3. Over view:
1.History
2.Tools for decision making in IPM
3.Decision Support Systems (DSSs)
4.Case studies
5.Advantages
6.Limitations
7.Future scope of research
4. History for development of IPM and its models
• In late 1970ʹs IPM concept came into light after the foundation of IOBC for
the management of agro ecosystem
• Later strict actions taken by the European union (EU) on limited use of
pesticides to reduce risks to human health and the environment
• Since 1980s application of Decision Support Systems gained importance after
Integrated Pest Management (IPM) models failed in technology transfer to
farmers field from researchers findings
• IPM relays on the integrated evaluation of dynamic processes characterising
the agriculture ecosystems towards a long term sustainability of crop
production and pest management in a economically and ecologically justified
way (Barzman et al., 2015)
• Farmers perceive IPM as complex, time and labour intensive, difficult to
implement process because of its limitation of complexity in decision making
(Parsa et al., 2014)
5. • Decision making in IPM involves three levels
(strategic, tactical and operational) (Rossi et
al., 2012).
• Strategic level long term decision making at
farm and field level like crop rotations and
variety to be grown etc., will be taken by
farm owners or directors.
• Tactical level decisions are taken by farm
managers in which different methodologies
that can be used to implement a strategy are
considered, and it requires day-by-day
decision-making in response to the crop
overall status (e.g., treatment against a
disease outbreak).
• Operational level, fast responses with
respect to the crop or within the crop
conditions (e.g., treatment to be adapted to
the size of the canopy) or unpredictable
events (e.g., rainfall that delays the
treatment of a pest) are selected and
implemented by employees who implement
crop protection measures.
6. Framework for the implementation of IPM, based on the EU Directive on Sustainable Use of Pesticides (modified
from European Commission, 2009)
7. Tools for decision making in IPM
• Most of the times decision making is mostly intuitive process rather than
reasoning or information based and it may be proactive (strategic) or forced
by an event (operational).
• Decision tools help decision makers in solving complex problems in
agriculture (Narayana 1995).
• To support the decision making of users a large number of tools developed by
public and private sources named decision tools (DTs) including:
1. Population dynamics
2. Epidemiology models
3. Risk algorithms
4. Intervention thresholds
5. Warning services
6. Onsite devices
7. Decision rules
8. Decision support systems (DSSs)
Magarey, 2002
8. • Warning services are provided by extension services or other public
agencies without considering the peculiarities of each farm at regional
scale in fixed time intervals by push and pull approaches through mail,
fax, e-mail, SMS etc.
Organization and information flow in the warning service of the Emilia-Romagna (North Italy) provided by the
regional plant protection organization
9. • On-site devices provide information at farm level by means of one way,
plug approaches
• These devices usually incorporate specific models and weather
sensors collect the model input data and produce output specific for
the site where the device is located
• There is lack of reliability of results as models are taken from literature
and lack specific validation for local conditions.
10. Decision-support system (DSS)
• DSS is an interactive computer-based system that helps decision makers
utilize data and models to solve unstructured problems under complex and
uncertain conditions facing during daily operations and while taking long
time strategic decisions.
• All sources of information regarding crop production will be collected,
organized, and integrated for further analysis and interpretation to
recommend the most appropriate action or action choices (Agrios, 2005)
• Agro data includes
• Weather records such as temperature, relative humidity, and weather output
• Biological data like pest population data and disease symptoms
• Biophysical data such as plant-growing phenological stage
• Geophysical data like season climate, soils, terrain, and other characteristics
• Socioeconomic information which often include farmer survey results and census
information, chemical registrations, residual levels of pesticides, commodity prices
11. • DSS can be further used to model agroecosystems and to provide
decision at the farm level. This may contribute to optimization of
regional specific crop productivity and ensure the rational utilization
of innate resources and rural sustainability
12. Key elements of DSS
Expert knowledge
Management models
Timely data (Sonka et al.,1997).
