You are on page 1of 11

Application of MCDM using PROMETHEE II Techniques in the Case of Fertilizer Selection for

Agriculture
Dr.A.Rajkumar [1] A.Ezhilarasi [2] J.Sharmila Jessie ignatia [3]
[1] Assistant Professor [2] Research Scholar [3] Research scholar
PG & Research Department of Mathematics
Annai Vailankanni Arts and Science College Thanjavur, Tamil Nadu, India.
(Affiliated to Bharathidasan University, Thiruchirappalli-24, Tamil Nadu, India.)
Email: [1] raj.math27@gmail.com
[2]ezhilselvi99@gmail.com
ABSTRACT:

If we want to make the best decision in a complex situation, MCDM is the way to go. This
paper provides an overview of the use of MCDM in determining the best fertilizer selection. The
Promethee method is a significant method for providing a brisk solution to problems. Data were
gathered through in-person communication with decision makers and the use of a likert scale. In
multicriteria analysis, the PROMETHEE method is a new class of outranking method. On a finite set
of feasible actions, a partial preorder (PROMETHEE I) or a complete preorder (PROMETHEE II) can
be obtained.

KEYWORDS: PROMETHEE II, MCDM, Fertilizer, Likert scale.

INTRODUCTION:

Multi criteria decision making (MCDM) method is referred as a method used for scoring and
ranking a finite number of alternatives. MCDM concern with evaluating and selecting alternatives
that fit with the goals and necessity. PROMTHEE is one of the many MCDM methods that are listed
in the literature, which includes many other MCDM techniques. Preference Ranking Organization
Method for Enrichment Evaluation is referred to as the PROMETHEE. In comparison to many other
MCDM methods, this ranking method is regarded as being straightforward in both idea and
computation. The first PROMETHEE implementation was made by Bertrand Mareschal on the ULB
mainframe computer in FORTRAN around 1984. It was very different from today's software. And it
was very difficult to adapt programs to different computers. The University of Split was a pioneer:
they got a stack of punched cards and had the software running on their Vax system in a matter of
days. Later the software was ported to the IBM PC. It was the basis for PromCalc.
Fertilizers enhance the growth of plants. This goal is met in two ways, the traditional one
being additive that provide nutrients. The second way that certain fertilisers work is to improve the
soil's productivity by altering its water retention and aeration. Fertilizers are one of the major inputs of
agriculture. The average fertilizer consumption (per hectare) was very meager amounting to 2kg in
1950.It increased to 128 kg in 2012-13 due to the development of technology. About 90% of
fertilizers are applied as solids. The most widely used solids inorganic fertilizer are urea,
Diammonium phosphate and potassium chloride. The three macronutrients are Nitrogen (N) –leaf
growth, Phosphorus (P) - development of roots, flowers seeds, fruits and potassium (k) - strong stem
growth, movement of water in plants, promotion of flowering and fruiting. The secondary
macronutrients are calcium (Ca), magnesium (Mg) and sulfur(S) and the next one is micronutrients,
like copper(Cu),iron(Fe), manganese(Mn), molybdenum(Mo),Zinc(Zn),Boron(B) of occasional
significance are silicon(Si) cobalt(Co),Vanadium(v).

Preference function value for various types


Types of generalized criterion functions: of criterion functions

1. Usual criterion
H ( d j) =
[ 0 if d j ¿ 0
1 if d j ¿ 0 ]
2. Quasi criterion
H ( d j) =
[0 if d j ≤q j
1 if d j ¿ q j ]
[ ]
3. Criterion with linear dj
d
preference and no H ( d j) = p j if j ¿ 0
if d j ¿ 0
indifference area 1

[ ]
4. Level criterion 0 if dj≤qj
H ( d j) = 0.5 if q j <d j ≤ p j
1 if d j> p j

[ ]
5. Criterion with linear 0 if dj≤qj
preference and H ( d j) = (d j −q j) if ¿ d j > p j ¿
indifference area if ¿ ¿
( p ¿ ¿ j−q j )¿

6. Gaussian criterion
[ ]
2
−d j
2σ' j2
H ( d j) = 1−e

Multicriteria preference index π (a ,b) a weighted average of the preference functions P j (a , b) for the
entire criterion is defined as:

Algorithm:
Step1. Enter the no. of alternatives, criteria, payoff matrix, and weight of each criterion

Step 2: Compute pair wise difference between values of alternative for each criterion (dj).

