IT Project: Artificial Intelligence In Agriculture

IT for MANAGERS

PGDM FINANCE
Sec-D(2010-12)
IT PROJECT
Artificial Intelligence in Agriculture
Term 1

ITM Group Members:

NISHANT JAIN

SAYAN MAJUMDER

ROHAN MITRA

PUNIT FRANCIS

PURNENDU

Acknowledgement
1
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

We would like to take the opportunity to thank everyone concerned whose

support was the basic reason we were able to complete the project successfully. The
assignment gave a true exposure to the actual functioning of the AI in Agriculture.
This is the exact time to get acquainted with the facts of the AI and its uses in human
life mainly focusing on agriculture .
This assignment has definitely helped in creating a very clear picture of the
working of the AI in agriculture, its styles and trends .

At the beginning of our report we want to thank a few important people without
whom we would not have been able to complete my training.
To begin with we would like to thank my Mr. Rupesh Kumar Sinha (Project
Coordinator) who helped me to do our project successfully.

Yours cordially, NISHANT JAIN

SAYAN MAJUMDER

ROHAN MITRA

PUNIT FRANCIS

PURNENDU

Project Contents Page No.

1. Artificial Intelligence 01

2. Applications of Artificial Intelligence

2
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

3. Need of Artificial Intelligence in Our life

4. Artificial Intelligence in Agriculture

5. Sectors in Agriculture

6. Conclusions

3
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

Artificial Intelligence (AI) is the area of computer science focusing on creating machines that can
engage on behaviours that humans consider intelligent. The ability to create intelligent machines has
intrigued humans since ancient times and today with the advent of the computer and 50 years of
research into AI programming techniques, the dream of smart machines is becoming a reality.
Researchers are creating systems which can mimic human thought, understand speech, beat the
best human chess player, and countless other feats never before possible. Find out how the military
is applying AI logic to its hi-tech systems, and how in the near future Artificial Intelligence may
impact our lives.

CONTENT 1
Intelligence and Artificial Intelligence
What do we mean by Intelligence or intelligent person? Generally we say in education, the
ability to learn or understand or to deal with new or challenging situations. In psychology, the term
may more specifically denote the ability to apply knowledge to manipulate one’s environment or to
think abstractly as measured by objective criteria (such as the IQ test). Intelligence is usually thought
of as deriving from a combination of inherited characteristics and environmental (developmental
and social) factors.

4
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

So Now a days when the world understand only machine language then they have
thought some different to work with their thinking capability also. The biological meaning of
Intelligence has change into mechanical. We termed this mechanical language as Artificial
Intelligence.

Now what is Artificial Intelligence

Artificial Intelligence (AI) is the area of computer science focusing on creating machines
that can engage on behaviours that humans consider intelligent. The ability to create intelligent
machines has intrigued humans since ancient times and today with the advent of the computer and
50 years of research into AI programming techniques, the dream of smart machines is becoming a
reality. Researchers are creating systems which can imitate human thought, understand speech,
beat the best human chess player, and countless other feats never before possible. Find out how the
military is applying AI logic to its hi-tech systems, and how in the near future Artificial Intelligence
may impact our lives.

Mechanical or "formal" reasoning has been

Developed by philosophers and mathematicians
since antiquity. The study of logic led directly to
The invention of the programmable digital
Electronic computer, based on the work of

Mathematician Alan Turing and others. Turing's

theory of computation suggested that a machine, by shuffling symbols as simple as "0" and
"1", could simulate any conceivable act of mathematical deduction.[23] This, along with recent
discoveries in neurology, information theory and cybernetics, inspired a small group of
researchers to begin to seriously consider the possibility of building an electronic brain.

The field of AI research was founded at a conference on the campus of Dartmouth College in
the summer of 1956. The attendees, including John McCarthy, Marvin Minsky, Allen Newell
and Herbert Simon, became the leaders of AI research for many decades. They and their
students wrote programs that were, to most people, simply astonishing: computers were
solving word problems in algebra, proving logical theorems and speaking English. By the
middle of the 1960s, research in the U.S. was heavily funded by the Department of Defence
and laboratories had been established around the world. AI's founders were profoundly
optimistic about the future of the new field: Herbert Simon predicted that "machines will be
capable, within twenty years, of doing any work a man can do “and Marvin Minsky agreed,
writing that "within a generation ... the problem of creating 'artificial intelligence' will
substantially be solved".

They had failed to recognize the difficulty of some of the problems they faced. In 1974, in
response to the criticism of England's Sir James Lighthill and ongoing pressure from
Congress to fund more productive projects, the U.S. and British governments cut off all
undirected, exploratory research in AI. The next few years, when funding for projects was
hard to find, would later be called an "AI winter".

5
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

In the early 1980s, AI research was revived by the commercial success of expert systems, a
form of AI program that simulated the knowledge and analytical skills of one or more human
experts. By 1985 the market for AI had reached over a billion dollars. At the same time,
Japan's fifth generation computer project inspired the U.S and British governments to restore
funding for academic research in the field.[36] However, beginning with the collapse of the
Lisp Machine market in 1987, AI once again fell into disrepute, and a second, longer lasting
AI winter began.

