crop modeling is future in agriculture to tackle changing environment conditions and increase food security in the world. These models incorporate various factors such as climate, soil characteristics, agronomic practices, and crop physiology to predict crop yields, water usage, nutrient uptake, and other important parameters. Crop modeling helps in understanding the complex interactions between different variables affecting crop growth and assists farmers, researchers, and policymakers in making informed decisions related to crop management, resource allocation, and risk assessment.
Role of AI in crop modeling: Artificial Intelligence (AI) plays a significant role in enhancing crop modeling by leveraging advanced computational techniques to improve model accuracy, efficiency, and scalability. One of the most important aspects of precision farming is sustainability. Using artificial neural networks (ANNs), a highly effective multilayer perceptron (MLP) model. The most common type in crop modeling is DSSAT , DSSAT (Decision Support System for Agro-technology Transfer).The Decision Support System for Agro-technology Transfer (DSSAT) is a software application program that comprises crop simulation models for over 42 crops (as of Version 4.8.2) as well as tools to facilitate effective use of the models. The tools include database management programs for soil, weather, crop management and experimental data, utilities, and application programs. The crop simulation models simulate growth, development and yield as a function of the soil-plant-atmosphere dynamics.DSSAT and its crop simulation models have been used for a wide range of applications at different spatial and temporal scales. This includes on-farm and precision management, regional assessments of the impact of climate variability and climate change, gene-based modeling and breeding selection, water use, greenhouse gas emissions, and long-term sustainability through the soil organic carbon and nitrogen balances.In conclusion, crop modeling stands as a crucial tool in modern agriculture, offering a systematic approach to understanding and predicting crop growth dynamics in diverse environmental conditions. By simulating the complex interactions between various factors influencing crop development, including climate, soil properties, agronomic practices, and genetic traits, crop models provide valuable insights for farmers, researchers, and policymakers.
4. Olericulture: Olericulture is the science of vegetable growing,
dealing with the culture of non-woody (herbaceous) plants for
food.
Vegetables play an important role in human nutrition(protective
foods)
They supply dietary fiber and are important sources of essential
vitamins, minerals, and trace elements. Particularly important
are the antioxidant vitamins A, C, and E.
India produces about 13 percent of the worlds vegetables (
horticultural crops contribute 17% to GDP)
5. Difficulty to grow crops
Use for manipulation and experiments that are impractical , too
expensive, too lengthy or impossible in real world.
Allow researchers to control environmental and experimental conditions.
Identify best management strategies( Through optimization)
Study long term effects of predictions and projections.
6. Map of world showing
in red are areas where
decrease in yields are
projected in future.
To tackle such
conditions in future
crop modelling comes
7. Model is a mathematical representation of real world.
Common in many disciplines, including the airplane
industry ,automobile industry, civil engineering etc.
The use of models in agricultural sciences is not been very
common .
Model stimulates or imitates the behaviour of a real crop
by predicting the growth of its components.
8. A crop model can be described as
a quantitative scheme .
Model simulates or imitates the
behaviour of a real crop .
Simple representation of crop.
crop model is expressed as
computer program.
9. Simulation is process of building models and analysing the
system.
Crop Simulation Models (CSM) are computerized
representation.
CSM simulated through mathematical equations .
crop models have great potential in practical use.
crop growth simulation , contains quantitative information
10. 1960
1965
1970
1977
1982
1994
1994
simple water-balance models
Model photosynthetic rates of crop canopies (De Wit)
Elementary Crop growth Simulator construction(ELCROS)
Basic Crop growth Simulator (BACROS) [de Wit and Goudriaan]
DSSAT( Decision support system for Agro-transfer technology)
ORYZA1 (Kropff et al., 1994)
India’s Ist crop model WTGROWS followed by the construction
of ORYZA1N
11. INPUT
• Genotype information , Soil information
• Weather informationManagement information
MODEL
• Based on mechanisms of plant growth and
development .
OUTPUT
• Biomass, yield , Water use, Nitrogen use and other
qualitative objectives.
WHAT MODEL CAN
PRODUCE
12. Statistical & Empirical Models
Mechanistic Models
Deterministic Models.
Stochastic model
Dynamic model
13. These model express the relationship between yield , yield
components and weather parameters.
In this system relations are measured in statistical
techniques(correlations)
These models give no information on the mechanisms that give
rise to the response.
Example:
14. Shows relationship between yield and weather parameters ,
but also the mechanism of these models.
