See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/358020581

Fuzzy Expert system for the Impact of Climate Change in Indian Agriculture

Article in International Journal of Pure and Applied Mathematics · January 2018

CITATION READS

1 225

4 authors, including:

Karthik Subramani Saroj KUMAR Dash

Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Che… Vellore Institute of Technology University
10 PUBLICATIONS 24 CITATIONS 8 PUBLICATIONS 30 CITATIONS

SEE PROFILE SEE PROFILE

Felix Augustin
Vellore Institute of Technology University
80 PUBLICATIONS 483 CITATIONS

SEE PROFILE

All content following this page was uploaded by Karthik Subramani on 22 January 2022.

The user has requested enhancement of the downloaded file.

International Journal of Pure and Applied Mathematics
Volume 118 No. 5 2018, 455-473
ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version)
url: http://www.ijpam.eu
Special Issue
ijpam.eu

Fuzzy Expert system for the Impact of Climate Change in

Indian Agriculture
S. Karthika, N. Punithavelanb,*, Saroj Kumar Dasha, A. Felixa
a
Mathematics Division, School of Advanced Sciences, VIT Chennai, India
b
Physics Division, School of Advanced Sciences, VIT Chennai, India
*
Corresponding author. E.mail: [email protected]
Abstract: Fuzzy Expert system is potent tool to mimic the human way of thinking and solve the
problem when there is full uncertainty in it. The goal of this paper is to frame the fuzzy expert
system to examine the impact of climate change in the Indian Agriculture. Agriculture is the
basis of Indian economy and agriculture is utterly relying on the environment. If there is any
undesirable change in the environment, it leads to a lot of unpleasant impact on the agriculture.
Climate change can easily interrupt the food availability and affect the food quality.
Keywords: Linguistic variable, Fuzzy Number, Fuzzy Expert system, Climate Change,
Agriculture.

1. Introduction:

Expert System is the division of applied artificial intelligence, it is well used to take an expert
view in the absence of a human expertise [18]. Due to the absence of expert in a particular field,
FES will solve the real world complex problem (Zadeh, 1965) [19]. It was first introduced by
Kandel (Kandel, 1992) [9]. It is an intelligent tool and capable of making decisions and dealing
with ambiguous data. FES improved the excellence, effectiveness and quality in recent years.
FES has been applied in many real world problems such as medical diagnosis, agricultural
problem to deal the vagueness by mimic the human way of thinking [18]. In 1998, Hayo M.G.
et.al, proposed a fuzzy expert system to compute an indicator of “Ipest” which reflects an expert
perception of the potential environmental impact by applying pesticides in the field [7]. In 2000,
Roussel, O et.al has revealed very large differences with respect to overall effect of pesticide
within each of the three crops and its environmental conditions [12]. In 2006, Duque et.al
constructed a fuzzy inference system (FIS) to assess water quality index with the fuzzy reasoning
[5]. In 2009, Reshmidevi, et.al, presented a GIS-integrated fuzzy rule-based inference system to
assess the land suitability for agrarian watersheds by incorporating both land potential and
surface water potential [11].

In 2010, Guillaume, S and Charnomordic, B presented fuzzy inference system profession

(FisPro), which is illustrated through three real world applications. FisPro is constructed to
respond precisely the needs of interpretable FIS and learning [6]. Rajaram,T., Das, A proposed a
fuzzy rule based model for the interactions of sustainability components in an agro-ecosystem
for the typical agricultural village in southern India [10]. In 2012, Amindoust et.al, reviewed to
decide the sustainable supplier selection indicators. Then, they have suggested a new ranking
method for FIS [1]. Sattler, C presented to depict a modeling approach for the ex-ante evaluation
of farming practices with regard to their hazard for several single-species biodiversity indicators
(Sattler, 2012) [14]. Yelapure, and Kulkarni explained the need of expert system in agriculture
and review of various expert systems in agriculture (Yelapure, 2012) [17]. In 2013, Dubey, S

455
International Journal of Pure and Applied Mathematics Special Issue

et.al., presented a review of various fuzzy expert systems in agriculture over the last two decades
[4].