In the 1990s and early 21st century, AI achieved its greatest successes, albeit somewhat
behind the scenes. Artificial intelligence is used for logistics, data mining, medical diagnosis
and many other areas throughout the technology industry.[9] The success was due to several
factors: the incredible power of computers today (see Moore's law), a greater emphasis on
solving specific sub problems, the creation of new ties between AI and other fields working
on similar problems, and above all a new commitment by researchers to solid mathematical
methods and rigorous scientific standards.[38]

Content 2:- Application of

Artificial Intelligence
Finance

Banks use artificial intelligence systems to organize operations, invest in stocks, and manage
properties. In August 2001, robots beat humans in simulated financial trading competition financial
institutions have long used artificial neural network systems to detect charges or claims outside of
the norm, flagging these for human investigation.

Medicine

6
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

In medical industry also AI Can is used effectively. A medical clinic can use this technique to organise
their medical stock, admission, staffs absenteeism etc.... Artificial neural networks are used for
medical diagnosis (such as in Concept Processing technology in EMR software), functioning as
machine differential diagnosis. EMR Experts is the leading broker of the most highly regarded
Electronic Medical Record (EMR) & Medical Billing Software.

Heavy industry & Robotics

Robots have become common in many industries. Robots have evolved over the last 50 years from
teleported machines – mechanical devices operated remotely by humans. Robots have proven
effective in jobs that are very repetitive which may lead to mistakes or accidents due to a lapse in
concentration and other jobs which humans may find degrading. General Motors Corporation uses
around 16,000 robots for tasks such as painting, welding, and assembly. Japan is the leader in using
and producing robots in the world. In 1995, 700,000 robots were in use worldwide; over 500,000 of
which were from Japan. For more information, see survey about artificial intelligence in business.

Transportation

In transport sector also Ai plays an important role. A fuzzy

Control system is a control system based on fuzzy logic—a

Mathematical system that analyzes analogy input values in

Terms of logical variables Fuzzy logic controllers have

been

Developed for automatic gearboxes in automobiles. It

Generally uses in machine control. Audi TT, VW Toureg

and VW Caravell feature the DSP transmission which utilizes Fuzzy logic.

Telecommunications

Many telecommunication companies using this artificial intelligence for their management work
force. For example BT Group has deployed heuristic in a scheduling application that provides the
work schedules of 20000 engineers.

Agriculture

In the domain of agriculture, the utilization of already developed models in a broad area is often
hindered. One frequent factor which impedes transportation is model inaccuracy. For example,
when models that perform well in one region, are transported to be used in a different region, they
often do not give accurate output (such as, recommendations, results, and/or indicators) in their
new environment (i.e., when they are run in a new region). The general component created by this

7
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

combinational methodology will here be called an ’Agricultural Model-GA’ or an AGMOD-GA. The

theory of this adaptation methodology is that by utilizing historical data from a particular region, a
model’s parameter settings can be adapted so that the new parameters allow the model to work
well in the particular region.

Toys and games

The 1990s saw some of the first attempts to mass-produce domestically aimed types of basic
Artificial Intelligence for education. This prospered greatly with the Digital Revolution, this idea
invented digital toys or electronic toys which can entertain more children, to a life of dealing with
various types of AI, specifically in the form of Tamagotchis and Giga Pets, the Internet (example:
basic search engine interfaces are one simple form), and the first widely released robot, Furby. A
mere year later an improved type of domestic robot was released in the form of Aibo, a robotic dog
with intelligent features and autonomy. AI has also been applied to video games.

Music

The evolution of music has always been affected by technology. With AI, scientists are trying to make
the computer emulate the activities of the skilful musician. Composition, performance, music theory,
sound processing are some of the major areas on which research in Music and Artificial Intelligence
are focusing.

Aviation

The Air Operations Division AOD, uses AI for the rule based expert systems. The use of artificial
intelligence in simulators is proving to be very useful for the AOD. Airplane simulators are using
artificial intelligence in order to process the data taken from simulated flights. Other than simulated
flying, there is also simulated aircraft warfare. The computers are able to come up with the best
success scenarios in these situations. The computers can also create strategies based on the
placement, size, speed, and strength of the forces and counter forces. The artificial intelligent
programs can sort the information and provide the pilot with the best possible manoeuvres, not to
mention getting rid of certain manoeuvres that would be impossible for a sentient being to perform.
The computer simulated pilots are also used to train future air traffic controllers.

In2003 NASA made an F-15 .made of newly developed soft wares emerging with Artificial Intelligent
which was a Triumph in AI. The Intelligent Flight Control System was tested on an F-15 [3], which
was heavily modified by NASA. The software compensates for all the damaged components by
relying on the undamaged components. The neural network used in the software proved to be
effective and marked a triumph for artificial intelligence.