Success of any DSS depends on
Efficiency to consider various models for interpretation of data
Easy and quick accessible user interface
Timely updating the system according to the suggestions given by the experts and
producers
Maintenance of its servers and web portals
13. Major Fields of DSS
Personal Decision Support Systems (PDSS): Usually small-scale systems that are
developed for specified managers
Group Support Systems (GSS): They use combination of DSS technologies to facilitate the
effective decision process
Negotiation Support Systems (NSS): Here primary focus remains on negotiation between
opposite perceptions
Intelligent Decision Support Systems (IDSS): It uses artificial intelligence techniques to
facilitate decision
Knowledge Management-Based DSS (KMDSS): They pro-vide knowledge storage,
retrieval, transfer using organizational memory and inter-group knowledge access
Data Warehousing (DW): Systems that provides the large-scale data infrastructure in
multiple formats for decision support
Enterprise Reporting and Analysis Systems: Enterprise focused DSS including executive
information systems (EIS), business intelligence (BI), and corporate performance manage-
ment systems (CPM). BI tools access and analyze data ware-house information using
business intelligence software, query and analysis tools (Nelson et al., 2005)
14. Classification of Decision Support Systems
Author Classification Features Example Criterion
Bhargava and
power (2001)
Model-driven DSS Emphasizes on access to and
manipulation of statistical,
financial, optimization or
simulations model.
Dicodess; production planning
management Decision Support.
Mode of
assistance
Communication-driven DSS Emphasizes communications,
collaboration, and shared
decision making support.
Microsoft’s Net Meeting or Groove;
Basic Group Decision Sup-port System.
Data-driven DSS Emphasizes on access to and
manipulation of time series data
Data Driven DSS with OLAP
Document-driven DSS Manages, retrieves and
manipulates unstruc-tured
information in a variety of
electronic formats
Search engine; Online Analytical
Processing
Knowledge-driven DSS Specialized problem solving
expertise stores as facts, rules,
procedures etc.
MYCIN ; EXSYS; DENDRAL.
15. Cont..
Author Classification Features Example Criterion
Power (2000)
Enterprise wide DSS Linked with large data warehouse,
which serves many managers
Web-based DSS
Scope
Desktop DSS Single user, small system that runs on
managers Personal Computer
Visible calculator
Haettenschwiler
(2001)
Active DSS It aids the process of decision without
bringing out explicit suggestions or
solutions
Walmart
User
relationship
Passive DSS Brings out explicit suggestions as Well Exsys
Cooperative DSS Modifies, completes or refines the
decision suggestions
Co-op
Holsapple &
Whinston
(2001)
Text-oriented DSS Works on text as input Management,
planning and
control Type of
Inputs used
for decision
making
Database oriented DSS Has a database in the back end for
Inputs
ONVAREF
Spread sheet oriented
DSS
Uses spread sheet as inputs e.g. Excel Optimmization
solver add in for
Microsoft EXCEL
16. Author Classification Features Example Criterion
Holsapple and
Whinston
(2001)
Solver Oriented DSS Mainly designed for solving
problems. e.g. Linear
Equations
Brandaid
Type of Inputs used
for decision making
Rule oriented DSS Uses inputs in the form of
rules based on reasoning
NuMaSS
Component
Oriented DSS
Hybrid System that includes
two or more of basic five
structures described by
Holsapple & whin-ston, 1996
GRAM++
Hackathorn &
Keen (1981)
Personal Support Supports only one user ONVAREF
Scope
Group Support Supports group of user Mindsight; Group
Systems ; SAMM;
PLEXSYS
Organizational
Support
Supports an organization as a
Whole
EXPRESS
Cont..
17. Role of plant pest and disease models for decision support
• For plant disease epidemics along with temperature biotic factors such as wet
conditions, relative humidity, wind speed are also influencial
• Disease models are trained to get data about the theoretical appearance and the
quantity of inoculum changes during the growth season
• Fungi spores germinate and cause infection only when they are kept at a certain
period at favourable temperatures and leaf wetness for certain hours. Hence,
plant disease forecasting models provide output risk levels, which are helping the
growers to assess the risk of disease epidemics and to avoid unnecessary
treatments with fungicides
• To date, the most common monocyclic and polycyclic growth descriptions growth
include: monomolecular, exponential, logistic, and Gompertz models
• More complex simulation models may additional include the life cycle of the host
crop as well as the influence of several other biotic and abiotic factors
18. Data processing and forecasting algorithms : modus
operandi of computer-aided decision support
• To exploit large datasets to be used as inputs for a certain population
model implies the development of algorithms, which serve as a basis to
develop computer programs to simulate pest phenology
• Algorithms are computer programs that handle the data and transform
them into relevant and understandable information
• Database management system software (DMSS) is traditionally used for
such purposes. The core of the software is a “prediction algorithm,” which
is a sequence of logical operations under certain predefined rules
• The algorithm then picks out the suitable data entry among available
information and stores them in a local host
• In a second step, the algorithm uses these data as input for the pest model
to simulate population projections and service warnings
19. Basic logical operations (flow diagram) of phenology model
simulating development of fungal disease (i.e., Class: Oomycota) and
related infection risk warnings (Magarey et al 1991)
Cont……..