In 2014, Djatkov, D., et.al, developed a fuzzy expert system for evaluating and improving the
efficiency of agricultural biogas plants in more consistent and systematic manner [3]. Sami, M
et.al., constructed fuzzy inference system, considered to be the suitable, uncomplicated and
effective tool for the Environmental comprehensive evaluation of agrarian frameworks at the
farm level (Sami, 2014) [13]. Tagarakis, A et.al aimed to the present study to develop and
validate a fuzzy expert system to categorize grape quality based on selected grape features and to
produce a total grape quality map and confirm its spatial significance by comparing with soil and
yields (Tagarakis, 2014) [16]. In 2015, Cavallaro, F proposed a synthetic index based on a fuzzy
inference system to evaluate the sustainability of production and use of crops devoted for energy
purposes (Cavallaro, 2015) [2]. Jasutkar and Khan, presented a paper to review of fuzzy
inference system is used worldwide for impact assessment of environment (Jasutkar, 2015) [8].
In 2016, Semeraro, T et.al constructed a model by integrating the multi-criteria analysis and
Fuzzy Expert System (FES) for GIS environment in order to recognize and map potential
“hotspots” of fire vulnerability, where fire security measures can be undertaken in advance [15].
From this review, it is perceived that a fuzzy expert system may be designed for the impact of
climate change in the Indian agriculture because Agriculture is the basis of Indian economy and
agriculture is utterly relying on the environment. If there is any undesirable change in the
environment, it leads to a lot of unpleasant impact on the agriculture.

2. Theoretical Background

Definition 2.1 A fuzzy set A is a subset of a universe of discourse X, which is characterized by a

membership function  A ( x) representing a mapping  A : X   0,1 . The function value of  A ( x) is
called the membership value, which represents the degree of truth that x is an element of fuzzy
set A .

Definition 2.2 A fuzzy set A defined on the set of real numbers R is said to be a fuzzy number
and its membership function A : R  [0,1] has the following characteristics,

(i) A is convex.
 A   x1  (1   ) x2   min(  A ( x1 ),  A ( x2 )), x   x1 , x2  ,   0,1.
(ii) A is normal if max  A ( x)  1 .
(iii) A is piecewise continuous.

Definition 2.3 The α-cut of the fuzzy set A of the universe of discourse X is defined as
A  {x  X /  A ( x)   } , where    0,1 .

Definition 2.4 A triangular fuzzy number N can be defined as a triplet (l, m, r) and the
membership function N ( x) is defined as:

456
International Journal of Pure and Applied Mathematics Special Issue

 0 xl

  x  l  l  x  m
 m  l 
 N ( x)  
 r  x  m  x  r
 x  m 

 0 xr
Where l, m, r are real numbers and l  m  r.

A(x)
1

0 x
l m r

Figure-1: Triangular Fuzzy Number

Definition 2.5 A trapezoidal fuzzy number A can be defined as (a1 , a2, , a3 , a4 ) and the
membership function is defined as

 x  a1 
  a1  x  a2
 a2  a1 
 1 a2  x  a3
 A ( x)  
 a3  x  a3  x  a4
 a  a 
  4 3 

 0 a1  0 & a4  0

Where a1 , a2 , a3 , a4 are real numbers a1  a2  a3  a4 .

