Salma Sekhra

About

Salma Sekhra is a researcher at the forefront of applying deep learning to precision agriculture, with a primary focus on the automated identification and classification of weeds and crops. Her most-cited work, "The Identification of Weeds and Crops Using the Popular Convolutional Neural Networks" (2023), has garnered 3 citations, establishing a foundational contribution to the field. In this study, Sekhra systematically evaluates the performance of widely-used convolutional neural network architectures—such as AlexNet, VGGNet, and ResNet—for distinguishing between crop plants and invasive weed species in agricultural imagery. Her major contribution lies in benchmarking these models under real-world conditions, providing a practical framework for farmers and agronomists to deploy AI-driven weed management systems. By demonstrating that CNNs can achieve high accuracy in complex field environments, Sekhra’s work directly supports the development of autonomous robotic weeders, reducing herbicide usage and promoting sustainable farming. Her research is particularly notable for its emphasis on transfer learning and dataset augmentation, making advanced computer vision accessible to agricultural applications. As a rising voice in the intersection of AI and agronomy, Salma Sekhra’s insights are paving the way for smarter, data-driven crop protection strategies.

Research Focus

Key Achievements

Top Papers

1. 1
   The Identification of Weeds and Crops Using the Popular Convolutional Neural Networks

   3 citations · 2023

Key Collaborators

Contact & Links