Title: Remote sensing enabled sustainable tomato plant health and pest surveillance using machine learning techniques

Authors: Weijia Yu; Si Li

Addresses: Nanfang College Guangzhou, Guangzhou 510970, China ' Liuzhou Railway Vocational Technical College, Liuzhou Guangxi 545616, China

Abstract: To ensure long-term food security, it's vital to detect pests and diseases in crops. Traditional monitoring methods are labour-intensive and lack real-time info, leading to ineffective interventions. To address this, an advanced plant health monitoring (APHM) system that uses remote sensing technology and machine learning-based classification to effectively identify plant diseases and pests in tomato plants is proposed. The proposed system allows unmanned aerial vehicles (UAV) to take detailed aerial images of tomato fields, which are processed and input into a convolutional neural network with a generating adversarial imitation learning (CNN-GAIL) model. The CNN-GAIL model efficiently differentiates between healthy plants, weak plants, and pest presence by capitalising on temporal relationships in image sequences. The APHM system's ability to quickly identify and fix problems, combined with remote sensing and machine learning in precision agriculture, could improve crop health, reduce yield losses, and promote long-term sustainability.

Keywords: plant disease; pest detection; remote sensing; convolutional neural network; CNN; generative adversarial imitation learning; GAIL; unmanned aerial vehicle; UAV.

DOI: 10.1504/IJSNET.2024.138509

International Journal of Sensor Networks, 2024 Vol.44 No.4, pp.237 - 248

Received: 19 Jan 2024
Accepted: 26 Jan 2024
Published online: 08 May 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article