paulsen, J.F. Reid, B. Ni, and E. Bonifacio; Corn Kernel
shape identification by machine vision using neural network classifier; ASAE paper No. 927017,
St. Joseph, Michigan, 1992.
[6] [Zhuang et al., 1992] Zhuang, X., A. Heztroni, and C.J. Precetti; Neuro-segmentation of
colour images in quality evaluation of pork images; ASAE paper No. 92-3595, St. Joseph,
Michigan, 1992.
[7] [Thai and Shewfelt, 1991] Thai, C.N., and R.L. Shewfelt; Modelling sensory colour quality
of tomato and peach: Neural networks and statistical regression; Transactions of the ASAE
34(3): 950-954, St. Joseph, Michigan, 1991.
[8] [Ozer and Engel, 1994] Ozer, N., B.A. Engel; An adaptative technique for mutisensor
fusion and classification of fruit; ASEA paper No. 946025, St. Joseph, Michigan, 1994.
[9] [Panigrahi, 1998] Panigrahi, Suranjan; Neuro-Fuzzy Systems: applications and potential in
biology and agriculture; Dept. of agricultural and biosystems engineering, North Dakota State
University, USA, 1998.
[10] [Easson and Barr, 1996] Easson, Gregory L.; Barr, David J.; Integration of GIS and
artificial neural networks for natural resource applications;
www.esri.com/userconf/proc96/TO150/PAP126/P126.html
[11] [Decatur, 1992] Decatur, S.E.; Application of neural networks to terrain classification;
Hughes Company, P.O. box 3310, Fulenton, California, 1992.
[12] [Callejas, 2002] Callejas Saenz, Luis Manuel; A computer system for land suitability
assessment based on fuzzy neural network; Trent University, Canada; 2002.
[13] [Callejas, 1999] Callejas Saenz, Luis Manuel; Ponce Hernandez, Raul; An approach to
develop a spatial decision support system for natural resources; Memorias del 2do. Encuentro
Internacional de Computo, Sociedad Mexicana de Ciencias Computacionales, México, 1999.
[Rossiter, 1986] Rossiter, D; ALES, an automated land evaluation system. Cornell University,
Ithaca, N.Y. 1986

You might also like