Understanding the Helicoverpa Armigera Pest Population Dynamics related to the chickpea crop using Neural Networks Rajat Gupta, B Narayana, Krishna Polepalli, G. Ranga Rao, C Gowda, Y. Reddy and G.Rama Murthy

1
Understanding the Helicoverpa Armigera Pest
Population Dynamics related to the chickpea crop
using Neural NetworksRajat Gupta, B
Narayana, Krishna Polepalli, G. Ranga Rao, C
Gowda, Y. Reddy and G.Rama Murthy
2
INDEX

• Introduction
• Objective
• Motivation
• Pest Dynamics
• Models Developed in the Past
• Why they Failed ?
• Preliminaries
• Dataset Description
• Results
• Mean Graphs
• Majority Voting
• Conclusion

3
Introduction
Helicoverpa Armigera
Chickpea Crop
4
Participating Organizations
International Institute of Information
Technology (IIIT)
International Crop Research for the Semi-Arid
Tropics (ICRISAT)
5
Objective

• To develop a pest forecasting mechanism by
  extracting pest dynamics from Pest surveillance
  database using Knowledge Discovery and Data
  Mining techniques.
• To understand the interaction of various factors
  responsible for pest outbreaks.

6
Motivation

• Insect pests are the major cause of crop loss.
• The crop loss due to lack of advance information
  about pest emergence often leads to financial
  bankruptcy of the farmers.

7
Pest Dynamics

• Highly dynamic nature of the Pest
• Ability to adapt to new conditions quickly
• Can migrate to long distances
• Hibernate when condition are not favorable
• Feeds on wide variety of hosts

8
Models Developed in the Past

• Techniques used were essentially Statistical
  (Correlation and Regression Analysis)
• T.P. Trivedi had proposed a regression model to
  predict the pest attack.
• Model seems to work only for some years
  (1992-1994)
• Correlation analysis was used by C.P. Srivastava
  to explore the relationship between the rainfall
  and pest abundance in different years.
• The technique is not effective as the attributes
  dont follow normal distribution

9
Why they FAILED?

• Techniques used are able to capture only linear
  relationships.
• Problems with the dataset (noisy data)
• All events are treated equally

10
Pest Surveillance Dataset

• Helicoverpa armigera pest data on Chickpea crop
  provided by International Institute for Semi-Arid
  Tropics (ICRISAT).
• The dataset spans over a period of 11 years
  (1991-2001).
• It contains information on 17 attributes.

11
Dataset Description

• These Dataset contains 17 attributes which
• can be classified as
• Weather parameters
• Pest Incidence
• Farm Parameters

12
Weather parameters

• Rainfall
• Relative Humidity
• Minimum Temperature
• Maximum Temperature
• Sunshine hours.

13
Pest Incidence

• Eggs/Plant
• Larvae/Plant
• Light Trap Catch
• Pheromone Trap Catch

14
Farm Parameters

• Zone
• Location
• Area Surveyed
• Plant Protection
• User
• Season

15
Neural Networks

• A Neural Network is an interconnected assembly of
  simple processing elements, units or nodes,
  called neurons.
• The processing ability of the network is stored
  in the inter-unit connection strengths or
  weights.
• Learns from a set of training patterns.

16
Multi Layer Neural Networks
Inputs
Outputs
Hidden Layer
17
Why Neural Networks ?

• Neural Networks dont make any distributional
  assumption about the data.
• It learns the patterns in the data, while
  statistical techniques try to do model fitting.
• This makes neural network modeling a powerful
  tool for exploring complex, nonlinear biological
  problems like pest incidence.

18
Data Preprocessing

• Data Selection
• Data Reduction
• Null Values
• Data Transformation
• Normalization
• Fourier Transform

19
Neural Network Training

• Dataset
• Advance Dataset (X) where X 0,12,3.
• Training Dataset - 8 years (1991 - 1998)
• Test Dataset - 3 years (1998 - 2001)
• Learning Algorithm Levenberg-Marquardt.
• Bayesian Regularization
• Hyperbolic Tangent Sigmoid function in hidden
  layers (2 hidden layers)
• Linear Transfer function in outer layer

20
Datasets Generated

• Advance (0)
• Advance (1)
• Advance (2)
• Advance (3)

21
Average R-value
Dataset Average R-value (for 15 models)
Advance(0) 0.91
Advance(1) 0.96
Advance(2) 0.91
Advance(3) 0.75
22
Larvae/Plant -Advance(0)
23
Larvae/Plant -Advance(1)
Larvae/Plant -Advance(1)
24
Larvae/Plant -Advance(2)
Larvae/Plant -Advance(2)
25
Larvae/Plant -Advance(3)
Larvae/Plant -Advance(3)
26
Majority Voting(40)
Hits Miss False Alarm
Advance(0) 27 4 6
Advance(1) 29 1 4
Advance(2) 27 2 12
Advance(3) 22 6 15
27
Majority Voting(50)
Hits Miss False Alarm
Advance(0) 27 4 6
Advance(1) 28 2 2
Advance(2) 26 3 11
Advance(3) 22 6 12
28
Majority Voting(60)
Hits Miss False Alarm
Advance(0) 25 6 6
Advance(1) 26 4 2
Advance(2) 26 3 11
Advance(3) 21 5 12
29
Conclusion

• We can now predict the pest attack using Neural
  Networks two weeks in advance with high
  probability.

30
References

• Data Mining Concepts and Techniques By Jiawei Han
  and Micheline Kamber
• Neural Networks A Comprehensive Foundation By
  Simon Haykin
• Applied Multivariate Statistical Analysis By By
  Richard Arnold Johnson, Dean A. Wichern, Dean W.
  Wichern.
• Advanced Engineering Mathematics By Erwin
  Kreyzig.
• Models for Pests and Disease Forecasting -
  T.P.Trivedi, D.K Das, A.Dhandapani and A.K.
  Kanojia
• Das D.K , Trivedi T.P and Srivastava C.P 2001.
  Simple rules to predict attack of Helicoverpa
  armigera on crops growing in Andhra Pradesh,
  Indian Journal of Agricultural Sciences 71
  421-423.
• Zhongua Zhao, Zuorui Shen .Theories and their
  applications of Stochastic Simulation Models for
  Insect population Dynamics. Department of
  Entomology, The China Agricultural University.
  http//www.cau.edu.cn/ipmist/chinese/lwzy/xuweil
  w/xwlw-zhzhao.htm
• Agarwal, R., Imielinshki, T., Swami, A. 1993.
  "Mining association rules between sets of items
  in large databases" .Proc. of ACM-SIGMOD Int'l
  Conf. on Management of Data 207-216.
• Agarwal, R. Srikant, R., 1994, Fast Algorithms
  for Mining Association Rules, Proc. of the 20th
  VLDB 487-499.