8
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

Content 3:-
Needs of Artificial Intelligence
Today artificial intelligence is already a major part of our lives. For example there are several
separate AI based systems just in Microsoft Word. The little paper clip that advises us on how to use
office tools is built on a Bayesian belief network and the red and green squiggles that tell us when
we've misspelled a word or poorly phrased a sentence grew out of research into natural language.
However, you could argue that this hasn't made a positive difference to our lives; such tools have
just replaced good spelling and grammar with a labour saving device that results in the same
outcome. For example I compulsively spell the word 'successfully' and a number of other word with
multiple double letters wrong every time I type them, this doesn't matter of course because the
software I use automatically corrects my work for me thus taking the pressure off me to improve.
The end result is that these tools have damaged rather than improved my written English skills.
Speech recognition is another product that has emerged from natural language research that has
had a much more dramatic effect on people's lives. The progress made in the accuracy of speech
recognition software has allowed a friend of mine with an incredible mind who two years ago lost
her sight and limbs to septicaemia to go to Cambridge University. Speech recognition had a very
poor start, as the success rate when using it was too poor to be useful unless you have perfect and
predictable spoken English, but now it’s progressed to the point where it’s possible to do on the fly
language translation. The system in development now is a telephone system with real time English
to Japanese translation. These AI systems are successful because they don't try to emulate the entire
human mind the way a system that might undergo the Turing test does. They instead emulate very
specific parts of our intelligence. Microsoft Words grammar systems emulate the part of our
intelligence that judges the grammatical correctness of a sentence. It doesn't know the meaning of
the words, as this is not necessary to make a judgement. The voice recognition system emulates
another distinct subset of our intelligence, the ability to deduce the symbolic meaning of speech.
And the 'on the fly translator' extends voice recognitions systems with voice synthesis. This shows
that by being more accurate with the function of an artificially intelligent system it can be more
accurate in its operation.

Content 4:-
Artificial intelligence in agriculture
The Automated Land Evaluation System, or ALES, is a land information system which allows
countries to determine the crops which are physically and economically best suited to their
respective land units. ALES allow land evaluators to build expert systems to evaluate land according
to the method presented in the Food and Agriculture Organization "Framework for Land Evaluation"

9
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

(FAO 1976). It is intended for use in project or regional scale land evaluation. The entities evaluated
by ALES are map units, which may be defined either broadly (as e.g. in reconnaissance surveys and
general feasibility studies) or narrowly (as e.g. in detailed resource surveys and farm-scale planning).

ALES' function is basically to match the land attributes to crop requirements and to determine the
most suitable options for land use, including in the analysis socio-economic variables such as cost.
ALES is being piloted in three Eastern Caribbean countries

Evaluators build their own expert systems with ALES, taking into account local conditions and
objectives. ALES are not by itself an expert system, and does not include by itself any knowledge
about land and land use. ALES are a framework within which evaluators can express their own, local,
knowledge.

ALES have seven components:- 

1. A framework for a knowledge base describing proposed land uses, in both physical and economic
terms; 
2. A framework for a database describing the land areas to be evaluated; 
3. An inference mechanism to relate these two, thereby computing the physical and economic
suitability of a set of map units for a set of proposed land uses; 
4. An explanation facility that allows model builders to understand and fine-tune their models; 
5. A consultation mode that allows a casual user to query the system about one land use at a time; 
6. A report generator (on-screen, to a printer, or to disk files); and 
7. An import/export module that allows data to be exchanged with external databases, geographic
information systems, and spreadsheets. This includes the ALIDRIS interface to the IDRISI geographic
information system as well as an interface to xBase (dBase III+) - format database files, including
Attribute Tables in PC-Arc/Info 

ALES are not a GIS and do not display maps. It can, however, analyze geographic land characteristics
if map units are appropriate defined, and it can directly reclassify IDRISI maps or Arc/Info Attribute
Tables with the same mapping unit legend as the ALES database. 

Given its characteristics, ALES is a good candidate for being used as a decision support system for
sustainable land-use purposes. Due to its flexibility, environmental and socioeconomic attributes
that are considered to be important for sustainability could be used to define desirable land
qualities. The definition of the appropriate data for estimating sustainability to be collected and
input into the system would be the main challenge left to overcome.

Application of artificial neural networks in mage recognition and

classification of crop and weeds.
The objective of this study was to develop a back propagation artificial neural network (ANN) model
that could distinguish young corn plants from weeds. Although only the colour indices associated
with image pixels were used as inputs, it was assumed that the ANN model could develop the ability
to use other information, such as shapes, implicit in these data. The 756x504 pixel images were

