Paper Title
Deep Neural Network Based Crop Yield Prediction Using Agricultural and Climatic Data

Abstract
Crop yield estimation is also a factor of food security to enhance agriculture productivity to meet the population growth of the world as the population keeps increasing. Conventional predictive models have challenges in terms of nonlinear and the complexities of crop yield and environmental factors. Recent studies have demonstrated that deep learning methods are capable of performing better than the traditional statistical predictive models on large and heterogeneous datasets in the agricultural sector. This paper introduces an agricultural dataset, which can predict crop yield based on Deep Neural Network (DNN) to make a yield prediction using temperatures and rainfall accumulation, soil type/texture, and the past yield as the input features. Our suggested approach will involve data preprocessing, feature engineering and supervised data mining to extract a meaningful and valued data out of the predictive modelling of the input values that we worked with. The experimental findings show that the DNN will be more precise and dependable in terms of predictions compared to the traditional machine learning algorithms in crop yield prediction [1], [2]. The resulting yield forecast of this research will offer beneficial and quality decision-making support to the farmers and individuals in the decision-making process in the agricultural sector in regards to making crop planning and resource management of their crops. This study has been used in developing intelligent farming systems and also in making agricultural practices sustainable.