Step 3: Compute preference function matrix for each criterion based on dj and type of chosen
criterion function.

Step 4: Compute the entering flow and leaving flow for each alternative.

Step 5: Compute the net ф value for each alternative and corresponding rank.

Step 6: Select the best suitable alternative having highest ф value.

METHODOLOGY:
Step 1: Normalize the evaluation matrix (Decision matrix)

r ij =
[ aij−min ( a ij) ] … … … … … (1 ) Beneficial
[max ⁡{aij −min ( aij ) ]

r ij =
[ max ( aij )−a ij ] … … … … ( 2 ) Non Beneficial
[ max ( aij )−min ( a ij) ]
Step 2: Calculation the preference function

p j( a ,b )=0 if r aj ≤ r bj → D( Sa −S b )≤ 0………… (3)

p j(a ,b )=( r aj −r bj ) if r aj >r bj → D(S a−Sb )>0 … … … …(4)

Step 3: Calculate aggregated preference aggregated preference function П (a ,b)

n n
¿ ∑ wjpj(a , b)/ ∑ wj ………… (5)
j=1 j=1

Sum of the weight is 1 (unity)

Step 4: Calculate the entering flow and leaving flow for ath alternative ф+

Leaving (positive) Flow

s
1
¿ ∑ π ( a , b )( a ≠ b )………… (6)
s−1 b =1

Entering (Outranking) Flow


m
1
¿ ∑ π ( a , b ) (a ≠ b) ………… (7)
s−1 b =1

Step 5: Calculate Net Flow


−¿( i)¿

ф ( i )=ф +¿ ( i)−ф ¿
………… (8)

NUMERICAL EXAMPLE:

The results of the tests in evaluating fertilizer selection for cultivation show that the
PROMETHEE Based on analytical evidence, the approach will aid in determining land potential. The
first step is to define the alternatives as well as the parameters that will be used.

Here are the five crop production criteria and four alternatives. In this case, alternative
indicates the amount of fertilizer in kilograms, and criteria indicate the five types of crops.

Table 1: criteria and alternatives for fertilizer selection

Alternative/ Pulses(C1) Gingelly Groundnut(C3) Paddy(C4) Sugarcane(C5)


Criteria (C2)
Nitrogen(A1) 78 86 73 70 77
Phosphorous(A2) 44 23 25 28 11
Manure(A3) 16 47 27 24 36
Potassium(A4) 90 89 94 88 92
Table 2: Value range of min and max value of criteria

Alternative/ Pulses(C1) Gingelly Groundnut(C3) Paddy(C4 Sugarcane(C5)


Criteria (C2) )
Nitrogen(A1) 78 86 73 70 77
Phosphorous(A2) 44 23 25 28 11
Manure(A3) 16 47 27 24 36
Potassium(A4) 90 89 94 88 92
Max 90 89 94 88 92
Min 16 23 25 28 11
Max-min 74 66 69 60 81

Once alternate principles and parameters have been defined, the next step is to classify them based on each
criterion's dominance. The meaning of the current path is then calculated using the outflow value outline to
achieve a better or alternate rating.
Table 3: PROMETHEE Flow Table
Alternative Phi Phi+ Phi- Rank
Alternative 3 0,6295 0,7233 0,0939 1
Alternative 2 0,4772 0,6472 0,1700 2
Alternative 1 -0,3550 0,1983 0,5533 3
Alternative 4 -0,7517 0,0000 0,7517 4

As shown in Table 3, Alternative 3 has the highest rating in the assessment table of fertilizer production
using the PROMETHEE method, indicating that the measure is the most significant alternative in evaluating
the suitability of fertilizer selection.

