Precision Agriculture: ML and DL-Based Detection and Classification of Agricultural Pests

In the agricultural sector, automatic pest detection is quite helpful. To focus on the Indian context more specifically, the agriculture business has seen a loss of almost $12 billion simply due to pests. In this study, a methodical strategy is put forth that will allow using the combined strength of machine learning (ML) and deep learning (DL) approaches to identify agricultural pests early on and avoid more extensive damage later on. After extracting features from an image using a DL-based convolutional neural network (CNN) model, use ML classifiers to classify the pests. Using the best-performed CNN and ML models from analysis, attained an overall accuracy of over 95%. The resultant hybrid model may be used in the agriculture industry to detect pest spread news coverage early on. This method will overcome the issue of pests affecting the plants and benefit agricultural researchers to quickly know the issues and give treatment as soon as possible.