Describes the behaviour of system in terms of lower levels
attributes (eg cell division)
Explain the relationship of influencing dependent
variables(soil,moisture, temperature)
Example :
15. Estimate the exact value of the yield( inputs and outputs
remain same)
Definite predictions for quantities ( e.g crop yield or rainfall
) without any associated probability distribution.
Example:
16. These models calculate the output at a given rate.
A probability element is attached to each level of output.
when variations and uncertainity reaches a high level , it
become advisible to follow stochastic model .
Gives an expected mean values as well as variance associated
with it.
17. Time is included as a variable and output is a function of
time .
Predict complex traits, like crop yield, for modern and future
genotypes in their current and evolving environments.
Designed to generate the interactions producing phenotypic
changes over the growing season
18.
19. :
• Predicting crop yields is a critical issue in agricultural production
optimization and intensification research.
• Accurate foresights of natural circumstances a year in advance can have
a considerable impact on management decisions regarding crop
selection.
• Using artificial neural networks (ANNs), a highly effective multilayer
perceptron (MLP) model.
• The model adjusts its weights and biases iteratively to minimize the
difference between the predicted crop yields and the actual crop yields
in the training dataset.
20. 1.Define goals: Agricultural system
2. Define system and its boundaries: Crop model
3. Define key variables in system:
State variables are those which can be measured. e.g. soil moisture
content, crop yield etc
Rate variables are the rates of different processes operating in a system.
e.g. photosynthesis rate, transpiration rate.
Driving variables are the variables which are not part of the system but
the affect the system. e.g. sunshine, rainfall.
21. cont.
4. Calibration:
Model calibration is the initial testing of a model and tuning it to reflect a
set of field data or process of estimating model parameters by comparing
model predictions (out-put) for a given set of assumed conditions with
observed data for the same conditions.
5. Validation:
Testing of a model with a data set representing "local" field data. This data
set represents an independent source different from the data used to
develop the relation
6. Sensitivity analysis:
Validated model is then tested for its sensitivity to different factors (e.g.
temperature, rainfall, N dose). This is done to check whether the model is
responding to changes in those factors or not.
22. Modeling helps us to understand, predict and control a
system in a more organised or methodological manner.
Models can help to identify areas where knowledge is
lacking, and can help to stimulate new ideas or approaches
for research.
Yield prediction and forecasting
Prepare adaptation strategies to minimize the negative
impacts of climate change.
Drive Efficiency :Proper usage of inputs occur that
increase the efficiencyof inputs.
23. Crop models are not able to give accurate projections
because of inadequate understanding of natural processes
and computer power limitation.
Models are not able to provide reliable projections of
changes in climate variability on local scale.
Crop models are not universal ( no site specificity).
Inappropriate for Heterogeneous plot.
Sampling errors also contribute to inaccuracies in the
observed data.
An ideal crop model cannot be developed because of
complex biological system
25. ).
The DSSAT is a software application program that comprises
crop simulation models for over 42 crops as well as tools to
facilitate effective use of the models.
The tools include database management programs for soil,
weather, crop management and experimental data, utilities,
and application programs.
The crop simulation models simulate growth, development
and yield as a function of the soil-plant-atmosphere
dynamics.
30. AquaCrop is a crop growth model developed by the Land
and Water Division of FAO to address food security and to
assess the effect of environment and management on crop
production.
AquaCrop simulates yield response to water of herbaceous
crops, and is particularly suited to address conditions where
water is a key limiting factor in crop production.
31.
32.
33.
34.
35.
36.
37.
38.
39. Tomato yield was observed to be higher under normal rainfall condition in
both Kharif and Rabi seasons compared to deficit and excess condition.
During the normal year the yield was 32.8 and 33.4 t ha-1 followed by 29.8 and 28.3
under deficit rainfall condition during Kharif and Rabi respectively. The low yield
was noticed under excess rainfall condition which was 27.9 and 25.1 t ha-1 during
Kharif and Rabi respectively.
V.Guhan*, V.Geethalakshmi , K.Bhuvaneswari , N.Kowshika
40.
41.
42.
43.
44. As a research tool, model development and application can
contribute to identify gaps in our knowledge, thus enabling more
efficient and targeted research planning..
Models are means to capture, condense and organize knowledge.
It helps to understand or foresee the behaviour of biological
systems on the basis of fundamental level of incorporation.
It offers dynamic, quantitative tools for analyzing the complexity
of agricultural systems.
Increase the efficiency of agricultural research and management
and improve agronomic efficiency and environmental quality.
Editor's Notes
1. when farmers have difficulty to grow crops in poor soils in harsh climate, to tackle such conditions crop models is used
2.
1. model is mathematical representation of real world