Predicting Cotton Whitefly Populations Through Deep Learning

Abstract

Agriculture is the principal foundation upon which a nation’s economy relies. Pakistan ranks as the fourth-largest cotton grower globally, establishing it as a principal cash crop. Their inability to determine the most suitable cotton variety for their climate is attributed to governmental rules, agricultural dangers, and a low literacy rate among the populace and farmers. This approach uses a temperature-based model to categorize various plant species. The pest population is primarily concerned with its diversity, the impact of weather on its numbers, and the fluctuations between high and low populations. The main objective of this study was to provide a framework capable of managing the intricate dynamics of cotton whitefly populations. Our primary objective was to ascertain the number of insects, including their eggs and progenitors. Another objective is to ascertain information regarding the variety with a diminished bug population. To acquire preliminary insights into individuals opposed to the temperature. Cotton yield could be enhanced, and the usage of chemicals should be minimized. Consequently, farmers’ income may be enhanced. We will develop the optimal ARIMAX model for predicting whiteflies on cotton. The accuracy of this model was almost equivalent to that of the statistical forecasting models. As a statistical model, ARIMAX can be utilized for forecasting purposes.