• The algorithm is associated with data processing
information, the values are interpreted from an
input source, written to an output device, and/or
stored for further processing. Next, subroutines
are performed which include the setup of
“weather rules’’
• Improving simulation models that integrate the
dynamic effects of climate variables on pest
population can be automated through the
development of algorithms that serve as small
computer programs
• Usually, the algorithm is represented with a form
of diagrams, referred to as flowchart
21. 2)When check disease is clicked it asks for type of crop sown
i)Field crops
ii)Commercial crops
iii)Fiber & Jute crops
iv)Horticultural crops
1)Home Page
3)When type of crop is given it shows the symptoms of different diseases present in that type of crop Here(for
instance horticultural crops is selected here)
4)Farmer can select the symptoms which he observed in his plant
5)F-Measure is calculated to predict the disease
6)Based on the prediction diagnosis is given
Description on working of DSS:-
26. Based on the symptoms given by the farmer system predicts the disease of the plant for that purpose data mining techniques
are used .In this process F-measure is calculated to measure the accuracy or chance of being a particular disease
True positives=> number of given symptoms by
farmer matched with those of a disease in the
database.
False positives=> number of given symptoms by
farmer not matched with those of a disease in
database.
False Negatives=>No of symptoms present for a
disease in database but it is not given by Farmer.
Disease TP FP FN Precision Recall F-
Measure
wilting 4 1 0 0.8 1 0.89
Flooding 3 2 2 0.7 0.7 0.7
necrosis 3 2 3 0.7 0.8 0.8
Root rot 1 4 1 0.2 0.5 0.285
27. System returns the diagnosis of the disease with maximum F-Measure value
29. Case study 1. PLANT-Plus: Turn-key solution for disease forecasting and
irrigation management
• PLANT-Plus was developed initially by Dacom as a DSS for management of
Phytophthora infestans and Alternaria solani since 1994
• The PLANT-Plus platform enables communication of data between farmer,
consultant, processor and other accredited users through user interface like
Windows software (PC based) and Internet Server application and can configure a
variety of output types such as SMS text messaging, Fax and Email warnings
• PLANT-Plus offers an integrated five day weather forecast which provides a
predictive risk assessment for the coming days with on-farm, automatic, weather
data
• PLANTPlus uses a biological model that is based on the lifecycle of the fungus and
combines infection events with the unprotected part of the crop
• The model will recommend when to apply a new spray and what type of chemical
to use: contact, translaminar or systemic
30. • Plant PLUS Model
Unprotected part of
the crop
Growth of new
leaves
Degradation and
wear off of
chemicals
Infection events
of the disease
Formation of spores
on each infected leaf
Ejection and dispersal
od spores into the air
Germination of spores
and penetration into
unprotected leaves
Treatment recommendations
31. Case study :3 Decision Support Systems for Plant Disease and
Insect Management in Commercial Nurseries in the Midwest
• Ag-Radar: Web-based weather charting and pest management
system developed by Glen Koehler at the University of Maine
• Ag-Radar include apple scab (Venturia inequalis), Fire blight [Erwinia
amylovora and sooty blotch (disease complex, Peltaster
fructicola, Geastrumia polystigmatis, and Leptodontium elatius)
• Ag-Radar users must provide key biofix (growth stage event) dates as
the starting point
32. • Output includes a variety of textual, graphical and tabled summaries
of weather, disease and insect reports
• There are multiple scenarios provided for fungicide and antibiotic
spray and resprays
33. • NEWA : Network for Environment and
Weather Applications was developed by
Cornell University in 1995 and is operated by
the New York State IPM programme
• Forecasting models for Apple scab and grape
include phomopsis (Phomopsis spp.), black
rot, powdery mildew (Podosphaera spp.) and
downy mildew (Peronospora spp.) and also
for alfalfa (Medicago sativa L, cabbage ,
onion (Allium cepa L.) , potato (Solanum
tuberosum L.) and tomato (Solanum
lycopersicum L. )
• Output of NEWA includes a simple summary
graphic, which clearly indicates whether a
critical threshold is expected to occur within
