A Strategic Analytics Using Convolutional Neural Networks for Weed Identification in Sugar Beet Fields

• Main Authors: Falih, N. (Author), Jabir, B. (Author), Sarih, A. (Author), Tannouche, A. (Author)
• Format: Article
• Language: English
• Published: Faculty of Economics and Management 2021
• Subjects: artificial neural network; Beni Mellal-Khenifra; Beni-Mellal; Beta vulgaris subsp. vulgaris; CNN; data set; Deep learning; identification method; Morocco; optimization; precision agriculture; strategic analytics; strategic approach; sugar beet; Varanidae; weed control
• Online Access: View Fulltext in Publisher

 Researchers in precision agriculture regularly use deep learning that will help growers and farmers control and monitor crops during the growing season; these tools help to extract meaningful information from largescale aerial images received from the field using several techniques in order to create a strategic analytics for making a decision. The information result of the operation could be exploited for many reasons, such as sub-plot specific weed control. Our focus in this paper is on weed identification and control in sugar beet fields, particularly the creation and optimization of a Convolutional Neural Networks model and train it according to our data set to predict and identify the most popular weed strains in the region of Beni Mellal, Morocco. All that could help select herbicides that work on the identified weeds, we explore the way of transfer learning approach to design the networks, and the famous library Tensorflow for deep learning models, and Keras which is a high-level API built on Tensorflow. © 2021, Agris On-line Papers in Economics and Informatics. All Rights Reserved.