Title: Weather intervention-based pest forewarning model for increasing crop yield using Bayesian discriminant analysis

Authors: S.R. Krishna Priya; N. Naranammal

Addresses: Department of Statistics, PSG College of Arts and Science, Coimbatore, Tamil Nadu, India ' Department of Statistics, PSG College of Arts and Science, Coimbatore, Tamil Nadu, India

Abstract: Forewarning crop pests can help prevent crop damage, which helps to increase the crop yield. This paper is an attempt to forewarn the sucking pests of cotton crops such as aphids, jassid, thrips and whitefly. The data used for the study is the pest incidence of sucking pests on cotton from the years 2015-2016 to 2022-2023. A comparative study has been carried out using the Bayesian discriminant analysis with weather variables and weather indices for two groups as well as three groups. Regression model is built by taking the posterior probability obtained from both weather variables and weather indices, along with the trend as a regressor and pest incidence as a response variable for forewarning. The models are compared by goodness of fit measures. It has been identified that two groups of Bayesian discriminant analysis using weather indices performed better for aphids and jassid, while three groups using weather indices performed better for thrips and whitefly.

Keywords: forewarning; discriminant analysis; crop pest; posterior probability; goodness of fit; weather indices; meteorological parameters; sustainable agriculture; integrated pest management; cotton.

DOI: 10.1504/IJARGE.2023.142807

International Journal of Agricultural Resources, Governance and Ecology, 2023 Vol.19 No.4, pp.311 - 324

Received: 16 Jan 2024
Accepted: 31 May 2024
Published online: 22 Nov 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article