A Novel Hybrid AI Federated ML/DL Models for Classification of Soil Components

Abstract

The soil is the most fundamental component for the survival of any living thing that can be found on this planet. A little less than 41 percent of Indians are employed in agriculture, which accounts for approximately 19 percent of the country's gross domestic product. As is the case in every other industry, researchers and scientists in this one are exerting a lot of effort to enhance agricultural practices by utilising cutting-edge methods such as machine learning, artificial intelligence, big data, and so on. The findings of the study described in this paper are predicated on the assumption that the method of machine learning results in an improvement in the accuracy of the prediction of soil chemical characteristics. The correlations that were discovered as a result of this research are essential for comprehending the comprehensive approach to predicting the soil attributes using ML/DL models. A number of findings from previous study have been reported and analysed. A state of the art machine learning algorithm, including Logistic Regression, KNN, Support Vector Machine and Random Forest are implemented and compared. Additionally, the innovative Deep Learning Hybrid CNN-RF and VGG-RNN Model for Categorization of Soil Properties is also implemented along with CNN. An investigation into the significance of the selected category for nutritional categorization revealed that a multi-component technique provided the most accurate predictions. Both the CNN-RF and VGG-RNN models that were proposed were successful in classifying the soil with average accuracies of 95.8% and 97.9%, respectively, in the test procedures. A study was carried out in which the CNN-RF model, the VGG-RNN model, and five other machine learning and deep learning models were compared. The suggested VGG-RNN model achieved superior accuracy of classification and real-time durability, respectively.