Brinjal Crop yield prediction using Shuffled shepherd optimization algorithm based ACNN-OBDLSTM model in Smart Agriculture

Abstract

The need to ensure food security in the face of growing environmental concerns like climate change and natural catastrophes is raising the need for accurate crop output predictions. Predicting agricultural output is difficult because of the various non-linear interactions involved. So, instead of using traditional statistical tools, many researchers are turning to deep learning approaches to investigate these connections. Since brinjal is so important to the diets of Indians, protecting their ability to eat is of paramount importance. To this end, the attention-based convolution neural network with optimised bidirectional long short-term memory (ACNN-OBDLSTM) model is used to analyse and determine brinjal forecasts in this study. The shuffling shepherd optimisation method (SSOA) is used for hyperparameter tuning of the BDLSTM model, which improves detection performance. The research concludes that the proposed approach is applicable not just to India but also to other leading producing states. India as a whole and its individual states are compared in terms of yield projection. Improved government decision-making, as well as better education and more accurate forecasting, are among the most important outcomes of this study for farmers in India.