Deep Learning (DL) techniques, mainly the methods of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), have received considerable attention and are being used in diverse fields including the agricultural sector. Most agricultural research frequently employs software frameworks without thoroughly investigating the ideas and mechanisms of a technique. The present article provides a concise summary of major DL algorithms (CNN and RNN), including concepts, implementation and applications to the scientific community to gain a holistic picture of techniques quickly. The article summarises and analyses research on DL applications in agriculture, and also focused on future opportunities which in turn help agricultural researchers in better understanding and learning of DL algorithms that facilitate data analysis, enhance research in agriculture, and thus effectively promote DL applications.
Adarsh V.S.*
Dept. of Agricultural Statistics, Bidhan Chandra Krishi Viswavidyalaya (BCKV), Mohanpur, West Bengal (741 252), India
Gowthaman T.
Sankarganesh E.
Dept. of Agricultural Entomology, Bidhan Chandra Krishi Viswavidyalaya (BCKV), Mohanpur, West Bengal (741 252), India
Adarsh, V.S., Gowthaman, T., Sankarganesh, E., 2022. Deep Learning: A futuristic approach to agriculture. Biotica Research Today 4(8), 570-572.
Gowthaman, T., Sankarganesh, E., 2022. Convolutional Neural Network (CNN) Architecture for Pest and Disease Detection in Agricultural Crops. Biotica Research Today 4(3), 178-180.
Magomadov, V.S., 2019. Deep learning and its role in smart agriculture. Journal of Physics: Conference Series 1399(4), pp. 044109.