10
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

taken in the field and were then cropped to 100x100-pixel images depicting only one plant, either a
corn plant or weeds. There were 40 images of corn and 40 of weeds. The ability of the ANNs to
discriminate weeds from corn was then tested on 20 other images. A total of 80 images of corn
plants and weeds were used for training purposes. For some ANNs, the success rate for classifying
corn plants was as high as 100%, whereas the highest success rate for weed recognition was 80%.
This is considered satisfactory, given the limited amount of training data and the computer hardware
limitations.Therefore, it is concluded that an ANN-based weed recognition system can potentially be
used in the precision spraying of herbicides in agricultural fields.
Significant progress in the development of machine vision and image processing technology has
been made in the past few years in conjunction with improvements in computer technology (Baxes
1994). Equipment for machine vision and image processing has been reduced in cost, size, and
weight, can beinstalled in most vehicles (e.g., tractors), and is accessible for civilian use. Machine
vision and image processing are used
increasingly in biology, materials science, photography, and other fields (Baxes 1994). Many
experiments have suggested that machine vision can be used to recognize and localize weeds in
agricultural fields (Anonymous 1994a, 1994b; Blackmer and Schepers 1996; Meyer et al. 1997;
Schmoldt et al. 1997; Staff and Benlloch 1997). It might therefore be used to control sitespecific
spraying herbicide application, thus reducing both
environmental pollution from the overuse of agrochemicals, as well as the cost of weed control.It is
presently quite difficult to use machine vision to distinguish weeds from the main crop in real time,
due to the substantial computational resources and the complicatedalgorithms required. Artificial
neural networks (ANNs) can overcome some of these difficulties by interpreting images quickly and
effectively. ANNs are composed of numerous processing elements (PEs) arranged in various layers,
with interconnections between pairs of PEs (Haykin 1994; Kartalopoulos 1996; Kasabov 1996). They
are designed to emulate the structure of natural neural networks such as those of a human brain.
For most ANNs, PEs in each layer are fully
connected with PEs in the adjacent layer or layers, but are not connected to other PEs in the same
layer. The PEs simulate the function of the neurons in natural neural networks, while the
interconnections between them mimic the functions of dendrites and axons. There have been many
applications of ANNs reported for the interpretation of images in the agri-food industry. Studies
have shown that for the interpretation of images ANNs can be as accurate as procedural models
(Deck et al. 1995; Timmermans and Hulzebosch 1996). For example, the accuracy of classification of
potted plants can be greater than 99% (Timmermans and Hulzebosch 1996), apples can be graded by
colour with an accuracy of 95% (Nakano 1997), the classification of logs for defects using computed
tomography imagery can be 95% accurate (Schmoldt et al. 1997), and theaccuracy for the
classification of wheat kernels by colour can be 98% or more (Wang et al. 1999). Generally, ANNs can
efficiently model various input/output relationships with the advantage of requiring less execution
time than a procedural model (Yang et al. 1997a, 1997b). These features make theANN approach
very appealing for real-time image processing.

Simulation: Biomass growth model

Agricultural models and decision support systems are becoming increasingly available for a wide
audience of users. The Great Plains Framework for Agricultural Resource Management (GPFARM)
DSS is a strategic planning tool for farmers, ranchers, and agricultural consultants that incorporates a
science simulation model with an economic analysis package and multi-criteriadecision aid for
evaluating individual fields or aggregating to the entire enterprise. The GPFARM DSS is currently
being expanded to include 1) better strategic planning by simulating a greater range of crops over a

11
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

wider geographic range and management systems, 2) incorporating a tactical planning component,
and 3) adding a production, environmental, and economic risk component. The plant growth
component within the science simulation model is subdivided into separate submodels for crops and
rangeland forage. User requirements have determined that the DSS must be easy to use in terms of
setup, and therefore little parameterization or calibration for a specific site can be required. Based
on evaluation of both the crop and rangeland forage growth module of GPFARM, improvements are
needed to more accurately
simulate plant responses to varying levels of water availability. This paper presents our approach
and some preliminary results for improving the plant growth models.Our approach is based on using
the stand-alone plant growth model derived from the Wind Erosion Prediction System (WEPS),
which is based on the EPIC plant growth model. Steps that should improve the plant growth models
include 1) incorporate modifications from ork done to other models that are based on the EPIC
plant growth model (e.g., GPFARM; Water ErosionPrediction Project, WEPP; ALMANAC; and Soil and
Water Assessment Tool, SWAT), and 2) Then there is an AI adaptation methodology designed to
assist in transporting agricultural models between regions is presented. Models frequently need
adaptation when transported because models developed in one region often do not produce valid
results when used in a different region. The methodology prescribes the linkage of a genetic
algorithm to a model. This makes the model more robust because it is able to adapt to the region in
which it is being used. This methodology has been implemented within a DSS, and preliminary
testing indicates this methodology has the ability to allow agricultural models developed in one In
the domain of agriculture, the utilization of already developed models in a broad area is often
hindered by one or more factors. One frequent factor which impedes transportation is model
inaccuracy. For example, when models that perform well in one region, are transported to be used
in a different region, they often do not give accurate output (such as, recommendations, results,
and/or indicators) in their new environment (i.e., when they are run in a new region). This is one of
the major difficulties of model technology transfer. To address this difficulty, an artificial intelligence
(AI) methodology is proposed. At the heart of this methodology is a genetic algorithm (GA) (an AI
search technique) which is linked to the agricultural model engine (e.g., a risk assessment,
provisional, or crop growth model). The general component created by this combinational
methodology will here be called an ’Agricultural Model-GA’ or an AGMOD-GA. The following sections
will describe the overall structure and elements of this methodology, the generic component
created by following this methodology, and discuss the application of this methodology.