Figure 2: Trapezoidal Fuzzy Number

457
International Journal of Pure and Applied Mathematics Special Issue

3. Problem Description:
Agriculture is an important sector of the Indian economy. If there is any undesirable change
in the environment, it leads to a lot of unpleasant impact on the agriculture. Climate change can
easily interrupt the availability and the quality of the food. For instance, increases in global
temperatures, alter extreme weather events and reductions in water availability may all lead in
to less agricultural yield. Increasing temperatures can contribute to wastage of things and
contamination as well. The followings are major issues faced by Indian agriculture, rise in
temperature, weather disasters, freshwater availability, monsoon level, species extinction,
spread of new diseases and deforestation. Therefore, this present study aims to construct the
expert system for analyzing the impact of climate change in the Indian agriculture.
In this system, we have seven input variables such as Rise in Temperature, Weather Disasters,
Fresh Water Availability, Monsoon Level, Species Extinction, Spread of New Diseases,
Deforestation, and one output Agriculture Productivity, which are classified and provided a the
suitable membership function using triangular and trapezoidal fuzzy number.
A1-Rise in Temperature (oC):
Temperatures are certain to go up further. Average surface temperature is increasing due to
emission of greenhouse gases in the atmosphere. Temperature is one of the vital variables
influencing crop production.
We have divided Rise in Temperature into five fuzzy sets as follows:

Very Low (VL) ≤ 20

Low (L) 15 to 25
Medium (M) 22 to 30
High (H) 28 to 40
Very High (VH) ≥ 35

Table 1: Classification of Age Rise in Temperature

The suitable membership functions of the above classifications are given below:

x0 
 1,  0, x  15 and x  25
 20  x 

VL  x    , 0 < x  20  x  15
L  x    , 15 < x  20
 20  5

 0, x  20  25  x
,  5 , 20 < x  25

458
International Journal of Pure and Applied Mathematics Special Issue


  0, x  28 and x  40
 0, x  22 and x  30 
  x  28
 x  22 H  x    , 28 < x  35
M  x    , 22 < x  26
 4  7
 30  x  40  x
 4 , 26 < x  30  5 , 35 < x  40
,

0, x  35
 x  35

VH  x    , 35< x  60
 25

1, x  60

Figure 3: Classification of Age Rise in Temperature

A2-Weather Disasters (%):

Agricultural impacts on natural events and disasters includes such as Flood, Drought,
Earthquakes, Windstorms Destruction. Floods create land as vulnerable for agricultural
production until waters move away, where as hurricanes washout arable land or permanently
increase its salinity through storm surges and flash floods. Drought impacts on crops growth and
development of soil moisture, root growth, shoot growth.
We have divided Weather Disasters into five fuzzy sets as follows:

Very Low (VL) ≤ 20

Low (L) 15 to 30
Medium (M) 25 to 40
High (H) 35 to 60
Very High (VH) ≥ 50
Table 2: Classification of Weather Disasters (%)
The suitable membership functions of the above classifications are given below:

459
International Journal of Pure and Applied Mathematics Special Issue

  0, x  15 and x  30
 0, x < 0 and x  20  x  15
  , 15 < x  20
VL  x    1, 0 x5  5
L  x   
 20  x  1, 20  x  23
 , 5 < x  20  30  x
 15 ,  , 23 < x  30
 7

 0, x  25 and x  40  0, x  35 and x  60
 x  25  x  35
 , 25 < x  30  , 35 < x  42
 
M  x    5 H  x    7
 1, 30  x  33  1, 42  x  50
 40  x  60  x
 , 33 < x  40  , 50 < x  60
 7 ,  10

 0, x  50
 x  50

VH  x    , 50 < x  60
 10
 1, x  60

Figure 4: Classification of Weather Disasters (%)

A3-Fresh Water Availability (%)
India is facing a decrease in available water resources that has implications on India’s agriculture
sector. India’s total water supply totally depends on groundwater resources, which is also a cause
of anxiety.