the upcoming seven days (Small et al. 2015)
34. RIMpro (Relative Infection Method)
• RIMpro’s initial aim was to produce an apple scab infection simulation tool that would
provide a better epidemiological approach than that offered by Mills system ( Apple scab
predictive model) alone, that could run with any weather station
• RIMpro contains disease simulation models for apple and pear scab, Fire blight, powdery
mildew, sooty blotch, apple canker (Neonectria galligena) and Marssonia blotch
(Marssonina coronaria)
• Nursery crop diseases that RIMpro could be used to manage include apple scab, fire
blight and powdery mildew for crabapple cultivars
• Additionally, powdery mildew control for dogwoods, sycamore (Platanus spp.), and birch
(Betula spp.) is possible
• To use RIMpro a weather station must be added to the cloud-based self-service network
by the user
• By entering spray dates and conditions and the fungicide applied, RIMpro estimates
fungicide coverage and degradation
• RIMpro estimates the decline of the fungicide cover in time as a result of wash-off by rain
and dilution by leaf growth
36. Application of DSS for insect and pest management
The DSS provide decision support for holistic treatment of crop
management problems like
Crop rotation
Determining the optimum rate of sowing
Checking crop growth and development
Defining nitrogen fertilization in terms of fertilizer dose and
application schedule
Weed management actions
Making decisions about disease control
37. • During 1990s development of weather based DSS helps in lowered
risk of crop damage by diseases and pests and minimal dosage of
other inputs (Bouma E, 2007)
• In 1985 CSIRO developed CLIMEX model is used in 20 countries to
examine the distribution of insect, plants, pathogens and vertebrates
and has had numerous applications under practical conditions
(McCrown 2002)
• An insect pest forecasting tool, known as SOPRA, has been developed
with the objective of optimizing timing of monitoring, management
and control measures related to fruit orchards in Switzerland (Samietz
et al., 2007)
• In Europe numerous late blight advice systems like Negfry, Prophy,
Plant Plus and Simphyt exist to predict appropriate pesticide
application times for various crops including potato
38. Advantages of DSS
• Rather than assessing DSSs according to immediate economic
benefits, they should be assessed in terms of overall sustainability,
i.e., in terms of economic, environmental, and social sustainability
• Reduced costs for protecting their crops from pests and diseases
because of a reduction in the number of treatments
• Improved use of the natural resources (soil and water)
• Increased crop quality and quantity, thanks to a better management
of biotic and abiotic stresses
• Reduced labour needed for crop management & reduced costs for
external consultancy
39. Limitations of existing DSS
• DSS address specific problems, while crop managers have to face
wide range of problems
• Few DSSs fail due to problem in implementation like lack of sustained
use in a way that influences practice
• Lack of clarity about the role of DSS and organization problems
related to user support
• Due to poor communication between DSS developer and users or
models are sometimes pushed into service before they have been
sufficiently refined and validated
• Lack of user friendly interface and providing data in quantitative
terms, which growers found difficult to interpret
40. • Some DSS fail because of delay in data processing or tedious input
requirements
• Many DSS are not properly maintained and updated timely with new
results
41. Conclusion
The innovative nature of new generation DSSs is based on:
Holistic vision of crop management problems with the focus on all the
different individual operation issues (e.g. pests, diseases, fertilisation,
irrigation, canopy management)
Provision of information on the focus of the decision in the form of easy-
to-understand decision supports able to reduce uncertainty
Easy and fast access through the Internet
Two-way communication between users and the providers, which make it
possible to consider context-specific information
This concern about short-term economic benefits should now be
outweighed by the increasing interest in sustainable agriculture and by the
requirement that farmers follow new regulations governing environmental
conservation and safety