DESCRIPTION OF THE AI METHODOLOGY FOR ADAPTING AGRICULTURAL

MODELS
The theory of this adaptation methodology is that by utilizing historical data from a particular region,
a model’s parameter settings can be adapted so that the new parameters allow the model to work
well in the particular region. This adaptation is done by trying to match the model parameter
settings to the particular region. To find matching model parameter settings, intelligent search are
performed which utilizes historical data as part of the objective function.
Overall, by following this methodology, a component will be created which can search for good
model parameter settings such that when the given model is applied and run at the location in
question, the output values given will be consistent with the historical outcome data; moreover it is
hoped that this will also allow the model to be generally used in this region, producing accurate
output values on data which it has not seen. The component that performs this search/adaptation
can be called an expert system component since it intelligently modifies and adjusts a model to work
in a new location in the same way an expert would modify and adjust a model.

12
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

Additionally, it should be emphasized that this methodology is particularly appealing because it is

not a strictly empirical or analytical, but both. That is, this methodology does not perform a search to
fit the historical data from a particular location into an empirical algorithm; rather it performs the
search in a larger context, fitting the model parameter settings to a particular location. Therefore,
the resulting instantiation of the adapted/localized agricultural model (with the new parameter
settings inside) is as good (or as bad) as the original model; consequently, if the model is biologically
significant (e.g., if it simulates biological events) then this is not lost by this adaptation methodology
since the model is used in the same form (i.e., the structure of the model is left intact), only the
model parameter settings are changed.

3. ELEMENTS OF THIS AI METHODOLOGY

In general, this methodology prescribes the utilization of:
(i) historical situation data,
(ii) historical outcome data,
(iii) the agricultural model, and
(iv) an intelligent search method (in this case, a genetic algorithm, also called a GA, which is an
artificial intelligence search technique).
Historical situation data is the basic data required by the model in question. In the domain of
agricultural models, this often includes meteorological data since this is frequently an important
input to the model. In this methodology, the more historical situation data that is available, the
better. The presence of historical outcome data plays a large part in how accurately a model will be
adapted using this methodology. This is due to the basic fact that models accepts situations and
computes outcomes. The historical outcome data will be used to fit the model parameter settings to
the new region in question. Therefore, when constructing a component using the methodology
described here, it must be possible to match model outputs to some combination of outcomes
and/or events in the real-world (and there must be one-to-one correspondence). For risk
assessment models, historical outcome data regards the occurrence of fungus or pest problems in
past years (epidemiological data); or for crop growth models, historical outcome data regards crop
yield in past years. In this methodology, the agricultural model (i.e., the engine or core of this model)
is fundamental because it will be used to obtain evaluations of how well particular model parameter
settings work in the given region (i.e., with the given data). In particular, the intelligent search
method will repeatedly call upon this model engine as it constructs new model parameter settings
that need to have their worth evaluated. This methodology has the capability to address many types
of agricultural models: risk assessment models, damage prediction models, crop growth simulation
models, etc. The intelligent search method is an important part of this component because, in this
particular domain of agricultural models, knowledge of the domain is often hard to codify (i.e., ’rules
of thumb’ are vague and difficult to construct), and the selection of an intelligent search method can
help to alleviate this difficulty. This is due to the fact that intelligent search methods do not rely on
’rules of thumb’, rather, rules are not required and these methods can actually facilitate the user in
identifying ’rules of thumb’. The selection of the actual intelligent search method to be employed
was made among the following possible methods: hill-climbing, simulated annealing, and genetic
algorithms (GAs). In the end, GAs were selected as the most desirable method based on the
arguments given in Goldberg (1989), Grefenstette (1985, 1987), and Schaffer (1989).
4. AGRICULTURAL MODEL-GA (AGMOD-GA) To allow a GA to search the space of an agricultural
model’s parameters, the agricultural model is linked to a GA, and the GA uses the model as the
evaluation function. Furthermore, the model uses the historical situation data (as this is necessary to
run the model in the given historical years), and the GA additionally uses the historical outcome data
(discussed earlier) in combination with the output of the model. Whenever the GA wants to evaluate
one instance of model parameter settings, the agricultural model is called, and the final outcome is
returned through an objective function to the GA so that a fitness can be computed. The resulting

13
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

general component created by employing this combinational methodology can be called an

’Agricultural Model-GA’ or an AGMOD-GA. Figure 1 illustrates an agricultural model and a GA linked
to form an AGMOD-GA.
Figure 1. Structure of an AGMOD-GA
The function of the AGMOD-GA is to find near-optimal model parameter settings for the given
desired behaviour (i.e., matching the given historical outcome data). There are three main steps
involved in the execution of a typical AGMOD-GA. First, the agricultural model and the GA are
initialized. With the simple GA implemented in this case, an entirely random initial set (i.e.,
population) of parameter settings is generated. This has the effect of starting the search in a number
of different random points in the space. A collection of random starting points does not have a
negative effect on GA performance because a GA searches from many different point at the same
time, not just from one point. The second step in a typical AGMOD-GA is the fitness computation
(i.e., valuation of each population member’s worth). This involves taking each GA population
member and executing one or more model executions using the model parameter settings
represented by this member. These model executions utilize the user-provided historical situation
data, with one execution initiated for each one of these sets of data. The outcomes from these
model executions are compared against the user-provided historical outcome data (which is the
target). The further the model outputs are from the historical outcome data, the lower the fitness,
and inversely, the closer the model outputs are, the higher the fitness. This fitness evaluation step is
executed many times because new population members are continually being generated by the GA.
Fitness evaluation is usually continued until the GA has converged on a suitable optimal or quasi-
optimal solution. The last step is the evolution of the GA population. This involves applying
operations to the population members. The three operators used in a typical GAs are reproduction,
crossover, and mutation. They act by treating the GA bit strings (which represent model parameters)
in a way analogous to the evolution of chromosomes in genetics (Goldberg, 1989).