460
International Journal of Pure and Applied Mathematics Special Issue

We have divided Fresh Water Availability into five fuzzy sets as follows:

Very Low (VL) ≤ 2.5

Low (L) 1 to 4
Medium (M) 3 to 5
High (H) 4.5 to 7
Very High (VH) ≥ 6.5

Table 3: classification of Fresh Water Availability (%)

The suitable membership functions of the above classifications are given below,

 1, x0  0, x  1 and x  4
 2.5  x 
  x 1
VL  x    , 0  x  2.5 L  x    , 1< x  2.5
 2.5  1.5
 0, x  2.5 4  x
,  1.5 , 2.5 < x  4

 0, x  4.5 and x  7
 0, x  3 and x  5  x  4.5
 
M  x    x  3, 3< x  4 H  x    , 4.5< x  6
5  x, 4<x5  1.5
 ,  7  x,
 6<x7
 0, x  6.5
 x  6.5

VH  x    , 6.5< x  10
 3.5
 1, x  10

Figure 5: Classification of Fresh Water Availability (%)

A4-Monsoon Level (mm)

461
International Journal of Pure and Applied Mathematics Special Issue

An increase (decrease) in rainfall is generally associated with an increase (decrease) in

agriculture production. Monsoon rains continue to be important in determining the levels of
agricultural output in India.
We have divided Monsoon Level into five fuzzy sets as follows:

Very Low (VL) ≤ 200

Low (L) 100 to 650
Medium (M) 500 to 1200
High (H) 900 to 2200
Very High (VH) ≥ 1800
Table 4: Classification of Monsoon Level (mm)
The suitable membership functions of the above classifications are given below,
 0, x  100 and x  650
  x  100
 0, x  0 and x  200  , 100 < x  200


VL  x    1, 0  x  100 ,  L  x    100
 1, 200  x  400
 200  x
 , 100 < x  200  650  x
 100  , 400 < x  650
 150

 0, x  500 and x  1200  0, x  900 and x  2200

 x  500  x  900
 , 500 < x  600  , 900 < x  1400
 100 
M  x     H  x    500
 1, 600  x  900  1, 1400  x  1700
1200  x  2200  x
 , 900 < x  1200  , 1700 < x  2200
 300 ,  500

 0, x  1800
 x  1800

VH  x    , 1800 < x  2100
 300

 1, x  2100

462
International Journal of Pure and Applied Mathematics Special Issue

Figure 6: Classification of Monsoon Level (mm)

A5-Species Extinction (%)

By using the pesticides and toxic fertilizers, agriculture affects our ecosystems through the
reduction of certain species of plants and animals. Use of pesticides, chemical fertilizers, energy
supplements, and grazing are other factors for species extinction.

We have divided Species Extinction into five fuzzy sets as follows:

Very Low (VL) ≤ 1.4
Low (L) 1 to 3.8
Medium (M) 3 to 5.2
High (H) 4.5 to 7.6
Very High (VH) ≥6
Table 5: Classification of Species Extinction (%)
The suitable membership functions of the above classifications are given below,

 1, x0  0,
1.4  x x  1 and x  3.8
 
VL  x    , 0 < x  1.4  L  x    x  1, 1< x  2
 1.4  3.8  x
 0, x  1.4  , 2< x  3.8
,  1.8
 
 0, x  3 and x  5.2  0, x  4.5 and x  7.6
 
M  x    x  3, 3< x  4  H  x    x  4.5, 4.5< x  5.5
 5.2  x  7.6  x
 , 4< x  5.2  , 5.5< x  7.6
 1.2 ,  2.1
 0, x6
x6

VH  x    , 6< x  8
 2
 1, x8

463
International Journal of Pure and Applied Mathematics Special Issue

Figure 7: Classification of Species Extinction (%)

A6-Spread of New Diseases (%)
Diseases have a harmful effect on crops and impact on market access and agricultural
production. Diseases incorporate small scale creatures, ailment specialists, infectious agents,
parasites and hereditary issues.
We have divided Spread of Diseases into five fuzzy sets as follows:
Very Low (VL) ≤ 10
Low (L) 5 to 20
Medium (M) 15 to 25
High (H) 20 to 30
Very High (VH) ≥ 25

Table 6 : Classification of Spread of New Diseases (%)

