Climate-Driven Forecasting of Brown Planthopper in Rice Fields Using Hybrid Machine Learning and Time Series Models
P. Lavanya Kumari *
ANGRAU, India.
I. Paramasiva
ANGRAU, India.
U. Vineetha
ANGRAU, India.
A. Veeraiah
KVK, Kadapa, ANGRAU, India.
SK. Shameem
ANGRAU, India.
P.N. Harathi
ANGRAU, India.
A.D.V.S.L.P Anand Kumar
ANGRAU, India.
M. Siva Rama Krishna
ANGRAU, India.
N. Sambasiva Rao
ANGRAU, India.
P. Udayababu
ANGRAU, India.
J. Manjunath
ANGRAU, India.
N. Kamakshi
ANGRAU, India.
V. Visalakshmi
ANGRAU, India.
P. Siva
Acharya NG Ranga Agricultural University, India.
*Author to whom correspondence should be addressed.
Abstract
Brown Planthopper (BPH) (Nilaparvata lugens) is a major pest impacting rice production in India, often causing severe yield losses across diverse agro-climatic zones. This study evaluates the predictive capabilities of several statistical and machine learning models using weekly BPH incidence data collected over multiple years from five research stations in Andhra Pradesh (Nellore, Maruteru, Bapatla, Ragolu, and Nandyal). The models tested include the Negative Binomial Integer-Valued Generalized Autoregressive Conditional Heteroskedasticity (NBINGARCH) model in combination with Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Extreme Learning Machines (ELM), as well as their standalone counterparts. Hybrid models, particularly NBINGARCH-SVR and NBINGARCH-ELM, outperformed standalone models based on Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) across different locations and seasons. Some models, however, demonstrated signs of overfitting, as evident in elevated testing errors. Climatic variables—temperature, relative humidity, and rainfall—were found to significantly influence BPH dynamics. While the Box-Pierce test confirmed model adequacy in most cases, residual autocorrelation remained in a few, indicating room for further refinement. These results highlight the potential of hybrid modeling approaches for climate-informed BPH forecasting and offer actionable insights for Integrated Pest Management (IPM). Future work may enhance forecasting accuracy by incorporating additional environmental and agronomic parameters.
Keywords: Brown planthopper, extreme learning machine, hybrid models, machine learning, NBINGARCH, rice pest forecasting