5. APPLICATION OF THE METHODOLOGY

An example of applying the above described methodology to create a real AGMOD-GA component is
given. To put this example in context, the project under which this methodology was developed
(Project SYBIL) and the DSS which utilizes this methodology (one of the SYBIL DSSes which focuses on
grapes and apples) are outlined.

5.1. Description of Project SYBIL

EC Project SYBIL (consisting of five partners from four countries) involves the implementation of
computerized decision support systems (DSSes) to assist farmers in intelligently governing their
crops such that environmental impact is reduced and economic returns are increased. Existing agro-
meteorological computer models from multiple sources are integrated into the portable, user-
friendly DSSes designed to assess the risk of a crop to pest and fungus damage. By evaluating this
risk, the farmer has the option to apply pesticides and fungicides only when needed and avoid using
these, often environmentally damaging, chemicals blindly on a regular basis or when the risk of pest
and fungus damage is small. This evaluation has the potential to save the farmer both time and
money because expensive chemicals will not be applied when they do not benefit the crop.

5.2. DSS Description

The SYBIL DSS described here (which includes the AI methodology discussed) is targeted to grape
and apple growers. Figure 2 displays the first screen of this DSS. The model focused on for illustrating
the adaptation methodology described here will be the P.R.O. model for grapes.
Figure 2. The System’s Main Screen
5.3. Description and Origin of the P.R.O. Model

14
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

The P.R.O. (Plasmopara Risikoprognose Oppenheim or Plasmopara Risk Oppenheim) model for
grapes was the first model selected for the application of the adaptation/localization methodology
discussed above.
This analytical model is a biological life cycle model that simulates the infection and growth of
downy mildew (viz. Plasmopara viticola, also called peronospora) on grape vines based on
meteorological conditions. The model was developed in Rheinhessen, Germany by Dr. Georg K. Hill
(Hill 93). It was designed to help growers determine when it is necessary to spray grape vines against
peronospora. The model had been used by multiple Rheinhessen region farmers with good results;
that is, the information provided to the farmer has assisted in the making of intelligent decisions
about when to perform the first spray of the season against peronospora. The goal is to overcome
the habit (which is not based on temporal information) of performing the first spray early in the
season (possibly around May), which is often before it is necessary. This goal is approached by using
the P.R.O. model to produce interpreted-operational temporal information (i.e., useful up-to-date
information about the status of the peronospora growth), then examining this information, and
deciding if it necessary to spray at the current moment, or if spraying can be delayed (possibly many
weeks beyond when growers would traditionally perform the first spray) because the grape vines are
not currently at risk to being damaged by peronospora. In the common caseswhere spraying can in
fact be delayed beyond when an agriculturalist would normally spray, the overall number of
interventions and amounts of chemicals sprayed on the crop are reduced. Agriculturalist using
this model in the region around Rheinhessen have been able to save between one and four spray
applications per year, with an average saving of two (Hill 93).
5.4. Results of Transporting the P.R.O. Model
After deciding that the P.R.O. model was a good choice for inclusion into the DSS (and therefore a
good choice for trying to transfer this model between countries), an instantiation of the model (with
only small changes so that the model would accept other types of meteorological data) was
programmed into the DSS, and test runs were made with various data from other regions (e.g.,
Würzburg, Germany and Trentino, Italy). Upon running these tests, it was found that the output
values (which in the case of the P.R.O. model are: the primary infection date, the end of the
incubation period, a list of special night occurrences, and a recommended spray date), were
inaccurate in the new regions. That is, the P.R.O. model outputs were rejected by agricultural
experts based on their historical epidemiological data (more generally, their historical outcome data)
and general knowledge of when epidemiological events occur in their regions.
For example, Table 1 displays the results from running the P.R.O. model with data from an area
inside the Trentino region of Italy. As this table shows, the dates produced by the original P.R.O.
model using original model parameter settings (i.e., model parameter settings selected by Dr. Hill for
the Rheinhessen area) (these dates shown in the column titled "Case 1") for data coming from
Trentino, only approached the dates known to be correct from observations done by agricultural
experts in Trentino (these dates shown in the column titled "Actual Dates") for the primary infection
dates (rows titled "Prim Inf 19xx"). For the recommended spray dates (rows titled "Rec Spray 19xx"),
the model could not even produce estimates of this date (with this data from Trentino) for two out
of the three years in which actual dates were available for comparison. Therefore, the model in this
state is of little use to agriculturalists in Trentino since it is generally not able to produce an accurate
estimate of the recommended spray date. Additionally, the difficulties observed in this case also held
true for data taken from other regions, so overall the P.R.O. model was problematic because it did
not give accurate output when run in regions external to where it was developed.