The suitable membership functions of the above classifications are given below,

 1, x0  0, x  5 and x  20
10  x 
  x 5
VL  x    , 0< x  10 L  x    , 5< x  13
 8
 10
 0, x  10  20  x
,  7 , 13< x  20

 
 0, x  15 and x  25  0, x  20 and x  30
 
 x  15  x  20
M  x    , 15< x  20 H  x    , 20< x  25
 5  5
 25  x  30  x
 5 , 20< x  25  5 , 25< x  30
,

464
International Journal of Pure and Applied Mathematics Special Issue

 0, x  25
 x  25

VH  x    , 25< x  35
 10

 1, x  35

Figure 8: Classification of Spread of New Diseases (%)

A7-Deforestation (%)
Deforestation is the destruction of forest into industrial areas. Loss of biodiversity occurs due to
deforestation. Deforestation is one of the reasons for global warming. It will also reduce the
agriculture productivity.
We have divided Deforestation into five fuzzy sets as follows:

Very Low (VL) ≤ 0.2

Low (L) 0.1 to 0.6
Medium (M) 0.5 to 1
High (H) 0.8 to 1.3
Very High (VH) ≥ 1.2
Table 7: Classification of Deforestation (%)

The suitable membership functions of the above classifications are given below,


 1, x0  0, x  0.1 and x  0.6
 0.2  x 
  x  0.1
VL  x    , 0< x  0.2 L  x    , 0.1< x  0.4
 0.2  0.3

 0, x  0.2  0.6  x
,  0.2 , 0.4  x  0.6

465
International Journal of Pure and Applied Mathematics Special Issue


 0, 
x  0.5 and x  1  0, x  0.8 and x  1.3
 
 x  0.5
M  x    , 0.5< x  0.7  x  0.8
H  x    , 0.8< x  1
 0.2  0.2
 1 x  1.3  x
 0.3 , 0.7  x  1  0.3 , 1  x  1.3
,

 0, x  1.2
 x  1.2

VH  x    , 1.2< x  1.5
 0.3
 1, x  1.5

Table 9: Classification of Deforestation (%)

Output Variable
R1-Agriculture Productivity
The productivity of Agricultural is measured as the ratio of agricultural outputs to agricultural
inputs. Agriculture production plays most important role in Indian economy and it must be
increased.
We have divided Agriculture productivity into five fuzzy sets as follows:

Very Low (VL) ≤ 0.25

Low (L) 0 to 0.5
Medium (M) 0.25 to 0.75
High (H) 0.5 to 1
Very High (VH) ≥ 0.75

Table 8: Classification of Agriculture Productivity

The suitable membership functions of the above classifications are given below,

466
International Journal of Pure and Applied Mathematics Special Issue

 1, x0 
 0.25  x  0, x  0 and x  0.5
 
VL  x    , 0  x  0.25  x
L  x    0  x  0.25
 0.25  0.25
 0, x  0.25  0.5  x
,  0.25 , 0.25  x  0.5

 
 0, x  0.25 and x  0.75  0, x  0.5 and x  1
 
 x  0.25  x  0.5
M  x    , 0.25  x  0.5 H  x    , 0.5  x  0.75
 0.25  0.25
 0.75  x  1 x
 0.25 , 0.5  x  0.75  0.25 , 0.75  x  1
,

 0, x  0.75
 x  0.75

VH  x    , 0.75  x  1
 0.25
 1, x 1

Figure 10: Classification of Agriculture Productivity

4. Algorithm for the Fuzzy Expert System

Step-1 Here, n input factor Ai , i = 1, 2, ..., n and m outputs Rj , j = 1, 2,...,m.
Step-2 Divide the input factors Ai , i = 1, 2,..., n and m outputs factors Rj , j = 1, 2,...,m
into linguistic terms.
Step-3 Construct the suitable fuzzy membership function for each linguistic terms Di,
Rj using the available information.
Step-4 Develop q If-then rules with aid of expert's (Ei), i = 1, 2, ... , k
(i) Input- Fuzzy strings from Rq and the value of the parameter Di.
(ii) Calculating the sting strength wq  A1  A2   Aq

467
International Journal of Pure and Applied Mathematics Special Issue

(iii) Op= pth rule's consequent fuzzy rules.

r O w
(iv) Output of the system =  q q
p 1 wq

Step-5 Final output would be the required impact.