RESULT AND DISCUSSION:

The PROMETHEE rankings:

There are two PROMETHEE rankings that are computed:

 The PROMETHEE I Partial ranking is based on the computation of two preference flows(Phi+ and
Phi-).It allows for incomparability between actions when both Phi+ and Phi- preference flows give
conflicting rankings.
 The PROMETHEE II complete ranking is based on the net preference flow (Phi).

While the PROMETHEE II complete ranking is easier to explain it is also less informative as the
differences between Phi+ and Phi- scores are not visible anymore. Incomparability in the
PROMETHEE I ranking is interesting because it emphasizes actions that are difficult to compare
and thus helps the decision-maker to focus on these difficult cases.

Fig1:PROMETHEE I Partial ranking Fig2:PROMETHEE II complete ranking


PROMETHEE Diamond :

The PROMETHEE Diamond is an alternative two dimensional joint representatio of both


PROMETHEE I and II rankings. The square corresponds to the (Phi+, Phi-) plane where each action is
represented by a point. The plane is angled 45° so that the vertical dimension gives the Phi net flow.
Phi+ scores increase from the left to the top corner and Phi- scores increase from the left to the bottom
corner.
For each action, a cone is drawn from the action position in the plane.

Fig3:PROMETHEE diamond

PROMETHEE Network:

In the PROMETHEE Network display each action is represented as a node and preferences are
represented by arrows. The nodes are located in relative positions corresponding to the PROMETHEE
Diamond so that the proximities between flow values appear clearly.
Fig4:PROMETHEE Network
PROMETHEE II rainbow:
For each action a bar is drawn. The different slices of each bar are colored according to the
criteria. Each slice is proportional to the contribution of one criterion (flow value times the weight of
the criterion) to the Phi net flow score of the action. Positive (upward) slices correspond to good
features while negative (downward) slices correspond to weaknesses. This way, the balance between
positive and negative slices is equal to the Phi score. Actions are ranked from left to right according to
the PROMETHEE II Complete Ranking.

Fig5:PROMETHEE Rainbow

PROMETHEE GAIA:

The GAIA plane is a descriptive complement to the PROMETHEE rankings.

Fig6:PROMETHEE GAIA
WALKING WEIGHTS:

The Walking Weights window allows you to change the weights of the criteria and see the impact on
the Visual PROMETHEE analysis.

Fig7: Walking Weights:

CONCLUSION:

Fertilizer selection is one of the necessary parts of agriculture, and this article gives the
conclusion of the best fertilizer for your field and crop production. In this case, we select the four
types of fertilizer for five crops, and among them, we select the one that is best for each crop using
this PROMETHEE method. This paper assumes that one of the most important aspects of agriculture
is fertilizer selection, and in this study, we examine the four types of fertilizer to determine which is
best for agricultural purposes. Finally, using the Prometheus II method, we can see that the manure
has the highest rank. In this paper, the author explores the use of Extended PROMETHEE II method
in solving the problem of determining the best fertilizer and generates more efficient decisions.
CONFLICT OF INTEREST:
There is no conflict of interest by authors
REFERENCE:

[1] Dr.A. Rajkumar,A.Ezhilarasi,J.Sharmila Jessie Ignatia (“Analysis of MCDM using Promethee