Multi-Crop Plant Growth Modeling for Agricultural

15
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

Models and Decision Support Systems

EXTENDED ABSTRACT
Agricultural models and decision support systems are becoming increasingly available for a wide
audience of users. The Great Plains Frameworkfor Agricultural Resource Management (GPFARM)
DSS is a strategic planning tool for farmers, ranchers, and agricultural consultants that incorporates a
science simulation model with an economic analysis package and multi-criteria decision aid for
evaluating individual fields or aggregating to the entire enterprise. The GPFARM DSS is currently
being expanded to include:-
1) better strategic planning by simulating a greater range of crops over a wider geographic range and
management systems,
2) incorporating a tactical planning component, and
3) adding a production, environmental, and economic risk component.

The plant growth component within the science simulation model is subdivided into separate
submodels for crops and rangeland forage. User requirements have determined that the DSS must
be easy to use in terms of setup, and therefore little parameterization or calibration for a specific site
can be required. Based on evaluation of both the crop and rangeland forage growth module of
GPFARM, improvements are needed to more accurately simulate plant responses to varying levels of
water availability. This paper presents our approach and some preliminary results for improving the
plant growth models. Our approach is based on using the stand-alone
plant growth model derived from the Wind Erosion Prediction System (WEPS), which is based on the
EPIC plant growth model. Steps that should improve the plant growth models include
1) incorporate modifications from work done to other models that are based on the EPIC plant
growth model (e.g., GPFARM; Water Erosion Prediction Project, WEPP; ALMANAC; and Soil and
Water Assessment Tool, SWAT), and
2) thoroughly evaluate how the plant processes are represented in these models. Deficiencies in
adequately simulating plant growth responses to water availability can fall under two general
categories: inadequate quantification of the process or omission of a needed process in the model.
High priority needs identified to date
include:-
1) seedling emergence,
2) phenology,
3)biomass generation,
4) biomass partitioning,
5) root growth, and
6) plant stress factors.

Initial work has created stand-alone submodels for predicting seedling emergence (as a function of
soil water and thermal time) and phenology (by predicting specific growth stages and responses to
different levels of soil water availability). Evaluation of alternative approaches for generating
biomass (e.g., radiation use efficiency, transpiration use efficiency, plant growth analysis), biomass
partitioning (e.g., modifications to generating LAI
and partitioning coefficients partly based on better phenology prediction), and stress factors (e.g.,
single-most limiting, additive, multiplicative) is underway. We envision that these modifications
and enhancements should improve model responses to varying levels of soil water availability.

GREENHOUSE ENVIRONMENTAL CONTROL SYSTEM WITH A

16
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

CROP MODEL AND AN EXPERT SYSTEM

Abstract:
Most greenhouse controllers are for automating greenhouse operation, and few crop models and
expert systems have been utilized in greenhouse control programs to maximize the production of
the crop grown in the greenhouse. This paper shows a way of controlling the greenhouse
environment using a built-in crop model and an expert system.

The new control system produced reasonable temperature set values. Although the absolute values
from the system needs to be verified by sequential, seasonal experiments, it showed the potential
for automation in the optimization of greenhouse production.

GREENHOUSES DETECTION USING AN ARTIFICIAL NEURAL NETWORK WITH A VERY HIGH

RESOLUTION SATELLITE IMAGE

ABSTRACT:

Detecting and locating greenhouses in south-east of Spain is very important for politicians and other
persons who may take decisions about management of natural resources and who must design
agricultural development plans. Agriculture is one of more important economic activities in this
zone, and till now, development and disposition of new greenhouses was uncontrolled. In this
paper, we present a methodology to detect greenhouses from 1.5 m pixel size QuickBird image,
based in Artificial Neural Network algorithm. Thanks to the information introduced as training sites,
we “teach” to the mathematical model to classify the image considering its radiometric and wavelet
texture properties. This assessment is known as training, and the algorithm to obtain it, back-
propagation. Classification accuracy was evaluated using multi-source data, comparing results
including and no-including wavelet texture analysis. We conclude that some texture analysis can not
improve classification accuracy but if one choose correctly parameters and texture model, it can
become better. Actually we are working on automatic detection and actualization of greenhouses
distributions.