5. Results and Discussion

Step-1 Choose the 7 input factors rise in temperature, weather disasters, fresh water availability,
monsoon level, species extinction, spread of new diseases and deforestation are chosen and the
Agriculture productivity is considered as output.
Step-2-3 All the input and output parameters are classified into linguistic term, then, suitable
membership functions are constructed using the available information for all the linguistics.

Step-4 Fuzzy Rule based is the most important part in fuzzy expert system and Excellency of
results in a fuzzy expert system depends on the fuzzy rules.

Designed system was designed with inference mechanism Mamdani approach. In this system, the
logical combination of inputs with AND operation is considered. For defuzzification process,
`centroid' method is used in the designed system. The 3D surface viewer designed on the basis of
the rule base.

Case 1: The input variables of agriculture productivity are {(35‫ﹾ‬C, Rise in Temperature), (35%,
Weather Disasters), (4.5%, Fresh Water Availability), (125mm, Monsoon Level), (4%, Species
Extinction), (17.5%, Spread of new Diseases), (0.75%, Deforestation)}.

A1: Rise in Temperature = {(0, VL), (0, L), (0, M), (1, H), (0, VH)}.
A2: Weather Disasters = {(0, VL), (0, L), (1, M), (0, H), (0, VH)}.
A3: Fresh Water Availability = {(0, VL), (0, L), (1, M), (0, H), (0, VH)}.
A4: Monsoon Level = {(0, VL), (1, L), (0, M), (0, H), (0, VH)}.
A5: Species Extinction = {(0, VL), (0, L), (1, M), (0, H), (0, VH)}.
A6: Spread of new Diseases = {(0, VL), (0, L), (1, M), (0, H), (0, VH)}.
A7: Deforestation = {(0, VL), (0, L), (1, M), (0, H), (0, VH)}.

This is the fuzzy set which represents the state of medium agriculture productivity, whose
linguistic string (Very Low (VL), Low (L), Medium (M), High (H), Very High (VH)).

The rule states that if rise in temperature is high and weather disaster is medium and fresh water
availability is medium and monsoon level is low and species extinction is medium and spread of
new diseases is medium and deforestation is medium then agriculture productivity is medium.
Hence, agriculture productivity is medium level with 0.5 membership grade.

468
International Journal of Pure and Applied Mathematics Special Issue

Figure 11: Rule Based system

Figure 12: Surface viewer weather disaster and Rise in temperature to Agricultural productivity

469
International Journal of Pure and Applied Mathematics Special Issue

Figure 13: Surface viewer of Rise in Temperature and fresh water availability to Agricultural
productivity

Figure 14: Surface viewer of Monsoon level and weather disaster to Agricultural productivity.

470
International Journal of Pure and Applied Mathematics Special Issue

Figure 15: Surface viewer Rise in temperature and deforestation to Agricultural productivity

6. Conclusion
This present study designed Fuzzy Expert System for the Impact of Climate Change in
Indian Agriculture. With aid of available information the causes of climate change are
considered as the input and the productivity of agriculture is taken as the output. Then, all the
input and output are classified with Linguistic term and provided suitable membership
functions and derived the certain IF-THEN rules. Later, this system has been tested with the
aid of expert under particular environment. Further research can be done of constructing the
expert system for analyzing the impact of fertilizer/pesticides on the human health.