II Techniques in the Case of River Water Quality Monitoring”)-Indian Journal Of Natural
Science.Vol.14/Issue 79/Aug/2023. ISSN:0976-0997.
[2] Muhammet Gul, Erkan celik, Alev Taskin Gumus, Ali Fuat Guneri (“A fuzzy logic based
PROMETHEE method for material selection problem”)- Benni-suef University Journal of
Basic and Applied Science 7(2018)68-79
[3] Albadvi, A., Chaharsooghi, S., Esfahan pour, A., 2007. Decision making in stock trading: an
application of PROMETHEE. Eur.J.Oper, Res.177, 673-683.
[4] Bilsel, R.U., Buyikozjan, G., Runa, D., 2006. A fuzzsy preference ranking model for a quality
evaluation of hospital web sites.Int.J.syswt.21, 1181-1197.
[5] S. Kusumadewi,S. Hartati, A. Harjoka, and r. Wardoyo, fuzzy multi Attribute Decision
Making (Fuzzy MADM). Yogyakarta: Graha Ilmu,2006.
[6] Risawandi And R.Rahim, “Study of the simple Multi Attribute Rating Techniques for
Decision support”, IJSRST, vol, no.6, pp.491-494, 2016.
[7] World Health Organization. (2020). Corona virus disease 2019(COVID -19): Situation Report,
59.
[8] Ghasemi P, Talebi E. An integrated FAHP-PROMETHEE approach for selecting the best
Flexible Manufacturing system. EUR Online J Nat soc sci. 2014:3:1137-1150.
[9] Dagdeviren, M.: Decision making in equipment selection: an integrated approach with AHP
and PROMETHEE. J. Intel. Manuf. 19(4), 397–406 (2008).
[10] Macharis, C., Springael, J., de Brucker, K., Verbeke, A.: PROMETHEE and AHP: the
design of operational synergies in multicriteria analysis. Stengthening PROMETHEE with
ideas of AHP. Eur. J. Oper. Res. 153(2), 307–317 (2004).
[11] Cude, 2001b. Oregon Water Quality Index: a tool for evaluating water quality
management effectiveness. J. Am. Water Resour. Assoc. 37 (1),125–137.
[12] ICMR (Council of Medical Research), 1975. Manual of Standards of Quality for
Drinking Water Supplies, Indian. Special Report No. 44., pp. 27.
[13] Verma, R.K., Murthy, S., Tiwary, R.K., Verma, S., 2019. Development of simplified
WQIs for assessment of spatial and temporal variations of surface water quality in upper
Damodar river basin , eastern India. Appl. Water Sci. 0–15 https://doi.org/10.1007/ s13201-
019-0893-0.
[14] Wu, Z., Wang, X., Chen, Y., Cai, Y., Deng, J., 2018. Assessing river water quality
using water quality index in Lake Taihu Basin, China. Sci. Total Environ. https://doi.org/
10.1016/j.scitotenv.2017.08.293.
[15] W. Bengal, W. Bengal, and W. Bengal, “A comparative study of preference
dominance-based approaches for selection of industrial robots,” Adv. Prod. Eng. Manag., vol.
9, no. 1, pp. 5–20, 2014.
[16] P. Chatterjee and S. Chakraborty, “Flexible manufacturing system selection using
preference ranking methods: A comparative study,” Int. J. Ind. Eng. Comput., vol. 5, no. 2, pp.
315–338, 2014.
[17] S. Kusumadewi, S. Hartati, A. Harjoko, and R. Wardoyo, Fuzzy Multi-Attribute
Decision Making (Fuzzy MADM). Yogyakarta: Graha Ilmu, 2006.
[18] Risawandi and R. Rahim, “Study of the Simple Multi-Attribute Rating Technique For
Decision Support,” IJSRST, vol. 2, no. 6, pp. 491–494, 2016.
[19] Jasri, D. Siregar, and R. Rahim, “Decision Support System Best Employee
Assessments with Technique for Order of Preference by Similarity to Ideal Solution,” Int. J.
Recent TRENDS Eng. Res., vol. 3, no. 3, pp. 6–17, 2017.
[20] ] Mesran, G. Ginting, Suginam, and R. Rahim, “Implementation of Elimination and
Choice Expressing Reality ( ELECTRE ) Method in Selecting the Best Lecturer ( Case Study
STMIK BUDI DARMA ),” Int. J. Eng. Res. Technol. (IJERT, vol. 6, no. 2, pp. 141–144,
2017.
[21] M. Iswan, W. Fitriani, N. Mayasari, and A. P. U. Siahaan, “Tuition Reduction
Determination Using Fuzzy Tsukamoto,” Int. J. Eng. Sci. Invent., vol. 5, no. 9, pp. 68–72,
2016.

You might also like