1. INTRODUCTION
Classification is the process by which we develop thematic maps from remote sensors images.
Traditionally this process was reached applying visual interpretation and drawing its boundaries
manually. Nevertheless with computer apparition, scientists focused in computed aided
interpretation. Information obtained from classified image can help us to designing of development
planning or to take decision about natural resources anagement. In this work, located in Campo de
Níjar region, in south-east of Spain, classified image will help to plan agricultural development or to
know greenhouses distribution changes due in last years. Greenhouses are
structures with the aim of protecting horticultural products of environments agents, mainly the win.
Its plastic roofs have a characteristic radiometric behaviour in which classification algorithms base
to separate this class of other different classes. Nevertheless, angle vision, plastic chemical
composition, age, and photosynthetic activity under plastic can change dramatically it spectral
signature. Besides, greenhouse’s owner paint plastic roof with white colour to decrease sun
radiation inside in summer time. Due maintenance operations between different crop cycles, plastic
roof may temporally disappear in greenhouses. So, all this motives can deteriorate accuracy in
greenhouse classification. There are two traditional approaches in classification of images:

17
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

supervised and unsupervised. The first one classification of pixel based on characteristics of classes.
To characterize a class, operator must to delineate pixel groups corresponding to each interesting
class, called training sites. So, a pixel will belong to the class more statistically similar to own
properties. In the second one, classification algorithm produces more frequent land cover by the
clustering method. Artificial Neural Network is a supervised classification method, recently applied
to land use/cover change detection (Xiou et al., 2002). This is a non-linear mathematical model that
imitates the way in which human brain interprets graphical information.
This particular parcel of Artificial Intelligence doesn’t require hypothesis a priori about distribution
functions or another statistical assumptions. Besides, thanks to the previous learning approach, a
neural network is able to classify unknown data. The aim of this work was to design an appropriate
methodology to obtaining classified images from very high resolution satellite. The resultant
classification is focused in greenhouses class in south-east of Spain and so, we studied the best
texture analysis to improving accuracy. Actually we claim to get automatic change greenhouses
cover detection to adapt it to actualization cartographic and thematic information.
2. AREA OF STUDY
Campo de Níjar is a region located in province of Almería (Spain) with an approximated surface
about 20.000 ha
(Figure 1).
Figure 1. Area of study Here, there is an intensive agricultural production system based on
greenhouses structures. This fact characterizes the landscape, besides coppice natural vegetation,
disperse urban cover, a soft.

Content 5:-
sectors in agriculture

 Agricultural Research
 Agro-Meteorology
 Agricultural Marketing
 Agricultural Engineering & Food Processing
 Agricultural Extension and Transfer of Technology
 Credit and Cooperation
 Crop production & protection Environment & Forest
 Fertilizers and Manure
 Fisheries
 Irrigation and Drainage System
 Livestock, Dairy Development & Animal Husbandry
 Rural Development & Planning
 Soil and Water Management

18
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

 Watershed Development
 Wasteland Development

Why is watershed management planning important?

When water flows across the land during rainfall events, it carries fertilizers, loose soil, litter and other
pollutants into streams and other surrounding water bodies. As a result, everything we do on the land
affects the quality and quantity of our water resources and the natural systems that surround us.
Therefore, the natural resources and the quality of life in our communities are directly affected by the
way we plan for and manage land use activities. Watershed management planning provides opportunities
to address water quality and habitat issues within the physical boundaries of a watershed rather than
political boundaries. It is an inclusive approach to support environmental protection, quality of life issues,
and economic development—using the watershed as a holistic planning framework.

Content 6:-
Conclusion
The artificial intelligence (AI) methodology discussed addresses model technology transfer (i.e., the
moving of functional and useful agricultural models that are developed in one location to a new
location so they can be used in this new location). In particular, it addresses one of the major
difficulties within thisarea, namely, model accuracy; that is, it addresses the instance when a useful
model is transported from a region where it is functioning accurately (viz. producing accurate
recommendations, results, and/or indicators) to a new region where it subsequently does not
function accurately.

The methodology employs four main elements, with a genetic algorithm (GA) at the center. By
employing this AI component in conjunction with the engine of an agricultural model and historical
data, model parameter settings can be adapted to new locations, allowing the model to give
accurate results when run in the new location. Specifically, the module created by this methodology
can be applied to localize models by deriving new model parameter settings that can be employed in
the particular location to give good suggestions/decision support.
With the assumption that model technology transfer is an advantageous action (refer to (Jacucci, et
al., 1994) for an elaboration of advantages and disadvantages in transporting models between
regions), this AI methodology has been found to efficiently addresses this issue and improves the
current state-of-the-art in model technology transfer. This has been shown through an example
which describes the utilization of this methodology within one of the decision support systems

19
[Type text] Page
 IT Project: Artificial Intelligence In Agriculture

(DSSes) developed under EC Project SYBIL. In particular, this DSS was designed to provide temporal
information to assist grape and apple agriculturalists in the management of crops with respect to
controlling fungus and pests. Specifically, this methodology has been applied to an instantiation of
the P.R.O. model that is programmed into one of the SYBIL DSSes. This model addresses the
infection and growth of Plasmopara viticola on grape vines, and has the capability to provide
information to a farmer so that decisions regarding when to apply fungicides are made more
intelligently. Due to difficulties in transporting this model to run in regions outside where it was
developed, our methodology to adapt model parameter settings was employed. The testing of new
model parameter settings produced by this adaptation showed that this methodology has great
potential to localize model parameter settings, and this should assist in achieving the goal of making
sound models more widely available.

20
[Type text] Page