7. References

[1] Amindoust, A., Ahmed, S., Saghafinia, A., Sustainable supplier selection: A ranking
model based on fuzzy inference system, Applied Soft Computing, 12, 1668–1677, (2012).
[2] Cavallaro, F., A Fuzzy Expert System For Designing A Sustainability Index Of Energy
Crops, 23rd European Biomass Conference and Exhibition, 1-4 June 2015, Vienna,
Austria.
[3] Djatkov, D., Effenberger, M., Martinov, M., Method for assessing and improving the
efficiency of agricultural biogas plants based on fuzzy logic and expert systems, Applied
energy, 134 163- 175, (2014).
[4] Dubey, S., Pandey, R.K., Gautam, SS., Literature Review on Fuzzy Expert System in
Agriculture, International Journal of Soft Computing and Engineering, 2(6), 281-191,
2013.
[5] Duque, WO., Huguet, NF., Domingo, JL., Schuhmacher, M., Assessing water quality in
rivers with fuzzy inference systems: A case study, Environmental International, 32, 733–
742, (2006).

471
International Journal of Pure and Applied Mathematics Special Issue

[6] Guillaume., S and Charnomordic, B., Interpretable fuzzy inference systems for
cooperation of expert knowledge and data in agricultural applications using FisPro, Fuzzy
Systems (FUZZ-IEEE) 2012 IEEE International Conference on, 1-8, (2012).
[7] Hayo M.G. Van Der Werf., Zimmer, C., An Indicator Of Pesticide Environmental Impact
Based On A Fuzzy Expert System, Chemosphere, 36(10), 2225- 2249, (1998).
[8] Jasutkar., D.B., Khan, A., Review on Rule based System of Fuzzy Logic for Assessment
of Environmental Impact, International Journal of Engineering Research & Technology,
4(10), (292-295) (2015).
[9] Kandel, A. (1992). Fuzzy Expert Systems. CRC Press, Inc., Boca Raton.
[10] Rajaram,T., Das, A., Modeling of interactions among sustainability components of an
agro-ecosystem using local knowledge through cognitive mapping and fuzzy inference
system, Expert Systems with Applications, 37, 1734–1744, (2010).
[11] Reshmidevi,T.V., Eldho,T.I., Jana, R., A GIS-integrated fuzzy rule-based inference system
for land suitability evaluation in agricultural watersheds, Agricultural Systems, 101, 101–
109, (2009).
[12] Roussel, O., Cavelier, A., Hayo M.G. van der Werf, Adaptation and use of a fuzzy expert
system to assess the environmental effect of pesticides applied to field crops, Agriculture,
Ecosystems & Environment, 80, 143-158, (2000).
[13] Sami, M., Shiekhdavoodi, MJ., Pazhohanniya,M., Pazhohanniya, F., Environmental
comprehensive assessment of agricultural systems at the farm level using fuzzy logic: A
case study in cane farms in Iran, Environmental Modeling & Software, 58, 95- 108,
(2014).
[14] Sattler, C., Stachow, U., Berger, G., Expert knowledge-based assessment of farming
practices for different biotic indicators using fuzzy logic, Journal of Environmental
Management, 95, 132- 143, (2012).
[15] Semeraro, T., Mastroleo,G., Aretano,R., Facchinetti, G., Zurlini, G., Petrosillo,I., GIS
Fuzzy Expert System for the assessment of ecosystems vulnerability to fire in managing
Mediterranean natural protected areas, Journal of Environmental Management, 168, 94- 103,
(2016).
[16] Tagarakis, A., Koundouras, S., Papageorgiou,E.I., Dikopoulou, Z., Fountas, S., Gemtos,
T. A., A fuzzy inference system to model grape quality in vineyards, Precision
Agriculture, 15(5), 555–578, (2014).
[17] Yelapure, S. J., Kulkarni, R. V., Literature Review on Expert System in Agriculture, 3
(5), International Journal of Computer Science and Information Technologies, 5086-
5089, (2012).
[18] Zadeh, L.A. Soft Computing and Fuzzy Logic, IEEE software, 11(6), 48-56, (1994).
[19] Zadeh, L.A., (1965). Fuzzy sets, Information and Control, 8, 338- 353, (1965).

472
473
 474

View publication stats